Browse Topic: Data acquisition and handling

Items (5,956)
Find
Data-Based Modeling of Power-Split Hybrids Using Cascaded Neural Networks2025-01-0522To be published on 11/25/2025
Power-split hybrid powertrains represent one of the most advanced and complex types of powertrain systems. The combination of multiple energy sources and power paths offers great potential but results in complex interactions that require improved strategies for optimal efficiency and emission control. The development and optimization of such operating strategies typically involve algorithms that demand fast computational environments. Traditional high-accuracy numerical simulations of such a complex system are computationally expensive, limiting their applicability for extensive iterative optimizations and real-time applications. This paper introduces a data-based approach designed specifically to address this challenge by efficiently modeling the dynamic behavior of power-split hybrid powertrains using cascaded neural networks. Cascaded neural networks consist of interconnected subnetworks, each specifically trained to represent individual drivetrain components or subsystems. This
Frey, Markus, Itzen, Dirk, Yang, Qirui, Grill, Michael, Kulzer, André Casal
Machine learning based audio classification for fully automated validation of off highway infotainment systems2025-28-032311/06/2025
Modern infotainment systems generate a wide range of audio based signals such as indicator chimes, turn signals, infotainment system audio, navigation prompts, and warning alerts. This is a novel and modern approach towards accurately classifying and transcription of these audio to enable fully automated validation. The proposed solution employs a hybrid deep learning architecture leveraging convolutional neural networks (CNNs) and recurrent neural networks (RNNs) trained using labeled audio samples. Automatic Speech Recognition (ASR) models are integrated for transcribing spoken navigation prompts and commands from infotainment systems. The proposed system delivers reliable results in near real-time audio classification and transcription, facilitating error free automation and validation. This provides a robust foundation for edge deployable audio intelligence systems.
Singh, Shwetha, Kamble, Amit, Mohanty, Ananta, Kalidas, Sateesh
Connected Aftermarket Services for Off-Highway Vehicles: Enhancing Fleet Management Through Real-Time Data and Predictive Maintenance2025-28-030711/06/2025
Off-highway vehicles (OHVs) are critical to industries such as construction, agriculture, and mining, where they often operate in challenging environments requiring constant maintenance and repair. This paper presents a connected platform designed to enhance customer support and fleet management by integrating real-time data monitoring, predictive maintenance, and e-commerce capabilities. Through IoT-enabled sensors, cloud computing, and data analytics, the system continuously collects and analyzes vehicle performance data, providing fleet owners with actionable insights for efficient resource allocation and maintenance scheduling. The platform offers automated alerts for part replacements, tracking of repair history, and optimization recommendations based on vehicle condition. By integrating e-commerce for aftermarket parts and services, fleet managers can easily purchase and manage the inventory required for their operations. This connected system not only improves operational
Vashisht, Shruti
Development of a Cost-Effective DCU for Diesel Emission Control: Design, Diagnostics, and Compliance2025-28-028611/06/2025
An essential aspect of contemporary emission control technology, especially in diesel engines with Selective Catalytic Reduction (SCR) systems, is the Doser Control Unit (DCU) for exhaust systems. Its main purpose is to accurately regulate the injection of urea or diesel exhaust fluid (DEF) into the exhaust stream to lower harmful emissions of nitrogen oxides (NOₓ) to meet CPCB4+ emissions. The Doser Control Unit architecture, operation, significance of analytical / experimental study and originality of contribution are described in this abstract. The ECU can determine and administer the exact dosage rate needed under various operating conditions since it gets real-time data from engine and exhaust sensors, such as exhaust temperature, NOₓ levels, and engine load. The DCU activates the Adblue pump in response to the ECU's dosage request, which is determined by the parameters listed above. In addition to having a solenoid actuator for quick dosing responses, the system has features of
Raju, Manikandan, K, Sabareeswaran, K K, Uthira Ramya Bala, Krishnakumar, Palanichamy, Arumugam, Arunkumar, YS, Ananthkumar
Automated Offboard system to measure the volume of harvested material2025-28-033111/06/2025
Problem Statement: Measuring the volume of harvested material behind the machine can be beneficial for various agricultural operations, such as baling, dropping, material decomposition, cultivation, and seeding. This paper aims to investigate and determine the volume of material for use in various agricultural operations. This proposed methodology can help to predict the amount of residue available in the field, assess field readiness for the next production cycle, measure residue distribution, determine hay readiness for baling, and evaluate the quantity of hay present in the field, among other applications which would benefit the customer. Solution Statement: • TO Improve the agricultural production system. • By – Measuring the volume of harvested material • Using – Remote Sensing and IoT Technology: System is going to use Onboard camera and satellite image to determine the volume of materials. The system collects data from the capture device during runtime to obtain information
Singh, Rana Shakti
Advanced Compliance Risk Assessment Using Big Data from Fleet Intelligence Data2025-28-034311/06/2025
In-Use compliance regulations globally mandate that machines meet emission standards in the field, beyond dyno certification. For engine manufacturers, understanding compliance risks early is crucial for technology selection, calibration strategies, and validation routines. This study focuses on developing analytical and statistical methods for compliance risk assessment using Leverage Fleet Intelligence (LFI) data, which includes high-frequency telematics data from over 500K machines, reporting 1300 measures at 1Hz frequency. Traditional analytical methods are inadequate for handling such big data, necessitating advanced methods. We developed data pipelines to query measures from the Enterprise Data Lake (A Structured Data storage system), address big data challenges, and ensure data quality. Regulatory requirements were translated into software logic and applied to pre-processed data for compliance assessment. The resulting reports provide actionable insights on NOx sensor activity
