Fault classification method based on one-dimensional multi-path convolutional neural network

Abstract

The invention discloses a fault classification method based on a one-dimensional multi-path convolutional neural network, and belongs to the technical field of industrial process monitoring. Accordingto the method, a traditional two-dimensional convolutional neural network is improved; multiple paths of parallel one-dimensional convolutional neural networks are applied in the variable direction;the cross correlation among variables is deconstructed, the variables are independently subjected to convolution and pooling to extract time sequence feature information, the extracted features are more diversified, the robustness is higher, the defect that a traditional two-dimensional convolutional neural network is sensitive to the prior arrangement order of the variables in input data is overcome, and the method is more suitable for complex and high-order industrial process data; experiments show that the fault classification model obtained based on the one-dimensional multi-path convolutional neural network training provided by the invention can effectively perform fault classification of industrial process data, and has higher generalization capability compared with a common model.

Description

technical field [0001] The invention belongs to the technical field of industrial process monitoring, and more specifically relates to a fault classification method based on a one-dimensional multi-channel convolutional neural network. Background technique [0002] Fault classification technology plays an important role in root cause diagnosis and troubleshooting after industrial process accidents. It has become a cross-cutting technology, mainly involving the fields of statistics, applied mathematics, signal analysis and machine learning. With the in-depth research and continuous development across fields, the different fault classification methods that many experts and scholars have applied can be summarized into two categories: mathematical modeling and data-driven. Among the data-driven methods, the deep learning method has achieved performance beyond the traditional signal analysis, multivariate statistical learning and other algorithms and has been widely used. [000...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the application defects of the existing two-dimensional convolutional neural network technology, the purpose of the present invention is to deconstruct the correlation between variables by using the multi-channel operation of one-dimensional convolution and pooling, and independently analyze the local timing characteristics of process variables For fault classification, it aims to solve the problem that the two-dimensional convolutional network is sensitive to the order of variables, resulting in low accuracy and precision of fault identification

Images