Rotary machine fault diagnosis method based on deep Laplace self-coding

Abstract

The invention discloses a rotary machine fault diagnosis method based on deep Laplace self-coding, which comprises the following steps: 1. collecting vibration signals at key parts of a rotary machine; 2. converting the collected vibration signals into frequency spectrum signals, and dividing the frequency spectrum signals into a test sample subset and a training sample subset; 3. inputting training samples into a Laplace self-coding model for pre-training, further adjusting the pre-trained Laplace self-coding model by using a supervised learning algorithm, and obtaining parameters of the Laplace self-coding model according to a loss function in the Laplace self-coding model; 4. inputting test samples into a trained deep Laplace self-coding model to obtain multilayer sensitive fault characteristics; and 5. inputting the fault characteristics obtained in the step 4 into a classifier to perform fault classification and diagnosis, so as to realize fault diagnosis of rotary mechanical equipment. Through adoption of the rotary machine fault diagnosis method of the invention, the fault diagnosis precision of the unbalanced data is improved, and the classification and diagnosis of the unbalanced data are effectively realized.

Description

Technical field [0001] The invention relates to the technical field of fault diagnosis in industrial production, and is a data-driven fault diagnosis method for rotating machinery. Background technique [0002] As an irreplaceable industrial device in modern industrial systems, rotating machinery occupies an extremely important position in industrial production and intelligent manufacturing. Therefore, real-time status monitoring and fault diagnosis of industrial equipment such as rotating machinery can not only ensure the normal operation of the mechanical equipment, but also detect and repair the mechanical equipment in time, which can avoid unnecessary economic losses and personal injuries. [0003] At this stage, most of the fault diagnosis methods of rotating machinery are to determine the operating state of the equipment through the detection and analysis of various state parameters, so as to determine the location of the fault and its degradation degree. Among them, the fau...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above problems, the present invention proposes an inventive method for fault diagnosis of rotating machinery based on deep Laplacian self-encoding, which overcomes the current situation that the existing fault diagnosis technology is difficult to deal with the diagnosis of unbalanced data of rotating machinery faults, and improves the unbalance Data fault diagnosis accuracy, effectively realize the classification and diagnosis of unbalanced data

Images