Browse Topic: Artificial intelligence (AI)

Items (973)
Find
Statistical Analysis of Data Acquired from Propagating Flames in Gasoline Engines Using a Multiple Ion Probe2024-32-003504/18/2025
Multiple-ion-probe method consists of multiple ion probes placed on the combustion chamber wall, where each individual ion probe detects flame contact and records the time of contact. From the recorded data, it is also possible to indirectly visualize the inside of the combustion chamber, for example, as a motion animation of moving flame front. In this study, a thirty-two ion probes were used to record flames propagating in a two-stroke gasoline engine. The experiment recorded the combustion state in the engine for about 3 seconds under full load at about 6500 rpm, and about 300 cycles were recorded in one experiment. Twelve experiments were conducted under the same experimental conditions, and a total of 4,164 cycles of signal data were obtained in the twelve experiments. Two types of analysis were performed on this data: statistical analysis and machine learning analysis using a linear regression model. Statistical analysis calculated the average flame detection time and standard
Yatsufusa, Tomoaki, Okahira, Takehiro, Nagashige, Kohei
Technical Paper
Study on Motorcycle Rider Model Using Reinforcement Learning - Learning Examples Including Following Target Velocity and Basic Research on Rider Proficiency2024-32-002804/18/2025
In this study, an initial approach using deep reinforcement learning to replicate the complex behaviors of motorcycle riders was presented. Three learning examples were demonstrated: following a target velocity, maintaining stability at low speeds, and following a target trajectory. These examples serve as a starting point for further research. Additionally, the proficiency of the constructed models was examined using rider proficiency evaluation methods developed in previous studies. Initial results indicated that the models have the potential to mimic real rider behaviors; however, challenges such as differences between the model’s output and what humans can produce were also identified for future work.
Mitsuhashi, Yasuhiro, Momiyama, Yoshitaka, Yabe, Noboru
Technical Paper
revision 2jms_bp_2 (Current)04/08/2025
revision 2
Automated Vehicle Safety Consortium
Technical Standard
SAE TOMORROW TODAY - AI-Powered Solution for Seamless EV Charging1350703/20/2025
It's no secret that the EV charging experience can be a frustrating one. But what if you could connect the various EV charging networks to apps and services, standardizing them into a single point of integration? One company is doing just that by harnessing data to create a seamless, secure, and reliable EV charging experience. Meet Emobi, the leader in critical digital infrastructure that delivers a single point of integration to a vast network of EV charging stations and e-mobility partners through advanced AI and data refinement models. As the largest roaming ecosystem in North America, the company also enables traditional and streamlined (JustPlug) Plug & Charge technology, facilitating automatic charging identification between EVs and chargers. The company is trusted by EV manufacturers, startups, utilities, and U.S. government agencies alike. To learn more, we sat down with Lin Sun Fa, CEO, Emobi, to discuss how his company's solutions are unifying the fragmented e-mobility
Hineman, Marcie
Podcast
Feasibility of Road Longitudinal Profiles for Automated Vehicles Based on Vehicle Dynamics2025-01-715003/19/2025
With the development and maturity of new generation digital technologies such as artificial intelligence, Internet of Things, and 5G mobile communication, their integration with physical products is becoming increasingly seamless. Automobiles serve as a prime example in this regard. In recent years, automated vehicle (AV) technologies have emerged as a prominent focal point, witnessing an escalating acceptance in the market and a growing number of self-driving vehicles on the roads, existing roads are primarily designed for traditional human-driven vehicles (HVs). Due to the differences in perception between automated systems and human drivers, it is essential to assess AVs' feasibility to current road infrastructure. This paper analyzes the safety and comfort of automated vehicles equipped with adaptive cruise control systems (ACC-AVs) on longitudinal road profiles from the perspective of vehicle dynamics. Firstly, a co-simulation platform integrating PreScan, CarSim, and Simulink
Li, Zezhou, Cai, Mingmao, Gu, Tianqi, Yu, Bin
Technical Paper
Research and Simulation Implementation of Self-Driving Vehicle Trajectory Optimization in Networked Intersection Environment2025-01-719402/21/2025
Nowadays, the rapidly developing Connected and Autonomous Vehicle (CAV) provides a new mode of intersection vehicle cooperative control, which can optimize vehicle trajectories and signal phases in real time and reduce intersection delays through the advantages of vehicle-road cooperative information interaction and the high controllability of CAV. In this paper, the intersection of Jintong West Road and Guanghua Road in Beijing is taken as the research object, and the vehicle trajectory constraints, acceleration constraints, speed constraints, safe driving constraints, signal switch constraints and traffic signal control constraints are set up with the minimization of traffic delay as the objective function. The DQN deep reinforcement learning network is constructed based on vehicle states, vehicle actions, reward functions, and update rules, and starts learning and updating to generate the target network. Then, SUMO software is used to simulate and test and compare the trajectory
Xu, Yuting, Zhang, Yong, Wu, Xianyu
Technical Paper
Intelligent Courier Delivery Scheduling Based on XGBoost Feature Selection and Reinforcement Learning: A Case Study Using Chongqing Cainiao Express Data2025-01-717602/21/2025
This study tackles the issue of order delays in logistics using XGBoost for feature analysis and reinforcement learning for intelligent courier scheduling. Pickup order data from May 1 to October 31, 2023, in Chongqing is analyzed using spatio-temporal statistical methods. Key findings include that order placement peaks at 9:00 a.m., delays peak at 10:00 a.m., and the delay rate is 8.6%. A significant imbalance exists between the regional daily average of dispatchable couriers and order volumes.XGBoost is employed to predict order delays, revealing that pickup location is the most influential factor (27%), followed by courier pickup location (22%). These factors and their relationships are identified as key drivers of delays.To address these issues, a reinforcement learning-based courier scheduling optimization model is developed. The model defines courier location, current time, and pending orders as state variables and adopts an epsilon-greedy strategy for action selection
Wang, Manjun, Yu, Xinlian
Technical Paper
Revolutionizing the Traffic Light21AVEP01_0501/27/2025
Two start-ups are using cameras, sensors and AI to enable more efficient vehicle flow through intersections. Every motorist has experienced the frustration of waiting at a red light when there is no traffic in sight. These days, countless household devices use sensors, cameras and connectivity to understand and respond to the world - so why do most traffic lights languish in the analog age, causing our vehicles to unnecessarily stop and idle? In a spring 2019 report, Guidehouse Insights forecast that just 7% of North America's signalized intersections would use so-called adaptive traffic-control technology in 2020. On a global level, that number was 2.3%.
