Bearing fault diagnosis method and system based on sparse auto-encoder and Softmax

Abstract

The invention discloses a bearing fault diagnosis method and system based on a sparse auto-encoder and Softmax, and the method comprises the steps: introducing local constraints into an original sparse auto-encoder, and obtaining an improved sparse auto-encoder; local constraints of an improved sparse self-encoding model are reflected in normalization of an encoder weight matrix, only k activation units with the maximum cosine similarity of a hidden layer are reserved to form a local subspace of an original sample, the local subspace is correspondingly characterized by k neighbors of a sample x, and a decoder reconstructs input through the reserved k coding units. Vibration signals of a rolling bearing in different running states are collected as a training set, the training set is used for training a local sparse auto-encoder model and a Softmax classifier model, model parameters are obtained, and therefore building of a fault diagnosis classification model is completed, due to the fact that local features of the vibration signals are considered, features learned by the local sparse auto-encoder are more complete, and the accuracy of the trained model is higher.

Description

technical field [0001] The invention belongs to a fault diagnosis method, in particular to a bearing fault diagnosis method and system based on a sparse autoencoder and Softmax. Background technique [0002] In recent years, mechanical equipment is developing in the direction of high integration and automation. Among them, rolling bearings, as an important part of rotating machinery and electrical equipment, are known as "the joints of industry". In order to ensure the production efficiency and safe and reliable operation of equipment, the condition monitoring of rolling bearings is very important. Since the vibration signal of the rolling bearing is rich in information reflecting the operating state when the rolling bearing is running, a large number of sensors are usually arranged in some large industrial equipment such as aeroengines and gas turbines to obtain the monitoring data of the rolling bearing, but how to obtain the monitoring data of the rolling bearing from a l...

AI Technical Summary

Problems solved by technology

However, the disadvantage of the original SAE is that it only considers the sparsity of the features, but ignores the internal structure information of the input samples, so it is difficult to fully mine useful fault information from the input data, and then contribute to the final classification result of the Softmax classifier.

Images