Xinyou Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xinyou Lin has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
Hailin Li
Department of Mechanical and Aerospace Engineering, West Virginia University, Morgantown, WV, USA
6 shared publicationsHao Huang
School of Mechanical Engineering and Automation, Fuzhou University, China
5 shared publicationsXinhao Xu
4 shared publicationsJiayun Wu
College of Mechanical Engineering & Automation Fuzhou University Fuzhou 350108 China
3 shared publications- Liping Xie
College of Mechanical:Engineering & Automation, Fuzhou University, Fuzhou 350108, China
3 shared publications Xuefan Li
3 shared publications
Latest Publications
- 7 August 2026
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Adhesion identification and tire-force coupling based torque distribution strategy for enhanced stability of distributed driving electric vehicle by using fuzzy broad learning system algorithm
The dynamic variations of the tire-road friction coefficient (TRFC) and tire lateral force are critical factors to improve the stability performance of distributed driving electric vehicle (DDEV). However, traditional strategies often overlook the critical interaction between the TRFC and tire lateral force which leads to potential instability when tire forces approach adhesion limits. To address this issue, a novel adhesion identification and tire-force coupling based torque distribution strategy is proposed to improve the stability performance of DDEV explicitly account for tire-road interactions. The first is development of a TRFC recognition method using a fuzzy broad learning system (FBLS) algorithm to real-time evaluate the TRFC. Second, the tire lateral force estimated algorithm based on the square-root cubature Kalman filter (SRCKF) combined with vehicle dynamics model is designed to predict tire lateral force. And most critically, the identified TRFC and estimated lateral forces are integrated to dynamically update the constraints of a combined longitudinal-lateral tire force boundary in the proposed strategy. Finally, in combination with the above efforts, the adhesion identification and tire-force coupling based torque distribution strategy by using FBLS and SRCKF algorithm has been further developed accordingly. The numerical validation results demonstrate that the excellent performance of the proposed strategy in stability control, and the effectiveness of the proposed strategy is validated by Hardware-in-the-loop (HIL) experiments. Both the numerical validation and HIL results indicate that the implementation of the proposed strategy could significantly decrease the influence of interaction between TRFC and tire lateral force, further improving the stability control for DDEV.
- 7 August 2026
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Adhesion identification and tire-force coupling based torque distribution strategy for enhanced stability of distributed driving electric vehicle by using fuzzy broad learning system algorithm
The dynamic variations of the tire-road friction coefficient (TRFC) and tire lateral force are critical factors to improve the stability performance of distributed driving electric vehicle (DDEV). However, traditional strategies often overlook the critical interaction between the TRFC and tire lateral force which leads to potential instability when tire forces approach adhesion limits. To address this issue, a novel adhesion identification and tire-force coupling based torque distribution strategy is proposed to improve the stability performance of DDEV explicitly account for tire-road interactions. The first is development of a TRFC recognition method using a fuzzy broad learning system (FBLS) algorithm to real-time evaluate the TRFC. Second, the tire lateral force estimated algorithm based on the square-root cubature Kalman filter (SRCKF) combined with vehicle dynamics model is designed to predict tire lateral force. And most critically, the identified TRFC and estimated lateral forces are integrated to dynamically update the constraints of a combined longitudinal-lateral tire force boundary in the proposed strategy. Finally, in combination with the above efforts, the adhesion identification and tire-force coupling based torque distribution strategy by using FBLS and SRCKF algorithm has been further developed accordingly. The numerical validation results demonstrate that the excellent performance of the proposed strategy in stability control, and the effectiveness of the proposed strategy is validated by Hardware-in-the-loop (HIL) experiments. Both the numerical validation and HIL results indicate that the implementation of the proposed strategy could significantly decrease the influence of interaction between TRFC and tire lateral force, further improving the stability control for DDEV.
