Rotary machine intelligent fault diagnosis method based on integrated depth auto-encoder

Abstract

The invention provides a rotary machine fault diagnosis method based on a depth automatic encoder, and aims to improve the fault diagnosis precision of a rotary machine, and the method comprises the steps: firstly collecting a vibration acceleration time domain signal of the rotary machine, and obtaining a training data set and a test data set; secondly, for each activation function, training a series of depth auto-encoders through different training sets by using a K-fold cross validation method; secondly, verifying the trained depth auto-encoder through a verification set, and obtaining theprecision of each fault label; thirdly, searching an optimal selection parameter by adopting a grid search method, screening the depth auto-encoder through the optimal selection parameter, and constructing an integrated depth auto-encoder model; and finally, obtaining a prediction label of the input sample, and mapping the prediction label back to the fault type of the rotating machine to realizefault diagnosis of the rotating machine.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis and signal processing and analysis, and relates to a fault diagnosis method for rotating machinery, in particular to an intelligent fault diagnosis method for rotating machinery based on an integrated depth autoencoder, which can be used for faults of rotating machinery such as rolling bearings and gearboxes Automatic diagnosis. Background technique [0002] Rotating machinery is the most widely used mechanical equipment in the industrial field and is of great significance to social and economic development. The key components of rotating machinery will inevitably experience various failures under harsh working conditions such as heavy load, heavy impact, high speed, and large background noise. These failures can cause huge losses and serious casualties. In order to monitor the operating status of rotating machinery, improve the safety and reliability of rotating machinery, and avoid une...

AI Technical Summary

Problems solved by technology

However, this method only considers the overall performance of the deep autoencoders. The deep autoencoders are directly combined using an integration strategy without selection, and the difference in the classification accuracy of each deep autoencoder for different fault categories is not considered, which affects the rolling bearing. diagnostic accuracy; at the same time, each activation function only generates a deep autoencoder, which has low generalization ability and low robustness

Images