Fault diagnosis method based on improved convolutional neural network

Abstract

The invention discloses a fault diagnosis method based on an improved convolutional neural network, and relates to the technical field of fault diagnosis. The method includes: establishing an improvedconvolutional neural network model, wherein the improved convolutional neural network model sequentially comprises an input layer, a plurality of feature extraction layers, a newly added convolutional layer, a full connection layer and an output layer, each feature extraction layer sequentially comprises a convolution layer and a pooling layer; performing training by using the training set and the test set based on an improved convolutional neural network model to obtain a fault diagnosis model for automatic fault diagnosis. According to the method, a newly-added convolution layer is furtherarranged between a feature extraction layer and a full connection layer, the newly-added convolution layer can extract deep features of the model, the generalization ability of the model is effectively enhanced, meanwhile, the feature extraction layer is improved, the risk of over-fitting can be reduced to a certain extent, and the calculation speed is increased.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to a fault diagnosis method based on an improved convolutional neural network. Background technique [0002] In recent years, the application of machine learning in the fields of fingerprint recognition, text recognition, speech recognition, fault diagnosis and image classification has become more and more extensive, basically meeting the requirements of commercialization. As a branch of machine learning, deep learning solves the difficult problems of traditional deep neural network training. [0003] As a member of the deep learning model, CNN (Convolutional Neural Network) is widely used in the field of image recognition and fault diagnosis. It can realize adaptive feature extraction and intelligent classification, and has a strong processing ability for high-dimensional and nonlinear data. In addition, , CNN can ensure the invariance of feature extraction while maintaini...

AI Technical Summary

Problems solved by technology

CNN combines the convolution operation with the backpropagation algorithm to complete the self-learning training of the convolution kernel parameters, but CNN has the inherent shortcomings of deep learning and traditional neural networks: gradient disappearance, over-fitting, large amount of calculation and model generalization Weak ability

Images