- 12 May 2026
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Energy prediction oriented SOC trajectory optimized multi-objective control strategy with equivalent factor corrected by PSO-fuzzy algorithm for a plug-in hybrid electric vehicle
The SOC trajectory is of great importance in fuel economy, emission reduction performance of plug-in hybrid electric vehicle (PHEV). This study proposes a energy prediction oriented SOC trajectory optimized multi-objective control strategy with equivalent factor corrected by particle swarm optimization fuzzy algorithm to improve the vehicle performance. First, a hybrid dynamic state transition mode including five different drive mode utilizing hybrid system theory is developed to obtain optimal mode switching. Next, the neural network algorithm is implemented to achieve demand energy prediction and the energy prediction oriented SOC trajectory is constructed. Moreover, equivalent factor (EF) based on fuzzy rules is corrected in real time combined with the PSO algorithm for tuning the PI factors to obtain the optimal EF. And the fuel consumption, the instantaneous HC emissions, the instantaneous CO emissions and the instantaneous NO x emissions are defined as the optimized objectives. Finally, a Fuzhou city driving condition based simulation research and HIL experiment are established to validate the effectiveness of the proposed strategy. The experiment results show that the proposed strategy has superior stability and significantly improves fuel economy and emission compared to traditional equivalent cost minimization strategy with constant EF.
- 12 May 2026
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Energy prediction oriented SOC trajectory optimized multi-objective control strategy with equivalent factor corrected by PSO-fuzzy algorithm for a plug-in hybrid electric vehicle
The SOC trajectory is of great importance in fuel economy, emission reduction performance of plug-in hybrid electric vehicle (PHEV). This study proposes a energy prediction oriented SOC trajectory optimized multi-objective control strategy with equivalent factor corrected by particle swarm optimization fuzzy algorithm to improve the vehicle performance. First, a hybrid dynamic state transition mode including five different drive mode utilizing hybrid system theory is developed to obtain optimal mode switching. Next, the neural network algorithm is implemented to achieve demand energy prediction and the energy prediction oriented SOC trajectory is constructed. Moreover, equivalent factor (EF) based on fuzzy rules is corrected in real time combined with the PSO algorithm for tuning the PI factors to obtain the optimal EF. And the fuel consumption, the instantaneous HC emissions, the instantaneous CO emissions and the instantaneous NO x emissions are defined as the optimized objectives. Finally, a Fuzhou city driving condition based simulation research and HIL experiment are established to validate the effectiveness of the proposed strategy. The experiment results show that the proposed strategy has superior stability and significantly improves fuel economy and emission compared to traditional equivalent cost minimization strategy with constant EF.
- 29 April 2026
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
A Pareto frontier-driven multi-objective energy management control strategy for fuel cell hybrid electric vehicles incorporating driving styles in adaptive cruise control scenarios
Traditional adaptive cruise control (ACC) systems relying on fixed algorithms cannot fulfill the comprehensive demands of fuel cell hybrid electric vehicles in driving safety, energy consumption, and component lifespan as they overlook driver behavior and traffic variability. This study proposes an integrated ACC strategy using a convolutional neural network for driving style recognition, a trip distance adaptive equivalent consumption minimization strategy, and Pareto multi-objective optimization via Non-dominated Sorting Genetic Algorithm-II. Key innovations include dynamic equivalent factor adjustment based on state of charge and driving style, and a multi-objective function balancing tracking performance, hydrogen consumption, and fuel cell degradation. Simulations and hardware-in-the-loop experiments demonstrate a 3.96% improvement in fuel economy, 15.9% reduction in fuel cell degradation, and enhanced tracking accuracy compared to sequential quadratic programming.
- 29 April 2026
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
A Pareto frontier-driven multi-objective energy management control strategy for fuel cell hybrid electric vehicles incorporating driving styles in adaptive cruise control scenarios
Traditional adaptive cruise control (ACC) systems relying on fixed algorithms cannot fulfill the comprehensive demands of fuel cell hybrid electric vehicles in driving safety, energy consumption, and component lifespan as they overlook driver behavior and traffic variability. This study proposes an integrated ACC strategy using a convolutional neural network for driving style recognition, a trip distance adaptive equivalent consumption minimization strategy, and Pareto multi-objective optimization via Non-dominated Sorting Genetic Algorithm-II. Key innovations include dynamic equivalent factor adjustment based on state of charge and driving style, and a multi-objective function balancing tracking performance, hydrogen consumption, and fuel cell degradation. Simulations and hardware-in-the-loop experiments demonstrate a 3.96% improvement in fuel economy, 15.9% reduction in fuel cell degradation, and enhanced tracking accuracy compared to sequential quadratic programming.
