Data-driven spiking neural networks for intelligent fault detection in vehicle lithium-ion battery systems

Abstract

Electric vehicles (EVs) powered by high-energy batteries are anticipated to be a primary avenue for achieving energy decarbonization in future societies. However, the high energy density of lithium batteries poses significant safety risks under complex conditions and sudden environmental changes. Thus, safety and fault issues of high-energy batteries during vehicle operation have gained much attention. This study proposes an intelligent fault diagnosis algorithm based on spiking neural networks (SNNs) using a data-driven approach. Time series data are stacked and fed into the SNN for learning, capturing temporal characteristics and forming a stable kernel representation. The predicted output is compared with the actual output to generate a residual signal for fault diagnosis. The algorithm is validated on a battery management experimental platform with injected internal and external short circuit faults. Results show the algorithm effectively and swiftly detects abnormal signals and has some transferability.