Fault Diagnosis Method for Lithium-Ion Battery Packs in Real-World Electric Vehicles Based on K-Means and the Fréchet Algorithm

• DOI: 10.1021/acsomega.2c04991
• Publication Date: 2022-10-25T04:51:07Z
• Authors: Minghu Wu; Wanyin Du; Fan Zhang; Nan Zhao; Juan Wang; Lujun Wang; Wei Huang
• Keywords: Robustness; Smoothing

Battery failure has traditionally been a major concern for electric vehicle (EV) safety, and early fault diagnosis will reduce many EV safety accidents. However, the short-circuit signal is generally very weak, so it still challenge to achieve timely warning of battery failure. In this paper, an initial microfault method proposed data vehicles in actual operation. First, robust locally weighted regression smoothing that can effectively remove noisy retain characteristics. Second, ordinary-least-squares-based voltage potential feature extraction proposed, which capture small features cells warning. Third, reference cell selection based on K-means clustering false alarms caused by inconsistency each cell. Fourth, Fréchet algorithm introduced into field pack combined with thresholds localization accomplish minor faults. Finally, validated three running verify effectiveness, reliability, robustness method.