文档介绍:工业仪表与自动化装置 年第 期
·86· ract
: In order to reduce the difficulty of troubleshooting IGBT open circuit faults of the three -
phase inverter bridge in the auxiliary inverter (SIV) of rail transit trains and to ensure the safe operation
of trains, a variety of common IGBT faults are diagnosed. A fault diagnosis method that combines an im⁃
proved fully adaptive noise ensemble empirical mode decomposition method ( ICEEMDAN) and an im⁃
proved bat algorithm (IBA) to optimize the least square support vector machine (LSSVM) model param⁃
eters is proposed to improve the feature extraction effect and diagnostic accuracy. Through MATLAB sim⁃
ulation experiments, it can be seen that compared to Bat Algorithm (BA) optimizing LSSVM and Particle
Swarm Algorithm ( PSO) optimizing LSSVM, IBA - LSSVM model has great advantages in diagnosis
speed and accuracy.
Keywords
: auxiliary inverter;fault diagnosis;LSSVM;improved bat algorithm
DOI:.cn61-1121/
出[2] 文献 提出了基于 和 实现
0 引言 。 [3] MEEMD GRNN
对故障信号提取和诊断