An early fault diagnosis method based on the optimization of a variational modal decomposition and convolutional neural network for aeronautical hydraulic pipe clamps

Abstract

An intelligent fault diagnosis method based on optimal variational modal decomposition (VMD) and a convolutional neural network (CNN) is proposed to solve the problems of the early faults and typical fault characteristics of hydraulic pipe clamps in aero-engines. Firstly, a modified genetic algorithm is used to optimize the selection of variational modal decomposition parameters, and the optimized VMD is used to decompose the signal. Secondly, the IMF weight of CNN fusion feature information is used. Finally, the fault pattern recognition is carried out by CNN, so as to realize the intelligent fault diagnosis of an air hydraulic pipeline clamp. Experimental results show that this method can not only effectively clamp the health condition while the fault type is used to identify the accuracy, but can also realize the clamp early fault diagnosis. At the same time, through the clamp health status and test data analysis of typical fault status, we found that the typical fault characteristic frequency band provides a reference for the fault diagnosis of aerial hydraulic pipe circuit clamps.