The SAE WCX2025 has recently announced its paper acceptance results for 2025. Several members of the TRANS group, including research assistants, undergraduates, graduate students, and doctoral candidates, have successfully had their submitted papers accepted.
About SAE WCX 2025
WCX 2025 (The WCX™ 2025 World Congress Experience), organized by the Society of Automotive Engineers (SAE), is a premier global conference and exhibition for automotive technology. SAE, a highly influential academic organization in the automotive, aerospace, and marine industries worldwide, serves as a critical resource for technical information in transportation machinery. SAE WCX2025 provides an exceptional platform for discussing cutting-edge insights into consumer metrics, regulatory standards, and technological advancements within the global automotive ecosystem. The event will take place in Detroit, Michigan, USA, from April 8 to April 10, 2025.
Accepted Paper Overview
01 Decoding User Experience: A Study of Public EV Charging Stations Based on Amap Comments
Abstract:The rapid expansion of the electric vehicle (EV) market has intensified the need for robust charging infrastructure. The quality of their experiences at public charging stations has become crucial to sustaining this transition. Key factors such as station accessibility, charging speed, and pricing transparency significantly affect user satisfaction. In Guangzhou, a China’s major metropolitan city with an EV penetration rate exceeding 50%, this city offers an ideal context to assess the alignment between expanding EV infrastructure and user needs. This study examines user satisfaction with EV public charging stations in Guangzhou using a dataset of over 2,000 user comments from Amap. The comments are first processed using the Jieba segmentation library, with sentiment analysis conducted through the Natural Language Processing tool SnowNLP, categorizing comments by sentiment (419 positive, 156 neutral, and 1,690 negative). Term Frequency-Inverse Document Frequency(TFIDF) is then applied for feature extraction, and the optimal number of clusters for K-means clustering was determined using the Elbow method. Findings reveal significant dissatisfaction with station availability, with 65.1% of negative comments highlighting insufficient charging spots even in high-charging-station-density
districts. These results emphasize the need for improved resource allocation and introducing the “Pile Turnover Rate” (PTR) to enhance charging efficiency. Moreover, 21.01% of negative comments cite slow charging speeds and high costs, while fast-charging technology is praised in 47.97% of positive comments for its affordability and convenience. Variability in service pricing also contributes to dissatisfaction, with higher service price ratios strongly correlating with negative feedback. These findings provide actionable insights for policymakers and charging station operators to optimize EV infrastructure.
Authors
First Author: Guo Haifeng (Research Assistant, TRANS Group)
Corresponding Author: Professor Shiqi Ou
Co-authors: Jing Hao (Class of 2024 Ph.D. Candidate), Qi Hao (Class of 2024 Ph.D. Candidate), and Shi Lanxin (Class of 2024 Ph.D. Candidate)
02 Assessing the Energy Impact of Intelligent Driving Technologies on Electric Vehicle: A Comprehensive Review
Abstract:With the continuous advancement of artificial intelligence technology, the automation level of electric vehicles (EVs) is rapidly increasing. Despite the improvements in travel efficiency, safety, and convenience brought about by automation, cutting-edge intelligent technologies also pose the potential of increased energy consumption, such as the computational power required by advanced algorithms and the energy usage of high-precision equipment, leading to a higher
overall energy consumption for autonomous electric vehicles (AEVs).To assess the impact of intelligent technologies on AEVs, this study innovatively provides a comprehensive evaluation of the impact of intelligent technologies on AEV energy consumption from both positive and negative perspectives. After reviewing 59 relevant studies, the findings highlight energy savings achieved through Vehicle-to-Infrastructure (V2I) and Vehicle-to-Vehicle (V2V) cooperation as positive effects, while increased energy consumption from complex equipment and intensive computational tasks associated with intelligent algorithms are noted as challenges. In addition to providing a comprehensive overview of the existing impacts, this paper concludes the review by proposing the most promising research directions to address these factors. For example, this study indicates that computer systems in autonomous driving account for the largest proportion of increased energy consumption, reaching approximately 41%. In contrast, strategies such as carfollowing and lane changing can reduce energy consumption by up to about 37%. Therefore, integrating these approaches can help balance the overall energy consumption of vehicles.
