Technical Papers - SAE Mobilus

SAE Technical Papers are written and peer-reviewed by experts in the automotive, aerospace, and commercial vehicle industries and provide the latest advances in technical research and applied technical engineering information.

Items (135,058)
Find
Onboard AI-Driven Autonomous Tasking for Rapid Wildfire Response with a LEO Wide-Swath Observation Satellite2026-99-0609To be published on 11/06/2026
Low Earth Orbit (LEO) remote sensing satellites exhibit significant limitations in emergency response operations, primarily due to the constraints of orbital mechanics and a traditional reliance on ground-involved, open-loop operational models. Current response latencies often span several hours, rendering acquired data less effective for disasters with rapid temporal dynamics. We propose a new intra-pass autonomous reaction application mode to solve this key problem in emergency response. We build the mode on an agile satellite platform operating in an 800 km sun-synchronous orbit. We equip the platform with two core sensors through an innovative design. The two sensors are an optical camera with 0.5-meter resolution and a forward-looking infrared camera. The infrared camera has a 600-kilometer swath and a 10-meter nadir resolution. We take onboard artificial intelligence technologies as the research core. The technologies support real-time and autonomous analysis of forward-looking infrared image data. This analytical capability facilitates the real-time detection and autonomous confirmation of stochastic events, such as wildfires, by leveraging onboard artificial intelligence (AI) to perform real-time analysis of IR imagery. This subsequently triggers immediate autonomous re-tasking for high-resolution follow-up observation within the same orbital pass. We establish an optimization model for the satellite system. The model is used to solve the key balance problem between the sensor forward-looking angle, achievable reaction time, and actual detection resolution. We conduct a detailed engineering time budget analysis for the whole satellite operation system. Analysis results show that a specific forward-looking angle must be set for the infrared camera to obtain a 70-second autonomous response window of the satellite. The 70second window contains 30 seconds for AI cognitive analysis, a maximum of 33.6 seconds for platform attitude maneuvering, and 10 seconds for platform stability adjustment. The minimum forward-looking angle required for the infrared camera is about 33.6 degrees. The ground sampling distance of the infrared camera will decrease to 12.2 meters at this angle. The resulting 12.2-meter ground sampling distance (GSD) remains sufficient to meet the practical requirements of early-stage detection. The proposed Intra-Pass Autonomous Reaction (IPAR) mode reduces emergency response times from hours to seconds, significantly enhancing the proactive observation capabilities of LEO platforms.
Qiu, Hu, Zhao, Xinwei, Liu, Dongfusheng, Wang, Honghai
Energy Management for Series Hybrid Aircraft Based on a Dual Adaptive Equivalent Fuel Minimization Strategy2026-99-0603To be published on 11/06/2026
Series hybrid tiltrotor aircraft operate under highly dynamic and multi-phase flight missions. This paper addresses the resulting energy management challenge. Moving beyond the direct application of existing optimization algorithms, this study proposes a novel codesign framework that synergizes offline global optimization with online fuzzy adaptive control. The key theoretical innovation lies in transforming the online, real-time optimization problem of determining the optimal equivalent factor into an offline global optimization problem for the parameters of a fuzzy-PI controller. This is achieved through a hybrid particle swarm optimization and genetic algorithm (PSOGA), which optimizes the controller's scaling factors and gains. The optimized controller embeds mission-level economic information into the online generation of the equivalent factor, so that the power-split decision is determined not only by the instantaneous operating conditions, but also by the overall economic objective of the mission. Simulation results under typical and stochastic flight conditions validate the framework's effectiveness. Compared to benchmark strategies, the proposed PSOGA-Fuzzy-A-ECMS achieves a 6.7% improvement in fuel economy while robustly maintaining the battery state of charge within a safe and stable range. This study provides a systematic and theoretically-grounded design paradigm for real-time energy management in complex, time-varying systems.
Wang, Zhihao, Wang, Xiangyang
Swarm Cooperative Strategy for Multi-UAV Based on Adaptive Boundary Discretization and Distributed Particle Swarm Optimization2026-99-0621To be published on 11/06/2026
In traditional multi-unmanned aerial vehicles (UAVs) cooperative strategies within complex irregular regions, the low coverage efficiency, boundary constraint failure, and insufficient robustness bring the challenges. This paper proposes a cooperative search-andattack algorithm, which integrates adaptive mission area discretization and distributed intelligent particle swarm optimization (DIPSO). An adaptive grid model is constructed with ray casting algorithm to discretize arbitrary polygonal mission areas precisely. It can effectively reduce the invalid searches in non-mission zones by abandoning the traditional rectangular assumption. Moreover, a multi-objective fitness function (MOFF) is designed by incorporating coverage ratio, path length, collision penalty, and load balancing. With the discrete path manipulation operators (PMOs) and dynamic learning factors, the proposed method achieves distributed trajectory planning in convex polygonal spaces. Simulation results demonstrate that compared with counterparts, the proposed method performs closer boundaries to actual ones. Furthermore, it achieves 100% coverage while shorten the mission time significantly, validating its adaptability in various convex polygonal scenarios.
Zhou, Yunbo, Zhang, Di, Xia, Wei
Knowledge-Driven Aerial Swarm Target Intent Recognition Method for Few-Shot Scenarios2026-99-0623To be published on 11/06/2026
With the continuous advancement of collaborative unmanned aerial vehicle (UAV) swarm applications, the importance of intent recognition for aerial swarms in UAV management and control has become increasingly evident. To address the shortcomings of existing intent recognition methods, this paper proposes a knowledge-driven aerial swarm target intent recognition method designed for few-shot scenarios. First, a target trajectory clustering algorithm is designed by combining trajectory similarity measurement (which considers directional features) with density peaks clustering. This algorithm groups targets exhibiting the same or similar motion trends, thereby transforming the swarm target intent recognition problem into a swarm member intent recognition problem, which reduces the complexity of intent recognition. Second, considering the behavioral dynamics inherent in aerial swarm collaborative applications, a target intent inference model is constructed based on a Dynamic Bayesian Network (DBN). Utilizing the characteristic information of swarm targets at different time points, this model achieves intent inference and recognition through a hierarchical process: “sub-intent inference → accumulation of historical sub-intent sequences → intent inference.” Finally, simulation experiments are conducted to verify the feasibility and effectiveness of the proposed method.
Jiang, Jianxiong, Gui, Yang, Sun, Peng, Yang, Xinyu, Yang, Guangwei, Zhong, Yun
Experimental Investigation on the Failure Behavior of TMC Open-Hole Panels under Tensile Loading2026-99-0602To be published on 11/06/2026
Investigating the load-bearing capacity of Titanium Matrix Composites (TMCs) open-hole panels and their mechanically connected components is of great significance for the application of titanium matrix composites in the aerospace field. This paper investigates the failure behavior of TMC open-hole panels with a [45°/45°/-45°/-45°] laminate configuration under tensile loading. Tensile tests were conducted in conjunction with finite element modeling to analyze the damage evolution process and identify the failure modes of the tensile samples. The results show that the simulation outcomes exhibit good consistency with the experimental results, providing a foundation for the structural optimization and theoretical study of TMC open-hole panels.
Gao, Ximan, Jia, Qiuyue, Liu, Shanshan, Meng, Fanling
Rapid Thrust Evaluation of Solid Rocket Motor Nozzles Using Neural Network with Geometric Variations2026-99-0618To be published on 11/06/2026
To address the complexity of the influence of expansion-section geometry on the thrust performance of solid rocket motor nozzles and the low efficiency of numerical-simulation-based optimization, this study proposes a deep-learning-based method for rapid nozzle thrust prediction. With a representative 70-lb BATES nozzle as the research object, the expansion-section contour is parameterized using cubic spline functions. Combined with Latin hypercube sampling and two-dimensional inviscid numerical simulations, a nozzle geometry– thrust dataset covering a wide range of contour characteristics is constructed. On this basis, surrogate models based on a fully connected neural network, a one-dimensional convolutional neural network, and a two-dimensional convolutional neural network are developed, and the applicability of different network architectures to the nozzle thrust prediction task is systematically compared. The results demonstrate that convolutional neural networks outperform fully connected networks in terms of geometric feature representation capability and prediction stability. In particular, by explicitly modeling the spatial structural features of the nozzle contour, the two-dimensional convolutional model achieves a coefficient of determination close to unity on the test set, with an average relative error of 0.03%. Further hyperparameter sensitivity analysis clarifies the effects of batch size, number of training epochs, and learning rate on model convergence behavior and generalization performance. This work provides a feasible technical support for rapid thrust evaluation and efficient optimization-oriented nozzle design.
