Browse Topic: Neural networks

Items (1,210)
As vehicle emission standards are becoming stringent worldwide because of the looming climate crisis, it is important to control the pollutants that vehicles emit. To achieve the stringent emission target, it has become a priority to enhance the capability of Emission Control System (ECS) which consist of Diesel Oxidation Catalyst (DOC), Diesel Particulate Filter (DPF) and Selective Catalytic Reduction (SCR) sub-systems. One of the bottlenecks is the limited operating temperature range of the after-treatment system. In modern emission control systems, the temperature characteristics should always be optimized to have the best efficiency involving chemical conversions. To achieve this optimal operating temperature, different thermal control strategies are followed in the Engine and emission control unit. Temperature sensor values are one of the primary inputs for thermal management strategies. In the event of temperature sensor malfunction, the ECS performance is affected due to
Kumar, AmitV H, YashwanthKumar, RamanHegde, KarthikManojdharan, Arjungopal
This study presents a comprehensive survey of the current state-of-the-art techniques in virtual scene generation, particularly within the context of autonomous driving. The integration of deep learning methods such as generative adversarial networks (GANs) and convolutional LSTM (ConvLSTM) is explored in detail. Additionally, the effectiveness and applicability of these techniques in simulating real-world traffic scenarios are analyzed. Our article aims to bridge the gap between theoretical models and practical applications, providing an in-depth understanding of how deep learning and virtual scene generation converge to enhance the efficacy of autonomous driving systems
Ayyildiz, Dilara VefaAlnaser, Ala JamilTaj, ShahramZakaria, MahtaJaimes, Luis Gabriel
ABSTRACT New generations of ground vehicles are required to perform tasks with an increased level of autonomy. Autonomous navigation and Artificial Intelligence on the edge are growing fields that require more sensors and more computational power to perform these missions. Furthermore, new sensors in the market produce better quality data at higher rates while new processors can increase substantially the computational power. Therefore, near-future ground vehicles will be equipped with large number of sensors that will produce data at rates that has not been seen before, while at the same time, data processing power will be significantly increased. This new scenario of advanced ground vehicles applications and increase in data amount and processing power, has brought new challenges with it: low determinism, excessive power needs, data losses and large response latency. In this article, a novel approach to on-board artificial intelligence (AI) is presented that is based on state-of-the
Ghiglino, PabloHarshe, Mandar
ABSTRACT In this paper we present an intelligent power controller for a vehicle power system that employs multiple power sources. In particular we focus on a vehicle power system architecture that is used in vehicles such as Mine Resistant Ambush Protected (MRAP) vehicle. These vehicles are designed to survive IED (Improvised Explosive Devices) attacks and ambushes. The power system has the following major components: a “clean” bus, a “dirty” bus, an engine, a hydraulic system and a switch between the clean and the dirty bus. We developed algorithms for intelligent energy management for this type of vehicle power system including DP (Dynamic Programming) optimization, DP online control and a machine learning technique that combines neural networks with DP to train an intelligent power controller. We present experiments conducted through modeling and simulation using a generic commercial software tool and a lab hardware setup
Chen, ZhihangMurphey, Yi L.Chen, ZhengMasrur, AbulMi, Chris
ABSTRACT Many recent advances in autonomy are derived from algorithm optimization and analysis with a large volume of data. The Autonomous Mobility Through Intelligent Collaboration (AMIC) program established a resource to host and access data to accelerate autonomy capability development across the U.S. Army Robotics and Autonomous Systems enterprise. The repository is seeded with high-quality multi-modal Autonomous Ground Vehicle sensor data collected from relevant operating environments. Development of unmanned air-ground teaming capability that extends the perception and planning horizon of an individual ground vehicle exercises and informs the development of the data warehouse. Collected data was also used to train a convolutional neural network to estimate relative vehicle position from camera images for communication-free formation control. Citation: M. Boulet, E. Cristofalo, P. DeBitetto, D. Griffith, A. Heier, S. Kassoumeh, A. Plotnik, A. Wu, “Applications of a Shared Data
Boulet, MichaelCristofalo, EricDeBitetto, PaulGriffith, DanielHeier, AndrewKassoumeh, SamPlotnik, AaronWu, Alan
ABSTRACT A promising approach to autonomous driving is machine learning. In machine learning systems, training datasets are created that capture the sensory input to a vehicle as well as the desired response. One disadvantage of using a learned navigation system is that the learning process itself may require both a huge number of training examples and a large amount of computing. To avoid the need to collect a large training set of driving examples, we describe a system that takes advantage of the immense number of training examples provided by ImageNet, but at the same time is able to adapt quickly using a small training set for the driving environment
Provodin, ArtemTorabi, LiilaMuller, UrsFlepp, BeatSergio, MichaelŽbontar, JureLeCun, YannJackel, L. D.
