Mechanical fault diagnosis method for unsupervised deep learning network

Abstract

The invention discloses a mechanical fault diagnosis method for an unsupervised deep learning network. The method comprises the steps of: (1) mounting corresponding sensors near the part such as bearing of a mechanical device to collect mechanical vibration signals; (2) converting the collected vibration signals into a mixed domain fault feature data set, and dividing the data set into a testing and a training sample feature subset; (3) inputting the training sample feature subset into the constructed unsupervised deep learning network (UDLN) model for learning and training, wherein the UDLN model is composed of two improved sparse filtering (L12SF) unsupervised feature extraction layers and one weighted Euclidean distance similarity affine (WE) clustering layer; (4) inputting the test sample into a trained diagnosis model to realize full-range unsupervised feature learning and fault clustering; and (5) calculating the recognition rate of the test sample clustering division according to the membership degree thereof to realize fault identification and diagnosis. According to the mechanical fault diagnosis method for the unsupervised deep learning network, the invention is simple and feasible, and can perform adaptive unsupervised fault diagnosis on various faults of mechanical equipment.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis in industrial production, in particular to a mechanical fault diagnosis method of an unsupervised deep learning network. Background technique [0002] At present, industrial equipment is developing in the direction of large-scale, high-speed, and automation. As the most common component in the field of industrial equipment, mechanical equipment is widely used in important fields such as aviation, aerospace, transportation, and intelligent manufacturing. At present, bearings and other components are still the most important power transmission and supporting components of machinery. According to statistics, 30% of mechanical failures are caused by local damage or defects of bearings and other components. Therefore, it is necessary to carry out inspections on mechanical equipment and its key parts Effective condition monitoring and fault diagnosis. [0003] Mechanical equipment such as cran...

AI Technical Summary

Problems solved by technology

However, in the actual industrial site, the phenomenon of "mechanical big data" also brings about the difficulty of obtaining label information of mechanical equipment

This is because the running time of mechanical equipment is much longer than the time of failure, the sparsity of mechanical data is inevitable, and it is difficult to manually mark information

For this reason, the lack of label information of mechanical data and the sparsity of data information have brought a series of challenges to fault diagnosis

Images