Yuan, Yuan, Wu, Wei-tao, Hua, Yue
Adaptive Multi-Agent Path Planning for UAV Formation Missions Based on MAPPO with Curriculum Learning and Graph Attention Networks2026-99-0615To be published on 11/06/2026
In high-end aerospace mission scenarios such as distributed sensing and tactical reconnaissance, path planning for multi-UAV cooperative formation flight has become an indispensable core component of mission systems. However, a key unresolved technical bottleneck remains: how to achieve an optimal balance between strictly maintaining the UAV formation’s preset geometric configuration and realizing collision-free, flexible flight in dynamically changing complex environments. Multi-Agent Reinforcement Learning (MARL) can theoretically solve this coupled optimization problem, but the control instructions generated by the existing mainstream MARL methods often have high-frequency fluctuation issues. Direct deployment of these fluctuating commands on physical UAV hardware will increase alternating stress on mechanical structures, raise the risk of motor overheating, and significantly boost battery energy consumption. These problems directly restrict the engineering application of such methods. To address the above challenges, this paper proposes a robust control framework that accounts for UAV physical characteristics to solve the model mismatch between simulation environments and real flight scenarios during carrier-based UAV deployment. Firstly, to improve the learning efficiency of the algorithm and avoid the cold start problem in the initial training stage, this paper introduces the Adaptive Curriculum Learning (ACL) method. Unlike the fixed-difficulty training mode, ACL can dynamically adjust the environmental complexity based on the real-time task performance of the UAVs. It first allows agents to master basic formation maintenance skills, before training is gradually transitioned to more complex tasks such as navigation in intricate environments. Additionally, considering the computational limitations of the onboard embedded processors of UAVs, this paper only integrates the Graph Attention Network (GAT) into the centralized Critic network of the centralized training and decentralized execution (CTDE) framework. The core advantage of this design is that the system no longer solely relies on distance as the judgment basis but assesses the influence of adjacent UAVs based on the collision risk level. This not only improves the accuracy of value estimation, but also does not compromise the response speed of local control instructions- a feature that is crucial for the real-time requirements of UAV flight control. The proposed method was tested and validated in a high-fidelity simulation environment built in strict compliance with UAV kinematic constraints. The experimental results fully demonstrate its superiority: in dense obstacle areas, the success rate of the task reached 80.4%; compared with the aggressive baseline method, the jerk was reduced by 10.9%. Most importantly, the flight trajectories generated by this framework are smooth and adaptable to actual flight conditions, and the corresponding control commands can be directly deployed on real flight controllers without additional parameter adjustments. This result demonstrates that the proposed framework achieves substantial technical progress in enhancing the autonomous response capabilities of UAV clusters to complex scenarios.
Huang, Xingyu, Zhang, Jiyu, Jiang, Yanshu, Fan, Yuhang
A Tail-Aware Enhanced YOLOv8 Framework for Robust Welding Defect Detection2026-99-0608To be published on 11/06/2026
In high-end manufacturing and aerospace equipment, reliable identification of welding defects is the key premise for intelligent fault diagnosis and structural health management because undetected or misclassified defects may lead to serious safety risks. However, the actual welding inspection scene is usually subject to some problems, such as limited training data, serious imbalance of categories, and low contrast of defect patterns, which significantly reduce the robustness of traditional vision-based inspection methods. In order to meet these challenges, this paper proposes a tail-sensing-enhanced welding defect detection framework based on YOLOv8, which is specifically aimed at the distribution of common long tail defects in industrial inspection tasks. On the premise of not changing the original network architecture, this method systematically enhances the learning ability of underrepresented defect categories through collaborative optimization in data, training, and loss levels. The specific measures include tailperceived data enhancement, convergence-oriented training strategy, and loss re-weighting of classification priority. The experimental results on multi-class welding defect datasets show that the proposed framework significantly reduces the false alarm rate and inter-class confusion of small samples and low contrast defects, and improves the reliability and robustness of the overall diagnosis. These results show that the proposed method provides an effective and practical solution for intelligent welding fault diagnosis and has great potential to be integrated into aerospace manufacturing quality inspection and health monitoring systems.
Fan, Yuhang, Zhang, Jiyu, Huang, Xingyu
A Flight Test Anomaly Detection Framework Based on Adaptive Weight Fusion2026-99-0606To be published on 11/06/2026
Flight anomaly detection plays a critical role in ensuring aviation safety. However, conventional anomaly detection methods often suffer from limited accuracy due to their reliance on single-sensor observations or fixed-weight multi-sensor fusion strategies. To address these limitations, this paper proposes an adaptive weight fusion framework for flight-test anomaly detection. The proposed framework integrates a signal-to-noise-ratio-based adaptive weighting strategy, an improved Kalman filtering algorithm, and an ensemble anomaly detection model within a hierarchical fusion architecture to achieve robust multi-sensor data fusion and anomaly identification. Experiments were conducted using the NASA DASHlink Tail_666_9 flight dataset. Compared with conventional methods, the proposed framework achieved improvements in overall accuracy, precision, recall, and F1-score. Specifically, the proposed method achieved an F1-score of 0.486 while reducing the average anomaly detection delay by more than 2 s. These results indicate that the proposed framework can improve the effectiveness and timeliness of flight anomaly detection, demonstrating its potential for real-time flight safety monitoring.
Wang, Yixin
A Hierarchical Optimization Strategy for On-Orbit Energy Management and Attitude Control of Spacecraft2026-99-0605To be published on 11/06/2026
This paper addresses an energy-optimal attitude control strategy for space solar power satellites (SSPSs) during on-orbit energy transmission missions. The study focuses on a space solar power generation and energy transmission experimental satellite as the research object. First, the attitude dynamics of the satellite are modeled using the Lagrange method, and the satellite’s attitude control actuators, namely the single-gimbal control moment gyroscopes (SGCMGs), are also modeled to capture their dynamic behavior and constraints. Second, a PD controller based on quaternion and angular velocity error feedback is designed to achieve the desired attitude necessary for the energy transmission task. Subsequently, a hierarchical optimization approach is developed to obtain the energy-optimal attitude control strategy over one orbital period, considering multiple factors such as the satellite’s on-orbit energy consumption, the energy collection efficiency of the solar array in non-shadow regions, and the energy transmission efficiency between the satellite and the ground station. The optimization process is divided into two levels. In the first level, within the ground station’s visibility window, an energy balance analysis at different potential transmission moments is performed to determine the optimal transmission timing that maximizes the energy received by the ground station. In the second level, during the energy transmission phase, a cost function is formulated that incorporates pointing accuracy, pointing stability, and actuator energy consumption, and the controller parameters are globally optimized using the Adaptive Particle Swarm Optimization (APSO) algorithm. The simulation results demonstrate that the proposed hierarchical optimization method can significantly enhance the operational efficiency of on-orbit energy transmission, providing a practical engineering approach for the efficient on-orbit operation of future space solar power stations.
Wang, Ke, Zhang, Ning, Ma, Wenlai, Zhao, Yang
Run Time Assurance Filter Framework for Collision Avoidance of Unmanned Aerial Vehicles Using Reinforcement Learning2026-99-0620To be published on 11/06/2026
In recent years, Reinforcement Learning (RL) has been increasingly applied to the collision avoidance systems of Unmanned Aerial Vehicles (UAVs) due to its high performance in complex tasks and relatively low online computational cost. Despite these advantages, the lack of interpretability in RL and decision-making processes poses significant challenges to safety verification, which severely limits the practical deployment of RL-based autonomous flight systems in safety-critical scenarios. Ensuring safety during both training and testing remains the key for real-world applications. To address this issue, a Run Time Assurance (RTA) filter framework for a UAV collision avoidance system based on RL is proposed. The framework continuously monitors the avoidance actions generated by RL and ensures that unsafe actions can be identified and corrected in real time. The framework provides security while retaining the performance advantages of RL. First, a discrete kinematics model of the UAV and a collision avoidance environment for a three-dimensional multi-intruder UAV are established. The Proximal Policy Optimization (PPO) algorithm is used to train the UAV avoidance policy. Secondly, the RTA filter with safe constraints is designed based on this model. To reduce the position error between the discrete kinematics model and the continuous dynamics model of the UAV, optimization is performed using the Sequential Least Squares Programming Method (SLSQP). The RTA is applied to the training and testing phases of UAV collision avoidance systems to monitor and correct unsafe actions online. Finally, three training and testing methods are set: no RTA, RTA without punishment, and RTA with punishment. Comparing different relaxation coefficients allows for analyzing their impact on filter performance. Simulation results demonstrate that the RTA effectively enhances safety throughout training and testing. Compared with the no RTA method, the collision rate is reduced by 7.04%, and the success rate is increased by 2.68%. In extreme collision avoidance scenarios, the average collision rate obtained by different reinforcement learning algorithms is reduced by 21.46%, and the average success rate is increased by 15.54%.