Arya, Satya Prakash, Shekarappa, Kiran
Cybersecurity: Applying Threat Modeling to Sensor-Control Architectures in Autonomous Off-Highway Vehicles2025-28-031611/06/2025
The increasing autonomy and connectivity of off-highway vehicles—such as tractors, harvesters, and construction equipment—introduce new cybersecurity challenges, particularly within the sensor-to-control data flow that governs real-time decision-making and actuation. These architectures comprise a mix of embedded sensors, electronic control units (ECUs), communication buses (e.g., CAN, Ethernet), and actuators, all of which are susceptible to cyber-physical threats that can compromise safety, performance, and reliability. This paper proposes a systematic application of threat modeling, using the STRIDE framework, to assess and mitigate risks in sensor-control systems specific to autonomous off-highway machinery. It provides a practical methodology for identifying trust boundaries, constructing Data Flow Diagrams (DFDs), and mapping threats such as spoofing of GNSS/GPS inputs, CAN message injection, sensor data tampering, and control logic manipulation. By contextualizing threat
Kotal, Amit
Digital solution using immersive technology for field failure2025-28-030611/06/2025
Warranty claims act as primary source of characterizing field failures across industries, wherein appropriate classification of these claims is critical for further analysis. The classification of warranty claims is a highly laborious effort involving significant man-hours of warranty analysts. This can be highly optimized & made efficient using direct interpretation of the claim data on 3D model using unity game engine. Additionally, the color perception technique using immersive technology (AR/VR) can help to identify the vital few & drive prioritization of the field failures leading to faster problem resolution. The capabilities of UIUX & Advanced Visualization integrated to develop novel method to classify the warranty claims & interpret it on a 3D model using immersive technology which is novel & one of its kind in Industry. Unique characteristics of this tool is it focuses on the warranty claim classification by claim cost & count of claims and presents the heat map (Red-High
Nankery, Vivek, savadatti, Sandeep, Shete, Atul, Apkare, Sanket, Ganapathi, Poongundran
A Framework for network protocol selection for Smart Factories2025-28-024511/06/2025
In the current phase of Industry 4.0, the selection of appropriate network protocols is a critical factor in enabling real-time data, high-speed motion control, and IT-OT connectivity in smart factories. Yet, selecting the right network protocols for smart factories remains a complex challenge, as no single protocol suits all 05 layers of the automation pyramid, from field-level sensors layer to enterprise layer. This paper explores how network protocols can be mapped to different layers of the automation pyramid, ranging from sensor layer (L0) to enterprise-level data layer (L4). For example, Profinet is shown to be highly effective for time-critical applications such as robotic assembly and motion control due to its deterministic, real-time Ethernet capabilities. Meanwhile, IO-Link offers a, point-to-point solution with its diagnostic capabilities for intelligent sensors and actuators, making it ideal for IoT-driven data collection. Other protocols, such as EtherCAT and OPC UA, each
Tarapure, Prasad
Reduction in Product Development Time by Field-to-Lab Simulation2025-28-028211/06/2025
KEYWORDS: Flywheel Inertia, Clutch system, Gear Box, Tractor application, Instrumentation, data analysis, Design and develop new test methodology. ABSTRACT: Puddling is a crucial process in rice cultivation, involving the preparation of the soil in a flooded field to create a soft, muddy seedbed. There are two classifications for puddling: full cage and half cage. Full cage puddling involves replacing the rear wheels of the tractor with steel paddle wheels, which are used to till the rice paddies directly without any additional implement. In the half cage puddling, the rear wheels remain on the tractor, and a smaller cage or paddle wheel is attached to the outside. Considering the field size, the operator often releases the clutch very quickly after a speed or direction change. This generates torque spikes, which are harmful to Transmission Gears and Clutches. This can lead to gear teeth bending fatigue failure due to repeated higher bending stresses. In this paper, a study related to
Pathan, Irfan Hamidulla, Bardia, Prashant
Smart Fleet Management for Mechanical Tillage Implements2025-28-031211/06/2025
Tillage, a fundamental agricultural practice involving soil preparation for planting, has traditionally relied on mechanical implements with limited real-time data collection or adjustment capabilities. The lack of real-time data and implement statistics results in fleet managers struggling to track performance, driver behavior, and operational efficiency of the implements. Lack of data on vehicle performance can result in unexpected breakdowns and higher maintenance costs, ensuring compliance with regulations is challenging without proper data tracking, potentially leading to fines and legal issues. Bluetooth-enabled mechanical implements for tillage operations represent an emerging frontier in precision agriculture, combining traditional soil preparation techniques with modern wireless technology. Implement mounted battery powered BLE (Bluetooth Low Energy) modules operated by solar panel based rechargeable batteries to power microcontroller. When Implement is operational turns
Kaniche, Onkar, Rajurkar, Kartik, Gokhale, Sourabha, Vadnere, Mohan
Revolutionizing Vehicle Warranty Management with AI and Real-Time Data Integration2025-28-030411/06/2025
Vehicle owners often face challenges in understanding product and part warranties, leading to frustration when warranty claims are rejected due to predefined manufacturer rules. This paper presents a novel solution to enhance vehicle warranty management and maintenance through an AI-driven mobile application. The proposed system provides personalized warranty information, real-time support, and maintenance cost estimates based on vehicle specific data. By leveraging AI and machine learning algorithms, the app interprets customer queries through text, voice, video, or image inputs and fetches relevant data from the manufacturer's database, ensuring accurate and timely responses. Continuous data collection improves the system's accuracy over time, enhancing customer satisfaction and support. The application also assists customers with product quality assessments, vehicle servicing plans, approximate servicing costs, product replacement costs, part availability from nearby dealers, and
Ramekar, Vedant Madhav, Chaudhari, Hemant
Integrating AI in Wiring Harness Design for enhanced efficiency2025-28-031111/06/2025