ABSTRACT Autonomous vehicle perception has been widely explored using camera images but is limited with respect to LiDAR point cloud processing. Furthermore, focus is primarily on well-regulated environments, obviating a need for an algorithm that can contextualize dynamic and complex conditions through 3D point cloud representation. In this report, an Echo State Network for LiDAR signal processing is introduced and evaluated for its ability to perform semantic segmentation on unregulated terrains, using the RELLIS-3D open-source dataset. The L-ESN contains 16 parallel reservoirs with point cloud processing time of 1.9 seconds and 83.1% classification rate of 4 classes defining terrain trafficability, with no prior feature extraction or normalization, and a training time of 31 minutes. A 2D cost map is generated from the segmented point cloud for integration as a perception node plug-in to system-level navigation architectures. Citation: S. Gardner, M. R. Haider, P. Fiorini, S. Misko
Gardner, S.Haider, M. R.Fiorini, P.Misko, S.Smereka, J.Jayakumar, P.Gorsich, D.Moradi, L.Vantsevich, V.
ABSTRACT Recurrent Neural Networks have largely been explored for low-dimensional time-series tasks due to their fading memory properties, which is not needed for feed-forward methods like the Convolutional Neural Network. However, benefits of using a recurrent-based neural network (i.e. reservoir computing) for time-independent inputs includes faster training times, lower training requirements, and reduced computational burdens, along with competitive performances to standard machine learning methods. This is especially important for high-dimensional signals like complex images. In this report, a modified Echo State Network (ESN) is introduced and evaluated for its ability to perform semantic segmentation. The parallel ESN containing 16 parallel reservoirs has an image processing time of 2 seconds with an 88% classification rate of 3 classes, with no prior feature extraction or normalization, and a training time of under 2 minutes. Citation: S. Gardner, M. R. Haider, J. Smereka, P
Gardner, S.Haider, M.R.Smereka, J.Jayakumar, P.Kulkarni, K.Gorsich, D.Moradi, L.Vantsevich, V.
ABSTRACT As the Army leverages Prognostic and Predictive Maintenance (PPMx) models to migrate ground vehicle platforms toward health monitoring and prescriptive maintenance, the need is imminent for a pipeline to quickly and constantly move operational and maintenance data off the platform, through analytic models, and push the insights gained back out to the edge. This process will reduce data-to-decision time and operation and sustainment costs while increasing reliability for the platform and situational awareness for analysts, subject matter experts, maintainers, and operators. The US Army Ground Vehicle Systems Center (GVSC) is collaborating with The US Army Engineer Research and Development Center (ERDC) to develop a system of systems approach to stream operational and maintenance data to appropriate computing resources, collocating the data with DoD High-Performance Computing (HPC) processing capabilities where appropriate, then channeling the generated insights to maintainers
Bond, W. GlennPokoyoway, AndrewDaniszewski, DavidLucas, CesarArnold, Thomas L.Dozier, Haley R.