Berman, Bradley
Magazine Article
EDITORIAL: Farewell and thanks, Mr. Birch21AUTP06_0401/27/2025
“We pay close attention to the SAE magazines because your guy in Europe writes interesting articles,” a BMW engineering executive told me one year at the Frankfurt Motor Show. He was referring to Stuart Birch, our veteran European Editor, who has recently decided - after nearly 37 years of outstanding reporting for SAE International - to hang up his keyboard and spend more time with his wife, Kim, their family and friends in the British countryside, and his classic Porsche 911. Our staff had been dreading the day that Stuart would announce his retirement, foremost because he's been a great friend as well as a colleague. And because journalists with his qualities - professionalism, perspective, a powerful work ethic and great wit - are increasingly rare in the mobility-technology space. As SAE's global audience knew, Stuart Birch delivered compelling technical and business information. He covered product, processes and people with equal poise. And he thrived on the R&D beat: Virtual
Brooke, Lindsay
Magazine Article
Cat’s Eye-Inspired Vision System for Autonomous RoboticsTBMG-5218012/01/2024
Researchers led by Professor Young Min Song from the Gwangju Institute of Science and Technology (GIST) have unveiled a vision system inspired by feline eyes to enhance object detection in various lighting conditions. Featuring a unique shape and reflective surface, the system reduces glare in bright environments and boosts sensitivity in low-light scenarios. By filtering unnecessary details, this technology significantly improves the performance of single-lens cameras, representing a notable advancement in robotic vision capabilities.
Magazine Article
Revolutionizing Seafood Production with Adaptive RobotsTBMG-5217812/01/2024
Robotic automation technology is reshaping food manufacturing, packaging, and handling by driving significant improvements in efficiency, quality, and flexibility. By integrating advanced artificial intelligence, computer vision, and proprietary force-sensing technology, Flexiv has introduced cutting-edge automation to the food processing sector.
Magazine Article
AI in Motion Control: Optimizing Servo SystemsTBMG-5218612/01/2024
Magazine Article
Scientists Fuse Simulations and Machine Learning to Accelerate Novel Additively Manufactured MaterialsTBMG-5212712/01/2024
Researchers at the Johns Hopkins Applied Physics Laboratory (APL) in Laurel, Maryland, have demonstrated a novel approach for applying machine learning to predict microstructures produced by a widely used additive manufacturing technique. Their approach promises to dramatically reduce the time and cost of developing materials with tailored physical properties and will soon be implemented on a NASA-funded effort focused on creation of a digital twin.
Magazine Article
Active-Learning method : An effective way to generate ground truth data to test & validate ADAS functions2024-26-036401/16/2024
In today’s autonomous industry, Machine learning plays an important role in development of various functions for self-driving vehicles. The learning models are trained using data, and their performance is determined by the quality of data they get trained on. For autonomous driving, sometimes, we don't have valid data and our model doesn't know what to do. As a result, the models must be trained on as much as diverse data as possible to make them efficient to deal with unusual situations in the actual world. Huge amount of unlabeled data is collected by cars moving around, equipped with multiple sensors to capture the surrounding environment in a frame. It becomes difficult to annotate each data manually and find data frame with more information. Therefore, automated methods are needed to identify and extract the most informative data from collected ones. Active learning is a powerful data selection technique which improves data efficiency for learning models. In Active Learning, the
Katariya, Rashmi, Kumari, Anita
Technical Paper
Method of Generating Real-Time Digital Customer Feedback Loop for Connected Vehicle Applications.2024-26-025801/16/2024
Modern cars are essentially computers on wheels in terms of the technology stack going into the car. Similarly, the customer experience is gone beyond the conventional touch and feel to more digital experiences around the car. While creating digital experiments around the car, getting honest customer feedback on the same is essential. Getting customer feedback in real-time and at scale is a challenge. Generally, this is limited to surveys and campaigns OEMs do to collect specific intent. In this paper, we propose a method of generating a real-time customer digital feedback loop. This method relay on real-time sourcing of data from openly available sources like Twitter, mobile app stores, etc. The real-time collected data is run through an analytics system. The analytics system contains four key stages, data preparation, sentiment segmentation, topic modelling and inference presentation. This paper in detail covers advanced machine learning techniques like natural language processing
Tidke, Pradeep, Venugopal, Vaisakh, Shukla, Manoj, Jali, Nagarjuna, Rathod, Chirag
Technical Paper
Cyber Threats and its Mitigation to Intelligent Transportation System2024-26-018401/16/2024
With the revolutionary advancements in modern transportation, offering advanced connectivity, automation, and data-driven decision-making has put the intelligent transportation systems (ITS) to a high risk from being exposed to cyber threats. Development of modern transportation infrastructure, connected vehicle technology and its dependency over the cloud with an aim to enhance safety, efficiency, reliability and sustainability of ITS comes with a lot more opportunities to protect the system from black hats. This abstract explores the landscape of cyber threats targeting Intelligent Transportation Systems, focusing on their potential impacts, vulnerabilities, and mitigation strategies. The cyber-attacks in ITS are not just limited to Unauthorized Access, Malware and Ransomware Attacks, Data Breaches, Denial of Service but also to Physical Infrastructure Attacks. These attacks may result in potentially disrupting critical transportation infrastructure, compromise user safety, and can
