Jixie chuandong (Feb 2019)
Feature Extraction and Wear Damage Degree Identification of Planetary Gear based on PSO-FC Optimization KPCA
Abstract
When the planetary gear transmission system fails， its signal transmission is coupled with each other， and the nonlinear characteristic is presented， which makes the fault type and damage degree of the planetary gear to be difficultly recognized. The optimization mathematical model of the kernel function scale parameter is constructed by means of Fisher criterion（FC） discriminate function in pattern recognition， and the improved particle swarm optimization method is applied to the optimization to fully improve the analysis performance of the kernel principal component analysis（KPCA） for nonlinear problem. It is applied to the identification and diagnosis of wear damage degree of planetary gear. The results of example analysis show that the intelligently optimized KPCA based on PSO-FC have improve the structure distribution of data in the feature space and achieved the good scale clustering effect in planetary gear wear damage degree recognition. It can effectively solve the identify problems of complex fuzzy damage boundary and damage degree in the mechanical transmission.
