Charging pile fault diagnosis method, computer readable medium and equipment

• Main Authors: FENG LONGJI, WANG ZHENYU, FANG LEI, CHU CHENGBO, DAI BAOQIN, CHEN XUEWEI, XING XIAOFAN, XU JUN, LIN HE, HE YINGHONG, ZHAO YI, LI NAN, WANG ZIHU, WU FANGZHU, ZHU ZE
• Format: Patent
• Language: Chinese; English
• Published: 06.02.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; ELECTRIC EQUIPMENT OR PROPULSION OF ELECTRICALLY-PROPELLEDVEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES, IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; PERFORMING OPERATIONS; PHYSICS; TRANSPORTING; VEHICLES IN GENERAL

The invention provides a charging pile fault diagnosis method, a computer readable medium and equipment, the method is a charging pile fault diagnosis method based on adaptive feature mode decomposition and a kernel extreme learning machine (AFMD-KELM), and the method comprises the following steps: (1) data acquisition and preparation; (2) signal self-adaptive decomposition; (3) fault feature screening; (4) building and training a charging pile fault diagnosis model; and (5) fault diagnosis of the charging pile. According to the method, the collected charging pile sensor signal can be adaptively decomposed into a plurality of feature components, important features are selected according to importance description indexes, effective information in the signal is extracted, and noise interference is reduced. And the extracted features are classified by using a tuna swarm optimized kernel extreme learning machine, so that the accuracy of charging pile fault diagnosis is further improved. 本申请提供了一种充电桩故障诊断方法、计算机可读介质及