An Online Learning Control Strategy for Hybrid Electric Vehicle Based on Fuzzy Q-Learning
In order to realize the online learning of a hybrid electric vehicle (HEV) control strategy, a fuzzy Q-learning (FQL) method is proposed in this paper. FQL control strategies consists of two parts: The optimal action-value function Q*(x,u) estimator network (QEN) and the fuzzy parameters tuning (FPT...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2015-10-01
|
Series: | Energies |
Subjects: | |
Online Access: | http://www.mdpi.com/1996-1073/8/10/11167 |
id |
doaj-6d04f05e6b49441a8b1ff82c34cdc3a5 |
---|---|
record_format |
Article |
spelling |
doaj-6d04f05e6b49441a8b1ff82c34cdc3a52020-11-24T23:04:52ZengMDPI AGEnergies1996-10732015-10-01810111671118610.3390/en81011167en81011167An Online Learning Control Strategy for Hybrid Electric Vehicle Based on Fuzzy Q-LearningYue Hu0Weimin Li1Hui Xu2Guoqing Xu3Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaJining Institutes of Advanced Technology, Chinese Academy of Sciences, Jining 272000, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaIn order to realize the online learning of a hybrid electric vehicle (HEV) control strategy, a fuzzy Q-learning (FQL) method is proposed in this paper. FQL control strategies consists of two parts: The optimal action-value function Q*(x,u) estimator network (QEN) and the fuzzy parameters tuning (FPT). A back propagation (BP) neural network is applied to estimate Q*(x,u) as QEN. For the fuzzy controller, we choose a Sugeno-type fuzzy inference system (FIS) and the parameters of the FIS are tuned online based on Q*(x,u). The action exploration modifier (AEM) is introduced to guarantee all actions are tried. The main advantage of a FQL control strategy is that it does not rely on prior information related to future driving conditions and can self-tune the parameters of the fuzzy controller online. The FQL control strategy has been applied to a HEV and simulation tests have been done. Simulation results indicate that the parameters of the fuzzy controller are tuned online and that a FQL control strategy achieves good performance in fuel economy.http://www.mdpi.com/1996-1073/8/10/11167hybrid electric vehiclefuzzy Q-learning (FQL) control strategyQ*(x,u) estimator network (QEN)fuzzy parameters tuning (FPT) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yue Hu Weimin Li Hui Xu Guoqing Xu |
spellingShingle |
Yue Hu Weimin Li Hui Xu Guoqing Xu An Online Learning Control Strategy for Hybrid Electric Vehicle Based on Fuzzy Q-Learning Energies hybrid electric vehicle fuzzy Q-learning (FQL) control strategy Q*(x,u) estimator network (QEN) fuzzy parameters tuning (FPT) |
author_facet |
Yue Hu Weimin Li Hui Xu Guoqing Xu |
author_sort |
Yue Hu |
title |
An Online Learning Control Strategy for Hybrid Electric Vehicle Based on Fuzzy Q-Learning |
title_short |
An Online Learning Control Strategy for Hybrid Electric Vehicle Based on Fuzzy Q-Learning |
title_full |
An Online Learning Control Strategy for Hybrid Electric Vehicle Based on Fuzzy Q-Learning |
title_fullStr |
An Online Learning Control Strategy for Hybrid Electric Vehicle Based on Fuzzy Q-Learning |
title_full_unstemmed |
An Online Learning Control Strategy for Hybrid Electric Vehicle Based on Fuzzy Q-Learning |
title_sort |
online learning control strategy for hybrid electric vehicle based on fuzzy q-learning |
publisher |
MDPI AG |
series |
Energies |
issn |
1996-1073 |
publishDate |
2015-10-01 |
description |
In order to realize the online learning of a hybrid electric vehicle (HEV) control strategy, a fuzzy Q-learning (FQL) method is proposed in this paper. FQL control strategies consists of two parts: The optimal action-value function Q*(x,u) estimator network (QEN) and the fuzzy parameters tuning (FPT). A back propagation (BP) neural network is applied to estimate Q*(x,u) as QEN. For the fuzzy controller, we choose a Sugeno-type fuzzy inference system (FIS) and the parameters of the FIS are tuned online based on Q*(x,u). The action exploration modifier (AEM) is introduced to guarantee all actions are tried. The main advantage of a FQL control strategy is that it does not rely on prior information related to future driving conditions and can self-tune the parameters of the fuzzy controller online. The FQL control strategy has been applied to a HEV and simulation tests have been done. Simulation results indicate that the parameters of the fuzzy controller are tuned online and that a FQL control strategy achieves good performance in fuel economy. |
topic |
hybrid electric vehicle fuzzy Q-learning (FQL) control strategy Q*(x,u) estimator network (QEN) fuzzy parameters tuning (FPT) |
url |
http://www.mdpi.com/1996-1073/8/10/11167 |
work_keys_str_mv |
AT yuehu anonlinelearningcontrolstrategyforhybridelectricvehiclebasedonfuzzyqlearning AT weiminli anonlinelearningcontrolstrategyforhybridelectricvehiclebasedonfuzzyqlearning AT huixu anonlinelearningcontrolstrategyforhybridelectricvehiclebasedonfuzzyqlearning AT guoqingxu anonlinelearningcontrolstrategyforhybridelectricvehiclebasedonfuzzyqlearning AT yuehu onlinelearningcontrolstrategyforhybridelectricvehiclebasedonfuzzyqlearning AT weiminli onlinelearningcontrolstrategyforhybridelectricvehiclebasedonfuzzyqlearning AT huixu onlinelearningcontrolstrategyforhybridelectricvehiclebasedonfuzzyqlearning AT guoqingxu onlinelearningcontrolstrategyforhybridelectricvehiclebasedonfuzzyqlearning |
_version_ |
1725628847861268480 |