- 12 March 2026
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Hierarchical optimization for multi-criteria lane-changing strategy and decoupled trajectory planning of autonomous vehicles in heterogeneous traffic
Lane-changing is a crucial component of autonomous vehicles. In mixed multi-vehicle scenarios, traditional lane-changing strategies may reduce traffic efficiency due to high competition. To address this issue, this study proposes a lane-changing strategy and trajectory planning for enhancing driving safety and traffic efficiency. First, optimize the traditional mixed traffic flow model and establish the lane-changing feasibility assessment model. Next, combine the double deep Q-network (DDQN) algorithm to formulate a lane-changing strategy. Second, decouple trajectory planning, using the fifth-degree polynomial curve to plan the path. Then dynamic programming is employed for speed planning and multi-objective functions are used to optimize the trajectory planning results. Simulation and prototype validation indicate that compared with traditional methods, the proposed lane-changing strategy and trajectory planning can efficiently generate trajectories for autonomous vehicles, enhancing overall traffic efficiency and safety.
- 12 March 2026
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Hierarchical optimization for multi-criteria lane-changing strategy and decoupled trajectory planning of autonomous vehicles in heterogeneous traffic
Lane-changing is a crucial component of autonomous vehicles. In mixed multi-vehicle scenarios, traditional lane-changing strategies may reduce traffic efficiency due to high competition. To address this issue, this study proposes a lane-changing strategy and trajectory planning for enhancing driving safety and traffic efficiency. First, optimize the traditional mixed traffic flow model and establish the lane-changing feasibility assessment model. Next, combine the double deep Q-network (DDQN) algorithm to formulate a lane-changing strategy. Second, decouple trajectory planning, using the fifth-degree polynomial curve to plan the path. Then dynamic programming is employed for speed planning and multi-objective functions are used to optimize the trajectory planning results. Simulation and prototype validation indicate that compared with traditional methods, the proposed lane-changing strategy and trajectory planning can efficiently generate trajectories for autonomous vehicles, enhancing overall traffic efficiency and safety.
- 23 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (1) , 1013-1025
Fuel Cell/Battery Aging-Conscious Ramp-Down Power Distribution Strategy for a Hybrid Energy Storage System-Based SOC Predicted by Using Self-Learning Markov Algorithm
Frequent high-power transient changes during vehicle driving are the key factors leading to the degradation of fuel cells and batteries. However, traditional energy management strategies predominantly emphasize power distribution under steady-state conditions, and often neglect the power distribution during transient conditions such as mode changes and emergency braking. In this regard, to enhance the economic and operational lifespan of fuel cells and batteries under transient power changes, a hybrid energy storage system (HESS) is applied, and a fuel cell/battery aging-conscious active power distribution control (APDC) strategy is proposed. First, a self-learning Markov algorithm, coupled with state of charge (SOC) control, is employed to predict the battery SOC trajectory, effectively attenuating power transients and minimizing battery degradation during mode transitions in a long-mixed driving cycle. Subsequently, a ramp-down power distribution strategy (RPDS) is designed for emergency braking, to constrain the power variation rate and suppress the fuel cell degradation. Finally, based on the above, an aging-conscious APDC strategy is developed, achieving optimal energy allocation in the HESS. The superiority of the proposed strategy was verified, compared with the strategies without ultracapacitors (UCs) and without considering durability and power distribution. Both comparative validation and hardware-in-the-loop (HIL) results indicate the proposed strategy’s effectiveness in suppressing battery and fuel cell degradation, optimizing energy distribution, and improving hydrogen economy performance.