Dewangan, Kheelesh Kumar, Panda, Vibek, Ojha, Sunil, Shahapure, Anjali, Jahagirdar, Shweta Rajesh
Technical Paper
Engine Warm-up Prediction using Machine Learning Methodology.2024-26-029501/16/2024
In the recent times, when emission & CO2 legislations are becoming more stringent, we need to adjust our simulation methods to the engine warm-up for better prediction. A typical fuel economy simulation for a WLTP drive cycle with and without considering warm-up effect differentiates up to 6-8%. Thus, there is a need to consider engine warm-up parameters for drive cycle simulations. The engine warm-up can be predicted in multiple ways but the most common way is detailed Physics based 1D modelling. These thermodynamic based models have a very good accuracy in temperature characteristics compared to actual test but take a lot of simulation time. The current requirement is to have models, which can do the same with 0.3 times real time so that these can be coupled with SiL simulation. The current paper will portrait a machine learning based methodology to predict Engine Oil & Coolant temperature based on driving profile and fuel consumption. ML model is trained by using data from one drive
Kelkar, Kshitij, Bensch, Simon, Gopalkrishnan, Suresh Kumar, Meissner, Ronny
Technical Paper
Adaptive Steering System for Improved User Experience2024-26-002301/16/2024
A car's steering is the first touchpoint for the driver and one of the most important factor which governs the buying decision of the vehicle. Currently steering system has a single EPAS map leading to constant steering feel during both low and high speed manoeuvres. Some vehicles are equipped with steering system having fixed driving modes which need manual intervention. In order to achieve the needs and to overcome the limitation of fixed mode steering system, this paper proposes Machine Learning based Adaptive Steering System which automatically switches from comfort to sports mode and vice a versa to provide soft and hard steering feel as per the user's requirement. The system identifies driving pattern and zone based on vehicle response to driver input and accordingly adapts steering assist / torque. The system comprises of two modules namely driving pattern recognition for sport and comfort mode and zone detection for city and highway driving. Both modules used already available
BHAMBRI, MIHIR, sheth, Malav, Iqbal, Shoaib, Salunkhe, Swapnil
Technical Paper
A unified Framework for Industry 4.0 based Automotive Homologation in India2024-26-036001/16/2024
The term Industry 4.0 is well known in contemporary automotive landscape. It encompasses a smart integrated framework of IoT (Internet of Things) and industrial automation with machine learning, artificial intelligence and big data analytics to arrive at optimal solutions to running the processes in a streamlined, efficient and effective manner. Industry 4.0 has assumed critical significance in the contemporary era of people working from remote locations to operate processes in order to build products, thus ensuring business continuity. Consequently, it follows that if industry 4.0 is applied to automotive homologation activity, it will lead to better evaluation, better fidelity of testing and accurate judgement of the product under test with regards to its certification. The author hereby elucidates a unified Industry 4.0 Framework for Automotive homologation in India which is the need of the hour. This framework consists of five elements. The first is use of IoT to ensure optimal use
S Thipse, Yogesh
Technical Paper
Enhancing Cargo Transportation using Intelligent systems for better Logistics Management2024-26-018301/16/2024
Efficient cargo transportation plays a crucial role in logistics management and supply chain operations. Accurately detecting and utilizing cargo space within vehicles is vital for maximizing transport capacity, minimizing costs, and optimizing resource allocation and time management. This research paper focuses on enhancing cargo utilization using intelligent systems to improve logistics management. The major research is on developing a system that combines computer vision algorithms and intelligent systems to detect and implement a combination of features for efficient use of cargo space within vehicles and monitor cargo to reduce losses. The proposed approach will use and utilize image processing methods to get relevant features and identify cargo areas. Machine learning models, such as convolutional neural networks (CNNs) and object detection frameworks, will be trained and evaluated on a comprehensive dataset of cargo images to identify the most effective approach for cargo space
JAGTAP, Pramod Prakash, Kale, Shreeja, Mahali, Rakesh
Technical Paper
Study Of Derived Battery Features for Real Time Estimation of SOH And RUL Of EV Battery Using Data Analysis2024-26-012301/16/2024
Lithium-ion batteries have been widely used in EV’s. It is desired to predict the SOH of batteries to achieve optimal operation and health management. The most significant obstacle to accurately predicting battery health is choosing battery features. In this study, numerous data analysis strategies are introduced to manage feature irrelevancy and help in determining which features can be selected and used in real time. The first step in manually crafting features is to analyses the evolution pattern of numerous essential characteristics of battery. Second, correlation between selected features and degraded capacity analyses. Then, selected features are fed into representative machine learning regression model to effectively predict remaining capacity of battery to find the SOH status. Finally, the remaining capacity of battery is selected as feature to predict the RUL in terms of remaining charge-discharge cycles.