Ma, Zan, Yan, Liqin, Bai, Jie, Liu, Yubin, Sun, Shuguang
Model Predictive Formation of Multi-AAVs in Underground Utility Tunnels2026-99-0607To be published on 11/06/2026
As a core carrier of urban underground infrastructure, underground utility tunnels have an increasingly urgent demand for AAV swarm technology in operation and maintenance tasks such as internal pipeline inspection and fault diagnosis. However, the special environment of utility tunnels, characterized by GPS signal loss, narrow and enclosed space, and complex types of obstacles (including fixed pipeline supports and temporary construction components), poses severe challenges to AAV swarm operations. In this scenario, while maintaining the predetermined formation configuration, AAV swarms are required to complete three tasks simultaneously: accurately avoiding complex static obstacles in the tunnels, real-time evading other AAVs within the swarm to prevent intra-formation collisions, and strictly maintaining a safe distance from the tunnel walls. The superposition of these three constraints and the narrow operating space greatly increases the difficulty of swarm control. Traditional control methods often suffer from problems such as formation collapse, jerky obstacle avoidance, or wall scraping. To address the above pain points, this paper proposes an AAV swarm Model Predictive Control (MPC) method integrated with the Adaptive Perceptual Cauchy Mutation Pigeon-Inspired Optimization (APCMPIO) algorithm. This method optimizes the receding horizon parameters and constraint weights of model predictive control through the APCMPIO algorithm to achieve rapid response to complex dynamic scenarios, and embeds a dynamic safe distance threshold mechanism to balance formation integrity and individual safety. A simulation experiment was built for a utility tunnel inspection scenario with 6 AAVs. It significantly improves the operational adaptability and robustness of AAV swarms in constrained utility tunnel environments, providing reliable technical support for the swarm-based operation and maintenance of underground infrastructure.
Li, Tian-Qi, Ma, Lei, Liu, Yan-Jun, Li, Shu, Li, Dapeng, Liu, Lei
An Interactive Click-Based UAV Path Planning Method for Anti-Corrosion Spraying Using BIM-SLAM Fused 3D Models2026-99-0637To be published on 11/06/2026
To solve the critical challenges of uncoordinated operational node selection and premature mission termination caused by dynamic energy or coating depletion during anti-corrosion spraying on largescale steel structures, this paper proposes an advanced path planning methodology for UAVs. The proposed approach is built upon a BIMSLAM fusion model. Specifically, a high-fidelity three-dimensional (3D) environmental model is reconstructed by integrating offline BIM structural priors with real-time SLAM data. Furthermore, the framework implements the ICP algorithm and Kalman filtering simultaneously to eliminate point cloud noise and compensate for perceptual occlusions, thereby achieving a 5 cm localization accuracy in cluttered industrial environments. A dual-stage pipeline is established for pre-screening and dynamic evaluation. In the offline phase, geometrically inaccessible task points are identified and pruned via spatial accessibility analysis. During real-time operations, the onboard system continuously calculates the battery State of Charge (SoC), operational power, and remaining paint volume to eliminate inefficient flights. For the path generation stage, a hybrid search strategy is developed, which implements a Genetic Algorithm for task sequencing alongside a multi-objective cost function parameterized by four metrics: energy consumption, paint requirements, obstacle proximity, and task density. Additionally, Softmax is used to dynamically regulate the weight coefficients, enabling the system to balance operational safety and efficiency based on the instantaneous state vector. Finally, a fifth-order B-spline parameterization is used to maintain flight stability under complex wind disturbances and heavy time-varying payloads. Consequently, the results show that the proposed method significantly outperforms conventional baselines. The recorded 96.7% mission completion rate demonstrates its operational reliability for the maintenance of bridges and towers.
Qian, Lei, Huang, Chen, Tan, Libin, Huang, Tao
A Multimodal Perception Unmanned System Based on GNN and SLAM2026-99-0633To be published on 11/06/2026
The complex environments encountered in emergency rescue scenarios pose severe challenges to the perception and navigation capabilities of unmanned ground systems. This paper designs and implements a ground unmanned rescue system named "SkyEye" based on multimodal perception fusion. The system adopts a four-wheel independent steering and four-wheel drive (4WIS-4WID) omnidirectional ground chassis and integrates a 4D-FMCW LiDAR, structured-light binocular cameras, a high-precision IMU, and Beidou RTK. Through a tightly coupled graph-optimization SLAM framework and GNN-based dynamic obstacle prediction, it achieves robust perception and autonomous navigation in complex rescue scenarios. Experiments show that under clear open-field conditions, the system achieves centimeterlevel positioning accuracy and obstacle recognition accuracy ≥95%. In extreme dense smoke, recognition accuracy remains at 82.6% with stable navigation. The obstacle avoidance response latency is ≤0.5 s in narrow spaces and GNSS-denied tunnels. This paper elaborates the platform kinematic model, multi-sensor spatio-temporal calibration, detailed SLAM implementation, and complete GNN trajectory prediction pipeline, providing a theoretical basis and engineering reference for ground emergency rescue unmanned systems.
Li, Yizhen, Wei, Yuxiao, Wen, Yuanhao, Xun, Xuhang, Wang, Chengjun, Wu, Peng
Design and Analysis of a Continuous Drying Process and Equipment for 3D Hollow Polyester Fiber Production2026-99-1903To be published on 11/06/2026
In the production of polyester fibers from recycled polyethylene terephthalate (rPET), the drying and crystallization of plastic bottle flakes are crucial for ensuring the consistency and strength of the finished fibers. Traditionally, rPET production lines still rely on vacuum drum dryers, which have been suffering from issues including agglomeration, uneven heating, and high energy demand. In this work, we developed a novel continuous system that is capable of achieving a total throughput of 1300 kilograms per hour. The design consists of a pulsating fluidized-bed crystallizer and two cylindrical drying towers operating in parallel. Structural performance of the main systems was analyzed using finite element analysis under material load, thermal expansion, and internal air pressure. Airflow behavior and temperature distribution inside the units were studied using Computational Fluid Dynamics (CFD) models, where the flake bed was treated as a porous medium based on experimental bulk density and pressure drop. Results showed that the drying tower maintained a minimum safety factor above 3 under full-load conditions, while the crystallizer also remained well within allowable stress limits. Additionally, flow-field analysis results indicated stable countercurrent airflow, adequate mixing near the inlet region, as well as acceptable axial temperature gradients for moisture removal below 50 ppm. Compared with conventional drum drying, we believe the continuous configuration simplifies operation and reduces heat loss. Our design approach has been combined with analytical calculations on structural and flow simulation, and can be beneficial when applied to similar rPET drying applications.
Wu, Ye, Wu, Tianqi, Ge, Yuchen, Ni, Hongjun, Tan, Linwei, Lv, Shuaishuai
Aeroseek: Exploring LLM-Enhanced Monte-Carlo Path Planning for UAV Navigation2026-99-0613To be published on 11/06/2026
While Unmanned Aerial Vehicles (UAVs) hold immense potential for transforming the low-altitude economy, developing an agent that combines both intelligence and flexibility remains a significant challenge. To this end, we propose a novel aerial navigation system, Aeroseek, to search for executable paths that coherently transition from cognitive understanding to physical movement, enabling more autonomous and flexible navigation with instruction guidance. Specifically, given a navigation instruction, we follow a fast-andslow thinking procedure inspired by human pilots by breaking down complex decisions into manageable sub-tasks and initiating motion planning immediately upon the completion of each sub-task for realtime movement. By integrating a multi-branch Chain-of-Thought, Aeroseek is capable of combining reasoning with spatial recognition and self-verification to search for robust sub-goals under expected constraints. For sub-goal navigation, we introduce Online Kinodynamic Monte-Carlo Path Planning (OnKi-MCPP), a novel motion planning approach handling both kinodynamic constraints and path search, while ensuring obstacle avoidance for UAVs. Benefiting from the proposed two-tier searching protocol, Aeroseek demonstrates comprehensive capabilities in processing complicated instructions and adapts to dynamic aerial conditions. Extensive experiments demonstrate the advantages of Aeroseek across tasks of varying complexity.
