Stacked SAE (Sparse Autoencoder) deep neural network-based bearing fault diagnosis method

Abstract

The invention relates to a stacked SAE (Sparse Autoencoder) deep neural network-based bearing fault diagnosis method. The first layer of a network is applied to the qualitative judgment of a bearing fault, that is, the first layer of the network is applied to the fault type judgment of the bearing fault; and the second layer of the network is applied to the quantitative judgment of the bearing fault, that is, the second layer of the network is applied to the severity judgment of the bearing fault. According to the method of the invention, empirical mode decomposition (EMD) and an autoregressive (AR) model are combined together to perform pre-processing on original bearing signals, the parameters of the AR model are extracted and are adopted as the input of the network, and therefore, the input dimensions of the network can be greatly reduced, the simplification of calculation can be facilitated, and the training and testing of the network can be accelerated; a deep neural network on which the method of the invention is based can further automatically extract features of the input and qualitatively and quantitatively determine the bearing fault automatically, and therefore, the diagnostic accuracy of the method of the present invention can be ensured, and at the same time, dependence on signal processing expertise can be decreased, manual judgment is not required, the consumption of manpower can be decreased; and thus, the method has a higher practical value in the era of big data.

Description

technical field [0001] The invention belongs to the field of intelligent analysis and detection of signals, and in particular relates to the research on a qualitative, quantitative and hierarchical diagnosis method for bearing faults based on a stacked sparse automatic encoder (Stacked SAE) deep neural network. Background technique [0002] With the development of the economy, people have higher and higher requirements for equipment fault diagnosis technology. It is not only necessary to judge the type of fault, but also to further judge the severity of the fault, and it is required to be suitable for the processing of big data. As one of the key components of rotating machinery, the state of the bearing directly affects the running state of the rotating machinery. Once the bearing fails, it is likely to bring huge economic losses and even cause casualties. Signal processing and analysis is one of the effective ways to realize bearing fault diagnosis. The commonly used metho...

AI Technical Summary

Problems solved by technology

However, the fault diagnosis methods that are currently studied, whether based on signal processing and analysis, or artificial neural network methods, are limited to solving the problem of judging the type of bearing fault, and there are few methods that can judge both the type of fault and the size of the fault. Therefore, there is an urgent need for a qualitative, quantitative, and hierarchical diagnosis method for bearing faults, which can not only qualitatively judge the type of bearing faults, but also quantitatively judge the severity of faults, and at the same time achieve the goal of not relying too much on professionals for fault characteristics. Extraction and identification of faults, making it more suitable for the era of big data

Images