Fault diagnosis of rotating machinery based on one-dimensional depth residual convolution neural network

Abstract

The invention discloses a rotating machinery fault diagnosis method based on a one-dimensional depth residual convolution neural network. Firstly, the network learns more deep and abstract fault characteristics of training samples through a stacked one-dimensional residual module. Then, the Adam optimization algorithm is used to optimize all the super-parameters to complete the deep-level featureextraction and fault classification, and the rotating machinery fault diagnosis system model based on one-dimensional depth residual convolution neural network is obtained. Finally, the test samples are inputted into the trained fault diagnosis model, and the deep-seated features are extracted automatically to diagnose the health status of the rotating machinery.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of rotating machinery, and more specifically, relates to a fault diagnosis method of rotating machinery based on a one-dimensional deep residual convolutional neural network. Background technique [0002] Rotating machinery is the most widely used component in industrial equipment. Once a failure occurs, it will inevitably lead to equipment failure, resulting in economic losses and even safety accidents. Therefore, it is of great significance to carry out fault diagnosis on rotating machinery. [0003] Traditional intelligent fault diagnosis methods mainly include data acquisition, feature extraction and fault identification. Among them, feature extraction and fault identification are the two most important steps, which have a direct impact on the accuracy of fault diagnosis results. However, traditional intelligent fault diagnosis methods have the following disadvantages: 1) The diagnos...

AI Technical Summary

Problems solved by technology

However, traditional intelligent fault diagnosis methods have the following disadvantages: 1) The diagnostic performance depends on the design of the feature extraction method by domain experts, and for each specific diagnostic task, the feature extraction method must be redesigned, so it is time-consuming and labor-intensive; 2 ) Manually extracted features cannot guarantee to fully represent the complex dynamic characteristics of rotating machinery; 3) Fault identification methods such as support vector machines, k-nearest neighbors, random forests, and naive Bayes all use shallow learning models, which are difficult Learn enough features to easily cause misjudgment

However, the published related methods almost all have the problems of low accuracy and poor domain adaptability under complex working conditions

Images