ABSTRACT The fundamental aspect of unmanned ground vehicle (UGV) navigation, especially over off-road environments, are representations of terrain describing geometry, types, and traversability. One of the typical representations of the environment is digital surface models (DSMs) which efficiently encode geometric information. In this research, we propose a collaborative approach for UGV navigation through unmanned aerial vehicle (UAV) mapping to create semantic DSMs, by leveraging the UAV wide field of view and nadir perspective for map surveying. Semantic segmentation models for terrain recognition are affected by sensing modality as well as dataset availability. We explored and developed semantic segmentation deep convolutional neural networks (CNN) models to construct semantic DSMs. We further conducted a thorough quantitative and qualitative analysis regarding image modalities (between RGB, RGB+DSM and RG+DSM) and dataset availability effects on the performance of segmentation
Brand, Howard J. J.Li, Bing
ABSTRACT A critical and time-consuming part of commissioning an unmanned ground vehicle (UGV) is tuning and calibrating the navigation and control systems. This involves selecting and modifying parameters for these systems to obtain a desired response. Tuning these parameters often requires experience or technical expertise that may not be readily available in a time of need. Even the simple task of measuring the mounting location of the sensors introduce opportunities for user error. In addition, the tuning parameters for these systems may change significantly between UGVs. These challenges motivate the need for automated tuning and calibration algorithms to set parameters without the interaction from a user. This work presents automated tuning and calibration approaches for UGVs. Citation: N. Bunderson, D. Bevly, A. Costley, W. Bryan, G. Mifflin, C. Balas “Automated Tuning and Calibration for Unmanned Ground Vehicles”, In Proceedings of the Ground Vehicle Systems Engineering and
Bunderson, NateBevly, DavidCostley, AustinBryan, WilliamMifflin, GregoryBalas, Cristian
ABSTRACT This paper describes the use of neural networks to enhance simulations for subsequent training of anomaly-detection systems. Simulations can provide edge conditions for anomaly detection which may be sparse or non-existent in real-world data. Simulations suffer, however, by producing data that is “too clean” resulting in anomaly detection systems that cannot transition from simulated data to actual conditions. Our approach enhances simulations using neural networks trained on real-world data to create outputs that are more realistic and variable than traditional simulations. Citation: P.Feldman, “Training robust anomaly detection using ML-Enhanced simulations”, In Proceedings of the Ground Vehicle Systems Engineering and Technology Symposium (GVSETS), NDIA, Novi, MI, Aug. 11-13, 2020
Feldman, Philip
ABSTRACT To advance development of the off-road autonomous vehicle technology, software simulations are often used as virtual testbeds for vehicle operation. However, this approach requires realistic simulations of natural conditions, which is quite challenging. Specifically, adverse driving conditions, such as snow and ice, are notoriously difficult to simulate realistically. The snow simulations are important for two reasons. One is mechanical properties of snow, which are important for vehicle-snow interactions and estimation of route drivability. The second one is simulation of sensor responses from a snow surface, which plays a major role in terrain classification and depends on snow texture. The presented work describes an overview of several approaches for realistic simulation of snow surface texture. The results indicate that the overall best approach is the one based on the Wiener–Khinchin theorem, while an alternative approach based on the Cholesky decomposition is the second
Vecherin, SergeyMeyer, AaronQuinn, BrianLetcher, TheodoreParker, Michael
ABSTRACT The real-world testing of robotic and autonomous vehicles faces many challenges including: safety; feasibility; effectiveness; expense; and timeliness. The development of high performance computing has created innumerable opportunities for effectively and efficiently processing large data sets. These data sets can range from modeling and simulation scenarios to the vast amounts of complex data being gathered by unmanned vehicles. In all cases, the data needs to be stored, managed, and processed to have usable information to drive smart decision making. Leveraging high performance computing to more efficiently, effectively, and economically conduct robotic and autonomous vehicle testing in a virtual environment is a logical step. Consequently, TARDEC has developed a real-time modeling and simulation capability to test and evaluate autonomy solutions while RAVE has designed and developed a specialized high performance computing system for TARDEC to support this capability
Rosenberger, KarlBlackmer, SaraWesoloski, SteveBrabbs, John