Authors
First Author: Liu Tianyi (Class of 2024 Master’s Candidate, TRANS Group)
Corresponding Author: Professor Shiqi Ou
Co-authors: Qi Hao (Class of 2024 Ph.D. Candidate)
03 Projected Perceived Cost of Ownership for Commercial Vehicle Powertrains in China by 2040
Abstract: The rapid advancement of alternative energy and energy-saving technologies in China underscores the importance of conducting a comprehensive analysis of the total cost of ownership (TCO) for commercial vehicles such as buses and trucks. To address the challenges of quantifying time-sensitive and implicit costs, this study has developed an extensive database and a web-based modeling tool to evaluate the TCO of these vehicles for the period 2020–2040. The tool allows for user-customized inputs and generates TCO estimates across multiple technology evolution scenarios, encompassing nearly 200 vehicle types categorized by class, intended use, and powertrain technology, within diverse technology development pathways. The model integrates critical cost factors, including vehicle purchase costs, financing costs, energy expenditures, and inconvenience costs, providing a detailed assessment of long-term ownership costs. Key findings indicate that under the reference scenario, battery electric buses are projected to achieve significant cost reductions of 30–40% by 2040. Similarly, fuel cell electric trucks are expected to reduce costs by 35–45%, potentially exceeding the cost reductions projected for battery electric trucks. Conversely, conventional vehicles such as those powered by compressed natural gas/liquefied petroleum gas (CNG/LPG) or compression ignition (CI) technologies are unlikely to realize substantial TCO savings over the same period. Among vehicle classes, intracity transit buses (M3 class) are anticipated to experience the most notable TCO reductions, potentially exceeding 50%, while mini buses consistently maintain the lowest TCO. Under a more pessimistic scenario, cost reductions are either limited or marginally increased for certain vehicle types, such as CI buses. This web-based platform is designed to offer valuable insights and guidance for fleet operators, policymakers, and manufacturers, supporting informed decision-making and strategic planning in the development and adoption of sustainable commercial vehicle technologies in China.
Notably, the TCO Model was officially launched in December 2024!
Online Access: http://tco.translab.top/
Authors
First Author: Tan Xiaolu (Class of 2021 Undergraduate, TRANS Group)
Corresponding Author: Professor Shiqi Ou
Co-authors: Wu Shuhong (Class of 2021 Undergraduate) and Chen Yongjian (Class of 2021 Undergraduate)
04 Optimizing Battery Charging Strategies through Q-Learning and Electric Vehicle Powertrain System Modeling
Abstract: Battery health status and driving range of electric vehicles (EVs) are critical factors in determining their market penetration. Choosing an optimal charging strategy—specifying how, when, and for how long to charge based on the driver’s travel behavior—can significantly mitigate battery degradation and extend battery life. This study introduces an EV powertrain system energy model designed to enhance the prediction accuracy of battery status under real-world driving conditions. By integrating with the Q-learning approach, this study provides tailored recommendations on charging behaviors, including charger type, start time, and charging duration. This study innovatively considers the rental costs caused by the battery capacity not being able to meet the daily driving range. Simulating a typical three-year usage scenario for an average driver in New England, the results indicate that the charging strategy proposed by this study reduces battery degradation rates by 1.53‰, 3.57‰, and 7.68‰ compared to strategies using only Level 2 charging, direct-current fast charging, or extreme fast charging, respectively. This combination of data-driven and physical-modeling approach demonstrates that integrating intelligent charging strategies can improve battery health, reduce operational costs, and meet driver travel demands, thereby enhancing the overall economic feasibility of EVs over their lifecycle.
Authors
First Author: Wang Jiayi (Class of 2021 Undergraduate, TRANS Group)
Corresponding Author: Professor Shiqi Ou
Co-authors: Professor Zhenhong Lin and Jing Hao (Class of 2024 Ph.D. Candidate)
05 Electric Vehicle Dynamic Operation Simulation with Data-driven and Physical-based Models
Abstract: Aiming at the complexity of the dynamic operation simulation of electric vehicles (EVs), this paper proposes a dynamic operation simulation model that integrates data-driven and physical-based principles. This model framework combines the advantage of interpretability from the physical model while leveraging the strength of rapid simulation under dynamic operating conditions of the electric vehicles from the data-driven model. The physical model part covers key aspects such as vehicle dynamics modeling, regenerative braking system, temperature model, and battery state estimation model. The data-driven part extracts key features and labels based on actual vehicle operation data, and establishes a capacity-life prediction model for the power pack of an electric vehicle by using the long-short-term memory model (LSTM). By combining the physical model with a data-driven approach, this model effectively simulates dynamic changes in vehicle cabin temperature, battery pack temperature, and battery capacity degradation across varying operating conditions during their use lifetime in a short timeframe. Simulation and validation results based on real-world driving data show that the fusion model is highly accurate and reliable in both energy consumption prediction and battery life prediction, and can provide effective tools and theoretical support for performance analysis, optimization design, and energy management of electric vehicles.
Authors
First Author: Jing Hao (Class of 2024 Ph.D. Candidate, TRANS Group)
Corresponding Author: Professor Shiqi Ou
Co-authors: Senior Engineer Jianyao Hu, Ouyang Jianheng (Class of 2022 Undergraduate), and Wang Jiayi (Class of 2021 Undergraduate)