Residual Life Prediction of Proton Exchange Membrane Fuel Cell Based on Improved ESN

Aiming at the problem that the current residual effective life prediction (RUL) technique for proton exchange membrane fuel cells (PEMFCs) has poor prediction effect in the medium and long term, a residual life prediction method based on the Improved Gray Wolf Optimization algorithm (IGWO) and Echo...

Full description

Saved in:
Bibliographic Details
Main Authors: Tiejiang YUAN, Rongsheng LI, Jiandong KANG, Huaguang YAN
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2025-05-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202402054
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722657150337024
author Tiejiang YUAN
Rongsheng LI
Jiandong KANG
Huaguang YAN
author_facet Tiejiang YUAN
Rongsheng LI
Jiandong KANG
Huaguang YAN
author_sort Tiejiang YUAN
collection DOAJ
description Aiming at the problem that the current residual effective life prediction (RUL) technique for proton exchange membrane fuel cells (PEMFCs) has poor prediction effect in the medium and long term, a residual life prediction method based on the Improved Gray Wolf Optimization algorithm (IGWO) and Echo State Network (ESN) is proposed, in which the voltage of the electric stack is firstly selected as a health indicator, and the PEMFC dataset is processed by using convolutional smoothing filtering method to carry out data Smoothing and normalization are used to effectively reduce the interference of outliers on the subsequent model training. Then the reserve pool parameters of the ESN are optimized using the local and global optimization search capability of IGWO, and the IGWO-ESN network model is constructed, and the processed dataset is used for the training of the remaining life prediction model of the PEMFC, and finally it is compared with the traditional ESN for verification. The results show that the improved ESN model predicts the root mean square error and average absolute percentage error of 0.0342 and 0.9315%, respectively, and the prediction accuracy is significantly improved compared with the ordinary ESN model, and the prediction accuracy of the medium- and long-term RUL is also higher.
format Article
id doaj-art-dd822aa6697b4b68bb0be4451b3dd44b
institution DOAJ
issn 1004-9649
language zho
publishDate 2025-05-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-dd822aa6697b4b68bb0be4451b3dd44b2025-08-20T03:11:17ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492025-05-0158510210910.11930/j.issn.1004-9649.202402054zgdl-58-03-yuantiejiangResidual Life Prediction of Proton Exchange Membrane Fuel Cell Based on Improved ESNTiejiang YUAN0Rongsheng LI1Jiandong KANG2Huaguang YAN3School of Electrical Engineering, Dalian University of Technology, Dalian 116081, ChinaSchool of Electrical Engineering, Dalian University of Technology, Dalian 116081, ChinaChina Electric Power Research Institute, Beijing 100192, ChinaChina Electric Power Research Institute, Beijing 100192, ChinaAiming at the problem that the current residual effective life prediction (RUL) technique for proton exchange membrane fuel cells (PEMFCs) has poor prediction effect in the medium and long term, a residual life prediction method based on the Improved Gray Wolf Optimization algorithm (IGWO) and Echo State Network (ESN) is proposed, in which the voltage of the electric stack is firstly selected as a health indicator, and the PEMFC dataset is processed by using convolutional smoothing filtering method to carry out data Smoothing and normalization are used to effectively reduce the interference of outliers on the subsequent model training. Then the reserve pool parameters of the ESN are optimized using the local and global optimization search capability of IGWO, and the IGWO-ESN network model is constructed, and the processed dataset is used for the training of the remaining life prediction model of the PEMFC, and finally it is compared with the traditional ESN for verification. The results show that the improved ESN model predicts the root mean square error and average absolute percentage error of 0.0342 and 0.9315%, respectively, and the prediction accuracy is significantly improved compared with the ordinary ESN model, and the prediction accuracy of the medium- and long-term RUL is also higher.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202402054proton exchange membrane fuel cellecho state networkgray wolf optimization algorithmremaining life prediction
spellingShingle Tiejiang YUAN
Rongsheng LI
Jiandong KANG
Huaguang YAN
Residual Life Prediction of Proton Exchange Membrane Fuel Cell Based on Improved ESN
Zhongguo dianli
proton exchange membrane fuel cell
echo state network
gray wolf optimization algorithm
remaining life prediction
title Residual Life Prediction of Proton Exchange Membrane Fuel Cell Based on Improved ESN
title_full Residual Life Prediction of Proton Exchange Membrane Fuel Cell Based on Improved ESN
title_fullStr Residual Life Prediction of Proton Exchange Membrane Fuel Cell Based on Improved ESN
title_full_unstemmed Residual Life Prediction of Proton Exchange Membrane Fuel Cell Based on Improved ESN
title_short Residual Life Prediction of Proton Exchange Membrane Fuel Cell Based on Improved ESN
title_sort residual life prediction of proton exchange membrane fuel cell based on improved esn
topic proton exchange membrane fuel cell
echo state network
gray wolf optimization algorithm
remaining life prediction
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202402054
work_keys_str_mv AT tiejiangyuan residuallifepredictionofprotonexchangemembranefuelcellbasedonimprovedesn
AT rongshengli residuallifepredictionofprotonexchangemembranefuelcellbasedonimprovedesn
AT jiandongkang residuallifepredictionofprotonexchangemembranefuelcellbasedonimprovedesn
AT huaguangyan residuallifepredictionofprotonexchangemembranefuelcellbasedonimprovedesn