Feng Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Feng Wang has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
- Xing Xu
Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, Jiangsu, CHINA
10 shared publications - Xiaoyuan Zhu
School of Mechanical Engineering, Southeast University, Nanjing, China
5 shared publications - Yi-Qing Ni
Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University, Hong Kong, China
4 shared publications - Chenghao Fang
Jiangsu University
3 shared publications - Cong Liang
Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, China
3 shared publications Yi-Qing Ni
Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong
3 shared publications
Latest Publications
- Open Access
Deep Learning-Based Optimization of Bionic Cooling Ducts for Heavy-Duty Vehicle Electric Drive Systems
Liquid cooling has become a predominant method for electric motor thermal management due to its superior heat transfer coefficient. However, conventional cooling channel designs often struggle to achieve an optimal balance between thermal dissipation performance and pressure loss. Inspired by the streamlined morphological features of diving beetles, this paper proposes a novel bionic cooling channel design. By extracting the hydrodynamic profile of the diving beetle’s body, a series of bionic diving beetle-inspired spoiler tubes were designed and integrated into the cooling ducts to optimize flow patterns. A deep learning-based framework was established to correlate these bionic geometric parameters with the thermal–hydraulic performance of the motor. The results demonstrate that the developed ANN model achieves an average R2 of 0.95 across the three output parameters, indicating high predictive accuracy. Compared to traditional structures, the optimized biomimetic channel yielded a 16.09% reduction in pressure drop relative to the conventional reference channel at the same flow rate. Furthermore, under real-vehicle operating conditions, the maximum winding temperature of OBDBS was comparable to that of IBDBS, while the cooling-channel pressure drop was reduced by 7.34%. This study demonstrates that the integration of bionic morphological principles with the GA-ANN-NSGA-II multi-objective optimization framework can reduce the hydraulic power requirement while maintaining a comparable winding temperature, providing an efficient optimization pathway for the thermal management of high-power-density motors.
Open AccessDeep Learning-Based Optimization of Bionic Cooling Ducts for Heavy-Duty Vehicle Electric Drive Systems
Liquid cooling has become a predominant method for electric motor thermal management due to its superior heat transfer coefficient. However, conventional cooling channel designs often struggle to achieve an optimal balance between thermal dissipation performance and pressure loss. Inspired by the streamlined morphological features of diving beetles, this paper proposes a novel bionic cooling channel design. By extracting the hydrodynamic profile of the diving beetle’s body, a series of bionic diving beetle-inspired spoiler tubes were designed and integrated into the cooling ducts to optimize flow patterns. A deep learning-based framework was established to correlate these bionic geometric parameters with the thermal–hydraulic performance of the motor. The results demonstrate that the developed ANN model achieves an average R2 of 0.95 across the three output parameters, indicating high predictive accuracy. Compared to traditional structures, the optimized biomimetic channel yielded a 16.09% reduction in pressure drop relative to the conventional reference channel at the same flow rate. Furthermore, under real-vehicle operating conditions, the maximum winding temperature of OBDBS was comparable to that of IBDBS, while the cooling-channel pressure drop was reduced by 7.34%. This study demonstrates that the integration of bionic morphological principles with the GA-ANN-NSGA-II multi-objective optimization framework can reduce the hydraulic power requirement while maintaining a comparable winding temperature, providing an efficient optimization pathway for the thermal management of high-power-density motors.
- Open Access
Integrated Fault Estimation and Fault-Tolerant Control for Drive-by-Wire Steering Systems in Four-Wheel Independent Drive Vehicles
This study proposes an integrated fault estimation and fault-tolerant control strategy for actuators of four-wheel independently driven vehicles. Firstly, a modeling approach is developed by combining the vehicle dynamics model with the steering actuator model to establish a system model in the presence of actuator faults. Subsequently, to simultaneously estimate the system states and actuator faults, an unknown input observer (UIO) is designed, treating actuator faults as unknown state variables and augmenting the system state variables to achieve simultaneous estimation of states and faults, providing a foundation for subsequent fault-tolerant control research. The gain matrices of the fault observer and the fault-tolerant controller are both obtained through single-step linear matrix inequality (LMI) computations, realizing the design of an integrated fault-tolerant control system. Finally, the effectiveness and superiority of the proposed method are verified through hardware-in-the-loop experimental tests.
Open AccessIntegrated Fault Estimation and Fault-Tolerant Control for Drive-by-Wire Steering Systems in Four-Wheel Independent Drive Vehicles
This study proposes an integrated fault estimation and fault-tolerant control strategy for actuators of four-wheel independently driven vehicles. Firstly, a modeling approach is developed by combining the vehicle dynamics model with the steering actuator model to establish a system model in the presence of actuator faults. Subsequently, to simultaneously estimate the system states and actuator faults, an unknown input observer (UIO) is designed, treating actuator faults as unknown state variables and augmenting the system state variables to achieve simultaneous estimation of states and faults, providing a foundation for subsequent fault-tolerant control research. The gain matrices of the fault observer and the fault-tolerant controller are both obtained through single-step linear matrix inequality (LMI) computations, realizing the design of an integrated fault-tolerant control system. Finally, the effectiveness and superiority of the proposed method are verified through hardware-in-the-loop experimental tests.
