Robust fault detection in electrochemical energy storage systems under label noise: applications to lithium-ion batteries and transformer windings

Reliable fault detection is essential for ensuring the safe and efficient operation of electrochemical energy storage systems, including lithium-ion batteries and transformer. However, the performance of machine learning-based fault diagnosis models is often degraded in practice due to label noise i...

Full description

Saved in:
Bibliographic Details
Main Authors: Tao He, Wei Liu, Xin Wu, Yu Wei
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Energy Research
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fenrg.2025.1647197/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849228882910117888
author Tao He
Wei Liu
Xin Wu
Yu Wei
author_facet Tao He
Wei Liu
Xin Wu
Yu Wei
author_sort Tao He
collection DOAJ
description Reliable fault detection is essential for ensuring the safe and efficient operation of electrochemical energy storage systems, including lithium-ion batteries and transformer. However, the performance of machine learning-based fault diagnosis models is often degraded in practice due to label noise in training data, caused by sensor inaccuracies, ambiguous fault transitions, and imperfect labeling processes. This paper proposes a lightweight and effective kernel-based data rectification framework to improve the robustness of fault detection under noisy label conditions. The method identifies and discards low-density data points that are statistically more likely to be mislabeled, using kernel density estimation and a tunable data discarding strategy. The approach is computationally efficient, classifier-agnostic, and easily applicable to existing fault diagnosis pipelines. We evaluate the proposed method on two datasets: simulated lithium-ion battery voltage data under various fault scenarios, and transformer winding oscillation wave data under multiple winding fault conditions. The results demonstrate that the rectification framework significantly improves classification accuracy across both Support Vector Machine (SVM) and Extreme Learning Machine (ELM) classifiers. Furthermore, the choice of discarding ratio is shown to be critical, with optimal performance achieved when the ratio is tuned close to the underlying noise level. These results highlight the potential of the proposed method to enhance the reliability of fault diagnosis in electrochemical energy storage systems. Future work will explore adaptive strategies to automatically optimize the rectification strength without requiring prior knowledge of the noise rate, and extend the framework to multi-sensor and multi-modal monitoring scenarios.
format Article
id doaj-art-8ea161e58fb64b7c9fb28cf4cf0bde94
institution Kabale University
issn 2296-598X
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Energy Research
spelling doaj-art-8ea161e58fb64b7c9fb28cf4cf0bde942025-08-22T14:52:31ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2025-08-011310.3389/fenrg.2025.16471971647197Robust fault detection in electrochemical energy storage systems under label noise: applications to lithium-ion batteries and transformer windingsTao He0Wei Liu1Xin Wu2Yu Wei3State Grid Anhui Electric Power Co., Ltd., Ma’anshan Power Supply Company, Anhui, ChinaState Grid Anhui Electric Power Research Institute, Anhui, ChinaState Grid Anhui Electric Power Co., Ltd., Ma’anshan Power Supply Company, Anhui, ChinaState Grid Anhui Electric Power Co., Ltd., Ma’anshan Power Supply Company, Anhui, ChinaReliable fault detection is essential for ensuring the safe and efficient operation of electrochemical energy storage systems, including lithium-ion batteries and transformer. However, the performance of machine learning-based fault diagnosis models is often degraded in practice due to label noise in training data, caused by sensor inaccuracies, ambiguous fault transitions, and imperfect labeling processes. This paper proposes a lightweight and effective kernel-based data rectification framework to improve the robustness of fault detection under noisy label conditions. The method identifies and discards low-density data points that are statistically more likely to be mislabeled, using kernel density estimation and a tunable data discarding strategy. The approach is computationally efficient, classifier-agnostic, and easily applicable to existing fault diagnosis pipelines. We evaluate the proposed method on two datasets: simulated lithium-ion battery voltage data under various fault scenarios, and transformer winding oscillation wave data under multiple winding fault conditions. The results demonstrate that the rectification framework significantly improves classification accuracy across both Support Vector Machine (SVM) and Extreme Learning Machine (ELM) classifiers. Furthermore, the choice of discarding ratio is shown to be critical, with optimal performance achieved when the ratio is tuned close to the underlying noise level. These results highlight the potential of the proposed method to enhance the reliability of fault diagnosis in electrochemical energy storage systems. Future work will explore adaptive strategies to automatically optimize the rectification strength without requiring prior knowledge of the noise rate, and extend the framework to multi-sensor and multi-modal monitoring scenarios.https://www.frontiersin.org/articles/10.3389/fenrg.2025.1647197/fullfault diagnosisrobust classificationkernel density estimationlabel noiselithium-ion batteriestransformer windings
spellingShingle Tao He
Wei Liu
Xin Wu
Yu Wei
Robust fault detection in electrochemical energy storage systems under label noise: applications to lithium-ion batteries and transformer windings
Frontiers in Energy Research
fault diagnosis
robust classification
kernel density estimation
label noise
lithium-ion batteries
transformer windings
title Robust fault detection in electrochemical energy storage systems under label noise: applications to lithium-ion batteries and transformer windings
title_full Robust fault detection in electrochemical energy storage systems under label noise: applications to lithium-ion batteries and transformer windings
title_fullStr Robust fault detection in electrochemical energy storage systems under label noise: applications to lithium-ion batteries and transformer windings
title_full_unstemmed Robust fault detection in electrochemical energy storage systems under label noise: applications to lithium-ion batteries and transformer windings
title_short Robust fault detection in electrochemical energy storage systems under label noise: applications to lithium-ion batteries and transformer windings
title_sort robust fault detection in electrochemical energy storage systems under label noise applications to lithium ion batteries and transformer windings
topic fault diagnosis
robust classification
kernel density estimation
label noise
lithium-ion batteries
transformer windings
url https://www.frontiersin.org/articles/10.3389/fenrg.2025.1647197/full
work_keys_str_mv AT taohe robustfaultdetectioninelectrochemicalenergystoragesystemsunderlabelnoiseapplicationstolithiumionbatteriesandtransformerwindings
AT weiliu robustfaultdetectioninelectrochemicalenergystoragesystemsunderlabelnoiseapplicationstolithiumionbatteriesandtransformerwindings
AT xinwu robustfaultdetectioninelectrochemicalenergystoragesystemsunderlabelnoiseapplicationstolithiumionbatteriesandtransformerwindings
AT yuwei robustfaultdetectioninelectrochemicalenergystoragesystemsunderlabelnoiseapplicationstolithiumionbatteriesandtransformerwindings