- 23 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (1) , 1013-1025
Fuel Cell/Battery Aging-Conscious Ramp-Down Power Distribution Strategy for a Hybrid Energy Storage System-Based SOC Predicted by Using Self-Learning Markov Algorithm
Frequent high-power transient changes during vehicle driving are the key factors leading to the degradation of fuel cells and batteries. However, traditional energy management strategies predominantly emphasize power distribution under steady-state conditions, and often neglect the power distribution during transient conditions such as mode changes and emergency braking. In this regard, to enhance the economic and operational lifespan of fuel cells and batteries under transient power changes, a hybrid energy storage system (HESS) is applied, and a fuel cell/battery aging-conscious active power distribution control (APDC) strategy is proposed. First, a self-learning Markov algorithm, coupled with state of charge (SOC) control, is employed to predict the battery SOC trajectory, effectively attenuating power transients and minimizing battery degradation during mode transitions in a long-mixed driving cycle. Subsequently, a ramp-down power distribution strategy (RPDS) is designed for emergency braking, to constrain the power variation rate and suppress the fuel cell degradation. Finally, based on the above, an aging-conscious APDC strategy is developed, achieving optimal energy allocation in the HESS. The superiority of the proposed strategy was verified, compared with the strategies without ultracapacitors (UCs) and without considering durability and power distribution. Both comparative validation and hardware-in-the-loop (HIL) results indicate the proposed strategy’s effectiveness in suppressing battery and fuel cell degradation, optimizing energy distribution, and improving hydrogen economy performance.
- 1 January 2025
- Published by Chinese Journal of Mechanical Engineering in Journal of Mechanical Engineering
- Vol. 61 (18) , 252-266
Research on Lane Change Decision Method of Reinforcement Learning Based on Motion Risk
- 1 January 2025
- Published by Chinese Journal of Mechanical Engineering in Journal of Mechanical Engineering
- Vol. 61 (18) , 252-266
Research on Lane Change Decision Method of Reinforcement Learning Based on Motion Risk
- 1 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 72 (5) , 4922-4932
Battery Degradation Oriented Active Control Strategy by Using a Reinforcement Learning Algorithm in Hybrid Energy Storage System
The integration of ultracapacitors (UCs) into hybrid energy storage systems is a solution to mitigate battery degradation. Traditional strategies focus on fuel cell and battery power regulation while treating UC management as a passive element, resulting in suboptimal UC utilization. To optimize the energy utilization of UCs, this article proposes an active state control strategy within the hybrid system. Initially, leveraging the battery severity factor, the optimal power split strategy for HESS is proposed for a reference state-of-charge (SOC) of UC. Subsequently, a driving pattern severity factor is designed, and an online self-learning Markov predictor is employed to quantify the operational state of vehicle. To provide optimal reference SOC guidance to HESS in real time, a reinforcement learning algorithm featuring an experience replay mechanism is developed. Utilizing pretrained agents that integrate vehicle driving state abstraction parameters, the system generates the reference SOC of UC, enabling the optimal battery-UC power split in real time. Both numerical and semiphysical validations confirm the efficacy of the proposed strategy in enhancing the power output ratio of UC, optimizing energy storage space utilization, and reducing the battery severity factor, consequently improving overall battery lifespan.
- 1 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 72 (5) , 4922-4932
Battery Degradation Oriented Active Control Strategy by Using a Reinforcement Learning Algorithm in Hybrid Energy Storage System
The integration of ultracapacitors (UCs) into hybrid energy storage systems is a solution to mitigate battery degradation. Traditional strategies focus on fuel cell and battery power regulation while treating UC management as a passive element, resulting in suboptimal UC utilization. To optimize the energy utilization of UCs, this article proposes an active state control strategy within the hybrid system. Initially, leveraging the battery severity factor, the optimal power split strategy for HESS is proposed for a reference state-of-charge (SOC) of UC. Subsequently, a driving pattern severity factor is designed, and an online self-learning Markov predictor is employed to quantify the operational state of vehicle. To provide optimal reference SOC guidance to HESS in real time, a reinforcement learning algorithm featuring an experience replay mechanism is developed. Utilizing pretrained agents that integrate vehicle driving state abstraction parameters, the system generates the reference SOC of UC, enabling the optimal battery-UC power split in real time. Both numerical and semiphysical validations confirm the efficacy of the proposed strategy in enhancing the power output ratio of UC, optimizing energy storage space utilization, and reducing the battery severity factor, consequently improving overall battery lifespan.