Fault diagnosis method based on minimum entropy deconvolution and stacked sparse auto-encoder

Abstract

The invention discloses a fault diagnosis method based on minimum entropy deconvolution and a stacked sparse auto-encoder, which belongs to the technical field of fault diagnosis. The method comprisesthe following specific steps of: acquiring an original fault vibration signal of a to-be-diagnosed object, performing minimum entropy deconvolution processing on the original fault vibration signal,dividing the fault samples into a plurality of training samples and test samples, training the multi-fault classifier based on the stacked sparse auto-encoder by adopting a plurality of training samples, classifying the test samples by adopting the trained multi-fault classifier, and identifying the working state and the fault type of the fault object according to the classification result. The fault diagnosis method provided by the invention has high innovativeness, and compared with a traditional intelligent diagnosis algorithm, the fault diagnosis method provided by the invention has high recognition degree in a fault recognition process.

Description

Technical field: [0001] The invention belongs to the technical field of fault diagnosis, in particular to a fault diagnosis method based on minimum entropy deconvolution (MED) and stacked sparse autoencoder (SSAE). Background technique: [0002] Rolling bearings are one of the most widely used mechanical parts in the industrial field, and have important practical significance for social and economic development. Faults of rolling bearings often cause huge economic losses and even casualties. In order to improve the safety and reliability of rolling bearings and avoid accidental casualties and economic losses, many researchers have devoted themselves to the research of rolling bearing fault diagnosis. [0003] With the development of machine learning technology, many intelligent fault diagnosis methods, such as support vector machine (SVM) and artificial neural network (ANN), have been successfully applied in the field of rolling bearing fault diagnosis. Although these mach...

AI Technical Summary

Problems solved by technology

This method can overcome the problem that the sample contains high noise and is difficult to make accurate diagnosis in the actual situation; secondly, it can use the method of intelligent classification to judge the type and degree of fault information, avoiding the cumbersome and time-consuming calculation of manual classification.

Images