ABSTRACT Accurate terrain mapping is of paramount importance for motion planning and safe navigation in unstructured terrain. LIDAR sensors provide a modality, in the form of a 3D point cloud, that can be used to estimate the elevation map of the surrounding environment. But, working with the 3D point cloud data turns out to be challenging. This is primarily due to the unstructured nature of the point clouds, relative sparsity of the data points, occlusions due to negative slopes and obstacles, and the high computational burden of traditional point cloud algorithms. We tackle these problems with the help of a learning-based, efficient data processing approach for vehicle-centric terrain reconstruction using a 3D LIDAR. The 3D LIDAR point cloud is projected on the ground plane, which is processed by a generative adversarial network (GAN) architecture in the form of an image to fill in the missing parts of the terrain heightmap. We train the GAN model on artificially generated datasets
Sutavani, SarangZheng, AndrewJoglekar, AjinkyaSmereka, JonathonGorsich, DavidKrovi, VenkatVaidya, Umesh
ABSTRACT Can convolutional neural networks (CNNs) recognize gestures from a camera for robotic control? We examine this question using a small set of vehicle control gestures (move forward, grab control, no gesture, release control, stop, turn left, and turn right). Deep learning methods typically require large amounts of training data. For image recognition, the ImageNet data set is a widely used data set that consists of millions of labeled images. We do not expect to be able to collect a similar volume of training data for vehicle control gestures. Our method applies transfer learning to initialize the weights of the convolutional layers of the CNN to values obtained through training on the ImageNet data set. The fully connected layers of our network are then trained on a smaller set of gesture data that we collected and labeled. Our data set consists of about 50,000 images recorded at ten frames per second, collected and labeled in less than 15 man-hours. Images contain multiple
Kawatsu, ChrisKoss, FrankGillies, AndyZhao, AaronCrossman, JacobPurman, BenStone, DaveDahn, Dawn
ABSTRACT This paper will document the development of the Combat Identification (CombatID) System. The CombatID System was designed to create a platform agnostic payload that could be attached to any fielded Unmanned Ground Vehicle (UGV) to assist the Soldier in contingency basing operations. This paper will describe the approach taken to develop the system, providing a detailed description of the system, including sample results for individual modules. This paper will also provide insight on the evaluation of CombatID system’s performance
Salgian, GarbisKira, ZsoltHadsell, RaiaChiu, Han-PangZhou, XunChai, Bing-BingSamarasekera, SupunTheisen, BernardRamsey, Jeffery
ABSTRACT Modern perception systems for autonomous vehicles are often dependent on deep neural networks, however, such networks are unfortunately susceptible to subtle perturbations to their inputs. Due to the interconnected nature of perception/control systems in autonomous vehicles, it is quite difficult to evaluate the autonomy stack’s robustness in different scenarios. Numerous tools have been developed to assist developers increase the robustness of these algorithms for on-road driving, but little has been accomplished for off-road driving. This work aims to bridge this gap by presenting a reinforcement learning framework to identify unsuspecting off-road scenes that confuse a custom autonomy stack with a DNN-based perception algorithm to ultimately lead the vehicle into a collision. Citation: T. Sender, M. Brudnak, R. Steiger, R. Vasudevan, B. Epureanu, “Using Deep Reinforcement Learning to Generate Adversarial Scenarios for Off-Road Autonomous Vehicles,” In Proceedings of the
Sender, TedBrudnak, MarkSteiger, ReidVasudevan, RamEpureanu, Bogdan
ABSTRACT A major benefit of intelligent and autonomous vehicles is their ability to navigate through hazardous environments that pose a significant danger to humans. In such environments, eventual damage to vehicle sensors is often inevitable. To address this threat to vehicle function, we propose a more robust system in which information from alternative sensors is leveraged to restore navigation capabilities in the case of primary sensor failure. This system employs image translation methods that enable the vehicle to use images generated from an auxiliary camera to synthesize the display of the primary camera. In this work, we present a conditional Generative Adversarial Network (cGAN) based method for view translation coupled with a Residual Neural Network for imitation learning. We evaluate our approach in the CARLA simulator and demonstrate its ability to restore navigation capabilities to a real-world vehicle by generating a front-view image from a left-camera view. Citation
Zhang, DanSanders, BradleyByrd, GraysonLuo, FengKrovi, VenkatGorsich, DavidSmereka, Jonathon M.Brudnak, Mark
ABSTRACT Due to the high complexity of modern internal combustion engines and powertrain systems, the proper calibration of the electronic control unit’s (ECU) parameters has a strong impact on project targets like fuel consumption, emissions and drivability, as well as development costs and project duration. Simulation methods representing the system behavior with a model can support the calibration process considerably. However, standard physics-based models are often not able to describe all effects with sufficient accuracy, or the effort to set up a detailed model is too high. Physics-based models can also have a high computational demand, so that their simulation is not real-time capable. More suited for ECU calibration are data-driven models, combined with Design of Experiment (DoE). The system to be calibrated is identified with few specific test bench or vehicle measurements. From these measurements, a mathematical regression model is built. This paper describes recently
Gutjahr, TobiasKruse, ThomasHuber, Thorsten
The highway diverging area is a crucial zone for highway traffic management. This study proposes an evaluation method for traffic flow operations in the diverging area within an Intelligent and Connected Environment (ICE), where the application of Connected and Automated Vehicles (CAVs) provides essential technical support. The diverging area is first divided into three road sections, and a discrete state transition model is constructed based on the discrete dynamic traffic flow model of these sections to represent traffic flow operations in the diverging area under ICE conditions. Next, an evaluation method for the self-organization degree of traffic flow is developed using the Extended Entropy Chaos Degree (EECD) and the discrete state transition model. Utilizing this evaluation method and the Deep Q-Network (DQN) algorithm, a short-term vehicle behavior optimization method is proposed, which, when applied continuously, leads to a vehicle trajectory optimization method for the
Fang, ZhaodongQian, PinzhengSu, KaichunQian, YuLeng, XiqiaoZhang, Jian
Butterflies can see more of the world than humans, including more colors and the field oscillation direction, or polarization, of light. This special ability enables them to navigate with precision, forage for food, and communicate with one another. Other species, like the mantis shrimp, can sense an even wider spectrum of light, as well as the circular polarization, or spinning states, of light waves. They use this capability to signal a “love code,” which helps them find and be discovered by mates
In this article, a novel tuning approach is proposed to obtain the best weights of the discrete-time adaptive nonlinear model predictive controller (AN-MPC) with consideration of improved path-following performance of a vehicle at different speeds in the NATO double lane change (DLC) maneuvers. The proposed approach combines artificial neural network (ANN) and Big Bang–Big Crunch (BB–BC) algorithm in two stages. Initially, ANN is used to tune all AN-MPC weights online. Vehicle speed, lateral position, and yaw angle outputs from many simulations, performed with different AN-MPC weights, are used to train the ANN structure. In addition, set-point signals are used as inputs to the ANN. Later, the BB–BC algorithm is implemented to enhance the path-tracking performance. ANN outputs are selected as the initial center of mass in the first iteration of the BB–BC algorithm. To prevent control signal fluctuations, control and prediction horizons are kept constant during the simulations. The
Yangin, Volkan BekirYalçın, YaprakAkalin, Ozgen
This article presents experimental investigations and machine learning-based analysis on depositions of super duplex stainless steel (SDSS ER2594) material in wire arc additive manufacturing (WAAM) considering the process parameters namely voltage, wire feed rate, torch travel speed, and gas flow rate. Deposition efficiency and surface height values of the accumulated material were measured to build machine learning models using artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). The developed ANN model could predict the deposition efficiency and surface height with mean absolute deviations (MADs) of 8.9% and 16.1%, respectively. The MAD for prediction of the two responses for ANFIS model was found to be 6.1% and 14.9% as compared to the experimental data. Multi-objective optimization was also performed to obtain optimal solutions to achieve desired deposition results. Mechanical properties and microstructures of the deposited materials with optimal
Kumar, PrakashMondal, SharifuddinMaji, Kuntal
In order to modify both stiffness and damping rates according to various road conditions, this research introduces a pneumatic spring in conjunction with a magnetorheological (MR) fluid damper as a single suspension unit for each wheel in the truck. Preventing weight transfer and improving riding comfort during braking, acceleration, and trajectory prediction are the main objectives. A two-axle truck has been used, consisting of three degrees of freedom for the sprung mass, including vertical, pitch, and roll motions, and four degrees of freedom for the unsprung masses, which have been redesigned according to the different types of springs and dampers. Pneumatic-controlled springs, often referred to as dynamic or classic models, replace laminated leaf springs commonly found in vehicles. Additionally, an MR damper replaces a hydraulic double-acting telescopic shock absorber. These models are studied to evaluate the effect of pneumatic spring parameters on truck dynamics. Pneumatic
Shehata Gad, AhmedEl-Zomor, Haytham M.
The integration of Artificial Intelligence (AI) and Machine Learning (ML) technologies has significantly changed various industries. This study demonstrates the application of a Convolutional Neural Network (CNN) model in Computational Fluid Dynamics (CFD) to predict the drag coefficient of a complete vehicle profile. We have developed a design advisor that uses a custom 3D CNN with a U-net architecture in the DEP MeshWorks environment to predict drag coefficients (Cd) based on car shapes. This model understands the relationship between car shapes and air drag coefficients calculated using computational fluid dynamics (CFD). The AI/ML-based design advisor feature has the potential to significantly decrease the time required for predicting drag coefficients by conducting CFD calculations. During the initial development phase, it will serve as an efficient tool for analyzing the correlation between multiple design proposals and aerodynamic drag forces within a short time frame
Bijjala, Sridhar
In recent times there has been an upward trend in “Connected Vehicles”, which has significantly improved not only the driving experience but also the “ownership of the car”. The use of state-of-the-art wireless technologies, such as vehicle-to-everything (V2X) connectivity, is crucial for its dependability and safety. V2X also effectively extends the information flow between the transportation ecosystem pedestrians, public infrastructure (traffic management system) and parking infrastructure, charging and fuel stations, Etc. V2X has a lot of potential to enhance traffic flow, boost traffic safety, and provide drivers and operators with new services. One of the fundamental issues is maintaining trustworthy and quick communication between cars and infrastructure. While establishing stable connectivity, reducing interference, and controlling the fluctuating quality of wireless transmissions, we have to ensure the Security and Privacy of V2I. Since there are multiple and diverse
Sundar, ShyamPundalik, KrantiveerUnnikrishnan, Ushma
Background: Road accident severity estimation is a critical aspect of road safety analysis and traffic management. Accurate severity estimation contributes to the formulation of effective road safety policies. Knowledge of the potential consequences of certain behaviors or conditions can contribute to safer driving practices. Identifying patterns of high-severity accidents allows for targeted improvements in terms of overall road safety. Objective: This study focuses on analyzing road accidents by utilizing real data, i.e., US road accidents open database called “CRSS.” It employs advanced machine learning models such as boosting algorithms such as LGBM, XGBoost, and CatBoost to predict accident severity classification based on various parameters. The study also aims to contribute to road safety by providing predictive insights for stakeholders, functional safety engineering community, and policymakers using KABCO classification systems. The article includes sections covering
Babaev, IslamMozolin, IgorGarikapati, Divya
Additive Manufacturing (AM) techniques, particularly Fusion Deposition Modeling (FDM), have received considerable interest due to their capacity to create complex structures using a diverse array of materials. The objective of this study is to improve the process control and efficiency of Fused Deposition Modeling (FDM) for Thermoplastic Polyurethane (TPU) material by creating a predictive model using an Adaptive Neuro-Fuzzy Inference System (ANFIS). The study investigates the impact of FDM process parameters, including layer height, nozzle temperature, and printing speed, on key printing attributes such as tensile strength, flexibility, and surface quality. Several experimental trials are performed to gather data on these parameters and their corresponding printing attributes. The ANFIS predictive model is built using the collected dataset to forecast printing characteristics by analyzing input process parameters. The ANFIS model utilizes the learning capabilities of neural networks
Pasupuleti, ThejasreeNatarajan, ManikandanD, PalanisamyA, GnanarathinamUmapathi, DKiruthika, Jothi
Elastomeric bushings are common components in vehicles, used to reduce noise, vibration, and harshness. Rubber bushings are employed in suspension components such as control arm bushings, subframe bushings, and motor mount bushings, each with varying static and dynamic stiffness requirements depending on vehicle weight and ride and handling performance. Traditional rubber bush simulations typically use simple material models like hyperelastic or viscoelastic models. However, recent advancements have introduced more sophisticated material models to capture the nonlinear and time-dependent behavior of rubber materials. These advanced models may incorporate nonlinear viscoelasticity, strain rate dependency, and damage mechanics. Rubber bushings experience multiple physical phenomena simultaneously, such as mechanical loading, thermal effects, and fluid-structure interaction. New simulation techniques enable the coupling of different physics domains, allowing for a comprehensive analysis
Hazra, SandipMore, VishwasTangadpalliwar, Sonali
Electrification is driving the use of batteries for a range of automotive applications, including propulsion systems. Effective management of thermal energy in lithium-ion battery pack is essential for both performance and safety. In automotive applications especially, understanding and managing thermal energy becomes a critical factor. Cells in the propulsion battery pack dissipate heat at high discharge rates. Cooling performance of battery can be realized by optimizing the various parameters. Computational Fluid Dynamics (CFD) model build and simulations are resource intensive and demand high performance computing. Traditionally, evaluating thermal performance involves time-consuming CFD simulations. To address this challenge, the proposed novel approach using Generalized Neural Network Regression (GNNR) eliminates complex CFD model building and significantly reduce simulation time. GNNR achieves up to 85% accuracy in predicting Heat Transfer coefficient. The benefits of GNNR extend
