KAN-Koopman Based Rapid Detection Of Battery Thermal Anomalies With Diagnostics Guarantees

TL;DR

This paper introduces a novel KAN-Koopman method for rapid, model-free detection of battery thermal anomalies, providing real-time diagnostics with guarantees and improved detection speed over existing approaches.

Contribution

The paper presents a combined KAN and Koopman-based approach for fast, online detection of battery thermal anomalies with analytical diagnostic guarantees.

Findings

Significant reduction in detection time compared to Koopman-only methods

Effective real-time core temperature estimation without detailed models

Robust anomaly detection despite aging and limited data

Abstract

Early diagnosis of battery thermal anomalies is crucial to ensure safe and reliable battery operation by preventing catastrophic thermal failures. Battery diagnostics primarily rely on battery surface temperature measurements and/or estimation of core temperatures. However, aging-induced changes in the battery model and limited training data remain major challenges for model-based and machine-learning based battery state estimation and diagnostics. To address these issues, we propose a Kolomogorov-Arnold network (KAN) in conjunction with a Koopman-based detection algorithm that leverages the unique advantages of both methods. Firstly, the lightweight KAN provides a model-free estimation of the core temperature to ensure rapid detection of battery thermal anomalies. Secondly, the Koopman operator is learned in real time using the estimated core temperature from KAN and the measured surface temperature of the battery to provide the core and surface temperature prediction for diagnostic residual generation. This online learning approach overcomes the challenges of model changes. Furthermore, we derive analytical conditions to obtain diagnostic guarantees on our KAN-Koopman detection scheme. Our simulation results illustrate a significant reduction in detection time with the proposed algorithm compared to the baseline Koopman-only algorithm.