Work

A Kolmogorov-Arnold neural networks approach to state of charge estimation and confidence assessment for Li-ion batteries

Year: 2025

Type: article

Abstract: This study aims to thoroughly examine the potential of the Kolmogorov-Arnold Network (KAN) and its application to improving energy management efﬁciency, particularly in lithium-ion batteries. The study employs a novel method that utilizes one-dimensional adaptive activation functions parameterized by splines, in contrast to traditional neural networks, where activation functions are ﬁxed. Traditional methods for activation function selection are based on empirical approaches and do not guarantee accurate approximation, potentially leading to suboptimal results. This approach enables the KAN to ﬂexibly adapt to complex data structures, ensuring precise state-of-charge estimation. To objectively evaluate the algorithm's effectiveness, experiments were conducted on real datasets, focusing on analyzing the accuracy of state-of-charge estimation at conﬁdence intervals of 95%, 90%, and 85%. The test results for various charge-discharge cycles demonstrated that the proposed method achieves high accuracy and maintains stability throughout the operation. The proposed method reduces the maximum error by at least 4.26% and signiﬁcantly improves key performance metrics such as Mean Absolute Error, Root Mean Square Error. Thus, the obtained results conﬁrm the efﬁciency and innovative nature of the KAN in energy management. This method holds great potential for energy management and can be effectively implemented in areas requiring precise time-series forecasting, including smart home systems, electric vehicles, and industrial devices. Future research will optimize the network architecture and expand its practical applications. Signiﬁ-cantly, this method can be ﬂexibly adapted to different types of batteries and energy systems, broadening its applicability in real-world conditions.

Source: iPolytech Journal

DOI: 10.21285/1814-3520-2025-1-66-81

Authors: Dao Minh Hien, Vo Van Truong, Liu Fang, D. N. Sidorov

Institutions: Irkutsk National Research Technical University, Central South University, Harbin Institute of Technology, Melentiev Energy Systems Institute, Siberian Branch of the Russian Academy of Sciences

Language: English

Topic: Advanced Battery Technologies Research

Subfield: Automotive Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Affordable and clean energy

Open Access status: diamond

OpenAlex ID: W4408909312

FWCI:

Cites: 16

Cited by:

Related to: 10