An Energy Management Strategy for a Super-Mild Hybrid Electric Vehicle Based on a Known Model of Reinforcement Learning

For global optimal control strategy, it is not only necessary to know the driving cycle in advance but also difficult to implement online because of its large calculation volume. As an artificial intelligent-based control strategy, reinforcement learning (RL) is applied to an energy management strat...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanli Yin, Yan Ran, Liufeng Zhang, Xiaoliang Pan, Yong Luo
Format: Article
Language:English
Published: Wiley 2019-01-01
Series:Journal of Control Science and Engineering
Online Access:http://dx.doi.org/10.1155/2019/9259712
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849305283111682048
author Yanli Yin
Yan Ran
Liufeng Zhang
Xiaoliang Pan
Yong Luo
author_facet Yanli Yin
Yan Ran
Liufeng Zhang
Xiaoliang Pan
Yong Luo
author_sort Yanli Yin
collection DOAJ
description For global optimal control strategy, it is not only necessary to know the driving cycle in advance but also difficult to implement online because of its large calculation volume. As an artificial intelligent-based control strategy, reinforcement learning (RL) is applied to an energy management strategy of a super-mild hybrid electric vehicle. According to time-speed datasets of sample driving cycles, a stochastic model of the driver’s power demand is developed. Based on the Markov decision process theory, a mathematical model of an RL-based energy management strategy is established, which assumes the minimum cumulative return expectation as its optimization objective. A policy iteration algorithm is adopted to obtain the optimum control policy that takes the vehicle speed, driver’s power demand, and state of charge (SOC) as the input and the engine power as the output. Using a MATLAB/Simulink platform, CYC_WVUCITY simulation model is established. The results show that, compared with dynamic programming, this method can not only adapt to random driving cycles and reduce fuel consumption of 2.4%, but also be implemented online because of its small calculation volume.
format Article
id doaj-art-07c26739da7a4db287a732b36627da02
institution Kabale University
issn 1687-5249
1687-5257
language English
publishDate 2019-01-01
publisher Wiley
record_format Article
series Journal of Control Science and Engineering
spelling doaj-art-07c26739da7a4db287a732b36627da022025-08-20T03:55:28ZengWileyJournal of Control Science and Engineering1687-52491687-52572019-01-01201910.1155/2019/92597129259712An Energy Management Strategy for a Super-Mild Hybrid Electric Vehicle Based on a Known Model of Reinforcement LearningYanli Yin0Yan Ran1Liufeng Zhang2Xiaoliang Pan3Yong Luo4School of Mechatronics & Automobile Engineering, Chongqing Jiao Tong University, Chongqing 400054, ChinaSchool of Mechatronics & Automobile Engineering, Chongqing Jiao Tong University, Chongqing 400054, ChinaSchool of Mechatronics & Automobile Engineering, Chongqing Jiao Tong University, Chongqing 400054, ChinaChongqing Changan Automobile Stock Co., Ltd., Chongqing 400054, ChinaKey Laboratory of Advanced Manufacturing Technology for Automobile Parts, Ministry of Education, Chongqing University of Technology, Chongqing 400054, ChinaFor global optimal control strategy, it is not only necessary to know the driving cycle in advance but also difficult to implement online because of its large calculation volume. As an artificial intelligent-based control strategy, reinforcement learning (RL) is applied to an energy management strategy of a super-mild hybrid electric vehicle. According to time-speed datasets of sample driving cycles, a stochastic model of the driver’s power demand is developed. Based on the Markov decision process theory, a mathematical model of an RL-based energy management strategy is established, which assumes the minimum cumulative return expectation as its optimization objective. A policy iteration algorithm is adopted to obtain the optimum control policy that takes the vehicle speed, driver’s power demand, and state of charge (SOC) as the input and the engine power as the output. Using a MATLAB/Simulink platform, CYC_WVUCITY simulation model is established. The results show that, compared with dynamic programming, this method can not only adapt to random driving cycles and reduce fuel consumption of 2.4%, but also be implemented online because of its small calculation volume.http://dx.doi.org/10.1155/2019/9259712
spellingShingle Yanli Yin
Yan Ran
Liufeng Zhang
Xiaoliang Pan
Yong Luo
An Energy Management Strategy for a Super-Mild Hybrid Electric Vehicle Based on a Known Model of Reinforcement Learning
Journal of Control Science and Engineering
title An Energy Management Strategy for a Super-Mild Hybrid Electric Vehicle Based on a Known Model of Reinforcement Learning
title_full An Energy Management Strategy for a Super-Mild Hybrid Electric Vehicle Based on a Known Model of Reinforcement Learning
title_fullStr An Energy Management Strategy for a Super-Mild Hybrid Electric Vehicle Based on a Known Model of Reinforcement Learning
title_full_unstemmed An Energy Management Strategy for a Super-Mild Hybrid Electric Vehicle Based on a Known Model of Reinforcement Learning
title_short An Energy Management Strategy for a Super-Mild Hybrid Electric Vehicle Based on a Known Model of Reinforcement Learning
title_sort energy management strategy for a super mild hybrid electric vehicle based on a known model of reinforcement learning
url http://dx.doi.org/10.1155/2019/9259712
work_keys_str_mv AT yanliyin anenergymanagementstrategyforasupermildhybridelectricvehiclebasedonaknownmodelofreinforcementlearning
AT yanran anenergymanagementstrategyforasupermildhybridelectricvehiclebasedonaknownmodelofreinforcementlearning
AT liufengzhang anenergymanagementstrategyforasupermildhybridelectricvehiclebasedonaknownmodelofreinforcementlearning
AT xiaoliangpan anenergymanagementstrategyforasupermildhybridelectricvehiclebasedonaknownmodelofreinforcementlearning
AT yongluo anenergymanagementstrategyforasupermildhybridelectricvehiclebasedonaknownmodelofreinforcementlearning
AT yanliyin energymanagementstrategyforasupermildhybridelectricvehiclebasedonaknownmodelofreinforcementlearning
AT yanran energymanagementstrategyforasupermildhybridelectricvehiclebasedonaknownmodelofreinforcementlearning
AT liufengzhang energymanagementstrategyforasupermildhybridelectricvehiclebasedonaknownmodelofreinforcementlearning
AT xiaoliangpan energymanagementstrategyforasupermildhybridelectricvehiclebasedonaknownmodelofreinforcementlearning
AT yongluo energymanagementstrategyforasupermildhybridelectricvehiclebasedonaknownmodelofreinforcementlearning