Nangare, Kapilraj, Nidubrolu, Kranthi, Gaikwad, Pooja
Technical Paper
Implementation Of Machine Learning In Acoustics Source Detection by Leveraging Synthetic Sound Data Generation Approach2024-26-021301/16/2024
E-Mobility and Low Noise IC Engines has pushed product development teams to focus more on sound quality rather than just focus on reduced noise levels and legislative needs. Further more qualification of products from a sound quality perspective from an end of line testing requirement is also a major challenge. End of line (EOL) NVH testing is key evaluation criteria for product quality with respect to NVH and warranty. Currently for subsystem or component level evaluation, subjective assessment of the components is done by a person to segregate OK and NOK components. As human factor is included, the process becomes very subjective and time consuming. Components with different acceptance criteria will be present and it’s difficult to point out the root cause for NOK components. In this paper, implementation of machine learning is done for acoustic source detection at end of line testing. To improve the fault detection an automated intelligent tool has been developed for subjective to
Shukle, Srinidhi, Iyer, Ganesh, Faizan, Mohammed
Technical Paper
Electric Vehicle Battery SOH and RUL prediction using Digital Twin Hybrid ML Model considering effect of Driving Behaviour2024-26-012201/16/2024
The adoption of Electric Vehicles (EVs) is primarily limited by their dependence on batteries, which have lesser power density as compared to conventional fossil fuels as well as its ageing deterioration issues over time. Therefore, there is an urgent need to understand the modifications in battery performance characteristics with respect to changes in temperature, charging behaviour and usage pattern, low and high charge states, current variations etc. To resolve such issues, this work proposes the development of a battery digital twin model to accurately reflect battery dynamics during run time. A digital twin is a virtual model replicating a physical system's characteristics. The digital twin is developed using a physics and machine learning model trained with bench-level and vehicle level actual test data. It uses an equivalent circuit model (ECM) to predict the battery's internal resistance and polarization effect due to ionic diffusion process in the cell. ECM model generates
Dongaonkar, Saharsh, Sarkar, Prasanta, Patil, Gaurav, KONDHARE, MANISH, nath, Subhrajyoti
Technical Paper
Twin Motor System for Electric Vehicle Propulsion by Means of Two Energy Sources2024-26-011301/16/2024
The transport sector in all domains like personal vehicles, public transport and logistics has seen a tremendous growth over the past decade, more so in the last 5 years. The main reasons for this rapid growth is the development of new energy storage systems in battery technology ( Lithium ion ,sodium ion ,aluminum air etc.), hydrogen fuel cells, super capacitors etc. On the other hand there has been tremendous development in the motor drive technology with the availability of brushless dc motors (BLDC Motors), induction motors, Permanent magnet synchronous motors (PMSM,IPMSM). Each motor having its own special characteristics and usage suited for a very specific application in terms of torque and load bearing capacities. In this paper we describe a unique platform with twin motor drive system electric vehicle which is powered by an artificial intelligence (AI) enabled electronic module DuoPackR. The basic platform is described with the help of a bicycle which has two BLDC motors on
PRATIWADIBHAYANKARAM, Ashwini Kumar Krishnaswamy, K A, Rakesh, Sangam, Manjunath
Technical Paper
Material Recognition Technology of Internal Loose Particles in Sealed Electronic Components Based on Random Forest01-17-02-000912/05/2023
Sealed electronic components are the basic components of aerospace equipment, but the issue of internal loose particles greatly increases the risk of aerospace equipment. Traditional material recognition technology has a low recognition rate and is difficult to be applied in practice. To address this issue, this article proposes transforming the problem of acquiring material information into the multi-category recognition problem. First, constructing an experimental platform for material recognition. Features for material identification are selected and extracted from the signals, forming a feature vector, and ultimately establishing material datasets. Then, the problem of material data imbalance is addressed through a newly designed direct artificial sample generation method. Finally, various identification algorithms are compared, and the optimal material identification model is integrated into the system for practical testing. The results show that the proposed material
Gao, Yajie, Wang, Guotao, Jiang, Aiping, Yan, Huizhen
Journal Article
Recurrent Neural Network Model for On-Board Estimation of the Side-Slip Angle in a Four-Wheel Drive and Steering Vehicle15-17-01-000309/23/2023
Abstract A valuable quantity for analyzing the lateral dynamics of road vehicles is the side-slip angle, that is, the angle between the vehicle’s longitudinal axis and its speed direction. A reliable real-time side-slip angle value enables several features, such as stability controls, identification of understeer and oversteer conditions, estimation of lateral forces during cornering, or tire grip and wear estimation. Since the direct measurement of this variable can only be done with complex and expensive devices, it is worth trying to estimate it through virtual sensors based on mathematical models. This article illustrates a methodology for real-time on-board estimation of the side-slip angle through a machine learning model (SSE—side-slip estimator). It exploits a recurrent neural network trained and tested via on-road experimental data acquisition. In particular, the machine learning model only uses input signals from a standard road car sensor configuration. The model
Giuliacci, Tiziano Alberto, Ballesio, Stefano, Fainello, Marco, Mair, Ulrich, King, Julian
Journal Article
Recurrent Neural Network Model for On-Board Estimation of the Side-Slip Angle in a Four-Wheel Drive and Steering Vehicle15-17-01-0003-TEST-REC09/23/2023