Modern vehicle manufacturing faces increasing challenges due to the complexity of wiring harness design for diverse variants, each with unique requirements and configurations. This paper introduces a transformative AI-driven approach to address these complexities. By utilizing Convolutional and Deep Neural Networks (CNN & DNN), the proposed system automates the generation of harness routing based on predefined specifications and constraints, significantly reducing human intervention, design time, and complexity. AI-trained models can also predict failures in production, minimizing downtime and improving efficiency, while AI integration seamlessly translates design parameters into manufacturable outcomes, optimizing tasks such as connector placements, grommet fittings and clip alignments. To tackle the inherent dynamic variant complexity, the system employs a novel framework that learns and adapts to unique design constraints in real-time. Unlike static master-slave frameworks, the
N, Rishi Kumaar, Patil R, Bharath, Rajavelu, Vivek, Ramachandran, Vignesh, Mohanty, Lalit, Padmarajan, Vishnu
Design IQ2025-28-032711/06/2025
Weight and cost are critical parameters in any new product development program, influencing aspects such as homologation and efficiency. Traditionally, tracking these parameters at the machine, subsystem, and module levels involves a manual, time-consuming process. This reactive approach often delays the program and hampers the productivity of design engineers. These challenges can be managed with an automation and simulation. WCOSAP automates the extraction of weight details, identifies outliers, calculates module-level impacts, and predicts future weight changes. This proactive tool eliminates repetitive manual work, enhances data accuracy, and supports dynamic updates. By integrating real-time data and predictive models, WCOSAP enables sound decision-making and proactive weight control during the design phase, ultimately improving efficiency and reducing the need for part revisions. This paper discusses the development, implementation, and benefits of the WCOSAP tool, highlighting
Patil, Vivek, Sahoo, Abhilash, Ballewar, Sachin, Chidanandappa, Basavaraj, Chundru, Satyanarayana
Analysis of Injected Mass Shot-To-Shot Dispersion and Injection Rate Profile for a PFI Injector in Actual Operating Conditions2025-32-001911/03/2025
In order to improve engine emission and limit combustion instabilities, in particular for low load and idle conditions, reducing the injected fuel mass shot-to-shot dispersion is mandatory. Unfortunately, the most diffused approach for the hydraulic analysis of low-pressure injectors such as PFIs or SCR dozers is restrained to the mean injected mass measurement in given operating conditions, since the use of conventional injection analyzers is unfeasible. In the present paper, an innovative injection analyzer is used to measure both the injection rate and the injected mass of each single injection event, enabling a proper dispersion investigation of the analysed low pressure injection system. The proposed instrument is an inverse application of the Zeuch’s method, which in this case is applied to a closed volume upstream the injector, with the injector being operated with the prescribed upstream-to-downstream pressure differential. Further, the injector can inject freely against air
Postrioti, Lucio, Maka, Cristian, Martino, Manuel
Smart Energy Management System for Hybrid Electric Vehicles: Integrating Fuel Cells and Ultra-Capacitors using Neural Network2025-28-036510/30/2025
This paper offers a state-of-the-art energy-management strategy specifically developed for FCHEV focusing on robustness under uncertain operations. Currently, energy management strategies try to optimize fuel economy and take into account the sluggish response of fuel cells (FCs); however, they mostly do so assuming all system variables are explicit and deterministic. In real-world operations, however, a variety of sources may cause the uncertainty in power generation, energy conversion, and demand interactions, e.g., the variation of environmental variables, estimated error, and approximation error of system model, etc., which accumulates and adversely impacts the vehicle performance. Disregarding these uncertainities can result in overestimation of operating costs, overall efficiency and overstepped performance limitations, and, in serious cases can cause catastrophic system breakdown. To mitigate these risks, the current work introduces a neural network-based energy management
Deepan Kumar, Sadhasivam, M, Boopathi, R, Vishnu Ramesh Kumar, Karthick, K N, R, Nithiya, R, Krishnamoorthy, V, Dayanithi
Development of Capacitive Pressure Sensor for Automotives2025-28-038710/30/2025
Measurement plays a crucial role in the precise and accurate management of automotive subsystems to enhance efficiency and performance. Sensors are essential for achieving high levels of accuracy and precision in control applications. Rapid technical advancements have transformed the automobile industry in recent years, and a wide range of novel sensor devices are being released to the market to speed up the development of autonomous vehicle technology. Nonetheless, stricter regulations for reliable pressure sensors in automobiles have resulted from growing legal pressures from regulatory bodies. This work proposes and investigates a tribo electric nano sensor that is affected by a changing parameter of the separation distance between the device's primary electrode and dielectric layers. The system is being modeled using the COMSOL multiphysics of electrostatics and the tribo-electric effect. Open circuit electric potential and short circuit surface charge density are two of the
P, Geetha, K, Neelima, Sudarmani, R, C, Venkataramanan, Satyam, Satyam, Nagarajan, Sudarson
A Physics-Guided Neural Network Approach for EGR Cooler Temperature Estimation: Addressing ECU Model Discrepancies2025-28-039310/30/2025
As the automotive industry explores alternative powertrain options to curb emissions, it is pertinent to refine existing technologies to improve efficiency. The Exhaust Gas Recirculation (EGR) system is one of the pivotal components in emission control strategies for Internal Combustion Engines (ICE). The EGR cooler is crucial in thermal management strategies, as it lowers the temperature of recirculated exhaust gases before feeding it along with fresh air, thereby reducing nitrogen oxides (NOx) emissions. Precise estimation of the EGR cooler outlet temperature is crucial for effective emission control. However, conventional Engine Control Unit (ECU) models fall short, as they often show discrepancies when compared to real-world test data. These models rely on empirical relationships that struggle to capture precisely the transient effect, and real time variation in operating conditions. To address these limitations and improve the accuracy of ECU based model, various signal processing