Althi, Tirupathi RaoManuel, NaveenK, Manu
For turbocharged engine design, manufacturer-provided turbocharger maps are typically used in simulation analysis to understand key engine performance metrics. Each data point in the turbocharger map is generated by physically testing the hardware or through CFD analysis—both of which are time-consuming and expensive. As such, only a modest set of data can be generated, and each data map must be interpolated and extrapolated to create a smooth surface, which can then be used for engine simulation analysis. In this article, five different machine learning algorithms are described and compared to experimental data for the prediction of Cummins Turbo Technologies (CTT) fixed geometry turbines within and outside of the experimental data range. The results were validated against xxx-provided test data. The results demonstrate that the Bayesian neural networks performed the best, realizing a 0.5%–1% error band. In addition, it is extrapolatable when suitable manually created extra data
Supe, ShreyasNatarajan, BharathShaver, Greg
The industrial internet of things (IIoT) is the nervous system in manufacturing facilities worldwide, with programmable logic controllers (PLCs) serving as its vital synapses. This digital neural network is transforming isolated machines into interconnected ecosystems of unprecedented intelligence and efficiency. PLCs have evolved from simple control devices into sophisticated nodes in a vast, responsive network
Tracking of energy consumption has become more difficult as demand and value for energy have increased. In such a case, energy consumption should be monitored regularly, and the power consumption want to be reduced to ensure that the needy receive power promptly. Our objective is to identify the energy consumption of an electric vehicle from battery and track the daily usage of it. We have to send the data to both the user and provider. We have to optimize the power usage by using anomaly detection technique by implementing deep learning algorithms. Here we are going to employ a LSTM auto-encoder algorithm to detect anomalies in this case. Estimating the power requirements of diverse locations and detecting harmful actions are critical in a smart grid. The work of identifying aberrant power consumption data is vital and it is hard to assure the smart meter’s efficiency. The LSTM auto-encoder neural network technique is used here for predicting power consumption and to detect anomalies
Deepan Kumar, SadhasivamArun Raj, VR, Vishnu Ramesh KumarManojkumar, R
The topic of decarbonisation involves improvements of hybrid vehicles powertrains design, from fuel type, powertrain components sizing and configuration up to control strategies. To reduce the emission of pollutants due to the combustion of traditional fuels, manufacturers are moving towards the use of “green fuels”, such as green hydrogen. In this context, the series hybrid vehicles demonstrate excellent potential: they can be equipped with hydrogen-fuelled combustion engines as range extenders, which can operate at optimal conditions without suffering from extreme transient manoeuvres. A suitable design of the control strategy of vehicle powertrain is mandatory to optimally manage the power split between range extender and battery, considering features and operating limits of both components according to power constraints. This paper proposes an Energy Management Strategy (EMS), derived from an optimal approach suitable for online applications, which accounts for the key points
Cervone, DavideSicilia, MassimoPandolfi, AlfonsoPolverino, PierpaoloSementa, PaoloArsie, IvanPianese, Cesare
Selective Catalytic Reduction (SCR) systems are crucial for automotive emissions control, as they are essential to comply with stringent emissions regulations. Model-based SCR controls are used to minimize NOx emissions in a broad range of real-word driving scenarios, constantly adapting the urea injection to diverse load and temperature operating conditions, also accounting for different catalyst ageing status. In this framework, Neural Networks (NN) based models offer a promising alternative to reduced-order physical models or map-based controls. This study introduces a hybrid modeling approach for SCR systems, leveraging the integration of machine learning techniques with detailed physics-based models. A high fidelity 1D-CFD plant model of a SCR catalyst, previously calibrated on experimental data, was used as digital twin of the real component. A standardized simulation protocol was defined to virtually characterize the SCR thermal and chemical behavior under the full range of
Sapio, FrancescoAglietti, FilippoFerreri, PaoloSavuca, Alexandru
An approach to performance assessment and evaluation of robustness' of delivered AI (artificial intelligence) solutions (e.g., Aided Target Detection and Recognition (AiTDR) or ground vehicle autonomy behaviors) is presented. The initial development assumes the AI solution is delivered as a blackbox solution taking specified inputs and delivering output or outputs per stated requirements. The methods developed seek to not only confirm that requirements are met but to confirm performance in a manner that provides supporting evidence of which input information contributed to the AI output. Methods are developed for both AI solutions that take a single sample input as well as AIs that take a sequence of inputs to produce an output. Examples are included for convolutional neural networks (CNN). Planned extensions to the blackbox methods are discussed. Extensions include adaptations to support Residual Network (ResNet) solutions, evaluation of solution robustness when hidden layer
Wells, DavidFowler, StuartWalters, JoshElrod, IvyFoley, Jacob
Items per page:
1 – 50 of 1210