引用本文:贾志桓,陈林,邵奥利,王宇鹏,高金武.基于ENSACO-LSTM的PEMFCs退化预测[J].控制理论与应用,2025,42(8):1578~1586.[点击复制]
JIA Zhi-huan,CHEN Lin,SHAO Ao-li,WANG Yu-peng,GAO Jin-wu.PEMFCsdegradation prediction based on ENSACO-LSTM[J].Control Theory & Applications,2025,42(8):1578~1586.[点击复制]
基于ENSACO-LSTM的PEMFCs退化预测
PEMFCsdegradation prediction based on ENSACO-LSTM
摘要点击 4053  全文点击 169  投稿时间：2024-07-30  修订日期：2025-07-11
查看全文  查看/发表评论  下载PDF阅读器   HTML
DOI编号  10.7641/CTA.2025.40411
  2025,42(8):1578-1586
中文关键词  质子交换膜燃料电池  群体优化算法  性能老化预测  强化搜索蚁群优化算法  数据驱动方法  深度学习
英文关键词  proton exchange membrane fuel cells  swarm optimization algorithm  performance aging prediction  en hanced search ant colony algorithm  data-driven approach  deep learning
基金项目  
作者单位E-mail
贾志桓 吉林大学汽车仿真与控制国家重点实验室 1302432279@qq.com 
陈林 吉林大学汽车仿真与控制国家重点实验室  
邵奥利 吉林大学汽车仿真与控制国家重点实验室  
王宇鹏 一汽集团研发总院动力总成研究所  
高金武* 吉林大学汽车仿真与控制国家重点实验室 gaojw@jlu.edu.cn 
中文摘要
      本文提出了一种基于基于强化搜索蚁群优化的长短期记忆神经网络(ENSACO-LSTM)的数据驱动算法,用于 预测质子交换膜燃料电池(PEMFCs)的功率退化趋势.首先,使用沙普利加和解释(SHAP)值方法筛选贡献度高的外特性 参数作为数据驱动方法的输入.接着,提出了一种新型群体优化算法–强化搜索蚁群优化算法(ENSACO).该算法基于强 化因子改进了蚁群优化(ACO)算法,以避免早熟并加快收敛速度.设置了对比实验,比较粒子群优化算法(PSO)、ACO和 ENSACO的性能差异.最后,提出了一种基于ENSACO-LSTM的数据驱动方法来预测PEMFC的功率退化趋势,并使用 实际老化数据对该方法进行了验证.结果表明,在有限的迭代次数内,ENSACO的优化能力显著优于PSO和ACO.此外, ENSACO-LSTM方法的预测精度也大幅提升,相比LSTM,PSO-LSTM和ACO-LSTM平均提升约50.58%.
英文摘要
      In this paper, a fusion model based on a long short-term memory (LSTM) neural network and enhanced search ant colony optimization (ENSACO) is proposed to predict the power degradation trend of proton exchange membrane fuel cells (PEMFC). Firstly, the Shapley additive explanations (SHAP) value method is used to select external characteristic parameters with high contributions as inputs for the data-driven approach. Next, a novel swarm optimization algorithm, the enhanced search ant colony optimization, is proposed. This algorithm improves the ant colony optimization (ACO) algo rithm based on a reinforcement factor to avoid premature convergence and accelerate the convergence speed. Comparative experiments are set up to compare the performance differences between particle swarm optimization (PSO), ACO, and ENSACO. Finally, a data-driven method based on ENSACO-LSTM is proposed to predict the power degradation trend of PEMFCs. Andactual aging data is used to validate the method. The results show that, within a limited number of iterations, the optimization capability of ENSACO is significantly stronger than that of PSO and ACO. Additionally, the prediction accuracy of the ENSACO-LSTMmethodisgreatly improved, with an average increase of approximately 50.58% compared to LSTM, PSO-LSTM, and ACO-LSTM.