发电技术 ›› 2024, Vol. 45 ›› Issue (6): 1163-1172.DOI: 10.12096/j.2096-4528.pgt.24017

• 新能源 • 上一篇    

基于强化学习的固体氧化物燃料电池输出电压自抗扰控制研究

管超骏1, 雷正玲1, 霍海波1, 王芳1, 姚国全2, 刘涛3   

  1. 1.上海海洋大学工程学院,上海市 浦东新区 201306
    2.高性能舰船技术教育部重点实验室(武汉理工大学),湖北省 武汉市 430063
    3.上海海事大学交通运输学院,上海市 浦东新区 201306
  • 收稿日期:2024-01-22 修回日期:2024-04-29 出版日期:2024-12-31 发布日期:2024-12-30
  • 通讯作者: 雷正玲
  • 作者简介:管超骏(1994),男,硕士研究生,研究方向为燃料电池建模与跟踪控制,17621922877@163.com
    雷正玲(1988),女,博士,讲师,研究方向为新能源动力系统建模与控制、基于深度学习方法的新能源功率预测等,本文通信作者,zllei@shou.edu.cn
    姚国全(1987),男,硕士,实验师,研究方向为船舶水动力学、船舶性能试验技术、海洋智能装备建模与控制等,604617856@qq.com
    刘涛(1988),男,博士,副教授,研究方向为人工智能、智能交通、大数据等,dlmult@hotmail.com
  • 基金资助:
    国家自然科学基金项目(52301420);高性能舰船技术教育部重点实验室开放基金课题项目(GXNC23052801);上海市地方院校能力建设计划项目(23010502200)

Active Disturbance Rejection Control of Output Voltage of Solid Oxide Fuel Cell Based on Reinforcement Learning

Chaojun GUAN1, Zhengling LEI1, Haibo HUO1, Fang WANG1, Guoquan YAO2, Tao LIU3   

  1. 1.College of Engineering Science and Technology, Shanghai Ocean University, Pudong New District, Shanghai 201306, China
    2.Key Laboratory of High Performance Ship Technology of the Ministry of Education (Wuhan University of Technology), Wuhan 430063, Hubei Province, China
    3.College of Transport and Communications, Shanghai Maritime University, Pudong New District, Shanghai 201306, China
  • Received:2024-01-22 Revised:2024-04-29 Published:2024-12-31 Online:2024-12-30
  • Contact: Zhengling LEI
  • Supported by:
    National Natural Science Foundation of China(52301420);Open Fund of Key Laboratory of High Performance Ship Technology of the Ministry of Education(GXNC23052801);Capacity Building Project of Local Universities in Shanghai(23010502200)

摘要:

目的 为提升固体氧化物燃料电池(solid oxide fuel cell,SOFC)系统性能及寿命,以100 kW SOFC系统为研究对象,探究在保证输出电压跟踪性能的同时,通过强化学习不断调整控制器系数以实现最佳的综合性能。 方法 建立基于机理的SOFC输出电压系统模型,采用改进型的非线性自抗扰控制器(nonlinear active disturbance rejection control,NLADRC),通过控制输入燃气流量,使输出电压很好地跟踪参考值。考虑到传统的单通道控制器无法同时满足多个目标,但若采用双通道控制器则会导致系统复杂性、成本和故障风险增加,提出一种基于双延迟深度确定性策略梯度(twin delayed deep deterministic policy gradient,TD3)的改进型非线性自抗扰控制器,对非线性误差反馈控制律系数进行实时调节和优化。 结果 所设计控制器可在不违反燃料利用约束的情况下提高SOFC输出电压跟踪性能。 结论 所设计控制器具备适应性强、稳定性高和能克服不确定性等优点,为实际SOFC系统的输出电压控制器设计提供理论参考。

关键词: 固体氧化物燃料电池(SOFC), 双延迟深度确定性策略梯度(TD3), 非线性自抗扰控制器(NLADRC), 燃料利用率, 非线性误差反馈控制律, 输出电压跟踪, 不确定性

Abstract:

Objectives In 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. Methods A 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. Results The designed controller can improve SOFC output voltage tracking performance without violating fuel utilization constraints. Conclusions The 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.

Key words: 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

中图分类号: