汽车电子研究中心

Research Direction

Based on the development of the intelligent driving vehicles and the related key technologies, systematic interdisciplinary research has been carried out from the communications security, laser radar, machine vision, active safety, energy saving such aspects.
1.Perception
Research on the information fusion technology of the vehicle radar and machine vision and new technology of space 3D information construction in visual detection and measurement technology
2.Autonomous driving decision
Based on the framework of deep reinforcement learning, to construct the automatic driving strategy learning model and to improve the training efficiency using parallel computing.
3.Car network communication security
Research on the encryption and decryption, identity authentication and key distribution of vehicle network access, safe driving, billing management, traffic management and data communication.
4.Energy-saving driving
Through the path planning and speed adjustment to achieve energy-saving, combined with large traffic data, so as to achieve energy conservation from the city level.

Deep reinforcement learning-based energy management strategy of hybrid electric vehicle research

It is significant for the promotion of fuel cell hybrid vehicles to design a reasonable energy management strategy and coordinate the power output between different power sources, so as to meet the vehicles dynamic demand, realize the energy saving and the emission reduction, and extend the lifetime of the fuel cell and the battery. Currently, energy management strategies can be divided into rule-based strategies and optimization-based strategies. The former has good real-time performance, but the control effect should be further improved; the latter has better control effect, but it is difficult to be applied in real time. In addition, for fuel cell hybrid vehicles, existing energy management strategies do not fully consider the fuel cell lifetime improvement. This project proposes a fuel cell lifetime-enhancing energy management strategy for fuel cell hybrid electric vehicles based on reinforcement learning and deep reinforcement learning, in which the stability and the calculation efficiency of the strategies are improved through various algorithm skills. A lifetime decay model of fuel cells is established to quantitatively evaluate the fuel cell lifetime-enhancing effect of the strategies. Simulation results show that the proposed strategy has the outstanding performance in terms of the algorithm convergence, the fuel economy, the fuel cell lifetime-enhancement, and the adaptability to different driving cycles. The real-time performance and control performance of the strategies are well considered at the same time, and this is helpful for the practical application and popularization.

Intellectual Properties

Selected Papers

[1] Chunhua Zheng*, Dongfang Zhang, Yao Xiao, Wei Li. Reinforcement learning-based energy management strategies of fuel cell hybrid vehicles with multi-objective control[J]. Journal of Power Sources, 2022, 543: 231841.
[2] Dezhou Xu, Yunduan Cui, Jiaye Ye, Suk Won Cha, Aimin Li, Chunhua Zheng*. A soft actor-critic-based energy management strategy for electric vehicles with hybrid energy storage systems[J]. Journal of Power Sources, 2022, 524: 231099.
[3] Chunhua Zheng, Wei Li, Weimin Li, Kun Xu, Lei Peng, Suk Won Cha*. A deep reinforcement learning-based energy management strategy for fuel cell hybrid buses[J]. International Journal of Precision Engineering and Manufacturing-Green Technology, 2022, 9(3): 885-897.

Selected Patents

（1）The invention relates to a method and equipment for verifying an automotive energy management strategy, China patent for invention, 2019/12/12
（2）The invention relates to a method and equipment for verifying an automotive energy management strategy, PCT patent, 2019/12/12

Shenzhen Institutes of Advanced Technology , Chinese Academy of Sciences —— Center for Automotive Electronics

Shenzhen Institutes of Advanced Technology , Chinese Academy of Sciences
—— Center for Automotive Electronics