Abstract A valuable quantity for analyzing the lateral dynamics of road vehicles is the side-slip angle, that is, the angle between the vehicle’s longitudinal axis and its speed direction. A reliable real-time side-slip angle value enables several features, such as stability controls, identification of understeer and oversteer conditions, estimation of lateral forces during cornering, or tire grip and wear estimation. Since the direct measurement of this variable can only be done with complex and expensive devices, it is worth trying to estimate it through virtual sensors based on mathematical models. This article illustrates a methodology for real-time on-board estimation of the side-slip angle through a machine learning model (SSE—side-slip estimator). It exploits a recurrent neural network trained and tested via on-road experimental data acquisition. In particular, the machine learning model only uses input signals from a standard road car sensor configuration. The model
Giuliacci, Tiziano Alberto, Ballesio, Stefano, Fainello, Marco, Mair, Ulrich, King, Julian
Journal Article
Topological Optimization of Non-Pneumatic Unique Puncture-Proof Tire System Spoke Design for Tire Performance15-17-01-0001-TEST-REC07/18/2023
Abstract Non-pneumatic tires (NPTs) have been widely used due to their advantages of no occurrence of puncture-related problems, no need of air maintenance, low rolling resistance, and improvement of passenger comfort due to its better shock absorption. It has a variety of applications as in earthmovers, planetary rover, stair-climbing vehicles, and the like. Recently, the unique puncture-proof tire system (UPTIS) NPT has been introduced for passenger vehicles segment. The spoke design of NPT-UPTIS has a significant effect on the overall working performance of tire. Optimized tire performance is a crucial factor for consumers and original equipment manufacturers (OEMs). Hence to optimize the spoke design of NPT-UPTIS spoke, the top and bottom curve of spoke profile have been described in the form of analytical equations. A generative design concept has been introduced to create around 50,000 spoke profiles. Finite element model (FEM) model is developed to evaluate the stiffness and
Dhrangdhariya, Priyankkumar, Maiti, Soumyadipta, Rai, Beena
Journal Article
Topological Optimization of Non-Pneumatic Unique Puncture-Proof Tire System Spoke Design for Tire Performance15-17-01-000107/18/2023
Abstract Non-pneumatic tires (NPTs) have been widely used due to their advantages of no occurrence of puncture-related problems, no need of air maintenance, low rolling resistance, and improvement of passenger comfort due to its better shock absorption. It has a variety of applications as in earthmovers, planetary rover, stair-climbing vehicles, and the like. Recently, the unique puncture-proof tire system (UPTIS) NPT has been introduced for passenger vehicles segment. The spoke design of NPT-UPTIS has a significant effect on the overall working performance of tire. Optimized tire performance is a crucial factor for consumers and original equipment manufacturers (OEMs). Hence to optimize the spoke design of NPT-UPTIS spoke, the top and bottom curve of spoke profile have been described in the form of analytical equations. A generative design concept has been introduced to create around 50,000 spoke profiles. Finite element model (FEM) model is developed to evaluate the stiffness and
Dhrangdhariya, Priyankkumar, Maiti, Soumyadipta, Rai, Beena
Journal Article
Intelligent analysis of components with regard to significant features for subsequent classification2023-01-121306/26/2023
The knowledge explosion in all areas, including the automotive industry, is both an opportunity and a risk. In order to shape the effects as positively as possible and create sustainable added value, the amount of information must be processed in a targeted manner and important content must be separated from ignorable content. In the automotive industry and especially in the development of new components, it is possible to look back on many past projects and thus knowledge. However, the decisive factor is whether this information is available in a suitably processed form or the knowledge is even held by just a single expert. A new and intelligent method is therefore required to analyze existing data appropriately and at the same time prepare it ideally for further applications, such as use within forecast models based on artificial intelligence. To achieve the aforementioned goal, several steps need to be taken. First, the voxelization of the component takes place, which results in the
Nüßgen, Alexander, Degen, René, Irmer, Marcus, Richter, Fabian, Boström PhD, Cecilia, Ruschitzka PhD, Margot
Technical Paper
Categorizing Simulation Models Using Convolutional Neural Networks2023-01-121706/26/2023
Engineers come across frequent problems solved using artificial intelligence. Tasks of neural networks are often considered solving problems in such an intelligent manner. Whether as an optimization problem or development tool, neural networks help engineers and create a more efficient approach. Furthermore, information is stored in a unique data structure, during a project cycle. Engineers often face a time-consuming search to get an understanding of the project itself. This process of understanding the data needs to be repeated by every engineer, if not further documented. E.g. searching for a past project with similar parameters can be a big task, regarding huge databases. Worker fluctuation can increase the cost of this process as well. To address this issue, neural networks make a significant contribution. The main aspect of this paper is to add meta data to the core files of the project. With such labels it is possible to get access to the content of the model files of an engine
Grbavac, Andrija, Angerbauer, Martin, Grill, Michael, Kulzer, André
Technical Paper
Recognition Method for Electronic Component Signals Based on LR-SMOTE and Improved Random Forest Algorithm01-17-01-000506/10/2023
Loose particles are a major problem affecting the performance and safety of aerospace electronic components. The current particle impact noise detection (PIND) method used in these components suffers from two main issues: data collection imbalance and unstable machine-learning-based recognition models that lead to redundant signal misclassification and reduced detection accuracy. To address these issues, we propose a signal identification method using the limited random synthetic minority oversampling technique (LR-SMOTE) for unbalanced data processing and an optimized random forest (RF) algorithm to detect loose particles. LR-SMOTE expands the generation space beyond the original SMOTE oversampling algorithm, generating more representative data for underrepresented classes. We then use an RF optimization algorithm based on the correlation measure to identify loose particle signals in balanced data. Our experimental results demonstrate that the LR-SMOTE algorithm has a better data
