欢迎访问《汽车安全与节能学报》，
汽车安全与节能学报

汽车安全与节能学报 ›› 2020, Vol. 11 ›› Issue (4): 553-559.DOI: 10.3969/j.issn.1674-8484.2020.04.016

• 汽车节能与环保 • 上一篇    

固体氧化物燃料电池系统的复合优化在线控制策略

罗浩文(), 吴小娟, 张铭涛   

  1. 电子科技大学 自动化工程学院,成都 611731,中国
  • 收稿日期:2020-06-23 出版日期:2020-12-30 发布日期:2021-01-04
  • 作者简介:罗浩文(1997–),男(汉),四川,硕士研究生。E-mail:dancells@foxmail.com。
  • 基金资助:
    汽车安全与节能国家重点实验室(KF2022);四川省科学技术厅(2020YJ0109);中央高校基本业务费(ZYGX2019J060)

Compound optimal online control strategy of a solid oxide fuel cell system

LUO Haowen(), WU Xiaojuan, ZHANG Mingtao   

  1. School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
  • Received:2020-06-23 Online:2020-12-30 Published:2021-01-04

RichHTML

21

PDF

111

摘要：

为高效安全运行固体氧化物燃料电池(SOFC),提出了一种考虑温度梯度瞬态响应的在线优化的2层复合控制策略。在优化层,用神经网络预测功率变化,采用粒子群优化(PSO)算法获取了不同功率下的系统最优操作曲线。在控制层,考虑负载的瞬态波动,以复合控制器跟踪系统最优工作点。结果表明：长短期记忆(LSTM)神经网络比非线性自回归神经网络(NARNN)对功率的预测均方根误差减少了20.2 W,预测精度更高;该复合控制器和传统的比例-积分-微分(PID)控制器对电堆温度、燃料利用率和空气过氧比的控制效果都较好;在负载功率快速变化时,复合控制器的温度梯度瞬态响应更小,且在阈值之下,避免系统出现过高的温度梯度。

关键词: 固体氧化物燃料电池(SOFC), 在线优化控制, 瞬态响应, 复合控制器, 非线性自回归神经网络(NARNN), 长短期记忆(LSTM)神经网络

Abstract:

An optimized control strategy was proposed for Solid Oxide Fuel Cells (SOFC) with two-layer compound considering temperature-gradient transient-response to online operate SOFC efficiently and safely. In the optimization layer, a neural network was used to predict the power change with a particle swarm optimization (PSO) algorithm being used to obtain the optimal operation curve of the system under different powers. In the control layer, considering the transient fluctuation of load, a compound controller was used to track the optimal operating point of the system. The results show that the root mean square error of the short-term and long-term memory (LSTM) neural network is reduced by 20.2 W, and the prediction accuracy is higher than that of the nonlinear autoregressive neural network (NARNN); The compound controller and the traditional proportion-integration-differentiation (PID) controller have good control effects on the stack temperature, the fuel utilization rate, and the air over-oxygen ratio; When the load power changes rapidly, the temperature gradient transient response of the compound controller is smaller, and it is below the threshold to avoid excessive temperature gradients in the system.

Key words: solid oxide fuel cell (SOFC), online optimal control, transient response, compound controller, nonlinear auto regressive neural network (NARNN), long short-term memory (LSTM) neural network

中图分类号: