Journal of Zhejiang University

Journal of Zhejiang University SCIENCE A

Accepted manuscript available online (unedited version)

A model for predicting the state of health of redox flow batteries based on an extreme learning machine model and swarm intelligence algorithm

Author(s): Lei ZHANG^1, ², Zebo HUANG³, Guo'an YANG², Fengming CHU^1, ²
Affiliation(s): ¹Beijing Key Laboratory of Heat Transfer and Energy Conversion, College of Mechanical and Energy Engineering, Beijing University of Technology, Beijing 100124, China ²College of Mechanical and Electrical Engineering, Beijing University of Chemical Technology, Beijing 100029, China ³School of Mechanical and Electrical Engineering, Guilin University of Electronic Technology, Guilin 541214, China
Corresponding email(s): Fengming CHU, chufm@bjut.edu.cn
Key Words: Group intelligence algorithm; Health feature subset; Spearman coefficient; Robustness; Interaction measure algorithm.

Share this article to： More <<< Previous Paper \|Next Paper >>>

Lei ZHANG^1,², Zebo HUANG³, Guo'an YANG², Fengming CHU^1,². A model for predicting the state of health of redox flow batteries based on an extreme learning machine model and swarm intelligence algorithm[J]. Journal of Zhejiang University Science A,in press.Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/jzus.A2500461

@article{title="A model for predicting the state of health of redox flow batteries based on an extreme learning machine model and swarm intelligence algorithm",
author="Lei ZHANG^1,², Zebo HUANG³, Guo'an YANG², Fengming CHU^1,²",
journal="Journal of Zhejiang University Science A",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/jzus.A2500461"
}

%0 Journal Article
%T A model for predicting the state of health of redox flow batteries based on an extreme learning machine model and swarm intelligence algorithm
%A Lei ZHANG^1
%A²
%A Zebo HUANG³
%A Guo'an YANG²
%A Fengming CHU^1
%A²
%J Journal of Zhejiang University SCIENCE A
%P
%@ 1673-565X
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/jzus.A2500461"

TY - JOUR
T1 - A model for predicting the state of health of redox flow batteries based on an extreme learning machine model and swarm intelligence algorithm
A1 - Lei ZHANG^{1
A1 -}²
A1 - Zebo HUANG³
A1 - Guo'an YANG²
A1 - Fengming CHU^{1
A1 -}²
J0 - Journal of Zhejiang University Science A
SP -
EP -
%@ 1673-565X
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/jzus.A2500461"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: Accurate assessment of the state of health (SOH) is essential for the safe, economical, and reliable operation of all-vanadium redox flow batteries (VRFBs). However, systems for monitoring their SOH have rarely been studied. In this study, capacity retention rate was used to characterize the SOH, and a series of charge/discharge cycling tests were conducted. Based on a series of operational parameters and grey relation analysis (GRA), the best health feature subset to characterize the SOH was determined. Extreme learning machine (ELM) combined with swarm intelligence algorithms were used to predict SOH, based on which the effects of different swarm intelligence algorithms and different activation functions on estimations of SOH performance were investigated. Results showed that all the models with poor prediction results had a sigmoid activation function, indicating that such functions are not capable of predicting SOH. Grey relational analysis based on LASSO (LGRA) Algorithm-ELM was more suitable for SOH prediction than the interaction measurement algorithm based on Spearman's correlation coefficient (SCIM) Algorithm-ELM model. It can not only estimate accurately but also predict recession characteristics. The most suitable swarm intelligence algorithm was particle swarm optimization (PSO), and the best activation function was linear, in which the maximum error was lower than 0.2%.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Full Text: <268>

CLC number:

On-line Access: 2026-03-09

Received: 2025-09-19

Revision Accepted: 2026-01-13

Crosschecked: 0000-00-00

Cited: 0

Clicked: 443

Citations: Bibtex RefMan EndNote GB/T7714

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

- Go to