Lv, Bingze, Wang, Guotao, Li, Shuo, Wang, Shicheng, Liang, Xiaowen
Journal Article
Leveraging user feedback to optimize the tuning of EVSE models2025-01-002005/05/2023
The implementation of active sound design models in vehicles requires precise tuning of synthetic sounds to harmonize with existing interior noise, driving conditions, and driver preferences. This tuning process is often time-consuming and intricate, especially facing various driving styles and preferences of target customers. Incorporating user feedback into the tuning process of Electric Vehicle Sound Enhancement (EVSE) offers a solution. A user-focused empirical test drive approach can be assessed, providing a comprehensive understanding of the EVSE characteristics and highlighting areas for improvement. Although effective, the process includes many manual tasks, such as transcribing driver comments, classifying feedback, and identifying clusters. By integrating driving simulator technology to the test drive assessment method and employing machine learning algorithms for evaluation, the EVSE workflow can be more seamlessly integrated. But do the simulated test drive results
Hank, Stefan, Kamp, Fabian, Gomes Lobato, Thiago Henrique
Technical Paper
A Comparative Analysis of Fault Diagnosis by vibration signals for Critical Gear Components in Electric Vehicle Motor Testing Machines Using Machine Learning Algorithms2025-01-004005/05/2023
Electric vehicles (EVs) represent the future of the automobile industry, with the drive motor being a crucial component in modern EVs. To ensure optimal performance, a motor testing machine is used to verify the essential parameters of these electrical motors. This machine regularly evaluates electric motor characteristic curves and their electromagnetic behavior under different conditions. However, it has been observed that flaws in the testing machine's helical gear arrangement frequently cause malfunctions and suboptimal performance, affecting the efficiency of the electric vehicle production line. This research project aims to improve the motor test bench apparatus by modifying critical design parameters using machine learning and vibration signal analysis methods. Vibration signals are recorded at various gear settings, and statistical features are extracted from these signals. These signals are then classified using classifiers such as Naive Bayes and Decision Trees. Machine
S PhD, Ravikumar, V, Muralidharan, Syed, Shaul
Technical Paper
Active noise control with head tracking system2025-01-001205/05/2023
In active noise control, the control region size(zone of control) decreases as the frequency increases, so that even a small moving of the passenger's head causes the ear position to go out of the control region. In order to increase the size of the control region, many speakers and microphones are generally required, but it is difficult to apply it in a vehicle cabin due to space and cost constraints. In this study, we propose moving zone of quite actvie noise control technique. An 2D images based head tracking system captured by a camera to generate the passenger's head coordinates in real time with deep learning algorithm. In the controller, the control position is moved to the ear position using a multi-point virtual microphone algorithm according to the generated ear position. After that, the multi-point adaptive filter training system applies the optimal control filter to the current position and maintains the control performance. Through this study, it is possible to secure the
Oh, ChiSung
Technical Paper
Cabin noise modeling for seat location variation using AI and Machine Learning2025-01-012905/05/2023
Analyzing acoustic performance in large and complex assemblies, such as vehicle cabins, can be a time-intensive process, especially when considering the impact of seat location variations on noise levels. This paper explores the use of AI and machine learning to streamline this analysis by predicting the effects of different seat configurations on cabin noise, particularly at the driver’s ear level. The study begins by establishing a baseline simulation of cabin noise and generating training data for various seat location scenarios. This data is then used to train an AI model capable of predicting the noise impact of further seat adjustments. These predictions are validated through detailed simulations. The paper discusses the accuracy of these predictions, the challenges encountered, and provides insights into the effective use of AI and machine learning in acoustic analysis for cabin noise, with a specific emphasis on seat location as a key variable. Keywords: Acoustic analysis, AI
Kottalgi, Santosh, Banerjee, Bhaskar
Technical Paper
High-Fidelity NVH Model Development for Electric Motors using Deep learning and Machine Learning Algorithms2025-01-012305/05/2023
Electric motor whine is a significant source of noise in electric vehicles (EVs). To improve the noise, vibration, and harshness (NVH) performance of electric propulsion systems, it is essential to develop a physics-based, high-fidelity stator model. In this study, a machine learning (ML) model is developed using an artificial neural network (ANN) method to accurately characterize the material properties of the copper winding, varnish, and orthotropic stator laminate structure. A design of experiments (DOE) approach using Latin hypercube sampling of parameters is implemented after evaluating alternative surrogate models. A finite element (FE) model is constructed using the nominal stator design parameters to train the ANN model using 121 DOE variables and 72,000 data points. The ML-trained ANN model is then verified to predict the driving point frequency response function (FRF) spectrum with reasonable accuracy. Subsequently, modal tests are conducted on the electric stator, and the
Rao, Bhyri Rajeswara, GSJ, Gautam, He, Song
Technical Paper
Brake Noise CAE Enhancement with the Synergy between Design of Experiments and Machine Learning2025-01-012405/05/2023
The digitalization of industrial systems has led to increased data availability. Machine learning (ML) methodologies are now commonly used for data analysis in industrial contexts. Not all contexts have abundant data; sometimes data collection can be scarce or expensive. DOE is a technique that provides an informative dataset for ML analysis when data are limited. It involves systematically designing experiments to collect relevant data points with regression models. Disc brake noise is a challenging problem in vehicle noise, vibration, and harshness (NVH). Different noise events occur under various operating conditions and across frequencies (1-16 kHz). To enhance computer-aided engineering (CAE) techniques for brake noise, ML is used to generate additional data. Sequential experimentation in DOE aligns well with ML’s ability to continuously learn and improve as more data become available. DOE is applied in CAE to collect data for training ML models. ML helps find patterns in high
Song, Gavin, Venugopal, Narayana, Vlademar, Michael
Technical Paper
Designing Rubber Flaps for Resonance Management: High-Frequency Tuning in Electric Vehicles Using AI/ML Approaches2025-01-012505/05/2023
High-frequency whine noise in electric vehicles (EVs) poses a significant challenge, affecting customer perception and the overall vehicle experience. One primary source of this undesirable noise is the interaction between motor pole resonance and the resonance of the engine mount rubber. This paper presents an innovative method for predicting and tuning the frequency response of engine mounts by precisely adjusting the dimensions of rubber flaps, specifically their length and width. The proposed solution employs a dual approach: fine-tuning rubber flap dimensions and utilizing machine learning (ML) techniques. An ML model, trained on historical data, predicts how varying flap dimensions impact frequency response, providing a data-driven foundation for optimization. This prediction capability is enhanced by a Python program that automates the optimization process using a linear combination formula, efficiently addressing resonance issues. By integrating ML insights with the linear
Hazra, Sandip, Khan, Arkadip
Technical Paper
Navigating Evolving Vehicle NVH Challenges with Application of Emerging Technologies in Artificial Intelligence and Machine Learning2025-01-013005/05/2023
The multifaceted, fast-paced evolution in the automotive industry includes noise and vibration (NVH) behavior of products for regulatory requirements and ever-increasing customer preferences and expectations for comfort. There is pressing need for automotive engineers to explore new and advanced technologies to achieve a ‘First Time Right’ product development approach for NVH design and deliver high-quality products in shorter timeframes. Artificial Intelligence (AI) and Machine Learning (ML) are trending transformative technologies reshaping numerous industries. AI enables machines to replicate human cognitive functions, such as reasoning and decision-making, while ML, a branch of AI, employs algorithms that allow systems to learn and improve from data over time. The purpose of the paper is to show an approach of using machine learning techniques to analyze the impact of variations in structural design parameters on vehicle NVH responses. The study begins by executing the Design of
Miskin, Atul R., Parmar, Azan, Raj, Sonia, himakuntla, Uma Maheswar
Technical Paper
Application of AI/ML in Hydrobush Tuning to Enhance Overall Value Proposition2025-01-013205/05/2023
In this intense market of the automotive industry, optimization of vehicle components for superior performance and customer satisfaction is paramount. Hydrobushes play an integral role in achieving this within vehicle suspension systems by absorbing vibrations and improving ride comfort. The methods traditionally used for tuning these components are not only time-consuming but also heavily reliant on extensive empirical testing. This paper explores the ever-growing field of artificial intelligence (AI) and machine learning (ML) in the hydrobush tuning process. Leveraging AI/ML algorithms such as random forest, artificial neural network, and logistic regression to analyse vast datasets, identify patterns, and predict optimal configurations more efficiently than conventional methods. The stated approach accelerates the tuning process while also enhancing the precision of the outcomes, leading to superior ride quality and durability. Thus, the integration of AI/ML techniques in hydrobush
Hazra, Sandip, Khan, Arkadip Amitava
Technical Paper
Data-Driven Machine Learning Approach for Rattle Risk Mitigation2025-01-012605/05/2023
In the modern automotive industry, squeak and rattle issues are critical factors affecting vehicle perceived quality and customer satisfaction. Traditional approaches to predicting and mitigating these problems heavily rely on physical testing and simulation technologies, which can be time-consuming and resource-intensive, especially for larger models. In this study, we propose a data-driven machine learning approach to mitigate rattle risks more efficiently. In this study, a floor console model has been evaluated using the traditional simulation-based E-line method to pinpoint high-risk areas. Data generation is performed by varying material properties, thickness, and flexible connection stiffness using the Modified Extensible Lattice Sequence (MELS) sampling algorithm, creating a diverse and comprehensive dataset for generating a machine learning (ML) model. Utilizing the dataset, the top contributing variables were identified for training the ML models. Various machine-learning
Parmar, Azan, Rao, Sohan, Reddy, Hari Krishna
Technical Paper
Condition Monitoring of High-Speed Rotating Machinery using Digital Twins & Machine Learning Techniques2025-01-012805/05/2023
In the era of Industry 4.0, maintenance of factory equipment is changing with new maintenance system using predictive or prescriptive methods. These methods leverage condition monitoring through digital twins, AI, & machine learning techniques to obtain early signs of faults, type of faults, locations of fault etc. Bearings and Gears are one of the most common components and cracking/misalignment/rubbing/bowing are the most common failure modes in high-speed rotating machinery. In the present work, an end-to-end automated Machine Learning based condition monitoring algorithm is developed for predicting and classifying internal gear and bearing faults using external vibration sensors. A digital twin model of the entire rotating system consisting of the gears, bearings, shafts, and housing was developed as a co-simulation between MSC ADAMS and MATLAB. The gears and bearing dynamic models were developed in MATLAB and shaft and housing models were developed in MSC ADAMS flexible body. The
Rastogi, Sarthak, SINGHAL, SRIJAN, Ahirrao, Sachin, Milind, T. R.