Luo, Guoan, Xu, Tian, Zhou, Jiacong, Wang, Xianyun
Design Strategy for Cislunar Space Navigation Constellations Based on Navigation and Autonomous Navigation Performance2026-99-0625To be published on 11/06/2026
This paper proposes a bi-objective design strategy for cislunar navigation constellations, simultaneously optimizing navigation performance for target users and the autonomous navigation performance of constellation itself. The design variables include orbital characteristic parameters and inter-satellite phases, while the objectives are defined as the worst-case Geometric/Position Dilution of Precision (GDOP/PDOP) for users and the constellation's aggregated Dynamic and Geometric Dilution of Precision (DAGDOP). To address phase jump issues, the optimization is formulated on a product manifold and solved using the Riemannian steepest descent algorithm via the Pymanopt toolbox. Three constellations are designed by this strategy, which are six-satellite constellation for the Lunar South Pole station, a twenty-satellite constellation for lunar surface and lunar orbit users, and an eight-satellite constellation for a LEO-to-DRO transfer trajectory. Simulation results demonstrate that the optimized designs achieve the required geometric visibility, maintain GDOP/PDOP below specified usable thresholds (e.g., max PDOP of 5.96 for the South Pole, max GDOP of 2.28 for the transfer), and exhibit stable autonomous navigation performance. The study confirms the feasibility of the proposed strategy for designing practical, high-performance navigation constellation deployments across diverse cislunar mission scenarios.
Chan, Meichen, Qiu, Haipeng, Hu, Jiaxin, Yang, Leping, Zhu, Yanwei, Chen, Yujie
Multi-Constraint Optimization-Based Perception and Trajectory Planning for Robotic Strand Cutting and Roughening in Box Girder Anchor Recesses2026-99-0634To be published on 11/06/2026
A robotic system that integrates prestressing-steel strand cutting with automated surface roughening was developed to address the high labor cost, harsh working conditions, and poor quality consistency encountered in anchor-hole operations for prefabricated box girders. To overcome perception bottlenecks in high-dust and strong-glare casting-yard environments, a coarse-to-fine, two-stage pose estimation method was proposed based on point-cloud semantic segmentation and geometric-feature constraints. A deep-learning network was employed to decouple and isolate regions of interest (ROIs), and a weighted ICP algorithm was applied to achieve submillimeter-level positioning. To mitigate mobile-chassis docking deviations and constrained workspace limitations, a multi-constraint trajectory-optimization model and an online re-planning strategy were implemented. Field experiments show that, under extreme conditions with point-cloud incompleteness up to 20%, the system yields a positioning error below 1.65 mm and a trajectory-tracking root-mean-square error (RMSE) consistently within 2.8 mm. While the automated process increases the operational speed by approximately 1.5 to 1.8 times compared to manual work, its primary value lies in eliminating occupational hazards and ensuring consistent processing quality, demonstrating significant engineering value.
Yi, Dongbo, Wang, Yong, Ma, Tengyue, Li, Yang, Liu, Daochang
Research on Methods for Assessing Bird-Drone Collision Probability in Urban Low-Altitude Airspace2026-99-0629To be published on 11/06/2026
As the use of low-altitude drones in urban environments continues to grow, the likelihood of near-miss events and collisions between birds and drones operating in shared airspace has drawn increasing attention. To address this issue, this paper proposes a collision probability assessment framework based on the Boids swarm behavior model and Monte Carlo statistical methods, using the Chengdu silky-tailed starling as a case study: simulating the relative motion between bird flocks and UAVs within typical flight segments, defining near-misses and physical collisions events based on minimum separation distance thresholds, and employing Wilson confidence intervals to quantify uncertainty and analyze convergence. The simulation results indicate that after introducing the detectionavoidance mechanism, the minimum distance distribution function curve shifts rightward overall, collision duration is significantly reduced, the probability of event occurrence is effectively lowered, and the cumulative estimate exhibits good convergence under large samples. Additionally, the probability of incidents exhibits a monotonically decreasing trend with enhanced detection capabilities, revealing a monotonically sensitive characteristic where higher detection capabilities reduce collision probability risks. This provides a quantitative basis for low-altitude planning and risk management.
Pan, Anqi, Long, Yong, Li, Xiaojing, Chen, Di, Yang, Jibo, Zhao, Jinchen, Wu, Honggang
Study on the Severity of Aircraft Ice Protection System Performance in the Icing Envelope2026-99-0611To be published on 11/06/2026
In the process of design and verification of the aircraft ice protection system, a prediction model of ice protection system performance based on Severity Index(IPSI) is proposed, which quantifies the relationship between input and output energy of the ice protection system. In this research, a theoretical calculation method is developed, and the water total collection coefficient and convective heat transfer coefficient on the skin surface were obtained using CFD calculations and rapid neural network prediction methods. The consistency between IPSI and ice protection system performance is verified through an aircraft wing ice protection wind tunnel test. The results show that the lower the slat skin temperature in the ice protection area, the higher the IPSI value, which means the more severe the ice protection system performance. The ice protection performance severity analysis method is carried out for the cases in the CCAR/FAR/CS-25 continuous maximum(CM) envelope of an aircraft, and the IPSI values of each case at some altitudes are calculated, as well as the distribution of the ice protection system performance severity cases in the CM altitude-temperature envelope. The ice protection system performance severity cases are not the highest or lowest atmospheric static temperature in the CM envelope, in which atmospheric static temperature ranges from -8°C to -23°C from low altitude (1500 ft) to high altitude (22000 ft). When the flight speed is constant, and the atmospheric static temperature is gradually reduced, the IPSI value decreases. When the atmospheric static temperature is constant, and the flight speed increases gradually, the IPSI value increases. The influence of water evaporation heat transfer on ice protection performance severity is greater than that of convection heat transfer. The total air temperature for the most severe condition is always 0°C at every altitude. The IPSI calculation model can be used to quickly predict the severity of ice protection system performance in other ice protection areas of aircraft, even wind blades.
Hu, Weixue
A Method for Disordered Circlip Recognition Based on Improved YOLOv11 and Association Strategy2026-99-0622To be published on 11/06/2026
To realize automated grasping of randomly placed C-type circlips in automotive and mechanical assembly processes, this paper proposes an identification method based on the improved YOLOv11 algorithm and an exclusive association strategy. First, a detail enhancement convolution (DEConv) module is introduced into the C3k2 module of the YOLOv11 network to enhance the ability to capture the edges and high-frequency details of the circlips; Second, the parallel patch-aware attention (PPA) module is adopted in the detection head instead of the traditional convolution, and through multi-branch fusion and channel-spatial attention mechanism, it adaptively focuses on the key areas of small targets; Finally, the normalized Wasserstein distance (NWD) loss function is used instead of the IoU loss to alleviate the gradient disappearance problem in the positioning of small targets and improve the model’s detection accuracy. Based on precise detection, this paper innovatively proposes a circlip-hole association strategy based on multi-level spatial constraints, achieving accurate pairing of randomly placed circlips through bounding box-inclusive attribution judgment, distance screening, and selection of the best circlip-pair. Experimental results show that compared with the original YOLOv11 model, our model improves the mAP50 and mAP50-95 significantly by 5.7% and 3.3%, respectively; its association accuracy reaches above 95%, and the average processing time is 142 ms. Both in terms of accuracy and speed, our model meets the requirements of industrial real-time grasping and provides reliable prior information for the subsequent precise clamping of the robotic arm.
Wang, Chuang, Li, Jiyan, Wang, Yongming, Tan, Libin
An Intelligent Scheduling Optimization Method for High-Speed Railway Beam Yards Integrating Dijkstra Algorithm and Linear Programming2026-99-0636To be published on 11/06/2026
As the core facilities for prefabricated box girder production, highspeed railway beam yards are confronted with multiple practical challenges, including large-scale operation, intricate production processes, and frequent dynamic interferences in construction. Traditional manual scheduling methods are unable to achieve optimal allocation of production resources and efficient coordination of the entire production chain. In view of this problem, this paper proposes an intelligent scheduling optimization method that combines the Dijkstra algorithm with linear programming, and constructs a coordinated scheduling system that covers the whole process of “girder erection-girder fabrication-girder storage”. Supported by BIM+GIS digital twin technology, this system integrates multisource data from the Internet of Things (IoT) and production management platforms. In the system, the Dijkstra algorithm is used to dynamically plan the optimal path for girder erection, while a linear programming model is adopted to realize precise scheduling of production resources. Taking the production task of 1,672 box girders at the Baohui Beam Yard as an engineering application case, the results show that this method can improve the girder erection efficiency by 20%, raise the utilization rate of production resources by 15%, and reduce the process waiting time by 30%. It effectively solves the prominent problems of traditional scheduling, such as resource idleness and construction schedule delays, and thus provides theoretical support and practical reference for the development of intelligent construction 2.0 in high-speed railway beam yards.
Yi, Dongbo, Ma, Tengyue, Li, Yang, Yu, Ziqi, Li, Linsen
Multi-Step Time Series Forecasting for Intermittent Demand Based on Transformer2026-99-0616To be published on 11/06/2026
Consumable spare parts for civil aircraft are characterized by intermittent demand patterns. Constrained by long order replenishment cycles, traditional single-step demand forecasting struggles to effectively support inventory decisions. Moreover, research on intermittent demand forecasting primarily focuses on single-step, short-term cycle predictions, while multi-step forecasting using advanced deep learning methods remains in its early stages. To address this issue, this study introduces a multi-step forecasting approach based on the Transformer architecture, employing a MIMO strategy to achieve long time series forecasting for intermittent demand. The model is validated using a dataset from an airline maintenance base consisting of 360 intermittent demand items. A comparative analysis is conducted against three traditional time series models (SES, Croston, and SBA) and several neural network architectures (FNN, GRU, and LSTM). The performance of different methods was compared using six evaluation metrics. Results demonstrate that the Transformer consistently delivers outstanding performance across various forecast horizons. Notably, in long-horizon forecasting tasks, the model’s advantage in prediction accuracy becomes increasingly significant as the forecast step increases.
Zhang, Zhaomin, Zhao, Xin, Zhang, Jian, Fu, Weifang
Comparative Analysis of BDS PPP-B2b on Shore-Based and Ship-Borne Platforms2026-99-0642To be published on 11/06/2026
The integration technology of autonomous navigation and positioning provides critical technical support for high-precision positioning in the marine environment. As an indispensable core technology in modern marine navigation, satellite navigation plays a vital role in marine navigation safety and precision operations, such as marine surveying, ship navigation, and offshore engineering. The BDS PPPB2b service is commonly used in the marine high-precision application. However, compared to the landing application, the BDS PPP in the marine environment performs poorly due to the complex environmental factors on the ship-borne platform, such as hull occlusion and sea surface signal reflection. To compare and analyze the positioning performance differences of BDS PPP-B2b between shore-based and ship-borne platforms, an experiment has been conducted by using real data of the BDS receiver on both shore-based and ship-borne platforms. The results have shown that the BDS PPPB2b positioning performance on a ship-borne platform achieves poor satellite visibility and stable positioning performance. The BDS PPPB2b positioning accuracy after convergence can reach centimeter and decimeter levels on shore-based and ship-borne platforms, respectively.
Wang, Xilong, Li, Menghao, Shi, Huiwen, Sun, Min, Lu, Yin
Modeling and Energy Consumption Characteristics Simulation Analysis of a Two-Speed Drive System for a Permanent Magnet Synchronous Motor2026-99-1927To be published on 11/06/2026
This study systematically analyzes the energy efficiency optimization requirements of the permanent magnet synchronous motor (PMSM) drive system for electric vehicles from three dimensions: motor topology, vector control algorithm, and two speed variable transmission mechanism. Firstly, analyze the electromagnetic structure of PMSM fixed rotor and compare the differences in magnetic circuit characteristics between surface mounted and built-in rotors, laying a theoretical basis for motor selection. Secondly, based on the id=0 control principle, a PMSM speed current dual closed-loop speed regulation architecture is built, and the PI regulator parameters are tuned according to the bandwidth characteristics of the current loop to ensure that the system has excellent dynamic response and speed following capabilities. Furthermore, key sub modules such as vehicle driving cycle, motor body, and two-speed transmission are integrated to construct a joint simulation environment. Evaluate the vehicle speed tracking accuracy and energy consumption level of the system under four typical operating conditions: NEDC, WLTC, CLTC-C, and CLTC-P, with a focus on revealing the mechanism of transmission ratio matching on the coverage range of the motor's high-efficiency zone. The core parameters of the simulation model in this article are calibrated based on the standard engineering parameters of mass-produced pure electric passenger vehicles and validated academic literature data. The model verification is completed by benchmarking the output results of existing mature simulation models to ensure the reliability of the simulation. Simulation data shows that the two speed transmission scheme significantly outperforms the single speed system in terms of energy consumption performance, and the optimal transmission ratio combination (8,5) can effectively broaden the high-efficiency working range of the motor, demonstrating optimal energy efficiency under WLTC and CLTC-P operating conditions. This study is mainly based on high fidelity simulation models for theoretical verification. Although bench tests have not been conducted, the model parameter calibration and verification process conforms to industry standards. The conclusion can provide theoretical reference and data support for parameter matching and energy-saving design of electric vehicle multi speed drive systems.
Liu, Chunhui
GeoPR: Label-free LiDAR Place Recognition with Hybrid Geometric Graphs2026-99-1926To be published on 11/06/2026
LiDAR place recognition plays a crucial role in SLAM systems and robot localization. To address the drawback of existing hand-crafted descriptors—namely, their limited topological representation capability in complex scenes—and the high training cost and strong dependence of semantic-assisted methods, our study proposes a label-free hybrid geometric graph-based LiDAR place recognition algorithm, termed Geometric Place Recognition (GeoPR). GeoPR exploits the intrinsic geometric structural information of point clouds. Our algorithm adopts a preprocessing module to directly extract stable geometric primitives from raw point clouds as geometric nodes. On this basis, we design a hybrid geometric graph descriptor by introducing logarithmic distance weighting and Gaussian soft binning to enhance robustness against discretization errors and dynamic disturbances. During the matching process, our research adopts a two-stage “global search - geometric verification” framework: using a KD-tree for rapid candidate screening, followed by a geometric consistency verification module based on correspondences to eliminate false positive loop closures. Experiments on public datasets show that, without any training data or GPU acceleration, GeoPR achieves significantly higher precision and recall than mainstream hand-crafted methods, while its scene adaptability is comparable to advanced deep learning methods. Therefore, this work provides an efficient and reliable place-recognition solution for automatic driving and lightweight mobile robot platforms.
Cao, Bingyin, Zhang, Xudong
Research on Lightweighting Wheel Hub for New Energy SUVs Based on ANSYS Workbench2026-99-1904To be published on 11/06/2026
In recent years, the sales volume of new energy vehicles (NEVs) in China has maintained a steady growth trend, and consumers have paid increasing attention to vehicle range. Against this backdrop, the demand for lightweighting of various core components of NEVs has significantly increased. As a key component of automobiles, the wheel hub accounts for a relatively large proportion of the unsprung mass, and its lightweighting is of great significance for improving the driving range and enhancing vehicle performance. In this paper, sunflower and bridge truss are integrated as design elements, and a small-sized new energy sports utility vehicle (SUV) is selected as the reference vehicle model to design a lightweight wheel hub. Creo is used for 3D modeling of the wheel hub, and static stress, radial fatigue, bending fatigue, and modal simulations are performed in ANSYS Workbench. The results show that all wheel hub performance indicators meet the service requirements. Meanwhile, the quality evaluation indicates that the weight of the designed wheel hub is 10.95 kg, which is 3.90 kg lighter than the original wheel hub, representing a weight reduction of 26.3% compared with the original one, thus meeting the lightweighting standards.
Li, Chang
Research on Quantification Methods for Nonlinear Forming Length of Ultra-Thin Flat Wires in Flat Wire Motors2026-99-1913To be published on 11/06/2026
Because of the imprecision of length quantification in the manufacturing of flat wire windings for flat wire motors, empirical allowances have long been a common practice in production, which in turn leads to considerable material waste and elevated production costs. This paper presents an integrated solution that fuses material experiments, reverse engineering, simulation iteration and parametric design, realizing accurate prediction and quantitative calculation of winding forming length. First, high-precision elastic-plastic constitutive relationships of flat wires are acquired through room-temperature uniaxial tensile tests. On this basis, reverse engineering is applied to derive the initial geometric characteristics and process motion paths of flat wire windings from the 3D model of finished products. Next, an innovative closed-loop iterative compensation algorithm is constructed, with the forming height of the innermost flat wire layer serving as an absolute reference; finite element simulation is then utilized to dynamically optimize the forming length of each flat wire layer. Finally, a parametric design system with a visual interactive interface is developed, which enables an intelligent workflow where precise cutting lengths and equipment motion curves are automatically generated upon input of key design parameters. Production validation results show that this method drastically reduces the length allowances of flat wires, markedly lowers the production scrap rate, and shortens the process debugging cycle of new motor models by more than 80%.
Li, Wenbin, Zhu, Ye
Design of a Gantry-Type Intelligent Grasping Device for Logistics Warehousing Based on MaixCam2026-99-1925To be published on 11/06/2026
Traditional warehousing suffers from low efficiency, high manual error rates, substantial labor costs, and complex deployment, while existing sorting devices remain poorly adaptable for small- and medium-sized operations. To address these issues, this paper presents an intelligent gantry-type grasping device for logistics warehousing based on the MaixCam. The device integrates mechanical design, computer vision, and electronic control. An Arduino Mega2560 serves as the main control board, with 57-series and 42-series stepper motors and servo motors driving the gantry and gripper. The mechanical structure adopts a miniaturized gantry architecture constructed from alloy steel, enabling operation in confined workspaces. A YOLOv5s model with transfer learning was trained for cargo box recognition using a dataset of 654 images collected under various lighting conditions and backgrounds. The model achieves a recognition accuracy of 93%–96% with inference times of 10–14 ms at 25–28 FPS. The proposed device provides a viable solution for automated sorting in small-to medium-sized warehouses, balancing recognition performance, power consumption, and cost.
Xiang, Chang’an, Zhou, Dan, Fan, Zhiwei
Study on Contact Stress Distribution at Curvic Couplings Fitting Surface under Pretightening Force2026-99-1924To be published on 11/06/2026
The curvic coupling configuration serves as a foundational element for the joining and torque transmission of aero-engine rotors. The uneven contact stress distribution at its fitting surface can cause tooth surface wear and failure, which in turn leads to the vibration of the entire engine. The curvic couplings are fixed by the pretightening force. The pretightening force greatly influences the contact stress distribution characteristics at the fitting surface. The influence of the pretightening sequence and times on the contact stress distribution characteristics under pretightening force is analyzed in this paper. To reduce the non-uniformity of the contact stress profile, a pretightening force correction model under different pretightening conditions was established. The impacts of the pretightening forces before and after correction on the homogeneity of the contact stress profile were compared. The results show that multi-time pretightening and an appropriate pretightening sequence improve the contact stress profile characteristics. Applying the corrected pretightening force significantly reduces the non-uniformity of the contact stress profile. Specifically, applying the corrected pretightening force multiple times in sequence is effective in further reducing the dispersion of contact stress distribution at the fitting surface. Pretightening in a diagonal sequence is more efficient in improving the homogeneity of contact stress. The research will contribute to precision manufacturing as well as the regulation of aero-engine rotor systems.
Liu, Enxiao, Zhang, Meng, Dong, Jiaxu, Li, Zhibin, Tong, Jinyu, Zheng, Jinde, Liu, Yongmeng
The Structure Design of the Rail Car with the Secondary Buffering System2026-99-1923To be published on 11/06/2026
To address the poor cushioning performance of traditional rail car systems, this study proposes a track rail car equipped with a two-stage buffer system. Based on the dynamic principles of the two-stage buffer system, SolidWorks was used to model both the rail car body and its buffer components. The force distribution on the rail car under identical impact loads served as the evaluation metric for cushioning performance. Through theoretical calculations, the optimal spring stiffness configuration that minimized car body stress was identified. Motion simulation software was employed to conduct dynamic analysis and modeling of these configurations. Following this, 3D printing and assembly were performed, with experimental testing conducted on the assembled rail car to compare the effects of different spring types and damping mechanisms on cushioning performance. Performance parameters were optimized accordingly. Results demonstrated that, based on the optimal stiffness combination of the secondary buffering system, a friction damper could be added to further optimize buffer performance.
Zhang, Chi, Yao, Hai
XGBoost–Bayesian Optimization Method for Multi-Blade Centrifugal Fan2026-99-1921To be published on 11/06/2026
To overcome the trade-off between airflow rate and efficiency in a multi-blade centrifugal fan for automotive air-conditioning systems, as well as the low optimization efficiency of conventional simulation- or experiment-based approaches resulting from the large number of impeller design parameters, a surrogate-model-based optimization framework coupled with an intelligent optimization algorithm is proposed for impeller design. Latin hypercube sampling was employed to generate 120 samples within the design space, and an XGBoost model was integrated with a Bayesian optimization strategy to perform the optimization process. Validation results indicate that the prediction error of the surrogate model is less than 3%. Under the final optimized impeller configuration, the airflow rate is increased by 22% at the design operating condition, while the total pressure efficiency is improved by approximately 20%, satisfying the prescribed design requirements.
Yan, Yaqin, Yue, Chen
Anchoring Mechanics Analysis and Structural Optimization of Slip for Pipeline Plugging Robot2026-99-1915To be published on 11/06/2026
Reliable anchoring of slip is essential for preventing axial slippage of pipeline plugging robots under high-pressure plugging conditions. However, excessive tooth penetration may induce furrow formation, local plastic deformation, and hard-contact damage on the inner wall of the pipeline. To balance anchoring capacity and pipe-wall protection, this study establishes a mechanical model for the slip–pipe interaction and analyzes the effects of key structural parameters on slip anchoring performance. The self-locking condition between the slip and slip bowl is first derived, and the minimum equivalent friction coefficient required for stable anchoring is determined. Subsequently, an explicit finite element model of the slip anchoring process is developed to evaluate the influence of bevel angle, tooth profile angle, and curvature radius on the von Mises stress and equivalent plastic strain of both the slip and the pipe wall. Based on the simulation results, an orthogonal parameter optimization scheme is conducted to identify the optimal structural combination. The results show that the optimized slip structure, consisting of a 20° bevel angle, a 90° tooth profile angle, and a 150 mm curvature radius, can effectively reduce pipe-wall damage while maintaining reliable anchoring performance. This study provides a theoretical and numerical basis for the structural design and optimization of anchoring slip in pipeline plugging robots.
Wang, Mingkuan, Zhang, Enchao, Gao, Ang, Shao, Hongyuan, Zhang, Shimin, Zhu, Xiaoxiao
UAV Positioning and Tracking Measurement Method Based on Laser-Vision Dual-Mode Fusion2026-99-1929To be published on 11/06/2026
Flight positioning accuracy is a key technical indicator of unmanned aerial vehicle (UAV) systems. To quantitatively and accurately evaluate the positioning accuracy of UAV flight trajectories, this paper proposes a theoretical model for motion trajectory measurement and positioning, as well as a systematic solution for tracking measurement, based on a 2D tracking turntable carrying a dual-mode optoelectronic fusion integration system consisting of a laser ranging sensor and a vision camera. It analyzes the main influencing factors of measurement errors and establishes a measurement error model for flight trajectory positioning. Finally, flight trajectory tracking, positioning, and measurement experiments are carried out based on the principle prototype, which verifies the correctness of the method model and the feasibility of the system scheme. This study provides a theoretical basis and technical support for the testing of UAV flight control positioning accuracy indicators.
Qi, Weijie, Qiao, Yongming
2026 International Conference on Intelligent Vehicles and Mechanical Engineering (IVME 2026)2026-99-1900To be published on 11/06/2026
TOC
Tobolski, Sue
Structural Optimization Design of a Compact Electric Tightening Tool for Narrow-Space Assembly Operations2026-99-1906To be published on 11/06/2026
This paper proposes an electric tightening tool for screw tightening in confined spaces during aero-engine assembly. By combining a gear with a curved rack, the tool converts the motor’s rotary motion into the swing motion of the tool head, thereby addressing torque transmission problems in narrow radial spaces. The tool head features an openable clamping mechanism to facilitate operation. Finite element analysis is used to evaluate the stress distribution and strain characteristics of key components under representative loading conditions. The results show that, under the specified working conditions, the stresses and deformations of the key components remain within reasonable ranges, and the structural strength meets the requirements for use.
Bu, Xin, Feng, Junping, Peng, Shuhao, Yang, Yinfei
Category-Aware Transformer for Automotive Spare Parts Demand Forecasting2026-99-1917To be published on 11/06/2026
In the modeling process, existing auto parts demand forecasting methods often fail to clearly distinguish structural differences at the demand-frequency level, which results in limited adaptability in real scenarios characterized by sparse demand and a complex category structure. In response to the above problems, this paper proposes a category-aware Transformer framework for auto parts demand forecasting. To explicitly represent demand differences across frequency-based accessory groups and to reduce training bias caused by long-tail sample imbalance, the framework first constructs frequency categories based on statistical demand characteristics and incorporates them into the model as embedding-based structural priors. It then designs a category-perception attention mechanism within the Transformer to guide differentiated modeling of category-related temporal dependencies. At the same time, in order to improve the expression ability of sparse and nonlinear disturbances, this paper introduces a nonlinear mapping module at the prediction end and uses a weighted loss function based on sample distribution to constrain the training target. Experimental results on three real auto-parts demand datasets from Dongfeng Automobile Co., Ltd. show that the proposed method outperforms five benchmark models in terms of RMSE and MAE, with especially strong performance in predicting intermediate-frequency and long-tail parts.
Yi, Yuxuan, Wang, Xiaodong, Yang, Wei, Cai, Yonghua
Research on a Structured Modeling Method for Aero-Engine Complex Piping System Based on L-System2026-99-0639To be published on 11/06/2026
This paper proposes a structured description and discretized modeling method for aero-engine complex piping systems based on the Lindenmayer system (L-system). By leveraging the grammatical rewriting rules and parametric extensions of L-system, a tree-like structural description and geometric discretization of piping are achieved, addressing the structural characteristics of both typical pipes (e.g., I-type, L-type) and complex three-dimensional pipes (e.g., bifurcated pipes, helical pipes). The proposed framework is further extended to integrate physical attributes, enabling the unified expression of geometry, topology, material, and cross-sectional properties within a single symbolic system. Furthermore, by comparing the dynamic characteristics of continuous and discrete structures in free modal analysis, the feasibility and accuracy of equivalent modeling using discrete straight segments are demonstrated. The discretization granularity is discussed, and the method’s adaptability for different analytical precision requirements is established. This approach successfully unifies the geometric description, structural discretization, and physical property assignment of complex piping, providing a new structured and automated pathway for rapid modeling, dynamic analysis, and optimization design of aero-engine piping. The inherent parameterization and automation advantages of the L-system also open avenues for automatic layout generation, integration with intelligent optimization algorithms, and future development towards a comprehensive “geometry compiler” for CAD/CAE interoperability and digital twin applications.
Zhao, Zhifang, Wang, Xin, Chen, Nan, Liu, Na, Li, Linjie, Wu, Feng
Investigation of Time-varying Limitations in Intelligent Ship Automatic Berthing Control2026-99-0626To be published on 11/06/2026
A backstepping control method combining a time-varying tangent barrier Lyapunov function (BLF) and dynamic surface control (DSC) technology is proposed to address the issue of automatic berthing control of underactuated intelligent ships with unknown time-varying environmental interference and limited position and speed. This approach aims to improve the control accuracy and response speed of the system. First, in order to handle the challenging challenge of controller design, the mathematical model is modified using differential homeomorphism transformation with an eye toward the underactuated properties of ships. Second, the tangent BLF is developed to realize the constraint of the ship’s location and speed error and guarantee the system’s safety by building the time-varying constraint border with exponential decay. When combined with DSC technology, the 'differential explosion' problem, which is common in the backstepping design process, is solved. On this premise, the extended state observer (ESO) is used to estimate and correct for the unknown time-varying disturbance. Lyapunov stability theory proves that the closed-loop system is stable, and the closed-loop signals are bounded. The simulation results show that the suggested control approach has a faster response time than the classic backstepping method and can provide safe and stable autonomous berthing of ships while meeting the limitations, indicating good engineering practicality.
Xu, Donghao, Xu, Yirong
Determination Method of Engagement Position of SSS Clutch in NCB Steam Turbine and Analysis of Its Impact on Shaft System Vibration2026-99-1901To be published on 11/06/2026
An SSS clutch is incorporated into the shaft system of the NCB steam turbine in the gas-steam combined cycle unit. The benefit of this specific design is that the shaft system of the NCB steam turbine can disengage from and engage with the LP rotor during operation, enabling rapid and flexible adjustment between power generation output and heat supply. However, this mode of operation presents some special vibration issues in the shaft system. Analysis of the shaft vibration fluctuations that occur in NCB steam turbines before and after operating mode transitions indicates that this issue arises because the random engagement position of the SSS clutch induces changes in the shaft train’s balance and alignment conditions. Based on the measurement principle of shaft vibration phase and the dual keyphasor measurement system of NCB steam turbines, this paper proposes a novel methodology for determining the optimal engagement position of SSS clutches. This approach establishes quantitative correlations between shaft vibration characteristics and clutch engagement positioning, thereby enabling precise identification of the optimal engagement configuration. The research conclusions provide operational guidance for power plants to optimize shaft vibration in NCB steam turbines.
Song, Tongtong, Song, Yajun, Zhang, Wei, Si, Paiyou, Gao, Yibo
Design and Optimization of an LQR-Based Multivariable Control System for an RBCC Engine2026-99-0632To be published on 11/06/2026
To achieve the key control objectives of thrust regulation and inlet protection for a rocket-based combined cycle (RBCC) engine under wide flight envelope, high-speed operating conditions, this study is based on a nonlinear component-level RBCC engine model developed in MATLAB/Simulink. A state space model is established using a least squares system identification method. By incorporating actuator dynamics, an augmented system model is formulated, and a Differential Evolution (DE) optimized Linear Quadratic Regulator (LQR) multivariable closed-loop control strategy is proposed. Simulation results show that the proposed strategy significantly improves both response speed and disturbance-rejection capability. Compared with the conventional LQR controller, the maximum oscillation of the inlet stability margin is reduced from 11% to 4.4%, and the thrust settling time is shortened by 83%. These results verify the feasibility of the proposed control method under complex operating conditions.
Zheng, Runtong, Han, Chongpeng, Xie, Zhenwei
Analysis and Verification of the Influence of the Fairings on Helicopter Vibration2026-99-0617To be published on 11/06/2026
Fairings can significantly improve the aerodynamic performance of helicopters by reducing drag. At the same time, the fairings' design has a significant effect on the vibration characteristics of the helicopter. The control of helicopter vibration through the optimal design of fairings is one of the key problems. To investigate the influence of fairing design on helicopter vibration, a detailed study was conducted based on aerodynamic theory. The influence of attitude and flight velocity changes during forward flight was analyzed. The causes and mechanisms of vibration induced by fairings were clarified, and the critical factors influencing the main vibration problems were obtained. An engineering example was used to analyze the influence of slightly different fairings on helicopter vibration. Numerical simulation and analysis were carried out for the fuselage flow field at a given indicated airspeed. The results proved that slight differences in fairing design can induce obvious vibration. Therefore, it is necessary to optimize fairing design to reduce vibration. Firstly, a streamlined design should be adopted for fairings to improve aerodynamic performance. Secondly, the locations of fairings must be optimized to avoid the influence of vortex shedding on helicopter structures. Further analysis of the effects of indicated airspeed, descent rate, and other factors shows that helicopter vibration can be significantly reduced by using these methods. It is effective and necessary to address such issues according to the suggestions provided in this paper, which offers valuable guidance for ensuring flight safety.
