首页|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

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

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

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
[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.
[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.

solid 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

管超骏、雷正玲、霍海波、王芳、姚国全、刘涛

展开 >

上海海洋大学工程学院,上海市 浦东新区 201306

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

上海海事大学交通运输学院,上海市 浦东新区 201306

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

2024

10.12096/j.2096-4528.pgt.24017

发电技术
华电电力科学研究院

发电技术

CSTPCD
影响因子：0.388
ISSN：2096-4528
年,卷(期)：2024.45(6)