Kumar, Amit, Kumar, Raman, Manojdharan, Arjungopal, Challa, Krishna, Kramer, Markus
Optimizing Electric Vehicle Motor Testing with Fine Gaussian SVM and Bilayered Neural Network2025-28-039710/30/2025
Electric vehicles are shaping the future of the automotive industry, with the drive motor being a crucial component in their operation. Ensuring motor reliability requires rigorous testing using specialized test benches to validate key performance parameters. However, inefficiencies in the helical gear configuration within these test systems have led to frequent malfunctions, affecting production flow. This study focuses on optimizing the motor test bench by refining critical design parameters through vibration signal analysis and machine learning techniques. Vibrational data is collected under different gear configurations, utilizing an accelerometer integrated with a Data Acquisition (DAQ) system and MATLAB-based directives for seamless data collection. Machine learning classifiers, including Fine Gaussian SVM and Bilayered Neural Network, are applied to categorize signals into normal and faulty conditions, both with and without a 0.25 KW load. The analysis reveals that SVM achieves
S, Ravikumar, Sharik, N, Syed, Shaul, V, Muralidharan, D, Pradeep Kumar
Simulation of Hydraulic Retarder Using Particleworks2025-28-038210/30/2025
This study explores the application of Particleworks, a meshless CFD solver based on the Moving Particle Simulation (MPS) method, for simulating hydraulic retarders. Two distinct models were used: one for validating physical fidelity and another for conducting performance-focused design investigations. Validation results demonstrated that Particleworks closely aligns with experimental data from the reference literature, effectively capturing torque variations with rotor speed effect. A sensitivity study also emphasized the importance of particle resolution on accuracy and computational cost. Design studies using an in-house hydraulic retarder model assessed the influence of flow rate, rotor speed, working fluid, temperature, and cup geometry on braking torque. Notably, torque increased with rotor speed and steeper cup angles, while thermal effects and fluid properties significantly impacted performance trends. Comparative analysis with Star-CCM+ showed that Particleworks offers similar
Kumar, Kamal S., Chaudhari, Gunjan B.
3D CFD Analysis of Flow and Thermal Dynamics of PEM Water Electrolyzer2025-28-035010/30/2025
The proton exchange membrane (PEM) water electrolyzer is an emerging technology to produce green hydrogen due to its compactness and producing high purity hydrogen. This study presents a numerical investigation on multiphase flow dynamics and heat transfer within the anode flow field of a PEM water electrolyzer. Two different channel configurations, i.e., rectangular, semi-circular are considered having same cross-sectional area while keeping the porous transport layer (PTL) thickness constant (which is within the commercially available ranges). Simulations are conducted for various oxygen generation rates and heat fluxes (corresponding to different current densities) and different inlet water flow rates. The effects of channel configurations on pressure drop, flow uniformity, and temperature distribution are illustrated pictorially and graphically. The impact of water flow rates and oxygen generation rates on phase distribution, pressure drop, and temperature profiles, particularly
Dash, Manoj Kumar, Bansode PhD, Annasaheb
Automotive Battery Thermal Management by Federated Learning Methodology - Real Time Thermal Runaway Detection2025-28-040810/30/2025
Modern battery management systems, as part of Battery Digital Twin, include cloud-based predictive analytics algorithms. These algorithms predicts critical parameters like Thermal runaway events, state of health (SOH), state of charge (SOC), remaining useful life (RUL), etc. However, relying only on cloud-based computations adds significant latency to time-sensitive procedures such as thermal runaway monitoring. This is a very critical and safety function and delay is not acceptable, but automobiles operate in various areas throughout the intended path of travel, internet connectivity varies, resulting in a delay in data delivery to the cloud and similarly delay in return of the detected warning to the driver back in the vehicle. As a result, the inherent lag in data transfer between the cloud and vehicles challenges the present deployment of cloud-based real-time monitoring solutions. This study proposes application of Federated Learning and applying to a thermal runaway model in low
Sarkar, Prasanta
Dome Profile Optimization and Stress Analysis of Type IV Composite Cylinders Using a CLT-Based MATLAB Program and FEA Validation2025-28-037410/30/2025
Type IV composite pressure (CP) vessels composed of a plastic liner and composite layers require special design attention to the dome region. The cylindrical portion of the composite cylinder is wrapped with composite layers consisting of the 900 hoop layers and low-angle helical layers, whereas the dome surface carries helical layers only. The winding angle of the helical layers being a constant over the cylindrical portion starts to vary from the cylinder-dome junction toward the boss at the top continuously. Along with the winding angle, the composite thickness also varies continuously resulting in a maximum thickness at the top crown region. The complete analysis and layer-wise stress prediction of Type IV composite cylinders for service pressures up to 70 MPa was analyzed by the Classical Lamination theory (CLT)-based MATLAB program. The MATLAB program developed in this work for the dome initially performs the dome profile generation through the numerical integration of the dome
R. S., Nakandhrakumar, Tandi, Ronak, M, Ramakrishnan, Raja, Selvakumar, Elumalai, Sangeethkumar, Velmurugan, Ramanathan
Diagnostics Methodology for Turbocharger System Using Data Driven Models2025-28-040410/30/2025
In a conventional powertrain driven by Internal combustion (IC) engines, turbocharger (TC) is a key component for enhancing performance and efficiency. Predominantly turbochargers are used to serve multiple purposes of downsizing, increased power, better fuel efficiency, reduced emissions, and improved performance at high altitudes. TC is responsible for fulfilling the air mass requirement of the engine at different operating conditions. Failure of TC system leads to abnormal engine operation. If the TC hardware is beyond repair, the associated replacement cost is very high. Ultimately, a predictive diagnostics approach is required to identify the issue with TC so that the failure of TC could be avoided. The proposed methodology uses advanced artificial intelligence technique called recurrent neural network (RNN) and long short-term memory (LSTM) network for predicting faults in a typical TC system. In this study, actual values of TC speed and boost pressure are obtained from physical
