Designing active vehicle suspension system using critic-based control strategy
In this paper, an adaptive critic-based neurofuzzy controller is presented for a 2 DOF active vehicle suspension system with a servo hydraulic actuator. Fuzzy critic-based learning is a reinforcement learning method based on dynamic programming. The only information available for the criti...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2015-09-01
|
| Series: | Nonlinear Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/nleng-2015-0004 |
| id |
doaj-93bc4b8dca0845f1bfb15bd00909301f |
|---|---|
| record_format |
Article |
| spelling |
doaj-93bc4b8dca0845f1bfb15bd00909301f2021-09-06T19:21:06ZengDe GruyterNonlinear Engineering2192-80102192-80292015-09-014314115410.1515/nleng-2015-0004Designing active vehicle suspension system using critic-based control strategyAkraminia Mahdi0Tatari Milad1Fard Mohammad2Jazar Reza N.3School of Mechanical Engineering, College of Engineering, University of Tehran, Tehran, Iran School of Mechanical Engineering, College of Engineering, University of Tehran, Tehran, Iran School of Aerospace, Mechanical, and Manufacturing Engineering, RMIT University, Melbourne, Victoria, Australia School of Aerospace, Mechanical, and Manufacturing Engineering, RMIT University, Melbourne, Victoria, Australia In this paper, an adaptive critic-based neurofuzzy controller is presented for a 2 DOF active vehicle suspension system with a servo hydraulic actuator. Fuzzy critic-based learning is a reinforcement learning method based on dynamic programming. The only information available for the critic agent is the system feedback, which is interpreted as the last action performed by the controller in the previous state. The signal produced by the critic agent is used alongside the algorithm of error back propagation to tune online conclusion parts of the fuzzy inference rules of the adaptive controller. Simulation results demonstrate the superior performance of this control method in terms of well disturbance rejection, improved ride comfort, robustness to model uncertainty and lower controller cost.https://doi.org/10.1515/nleng-2015-0004active vehicle suspensiondisturbance rejection critic-based controller reinforcement learning |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Akraminia Mahdi Tatari Milad Fard Mohammad Jazar Reza N. |
| spellingShingle |
Akraminia Mahdi Tatari Milad Fard Mohammad Jazar Reza N. Designing active vehicle suspension system using critic-based control strategy Nonlinear Engineering active vehicle suspension disturbance rejection critic-based controller reinforcement learning |
| author_facet |
Akraminia Mahdi Tatari Milad Fard Mohammad Jazar Reza N. |
| author_sort |
Akraminia Mahdi |
| title |
Designing active vehicle suspension system using
critic-based control strategy |
| title_short |
Designing active vehicle suspension system using
critic-based control strategy |
| title_full |
Designing active vehicle suspension system using
critic-based control strategy |
| title_fullStr |
Designing active vehicle suspension system using
critic-based control strategy |
| title_full_unstemmed |
Designing active vehicle suspension system using
critic-based control strategy |
| title_sort |
designing active vehicle suspension system using
critic-based control strategy |
| publisher |
De Gruyter |
| series |
Nonlinear Engineering |
| issn |
2192-8010 2192-8029 |
| publishDate |
2015-09-01 |
| description |
In this paper, an adaptive critic-based neurofuzzy
controller is presented for a 2 DOF active vehicle
suspension system with a servo hydraulic actuator. Fuzzy
critic-based learning is a reinforcement learning method
based on dynamic programming. The only information
available for the critic agent is the system feedback, which
is interpreted as the last action performed by the controller
in the previous state. The signal produced by the
critic agent is used alongside the algorithm of error back
propagation to tune online conclusion parts of the fuzzy
inference rules of the adaptive controller. Simulation results
demonstrate the superior performance of this control
method in terms of well disturbance rejection, improved
ride comfort, robustness to model uncertainty and lower
controller cost. |
| topic |
active vehicle suspension disturbance rejection critic-based controller reinforcement learning |
| url |
https://doi.org/10.1515/nleng-2015-0004 |
| work_keys_str_mv |
AT akraminiamahdi designingactivevehiclesuspensionsystemusingcriticbasedcontrolstrategy AT tatarimilad designingactivevehiclesuspensionsystemusingcriticbasedcontrolstrategy AT fardmohammad designingactivevehiclesuspensionsystemusingcriticbasedcontrolstrategy AT jazarrezan designingactivevehiclesuspensionsystemusingcriticbasedcontrolstrategy |
| _version_ |
1717775176046739456 |