- 3 May 2026
- Published by Springer Nature in International Journal of Dynamics and Control
- Vol. 14 (5) , 164
Torque and shift decision for quadri-motor mining truck based on expert-informed DDPG
- 3 May 2026
- Published by Springer Nature in International Journal of Dynamics and Control
- Vol. 14 (5) , 164
Torque and shift decision for quadri-motor mining truck based on expert-informed DDPG
- 12 March 2026
- Published by Elsevier in Measurement
- Vol. 273
Bayesian probability-based intelligent diagnosis of mechanical faults of integrated high-speed electric powertrain with small samples
- 12 March 2026
- Published by Elsevier in Measurement
- Vol. 273
Bayesian probability-based intelligent diagnosis of mechanical faults of integrated high-speed electric powertrain with small samples
- 25 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (3) , 5358-5371
Multitask Physics-Informed Neural Network-Based Steering Control Strategy for Steer-by-Wire Systems
The steer-by-wire (SBW) system is recognized as a crucial technology for facilitating autonomous driving. However, system nonlinearities, parametric uncertainties, and external disturbances present significant challenges to steering control. This article proposes a control strategy integrating the multitask physics-informed neural network (MTPINN) with model predictive control (MPC), using the rack position as the tracking target. First, the SBW model, including the motor, synchronous belt, ball screw, and rack, is established, with the rack force being treated as an extended state of the system to construct the extended disturbance observer (EDO). Then, by embedding both the extended disturbance observation equation and the prediction equation into the neural network, the MTPINN model that represents the transient behavior of the SBW system is constructed. This model is integrated with the MPC architecture to improve the performance of rack position tracking control. Finally, the bench test results indicate that the maximum observation error root-mean-squared error (RMSE) and the maximum tracking error RMSE are 0.348 kN and 0.784 mm, respectively, validating the effectiveness of the MTPINN-MPC steering control strategy.
- 25 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (3) , 5358-5371
Multitask Physics-Informed Neural Network-Based Steering Control Strategy for Steer-by-Wire Systems
The steer-by-wire (SBW) system is recognized as a crucial technology for facilitating autonomous driving. However, system nonlinearities, parametric uncertainties, and external disturbances present significant challenges to steering control. This article proposes a control strategy integrating the multitask physics-informed neural network (MTPINN) with model predictive control (MPC), using the rack position as the tracking target. First, the SBW model, including the motor, synchronous belt, ball screw, and rack, is established, with the rack force being treated as an extended state of the system to construct the extended disturbance observer (EDO). Then, by embedding both the extended disturbance observation equation and the prediction equation into the neural network, the MTPINN model that represents the transient behavior of the SBW system is constructed. This model is integrated with the MPC architecture to improve the performance of rack position tracking control. Finally, the bench test results indicate that the maximum observation error root-mean-squared error (RMSE) and the maximum tracking error RMSE are 0.348 kN and 0.784 mm, respectively, validating the effectiveness of the MTPINN-MPC steering control strategy.
- 1 October 2025
- Published by Elsevier in ISA Transactions
- Vol. 167, 2030-2045
PCE-based uncertain PWA modeling and control for DMHP mode transition system
- 1 October 2025
- Published by Elsevier in ISA Transactions
- Vol. 167, 2030-2045
PCE-based uncertain PWA modeling and control for DMHP mode transition system
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (1) , 168-180
Novel Multiphysics Informed Neural Network-Based Coordinated Control Strategy for Mode Transitions of PHEV Considering Torsional Oscillation
This article proposes a novel multiphysics informed neural network-based model predictive control (MPINN-MPC) strategy to address torsional vibrations and torque fluctuations during electric mode to hybrid mode (EM-to-HM) transitions in plug-in hybrid electric vehicles (PHEVs). The powertrain’s mode transition process (MTP) is divided into five distinct stages, where physics-informed neural networks (PINNs) are introduced to capture transient nonlinear dynamics in each stage, ultimately constructing an MPINN model that accurately represents the transient MTP behavior. By embedding physical laws into neural network training, the MPINN framework combines the interpretability of physical equations with the adaptability of data-driven learning, enabling precise prediction of system states under uncertainties. Integrated with the MPC architecture, the proposed strategy accurately coordinates the clutch oil pressure and motor torque during the MTP. Experimental results demonstrate that, compared to noncontrol and MPC based on hybrid model (H-MPC) strategies, MPINN-MPC achieves greater reduction of vehicle jerk (by 92.4% and 49.3%, respectively) and clutch slip energy loss (by 6.9% and 1.6%, respectively). This method provides a robust solution for improving ride comfort and energy efficiency during complex powertrain mode transitions.
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (1) , 168-180
Novel Multiphysics Informed Neural Network-Based Coordinated Control Strategy for Mode Transitions of PHEV Considering Torsional Oscillation
This article proposes a novel multiphysics informed neural network-based model predictive control (MPINN-MPC) strategy to address torsional vibrations and torque fluctuations during electric mode to hybrid mode (EM-to-HM) transitions in plug-in hybrid electric vehicles (PHEVs). The powertrain’s mode transition process (MTP) is divided into five distinct stages, where physics-informed neural networks (PINNs) are introduced to capture transient nonlinear dynamics in each stage, ultimately constructing an MPINN model that accurately represents the transient MTP behavior. By embedding physical laws into neural network training, the MPINN framework combines the interpretability of physical equations with the adaptability of data-driven learning, enabling precise prediction of system states under uncertainties. Integrated with the MPC architecture, the proposed strategy accurately coordinates the clutch oil pressure and motor torque during the MTP. Experimental results demonstrate that, compared to noncontrol and MPC based on hybrid model (H-MPC) strategies, MPINN-MPC achieves greater reduction of vehicle jerk (by 92.4% and 49.3%, respectively) and clutch slip energy loss (by 6.9% and 1.6%, respectively). This method provides a robust solution for improving ride comfort and energy efficiency during complex powertrain mode transitions.