Multichannel time series data fault diagnosis method based on convolutional neural network

Abstract

The invention discloses a multi-channel time series data fault diagnosis method based on a convolutional neural network. The method comprises the following steps: (1) collecting multi-channel one-dimensional time series fault data of a monitored object; (2) constructing a multi-channel one-dimensional time sequence original fault data set, and carrying out normalization and data truncation preprocessing; (3) constructing a multi-channel two-dimensional feature map fault data set; (4) dividing into a training set, a verification set and a test set; (5) constructing a multi-channel deep learningfault diagnosis model which comprises an input layer, a feature extraction layer, a dimension reduction and parameter reduction layer, a softmax classification layer and a support vector machine output layer, wherein the dimension reduction and parameter reduction layer comprises a transition convolution layer with a convolution kernel of 1 * 1 and a global mean pooling layer; and (6) training, verifying and testing a multi-channel deep learning fault diagnosis model, and finally automatically outputting a diagnosis result by a support vector machine, so that people can diagnose faults of theelectromechanical equipment more intelligently and conveniently.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis, in particular to a multi-channel time series data fault diagnosis method based on a convolutional neural network. Background technique [0002] With the advent of the intelligent era, more and more electromechanical equipment products are developing in the direction of intelligence, automation, multi-function and precision. Today, the complexity of the application environment of electromechanical equipment products is gradually increasing. Under such circumstances, the long-term continuous operation of electromechanical equipment is prone to various faults. If the fault cannot be diagnosed and eliminated in time, once the fault hazard spreads, it may cause heavy losses. Therefore, it is extremely necessary to provide effective intelligent fault diagnosis methods for electromechanical equipment; Nowadays, with the wide application of "Internet +", Internet of Things and advanced smart sens...

AI Technical Summary

Problems solved by technology

In recent years, some scholars have applied CNN to the field of fault diagnosis, but they still need to use traditional feature extraction methods for pre-processing of feature extraction on the original fault data, and fail to make full use of the powerful feature extraction capabilities of convolutional neural networks, which limits fault diagnosis. Further improvement of the effect; the problem of too many parameters in the traditional convolutional neural network, the traditional convolutional neural network contains a 2-3 layer fully connected layer network structure part, usually located in the last pooling layer and Softmax classification Between the output layers, the amount of training parameters generated by the existence of the fully connected layer accounts for 80% to 90% of the total parameters of the CNN. This defect greatly offsets the advantages of CNN in reducing the number of parameters through pooling. The layer structure not only takes up too many computing resources, but also easily leads to overfitting of CNN model training, especially the fully connected layer containing multiple hidden layers. The number of CNN model parameters will increase exponentially with the number of fully connected layers. As a result, the traditional CNN model has too many parameters, which makes the test time-consuming when used in online fault diagnosis, which is not conducive to real-time and rapid fault diagnosis.

The Softmax classification function used in traditional CNN is far less powerful than SVM in terms of multi-classification functions, and it is difficult to exert superior performance in intelligent fault diagnosis

Images