A Simple and Effective KAN-Based Architecture for Accurate Battery RUL Prediction

Accurately estimating a lithium-ion battery’s Remaining Useful Life (RUL) is crucial for ensuring the safety and reliability of battery management systems. However, the performance of emerging architectures, such as Kolmogorov-Arnold Networks (KANs), is often hindered by the significant n...

Full description

Saved in:
Bibliographic Details
Main Authors: Guangzai Ye, Li Feng, Jianlan Guo, Yuqiang Chen, Shufei Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11084810/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713169309630464
author Guangzai Ye
Li Feng
Jianlan Guo
Yuqiang Chen
Shufei Li
author_facet Guangzai Ye
Li Feng
Jianlan Guo
Yuqiang Chen
Shufei Li
author_sort Guangzai Ye
collection DOAJ
description Accurately estimating a lithium-ion battery’s Remaining Useful Life (RUL) is crucial for ensuring the safety and reliability of battery management systems. However, the performance of emerging architectures, such as Kolmogorov-Arnold Networks (KANs), is often hindered by the significant noise and complex temporal dynamics present in real-world battery data. To overcome this, we propose a novel Knowledge Distillation-Based Denoising and Channel-Independent Kolmogorov-Arnold Networks (DCI-KANs) architecture, specifically designed to enhance robustness and accuracy for multivariate time series RUL prediction. Our approach integrates a VMD-based denoising mechanism, compressed into a more compact KAN model via knowledge distillation, to mitigate noise efficiently. It also incorporates a channel-independent KANs structure with a regularized weighted loss function to handle variable-specific degradation patterns. Experimental results on two public battery datasets show that DCI-KANs substantially outperform existing state-of-the-art methods in RUL prediction accuracy, achieving a 43 % and 22 % reduction in Absolute Relative Error (ARE) on the NASA and CALCE datasets, respectively. This work presents a simple yet effective framework that makes KANs a practical, robust, and computationally efficient solution for the challenging task of real-world battery RUL prediction.
format Article
id doaj-art-ab6fd4aa2c9d41abb48371fba70fb216
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-ab6fd4aa2c9d41abb48371fba70fb2162025-08-20T03:14:02ZengIEEEIEEE Access2169-35362025-01-011312870012871510.1109/ACCESS.2025.359048011084810A Simple and Effective KAN-Based Architecture for Accurate Battery RUL PredictionGuangzai Ye0https://orcid.org/0000-0002-0075-9602Li Feng1https://orcid.org/0000-0001-6172-8650Jianlan Guo2Yuqiang Chen3Shufei Li4School of Computer Science and Engineering, Macau University of Science and Technology, Macau, SAR, ChinaSchool of Computer Science and Engineering, Macau University of Science and Technology, Macau, SAR, ChinaDongguan Polytechnic, Dongguan, ChinaDongguan Polytechnic, Dongguan, ChinaDongguan Polytechnic, Dongguan, ChinaAccurately estimating a lithium-ion battery’s Remaining Useful Life (RUL) is crucial for ensuring the safety and reliability of battery management systems. However, the performance of emerging architectures, such as Kolmogorov-Arnold Networks (KANs), is often hindered by the significant noise and complex temporal dynamics present in real-world battery data. To overcome this, we propose a novel Knowledge Distillation-Based Denoising and Channel-Independent Kolmogorov-Arnold Networks (DCI-KANs) architecture, specifically designed to enhance robustness and accuracy for multivariate time series RUL prediction. Our approach integrates a VMD-based denoising mechanism, compressed into a more compact KAN model via knowledge distillation, to mitigate noise efficiently. It also incorporates a channel-independent KANs structure with a regularized weighted loss function to handle variable-specific degradation patterns. Experimental results on two public battery datasets show that DCI-KANs substantially outperform existing state-of-the-art methods in RUL prediction accuracy, achieving a 43 % and 22 % reduction in Absolute Relative Error (ARE) on the NASA and CALCE datasets, respectively. This work presents a simple yet effective framework that makes KANs a practical, robust, and computationally efficient solution for the challenging task of real-world battery RUL prediction.https://ieeexplore.ieee.org/document/11084810/Remaining useful life predictionmultivariate time seriesKolmogorov-Arnold networkschannel independentvariational mode decompositionlithium-ion batteries
spellingShingle Guangzai Ye
Li Feng
Jianlan Guo
Yuqiang Chen
Shufei Li
A Simple and Effective KAN-Based Architecture for Accurate Battery RUL Prediction
IEEE Access
Remaining useful life prediction
multivariate time series
Kolmogorov-Arnold networks
channel independent
variational mode decomposition
lithium-ion batteries
title A Simple and Effective KAN-Based Architecture for Accurate Battery RUL Prediction
title_full A Simple and Effective KAN-Based Architecture for Accurate Battery RUL Prediction
title_fullStr A Simple and Effective KAN-Based Architecture for Accurate Battery RUL Prediction
title_full_unstemmed A Simple and Effective KAN-Based Architecture for Accurate Battery RUL Prediction
title_short A Simple and Effective KAN-Based Architecture for Accurate Battery RUL Prediction
title_sort simple and effective kan based architecture for accurate battery rul prediction
topic Remaining useful life prediction
multivariate time series
Kolmogorov-Arnold networks
channel independent
variational mode decomposition
lithium-ion batteries
url https://ieeexplore.ieee.org/document/11084810/
work_keys_str_mv AT guangzaiye asimpleandeffectivekanbasedarchitectureforaccuratebatteryrulprediction
AT lifeng asimpleandeffectivekanbasedarchitectureforaccuratebatteryrulprediction
AT jianlanguo asimpleandeffectivekanbasedarchitectureforaccuratebatteryrulprediction
AT yuqiangchen asimpleandeffectivekanbasedarchitectureforaccuratebatteryrulprediction
AT shufeili asimpleandeffectivekanbasedarchitectureforaccuratebatteryrulprediction
AT guangzaiye simpleandeffectivekanbasedarchitectureforaccuratebatteryrulprediction
AT lifeng simpleandeffectivekanbasedarchitectureforaccuratebatteryrulprediction
AT jianlanguo simpleandeffectivekanbasedarchitectureforaccuratebatteryrulprediction
AT yuqiangchen simpleandeffectivekanbasedarchitectureforaccuratebatteryrulprediction
AT shufeili simpleandeffectivekanbasedarchitectureforaccuratebatteryrulprediction