Active Disturbance Rejection Control of Output Voltage of Solid Oxide Fuel Cell Based on Reinforcement Learning
ObjectivesIn order to improve the performance and lifetime of solid oxide fuel cell (SOFC) systems, the 100 kW SOFC system was taken as the research object. The continuous adjustment of the controller coefficients was explored through reinforcement learning to realize the best comprehensive performa...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Editorial Department of Power Generation Technology
2024-12-01
|
| Series: | 发电技术 |
| Subjects: | |
| Online Access: | https://www.pgtjournal.com/article/2024/2096-4528/2096-4528-2024-45-6-1163.shtml |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846100276715454464 |
|---|---|
| author | GUAN Chaojun LEI Zhengling HUO Haibo WANG Fang YAO Guoquan LIU Tao |
| author_facet | GUAN Chaojun LEI Zhengling HUO Haibo WANG Fang YAO Guoquan LIU Tao |
| author_sort | GUAN Chaojun |
| collection | DOAJ |
| description | ObjectivesIn order to improve the performance and lifetime of solid oxide fuel cell (SOFC) systems, the 100 kW SOFC system was taken as the research object. The continuous adjustment of the controller coefficients was explored through reinforcement learning to realize the best comprehensive performance, while ensuring the output voltage tracking performance.MethodsA mechanism-based SOFC output voltage system model was established, an improved nonlinear active disturbance rejection controller (NLADRC) was used to make the output voltage track the reference value well by controlling the input gas flow. Conventional single-channel controllers can only satisfy one objective at a time, and dual-channel controllers will increase system complexity, cost and risk of failure. An improved NLADRC controller based on the twin delayed deep deterministic policy gradient (TD3) was proposed to optimize the coefficients of nonlinear error feedback control law.ResultsThe designed controller can improve SOFC output voltage tracking performance without violating fuel utilization constraints.ConclusionsThe designed controller has the advantages of strong adaptability, high stability, and the ability to overcome uncertainty, providing theoretical reference for designing output voltage controllers in practical SOFC systems. |
| format | Article |
| id | doaj-art-c0ecdfb7a5054b6ebaa64a2e66312c09 |
| institution | Kabale University |
| issn | 2096-4528 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Editorial Department of Power Generation Technology |
| record_format | Article |
| series | 发电技术 |
| spelling | doaj-art-c0ecdfb7a5054b6ebaa64a2e66312c092024-12-30T11:55:32ZengEditorial Department of Power Generation Technology发电技术2096-45282024-12-014561163117210.12096/j.2096-4528.pgt.240172096-4528（2024）06-1163-10Active Disturbance Rejection Control of Output Voltage of Solid Oxide Fuel Cell Based on Reinforcement LearningGUAN Chaojun0LEI Zhengling1HUO Haibo2WANG Fang3YAO Guoquan4LIU Tao5College of Engineering Science and Technology, Shanghai Ocean University, Pudong New District, Shanghai201306, ChinaCollege of Engineering Science and Technology, Shanghai Ocean University, Pudong New District, Shanghai201306, ChinaCollege of Engineering Science and Technology, Shanghai Ocean University, Pudong New District, Shanghai201306, ChinaCollege of Engineering Science and Technology, Shanghai Ocean University, Pudong New District, Shanghai201306, ChinaKey Laboratory of High Performance Ship Technology of the Ministry of Education (Wuhan University of Technology), Wuhan430063, Hubei Province, ChinaCollege of Transport and Communications, Shanghai Maritime University, Pudong New District, Shanghai201306, ChinaObjectivesIn order to improve the performance and lifetime of solid oxide fuel cell (SOFC) systems, the 100 kW SOFC system was taken as the research object. The continuous adjustment of the controller coefficients was explored through reinforcement learning to realize the best comprehensive performance, while ensuring the output voltage tracking performance.MethodsA mechanism-based SOFC output voltage system model was established, an improved nonlinear active disturbance rejection controller (NLADRC) was used to make the output voltage track the reference value well by controlling the input gas flow. Conventional single-channel controllers can only satisfy one objective at a time, and dual-channel controllers will increase system complexity, cost and risk of failure. An improved NLADRC controller based on the twin delayed deep deterministic policy gradient (TD3) was proposed to optimize the coefficients of nonlinear error feedback control law.ResultsThe designed controller can improve SOFC output voltage tracking performance without violating fuel utilization constraints.ConclusionsThe designed controller has the advantages of strong adaptability, high stability, and the ability to overcome uncertainty, providing theoretical reference for designing output voltage controllers in practical SOFC systems.https://www.pgtjournal.com/article/2024/2096-4528/2096-4528-2024-45-6-1163.shtmlsolid oxide fuel cell (sofc)twin delayed deep deterministic policy gradient (td3)nonlinear active disturbance rejection control (nladrc)fuel utilizationnonlinear error feedback control lawoutput voltage trackinguncertainty |
| spellingShingle | GUAN Chaojun LEI Zhengling HUO Haibo WANG Fang YAO Guoquan LIU Tao Active Disturbance Rejection Control of Output Voltage of Solid Oxide Fuel Cell Based on Reinforcement Learning 发电技术 solid oxide fuel cell (sofc) twin delayed deep deterministic policy gradient (td3) nonlinear active disturbance rejection control (nladrc) fuel utilization nonlinear error feedback control law output voltage tracking uncertainty |
| title | Active Disturbance Rejection Control of Output Voltage of Solid Oxide Fuel Cell Based on Reinforcement Learning |
| title_full | Active Disturbance Rejection Control of Output Voltage of Solid Oxide Fuel Cell Based on Reinforcement Learning |
| title_fullStr | Active Disturbance Rejection Control of Output Voltage of Solid Oxide Fuel Cell Based on Reinforcement Learning |
| title_full_unstemmed | Active Disturbance Rejection Control of Output Voltage of Solid Oxide Fuel Cell Based on Reinforcement Learning |
| title_short | Active Disturbance Rejection Control of Output Voltage of Solid Oxide Fuel Cell Based on Reinforcement Learning |
| title_sort | active disturbance rejection control of output voltage of solid oxide fuel cell based on reinforcement learning |
| topic | solid oxide fuel cell (sofc) twin delayed deep deterministic policy gradient (td3) nonlinear active disturbance rejection control (nladrc) fuel utilization nonlinear error feedback control law output voltage tracking uncertainty |
| url | https://www.pgtjournal.com/article/2024/2096-4528/2096-4528-2024-45-6-1163.shtml |
| work_keys_str_mv | AT guanchaojun activedisturbancerejectioncontrolofoutputvoltageofsolidoxidefuelcellbasedonreinforcementlearning AT leizhengling activedisturbancerejectioncontrolofoutputvoltageofsolidoxidefuelcellbasedonreinforcementlearning AT huohaibo activedisturbancerejectioncontrolofoutputvoltageofsolidoxidefuelcellbasedonreinforcementlearning AT wangfang activedisturbancerejectioncontrolofoutputvoltageofsolidoxidefuelcellbasedonreinforcementlearning AT yaoguoquan activedisturbancerejectioncontrolofoutputvoltageofsolidoxidefuelcellbasedonreinforcementlearning AT liutao activedisturbancerejectioncontrolofoutputvoltageofsolidoxidefuelcellbasedonreinforcementlearning |