RBF Neural Network Based Control Strategy for Thermal Management System in Parallel Hybrid Electric Bus

2012 ◽  
Vol 4 (23) ◽  
pp. 779-787
Author(s):  
Yan Wei ◽  
Wang Guihua ◽  
Li Guoxiang ◽  
Tian Ji an ◽  
Peng Wei Li Yunhui
Keyword(s):  
Neural Network ◽  
Thermal Management ◽  
Control Strategy ◽  
Management System ◽  
Rbf Neural Network ◽  
Hybrid Electric Bus ◽  
Thermal Management System ◽  
Electric Bus ◽  
Parallel Hybrid ◽  
Hybrid Electric

Study of Thermal Management System for a Series-Parallel Hybrid Electric Vehicle Using Numerical Simulation

2013 ◽  
Vol 300-301 ◽  
pp. 932-937 ◽  
Author(s):  
Xiao Xia Sun ◽  
Yi Chun Wang ◽  
Chun Ming Shao ◽  
Yu Feng Wu ◽  
Guo Zhu Wang
Keyword(s):  
Electric Vehicle ◽  
Thermal Management ◽  
Management System ◽  
Hybrid Electric Vehicle ◽  
Heat Dissipation ◽  
Pollutant Emission ◽  
Parallel Hybrid Electric Vehicle ◽  
Thermal Management System ◽  
Parallel Hybrid ◽  
Hybrid Electric

Advanced thermal management system (TMS) has the potential to increase the life of the vehicle’s propulsion, and meanwhile, decrease fuel consumption and pollutant emission. In this paper, an advanced TMS which is suitable for a series-parallel hybrid electric vehicle (SPHEV) is presented. Then a numerical TMS model which can predict the thermal responses of all TMS components and the temperatures of the engine and electric components is developed. By using this model, the thermal response of the TMS over a realistic driving cycle is simulated. The simulation result shows that the TMS can fulfill the heat dissipation requirement of the whole vehicle under different driving conditions. It also demonstrates that a numerical model of TMS for SPHEV is an effective tool to assess design concepts and architectures of the vehicle system during the early stage of system development.

scholarly journals Optimization of fuel cell thermal management system based on back propagation neural network

2021 ◽  
Vol 25 (4 Part B) ◽  
pp. 2975-2982
Author(s):  
Qianqian Ge ◽  
Cuncun Wei
Keyword(s):  
Neural Network ◽  
Fuel Cell ◽  
Thermal Management ◽  
Control Strategy ◽  
Management System ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Current Control ◽  
Control Effect ◽  
Thermal Management System

Two thermal management control strategies, namely flow following current and power mode and back propagation neural network auto-disturbance rejection method, were proposed to solve significant temperature fluctuation problems, long regulation time, and slow response speed in fuel cell thermal management system variable load. The results show that the flow following current and power control strategy can effectively weaken the coupling effect between pump and radiator fan and significantly reduce the overshoot and adjustment time of inlet and outlet cooling water temperature and temperature difference reactor. Although the control effect of the neural network and strategy is insufficient under maximum power, the overall control effect is better than that of the flow following the current control strategy.

Sign in / Sign up

Export Citation Format

Share Document