Technical Paper
Mode Shape Identification Using Graph Neural Networks for Vehicle Structure Design2025-01-013105/05/2023
This paper introduces a novel, automated approach for identifying and classifying full vehicle mode shapes using Graph Neural Networks (GNNs), a deep learning model for graph-structured data. Mode shape identification and naming refers to classifying deformation patterns in structures vibrating at natural frequencies with systematic naming based on the movement or deformation type. Many times, these mode shapes are named based on the type of movement or deformation involved. The systematic naming of mode shapes and their frequencies is essential for understanding structural dynamics and “Modal Alignment” or “Modal Separation” charts used in NVH analysis. Current methods are manual, time-consuming, and rely on expert judgment. The integration of GNNs into mode shape classification represents a significant advancement in vehicle modal identification and structure design. Results demonstrate that GNNs offer superior accuracy and efficiency compared to current labor intensive manual modes
Tohmuang, Sitthichart, Swayze, James L., Fard, Mohammad, Fayek PhD, Haytham, Marzocca, Piergiovanni, Bhide, Sanjay, Huber, John
Technical Paper
Test:15/2SAE-PP-0781002/15/2023
Test:15/2
Mutagaana, Festo
Pre-Print Article
Utilizing Machine Learning Algorithms in a Data-Driven Approach to the Prediction of Vehicle Battery State of Charge with BMW i3 Datasets2022-01-508810/17/2022
The state of charge (SoC) in an electric vehicle must be assessed and projected for any scenario, using the array of data points that can be extracted from a vehicle. In this paper, we explored the utility of data-driven approaches to SoC prediction that do not rely upon any internal or equation-based understanding of the device operation. We leveraged three unique machine learning algorithms to predict the battery SoC using data from other features of electric vehicles. We leveraged a publicly available dataset describing vehicle parameters and trip details for 70 trips in EV BMW™ i3 (60 ah) vehicles and evaluated aforementioned machine learning algorithms for predicting SoC percentage. We utilized a data processing technique (delta and stagger) to extract different perspectives from each trip record and demonstrated that machine learning techniques can be effectively used to predict battery SoC for a wide range of driving conditions and trip parameters.
Puri, Shreya
Technical Paper
Panel Discussion: Role of AI in Brake/Friction Testing Today and Future1334910/12/2022
The concept of Artificial Intelligence is presently being employed in several industries and it's use is expanding. Although AI strategies have been evolving over a period of several decades, it is within the past few years that its practicality has increased to a point where we are now truly at the forefront of a disruptive technological trend. The automotive industry is ripe with applications for this technology and the benefits of employing AI may be boundless. It is imperative that the Automotive Industry embrace AI, but with a clear understanding of not only the capabilities but also limitations. This panel will focus on how AI can be employed in the field of Automotive Brake and Friction development testing. The expert panelists will share their thoughts about where the industry currently stands with respect to potential brake/friction development AI applications, and the outlook for future improvements and constraints of this new tool. Moderator: Saikiran Divakaruni, ZF
Schandelmeier, Brandie
Video
Letter from the Guest Editors01-15-02-000809/24/2022
Letter from the Guest Editors
Rajpathak, Dnyanesh, Roboff, Mark, Yu, Huafeng, Biswas, Gautam
Journal Article
Enhancing Meta Model of the Brake Pad Friction Coefficient using the Explainable Machine Learning2022-01-117509/19/2022
As increasing system complexity and various customer demands result in the need for highly efficient vehicle development processes. Once the brake torque is predicted accurately during the driving scenario in the earlier stage, it will be able to prevent the changing the vehicle or brake system design to satisfy the legal regulation and customer requirement. As brake torque performance target allocate brake pad friction coefficient level and characteristic, the accurate friction coefficient prediction should be preceded for accurate prediction for brake torque. Generally, the friction coefficient of the brake pad is known to vary nonlinearly depending on the physical properties of the disc and the pad, as well as the rotational speed of the brake disc, the disc temperature, and the hydraulic pressure. Furthermore, it varies depending on the driving scenario even the same condition. Therefore, there was a need for a new method : machine learning to solve this problem. A Mixed Effect
Cho, Sunghyun, Bang, Sunghoon, Jang, Jiwoo, Kim, Youngjae
Technical Paper
Teaching Drones How to Navigate Real-World WeatherTBMG-4649509/01/2022
Right now, drones are either flown under controlled conditions, with no wind, or are operated by humans using remote controls. However, for drones to autonomously perform necessary but quotidian tasks, such as delivering packages or airlifting injured drivers from a traffic accident, drones must be able to adapt to wind conditions in real time.
Magazine Article
Items per page:
1 – 50 of 973