Wang, Ying, Wang, Wentao, Cheng, Qi-you
Research on the Effect of Aft-Mounted Propeller Slipstream on Aircraft Aerodynamic Characteristics2026-99-0612To be published on 11/06/2026
Propeller aircraft can generally be divided into tractor and pusher configurations. The difference in propeller installation leads to completely different effects of the propeller slipstream on the aircraft's overall aerodynamic properties. This work focuses on a twin-boom aircraft with a tractor propeller and numerically simulates the effect of the slipstream generated by its aft-mounted propeller on the aircraft's overall aerodynamics. The results show that the primary lifting component's lift performance is not significantly impacted by the aft-mounted propeller and wing, and the overall aircraft lift coefficient is basically unaffected by the slipstream. Because the aftmounted propeller is relatively close to the rear of the fuselage, its suction effect increases the airflow velocity and decreases the pressure ahead of the propeller, while also changing the pressure distribution on the fuselage tail. This causes the overall aircraft drag coefficient to increase by about 30%. When the horizontal tail is high-mounted and far from the propeller slipstream area, it is mainly influenced by a combination of factors, including wing downwash, aircraft angle of attack, and additional downwash generated by the propeller. The reduced nose-down pitching moment is a result of the additional downwash from the propeller, which lowers the effective angle of attack at the tail. When the horizontal tail is within the core influence area of the slipstream, the entering flow gains additional energy from the propeller's high-speed rotation, increasing the velocity of the airflow entering the slipstream region. This improves the horizontal tail's aerodynamic efficiency, contributing more to the nose-down pitching moment and a slight increase in its longitudinal static stability.
Li, Shuai, Guan, Chenglin, Li, Tian, Yang, Haohao
Human–Machine Simulation of Lunar Surface Environment Maintenance2026-99-0628To be published on 11/06/2026
In China's manned space programs, extravehicular activities (EVAs) of astronauts on the lunar surface include the assembly, maintenance, and repair of the space station, as well as the operation of extravehicular equipment. Scientific working postures can alleviate occupational fatigue, ensure the health of astronauts, and significantly improve operational efficiency. The human engineering of aerospace equipment based on virtual simulation technologies has long been a focus of attention in the aerospace field. The Jack Software can be used to conduct ergonomic simulation analysis of the comfort of the operating postures of different percentile operators, and thereby explore the rationality of aerospace maintenance operation postures. Based on this, the Jack virtual simulation technology is employed here to study the ergonomics of the entire process of aerospace maintenance operations. The rationality of the simulation results is verified through simulation–based optimization, and corresponding design improvements are realized according to the analysis results to improve the operational efficiency and comfort of operators. This study provides a reference for the ergonomic evaluation and design improvement of domestic aerospace maintenance operations.
Wang, Xi, Gan, Yu
Covariance-based Filtering and Smoothing Estimation under a Round-Robin Protocol2026-99-0627To be published on 11/06/2026
This paper focuses on recursive estimation for stochastic systems under the round-robin (RR) protocol. In recursive estimation, it is assumed that the state evolution process of the signal is unknown, and the relevant estimation research is only carried out relying on the mean and covariance functions of the process. To effectively avoid the occurrence of transmission channel conflicts and ensure the fairness of data allocation during transmission, this paper chooses to adopt the RR protocol to schedule and manage data communication. Specifically, this scheduling rule stipulates that only one sensor is allowed to acquire the network communication opportunity within a fixed time period, and the entire scheduling process is executed cyclically in a preset fixed order. Based on the observable information available in the system, this paper further designs and proposes a recursive estimation algorithm by means of the innovation method. Finally, a numerical simulation experiment is given to verify the effectiveness and feasibility of the proposed estimation algorithm.
Lin, Xiao, Li, Jiaxing, Du, Junhua, Wu, Meiyun
Cooperative Adaptive Cruise Control for Connected Vehicle Platoons with Unknown Control Directions Under Output Constraints2026-99-0624To be published on 11/06/2026
In this paper, a distributed cooperative adaptive cruise control (CACC) strategy is designed for connected vehicle platoons under unknown control directions and time-varying speed constraints. To address vehicle control directions unknown problem arising from uncertain actuator and vehicle parameters, a Nussbaum-type gain is incorporated into the controller design processes, enabling stable operation without prior knowledge of the vehicle direction. Furthermore, the barrier Lyapunov function is employed to enforce speed constraints, ensuring all vehicles remain within safe and admissible velocity bounds. The designed leaderless scheme allows all vehicles to participate equally in coordination, enhancing robustness and scalability under a bidirectional communication topology. Finally, a simulation result is proposed to validate the effectiveness of the CACC strategy.
Li, Xin, Wei, Xiaozong, Chen, Si, Yang, Shaopeng, Liu, Mingyang, Zhu, Liangkuan
A Rapid Determination Method for Key Node Parameters in the Full-Process Launch Vehicle Mission Design2026-99-0641To be published on 11/06/2026
-7
Dong, Chenyu, Liu, Lingyu, Han, Hongwei, Zhang, Longxi, An, Yang, You, Zhipeng
Investigation on Interface Analysis and Process Simulation of Electromagnetic Pulse Welding for Automotive Copper Terminal/Aluminum Conductor Joints2026-99-1922To be published on 11/06/2026
To suppress the formation of brittle intermetallic compounds typically generated during conventional joining of Cu/Al dissimilar materials in the automotive lightweighting sector, this study examines the interface properties and process simulation of electromagnetic pulse welding technology for connecting copper terminals to aluminum conductors. High-quality welds exhibit a wavy interface composed of interpenetrating metallic phases, according to microstructural research. To represent workpiece dynamics, magnetic field distribution, and impact behavior under discharge voltages ranging from 4 to 5.5 kV, a linked electromagnetic-structural finite element model was developed. According to simulation data, increasing the discharge voltage significantly enhances impact pressure, strain rate, and magnetic flux density, all of which support strong contact bonding. The study offers a reference for the lightweight production of automobile electrical connectors by demonstrating the impact of process factors on weld quality.
Li, Liang, Lei, Xiaokun, Fang, Cheng, Li, Yaxiong, Tang, Ming, Wang, Hu, Xie, Chong, Du, Changqing
Regenerative Braking Control Strategy for Electric Vehicle Based on Improved Ant Colony Algorithm2026-99-1919To be published on 11/06/2026
To address low energy recovery efficiency and inaccurate torque distribution of regenerative braking in electric vehicles, this paper proposes an optimized fuzzy control strategy for regenerative braking based on an improved ant colony algorithm. The design focuses on using the battery state of charge, real-time vehicle speed, and braking intensity as fuzzy control inputs, with the regenerative braking ratio as the output. By employing the improved ant colony algorithm to dynamically optimize the parameters of the fuzzy controller, the accuracy of electric motor braking force distribution is effectively improved; Building on this foundation, the introduction of the Elite Ant Guidance Algorithm enhances the speed of adaptive pheromone updates and dynamic path selection, thereby improving regenerative braking energy recovery efficiency. A MATLAB/Simulink simulation model was developed, and comparisons under the NEDC and UDDS test cycles demonstrated that, compared to traditional fuzzy control strategies, the optimized algorithm increases energy recovery efficiency by 12.8% and 8.1%, respectively, confirming the effectiveness and validity of the improved control strategy.
Yang, Zijiang, Zhang, Wei, Zhang, Jihong, Qi, Ye, Zhang, Zilei
The Dynamic Analysis of the Passenger Car Steering and Braking Stability2026-99-1912To be published on 11/06/2026
During cornering-braking maneuvers, an excessively high braking torque can consume a substantial portion of the available tire-road friction and cause insufficient frictional capacity to satisfy the lateral force demand generated by cornering. As a result, the vehicle may experience stability degradation and, in severe cases, lose control, potentially causing accidents. In this study, an AMESim-based vehicle dynamics model is developed, and yaw rate and sideslip angle are adopted as the primary evaluation indices to characterize steering-braking behavior. Under conditions of a fixed turning radius and initial braking speed, the critical braking force was simulated and analyzed. Additionally, the critical steering wheel angle was examined under conditions of a fixed braking torque and steering speed. The results indicate that if either the braking force or the steering wheel angle exceeds its critical value, the vehicle will lose stability during combined steering and braking.
Ma, Lianglin, Yi, Bingjun, Hu, Yang
Items per page:
1 – 50 of 135058