Jagtap, Virendra Shashikant, Ganguly, Gourav, Mitra, Partha, Patidar, Sachin
Research on the Degree of Airport Intelligence Level Based on Three-Scaled Hierarchical Analysis Method2025-99-003710/17/2025
Smart airport is a key driver for the future development of civil aviation and a cornerstone of China’s ongoing “Four Airport” construction initiative. It is important to improve technology in many areas. This includes airport building, daily work, management, and making decisions. As air travel changes, using new tools like artificial intelligence, big data, and the Internet of Things (IoT) is very important. These tools help make airports more efficient, safe, and better for the environment. Because of this, building smart airports is not just a big goal but also a new way to deal with the challenges in today’s air travel systems. A key part in building smart airports is making a full evaluation system to check how well the projects are working. When a strong index system is made for smart airports, people involved can see clearly what is working well and what is not. So, chose using a three-scale hierarchical analysis method gives a clear and step-by-step way to look at different
Li, Shi-ling, Fu, Lu
Spatial-temporal Information Organization Model with All Elements in Whole Domain for Shuozhou-Huanghua Railway2025-99-007910/17/2025
In view of the complexity of railway engineering structure, the systematicness of professional collaboration and the high reliability of operation safety, this paper studied the spatial-temporal information data organization model with all elements in whole domain for Shuozhou-Huanghua Railway from the aspect of Shuozhou-Huanghua Railway spatial-temporal information security. Taking the unique spatial-temporal benchmark as the main line, the paper associated different spatial-temporal information to form an efficient organization model of Shuozhou-Huanghua Railway spatial-temporal information with all elements in the whole domain, so as to implement the effective organization of massive spatial-temporal information in various specialties and fields of Shuozhou-Huanghua Railway; By using GIS (Geographic Information System) visualization technology, spatial analysis technology and big data real-time dynamic rendering technology, it was realized the real-time dynamic visualization display
Liu, Kun, Yu, Hongsheng, Zhu, Panfeng, Liu, Wenbin, Wang, Yaoyao
Research on the Sinker Location of Light Buoy Based on Mean Shift Algorithm2025-99-003610/17/2025
In order to determine the actual position of the beacon buoy, improve the casting accuracy of the beacon buoy, and reduce the frequency of the beacon buoy being hit, the mean shift model of the sinker location was established according to the real-time position data of the beacon telemetry and remote control, and the probability density distribution of the beacon buoy position was obtained and the actual position of the beacon buoy was analyzed. In order to ensure the comprehensiveness and accuracy of the research results, real-time data of light buoy positions in different sea areas and at different times were selected, and MATLAB simulation experiments were conducted to compare the actual sinker location with the designed position. The experimental results show that the mean shift algorithm can accurately predict the actual position of the stone, which provides a useful reference for improving the casting accuracy of the Marine light buoy.
Liu, Huan, Song, Shaozhen, Ju, Xin, Lin, Xiaozhuo
The Morning Commute Problem with Carpool and Dynamic Toll Scheme2025-99-002210/17/2025
This study extends the bottleneck model to analyze dynamic user equilibrium (UE) in carpooling during the morning peak commute. It is assumed that the carpooling platform offers both traditional human-driven vehicles and novel shared autonomous vehicles. First, we analyze the traffic distribution on a two-lane road. We find that traffic distribution is influenced by the additional cost of carpooling behavior. A corresponding functional relationship is established and visualized. Second, we derive the critical fare threshold for carpooling. Carpooling occurs only when the fare is below this threshold. Third, we obtain the user equilibrium (UE) solution under a specified case, including flow distribution, equilibrium cost, and total number of vehicle. Furthermore, a system-optimal dynamic tolling scheme is proposed to minimize total system cost while maintaining commuter UE. By equating the system marginal cost to the equilibrium cost, we derive the analytical expression for the lane
Zheng, XiaoLong, Zhong, RenXin
Robust Object Tracking Method Based on Multi-Level Association Matching2025-99-002010/17/2025
Target tracking is an important component of intelligent vehicle perception systems, which has outstanding significance for the safety and efficiency of intelligent vehicle driving. With the continuous improvement of technologies such as computer vision and deep learning, detection based tracking has gradually become the mainstream target tracking framework in the field of intelligent vehicles, and target detection performance is the key factor determining its tracking performance. Although remarkable progress has been made in current 3D object detection networks, a single network still struggles to provide stable detection for distant and occluded targets. Besides, traditional tracking methods are based on single-stage association matching, which can easily lead to identity jumps and target loss in case of missed detections, resulting in poor overall stability of the tracking algorithm. To solve the above problem, a hierarchical association matching method using a dual object
Wu, Shaobin, Chu, Yunfeng, Li, Yixuan, Su, Shengjie, Liu, Zhaofeng, Li, Xiaoan, Si, Lingrui
Evolution of Port and Terrestrial Space in the Coast Zone of Bohai Bay from 1974 to 20232025-99-006310/17/2025
In the past half - century, China’s reclamation area has exceeded 15,000 km2, making it the country with the largest reclamation area in the world. Among them, 3% of the area of the Bohai Sea has been reclaimed, and the land - sea changes are very significant, making accurate and continuous monitoring and analysis of the area necessary. Starting from “dynamic monitoring - utilization analysis”, this paper studies the dynamic spatial distribution and quantitative changes of reclaimed areas in Bohai Bay based on the yearly remote sensing images from 1974 to 2023, using ENVI and GIS technologies. In the past 40 years, a total of 1379.79 km2 of the sea area has been reclaimed in the study area, mainly in the inshore and tidal flats. The land - use change map shows that land - use changes are closely related to policy and economic mode changes. Under the five - year time slice, the comprehensive land - use degree of the Bohai Bay is less than 4%, showing an extremely slow chagne.
Li, Yi, Zhu, Gaoru
Key Influential Factors for Smart Logistics in Guangzhou Based on DEMATEL -AHP2025-99-002310/17/2025
Use Decision Making Trial and Evaluation Laborator (DEMATEL) and Analytic Hierarchy Process (AHP) to jointly analysis and determine the key factors of Guangzhou intelligent logistics. Through the questionnaire survey of 92 logistics enterprises in Guangzhou, it is concluded that Information infrastructure, big data, Internet of Things, artificial intelligence, Logistics dynamic updates, and Smart warehousing have a great impact on intelligent logistics. Combining practical engineering with theory to make the implementation of Guangzhou’s smart logistics project more scientific, It is characterized by a higher degree of scientificity. Moreover, it is of great warning value, which can alert relevant parties to potential issues. Meanwhile, it provides essential guidance for the implementation of the smart city project in Guangzhou, facilitating a more efficient and well - directed execution process. This study is limited to logistics business respondents in Guangzhou and may limit the
Zhang, Shuangshuang, Chen, Ning, Khaw, Khai Wah, Liu, Chenxi, Jin, Lili
Research on the Layout and Robustness Testing of Electric Vehicle Battery Swap Stations Based on Graph Neural Networks: A Case Study of the Main Urban Area of Nanchang City2025-99-000810/17/2025
With the rapid increase in the number of electric vehicles, the rational placement of battery swapping stations has become a critical issue in optimizing urban transportation infrastructure. This paper proposes a site selection optimization method based on Graph Neural Networks (GNN). By constructing an urban transportation graph model grounded in Points of Interest (POI) and road traffic data, the method analyzes battery swapping station layout plans and validates their robustness and scalability. Taking the main urban area of Nanchang City as a case study, the research integrates data on POI distribution and land-use functional diversity within buffer zones to construct a graph structure. It then employs GNN for node classification to identify optimal battery swapping station locations. Experimental results show that, compared to traditional methods, the proposed approach improves site selection accuracy by 15% and enhances optimization efficiency by 20%. This method can provide
Zeng, Yi, Yi, Xinyu
Study on Fluctuation Rules of CCFI Main Routes Based on Empirical Mode Decomposition2025-99-003510/17/2025
The China Container Freight Index (CCFI) is an important barometer of the global container shipping market. It is very important for participants in the shipping market to understand its composition. This study takes six representative routes as the research objects and conducts a detailed analysis of the composition of CCFI. The freight rate indices of these routes are decomposed and reconstructed by using the Empirical Mode Decomposition (EMD) algorithm, aiming to clarify the economic significance of each route and the fluctuation law of the reconstructed components. The research results show that the freight rate fluctuations of the west Coast, Southeast Asia and Mediterranean routes exhibit a complex nonlinear interdependence, and the simple linear model cannot fully reflect this relationship. On the contrary, the trend components of the European and Mediterranean routes effectively identify and represent the main trends within the original freight rate index. Global major events
Yin, Sitian
Road Traffic State Classification Method Based on AutoEncoder and Clustering Algorithm2025-99-004810/17/2025
Urban road traffic state classification is essential for identifying early-stage deterioration and enabling proactive traffic management. This study presents a novel method to accurately assess the traffic state of urban roads while addressing the limitations of existing methods in spatial generalization performance. The approach consists of three key components. First, several indicators are designed to capture the spatial-temporal evolution mechanisms of traffic state, speed freedom, flow saturation, and their variations over time and space. Then, a feature learning module based on an AutoEncoder network is introduced to reduce the dimensionality of the constructed feature set. This enhances feature distinction while mitigating noise effects on classification results. Third, k-means clustering is applied to analyze significant features extracted from the AutoEncoder latent space, categorizing road traffic states into fluent, basic fluent, moderate congested and severe congested
Wang, Xiaocong, Huang, Min, Guo, Xinling, Xie, Jiemin, Zhang, Xiaolan
Architecture Analysis & Design Language (AADL) Annex F: AADL Annex for the FACE™ Technical Standard Edition 3.0AS5506/4 (Current)10/13/2025
AS-2C Architecture Analysis and Design Language
Strength Prediction of Self-Piercing Riveted Joints Using Practical Regression and Bayesian Neural Network2025-01-506810/10/2025
Self-piercing riveting (SPR) is a key joining method in multi/thin-material automotive structures, yet accurately predicting the mechanical strength of SPR joints remains challenging due to numerous influencing factors. Empirical engineering equations [1] provide a foundation for estimating lap-shear and cross-tension strength but require several geometric parameters that are often unavailable in the design phase. To address this limitation, we extract and leverage the core physical relationships embedded in these formulas. By reformulating the dependence of joint strength on the yield strength and total thickness of the sheet stack as practical regression models, we enable strength prediction using only commonly available material properties. Furthermore, a Bayesian convolutional neural network (BCNN) model is developed to incorporate additional material features, offering improved prediction accuracy and uncertainty quantification.
Soproni, Istvan, Womack, Darren, Liu, Zongyue, Balaji, Ashwin, Kulange, Deepak
Deep Reinforcement Learning with Behavioral Cloning for Path Tracking of Four-Wheel Steering Vehicles10-10-01-000110/09/2025
When the vehicle system performs trajectory tracking control, it presents relatively complex nonlinear coupling dynamics characteristics. The traditional coordination algorithm relying on a simplified linear model is mostly unable to deal well with the actual nonlinear dynamic behaviors. In contrast, reinforcement learning (RL) method will derive the optimal strategy by means of interaction with the environment. This eliminates the need for accurate vehicle modeling. These methods use all of the nonlinear approximation capabilities of deep neural networks and can effectively reflect the complex relationship between vehicle state and control actions. The framework itself supports multidimensional input processing and continuous operation space optimization because of the development of parallel processing architectures. In order to reduce the motion jitter caused by the direct generation of front and rear wheel angles by the network, this article uses steering angle increments as
Ren, Gaotian, Wang, Yangyang
Reducing Powertrain Software Release Cycles from Months to Days: Streamlined Compliance and Rapid Deployment2025-01-037910/07/2025
The automotive industry's rapid shift towards electric and connected vehicles intensifies the demand for robust solutions addressing software integrity, cybersecurity, and stringent regulatory compliance, particularly concerning powertrain components and related control units. This paper addresses the significant challenge faced by automotive companies in efficiently managing and deploying an exponentially increasing number of software and hardware variants under the rigorous requirements of UNECE Regulation No. 156. This regulation mandates secure, traceable, and systematic software update processes for new vehicles and their components [1]. The proposed solution demonstrates a transformative approach that significantly reduces the software release cycle for Over-The-Air (OTA) updates which usually take 6 to 8 months to emerge [2]. By leveraging advanced techniques in automated compliance tracking, efficient parameter management, and centralized documentation, this approach bridges
Sammer, Gerald, Schuch, Nikolas, Kammerhofer, Markus
ML-Based System Level Optimization of EV Cooling Circuit2025-01-037610/07/2025
Efficient thermal management is vital for electric vehicles (EVs) to maintain optimal operating temperatures and enhance energy efficiency. Traditional simulation-based design approaches, while accurate, are often computationally expensive and limited in their ability to explore large design spaces. This study introduces a machine learning (ML)-based optimization framework for the design of an EV cooling circuit, targeting a 5°C reduction in the maximum electric motor temperature. A one-dimensional computational fluid dynamics (1D-CFD) model is utilized to generate a Design of Experiments (DOE) matrix, incorporating key parameters such as coolant flow rate and heat exchanger dimensions. A Radial Basis Function (RBF) neural network is trained on the simulation data to serve as a surrogate model, enabling rapid performance prediction. Optimization is performed using the Non-Dominated Sorting Genetic Algorithm II (NSGA2), yielding three distinct design solutions that meet the thermal
Paul, Kavin, Ganesan, Arul, Mansour, Youssef
Investigation of Transient High Current Ignition for Lean Mixture in Spark Assisted Compression Ignition2025-01-039010/07/2025
Lean burn combustion is an effective strategy to reduce the in-cylinder temperature. Hence reduce NOx emissions and increase the thermal efficiency of the system. One essential aspect of successful combustion is the flame kernel initiation and development. However, as the fuel-air mixture becomes leaner, challenges arise in achieving a stable flame kernel initiation and a moderate speed of flame propagation. This empirical research aims to investigate the impact of the transient high current ignition strategy on flame kernel development, flame propagation and auto-ignition timing of lean Dimethyl Ether (DME). In this work, a rapid compression machine is employed at engine-relevant conditions, a pressure of ~15 bar and temperature of ~650K. Spark-assistance is applied at the end of compression to enable a spark-assisted compression ignition combustion mode. The spark event is initiated by a transient high current ignition system, which includes a traditional transistorized coil ignition
Asma, Sabrina, Yu, Xiao, Jin, Long, Tjong, Jimi, Zheng, Ming
Remaining Useful Life prediction of Engine Fuel System Using Machine Learning2025-01-037710/07/2025
Reliability and uptime are critical priorities in the automotive industry, prompting a shift toward predictive maintenance (PdM) to minimize unexpected failures and associated costs. This study presents a machine learning-based framework for early prediction of engine fuel system failures using embedded field performance data. This study introduces a machine learning-based framework for predicting failures and estimating the remaining useful life (RUL) of mid-range diesel engines with high-pressure common rail fuel systems in vehicles using classification and regression models applied to embedded field performance analysis data, aiming to enhance reliability and reduce unplanned downtime. Two classification models --- Random Forest and XGBoost top our model metrics chart. They were further tuned and evaluated, with XGBoost achieving superior performance, including 94% accuracy and 87% precision, and a low false positive rate of 0.01, enabling an 8-day lead time for proactive
Wang, Tingting, Goswami, Anil, Akinola, Michael, Yang, Tina, An, Qi
Automotive Engineering: October 202525AUTP1010/02/2025
Engineering EV, charger safety and security From a quick access port to help firefighters fight EV battery fires faster than otherwise possible to preventing public charger vandalism, here are some developments that haven't made the big headlines. Electronic stability control builds the foundation for safer roads How a mechanically simple idea has kept cars stable for decades, and why it can still evolve for an autonomous future. The factory's hidden power grid Why smart electrical distribution is the new frontier in sustainable manufacturing. Safety by design: a next-gen blueprint for EV batteries The EV industry can - and should - stop pushing decades-old battery architecture well past its limits. Vehicle fire safety with Erbis Biscarri Author turns classroom quest into a tome for anyone who wants to engineer safer cars. Editorial IAA Mobility: A new class of auto show Supplier Eye The new supplier strategy playbook BMW brings EV motor production to Steyr in Austria Ford unveils its
High Performance Enclosure Systems for Aerospace and Defense Applications: Preparing for What's Next25AERP10_0210/01/2025
As mission-critical systems demand more processing power, real-time data movement, and multi-domain interoperability, rugged embedded systems are being transformed. Today's military and aerospace applications increasingly demand the merging of AI computing, enhanced sensor interfaces, and cybersecurity - all under harsh environmental conditions. At the heart of this evolution is the 3U OpenVPX form factor, a modular, compact, and ruggedized hardware standard and increasingly the SOSA aligned subset of the architecture. However, next-generation systems need to go further: supporting higher bandwidth, better thermal efficiency, improved security, while maintaining multi-vendor interoperability and long-term sustainability. We'll discuss some of today's enclosure solutions as well as emerging technologies.
Health and Usage Monitoring System Data Interchange SpecificationAS5395A (Current)09/18/2025
This document establishes the Rotorcraft Industry Technology Association (RITA) Health and Usage Monitoring System Data Interchange Specification. The RITA HUMS Data Interchange Specification will provide information exchange within a rotorcraft HUMS and between a rotorcraft HUMS and external entities.
HM-1R Rotorcraft Integrated Vehicle Health Management
Using Artificial Neural Networks for Predicting Vehicle Survivability within a Virtual Simulation2025-01-048209/16/2025
A unique contribution the U.S. Army currently provides is what is known as Virtual Experiments (VEs). A VE consists of a large group of active-duty soldiers who participate in a video game simulating a battlefield scenario. During these simulations, the soldiers are provided with novel protective vehicle capabilities in an effort to evaluate their effectiveness on the battlefield. However, these VEs take a significant amount of time to conduct and are expensive. Using Artificial Neural Networks (ANNs) this study looks to predict vehicle survivability based on a limited amount of VE data. The results entail an overall predictive accuracy of 76.8% using only two ANN input features and provides a framework for the eventual addition of more VE datasets.
O’Bruba, Joseph
Leveraging Spectral Unmixing for Improved Mobility in Vegetated Environments2025-01-048009/16/2025
The success of off-road missions for ground vehicles depends heavily on terrain traversability, which in turn requires a thorough understanding of soil characteristics a key component being soil moisture content. When large areas need to be analyzed, satellite imagery is often used, although this approach typically reduces the spatial resolution. This decrease of spatial resolution creates what are known as mixed pixels, when two or more classes or features are in a single pixel’s area, which can lead to noisier data and lower accuracy models. This paper investigates using linear spectral unmixing as a way to help clean / mitigate noisy data to yield better predictive models. Hyperspectral remote sensing from the Hyperion satellite platform and ground truth from the International Soil Moisture Network (ISMN) are used for the dataset. This study found that soil moisture content prediction, comparing the mixed multilayer perceptron (MLP) model with an unmixing approach revealed a 10–30
Ewing, Jordan, Jayakumar, Paramsothy, Kasaragod, Anush, Oommen, Thomas
Infoscraps: Enforcing Information Security by Mechanism2025-01-049509/16/2025
Several information security problems currently require the vigilance of the defender to prevent exploitation or misclassification of information, specifically code injection vulnerabilities and enforcement of Security Classification Guides. This paper discusses a potential solution that can enforce some of these rules by computer mechanism, reducing the potential for security problems. The solution is to replace using simple text strings with data structures containing both a string and a key-value data store. This metadata allows the computer to apply automated rules to enforce data sanitization and classification.
Czerniak, Gregory P.
Commander’s Decision Analysis Tool for Maintenance: Applications of Unsupervised Learning with Pattern Characterization (ULPC) in Vehicle Health Assessment2025-01-049009/16/2025
Within the military maintenance cycle, commanders and units struggle with understanding the operational readiness of their fleets from a data driven perspective. Many unsupervised learning techniques have been developed with applications for vehicle maintenance with pattern classification. In this paper, Predictive Maintenance using Unsupervised Learning with Pattern Characterization (ULPC) is proposed to classify the overall health of the platform system and subsystems. In this model, the key features are selected using an intelligent pre-processing system for signal classification for each subsystem. Next the data is processed and compared to a normalcy baseline dataset using the unsupervised machine learning (ML) model. Operational data collected post-baseline is then processed through a Recurrent Neural Network (RNN) and clustered. An overall “normalcy” metric is calculated to show the difference in operation when compared to the baseline patterns. This normalcy servers as an
Bailey, Jeffrey, Cabrey, Connor, Hsu, Charles
Using Power BI to Visualize and Configure System Variants in Model-Based Product Line Engineering2025-01-045009/16/2025
This paper explores the integration of Microsoft Power BI into Model-Based Systems Engineering (MBSE) workflows, specifically within a Model-Based Product Line Engineering (MBPLE) context. Power BI provides a versatile platform for visualizing, analyzing, and manipulating data, enabling users to configure system variants outside traditional MBSE environments while maintaining integration back into the original MBSE model. This approach enhances collaboration between engineering and business disciplines, improves decision-making with real-time data analysis, and allows users to configure and evaluate multiple system variants efficiently. Additionally, the paper discusses how Power BI’s interactive dashboards facilitate better accessibility and analysis, bridging the gap between technical teams and non-technical stakeholders. Future work will focus on improving data pipeline automation and incorporating feature performance metrics to enable real-time trade study analysis, further
Pykor, Ryan, Engle, Jake
MOSA C2 for Autonomous Vehicles to Counter UAS, SWARM, and Ground-Based Robotic Threats2025-01-043509/16/2025
A Modular Open Systems Approach (MOSA) for command and control (C2) of autonomous vehicles equipped with sensor and defeat mechanisms enhances force protection against unmanned aerial systems (UAS), swarm, and ground-based robotic threats with current technology while providing an adaptable framework able to accommodate technological advances. This approach emphasizes modularity, which allows for independent upgrades and maintenance; interoperability, which ensures seamless integration with other systems; and scalability, which enables the system to grow and adapt to increasing threats and new technologies – all of which are essential for managing complex, dynamic, and evolving operational threats from UAS, swarm, and ground-based robots. The proposed systems approach is designed around component-based modules with standardized interfaces, ensuring ease of integration, maintenance, and upgrades. The integration of diverse sensors through plug-and-play capabilities and multi-sensor
Davidson, Jeremy, Drewes, Peter, Graham, Roger, Haider, Eric, Phillips, Michael
Items per page:
1 – 50 of 5956