Industrial fault diagnosis method based on improved KPCA (kernel principal component analysis) and hidden Markov model

Abstract

The invention discloses an industrial fault diagnosis method based on an improved KPCA (kernel principal component analysis) and hidden Markov model and belongs to the technical field of industrial process monitoring and diagnosing. Calculation efficiency of KPCA under the condition of large samples is greatly improved by a similarity analysis method, and industrial faults can be classified by means of high dynamic process time sequence modeling capability and time sequence model classifying capability of the hidden Markov model. Accordingly, compared with the existing methods of the prior art, the industrial fault diagnosis method has the advantages that complexity in calculation can be reduced, nonlinear characteristics can be more efficiently processed and nonlinear industrial fault diagnosis is high in accuracy since the nonlinear characteristics and massive data of industrial data are sufficiently considered.

Description

technical field [0001] The invention belongs to the field of industrial process monitoring and fault diagnosis, in particular to an industrial fault diagnosis method based on improved KPCA and hidden Markov model. Background technique [0002] As the complexity of industrial processes grows, the effectiveness of industrial process monitoring and diagnostics becomes increasingly important to ensure process safety, maintain product quality, and optimize product profitability. [0003] For process monitoring and fault diagnosis, traditional methods mostly use multivariable statistical process monitoring (Multivariable Statistical Process Monitoring, MSPM), in which principal component analysis (Principal Component Analysis, PCA), partial least squares (Partial Least Squares, PLS) ) and Independent Component Analysis (ICA) have been successfully applied in industrial process monitoring. Traditional PCA, ICA and other methods all assume that the relationship between process vari...

AI Technical Summary

Problems solved by technology

Traditional PCA, ICA and other methods all assume that the relationship between process variables is linear, but in practice, it is difficult for measured variables to meet this assumption, and they often show strong nonlinear characteristics.

Although the introduction of kernel methods, such as kernel ICA, kernel PCA (Kernel PCA) and other methods are proposed to solve the non-linearity between variables, however, the above methods have the following disadvantages, the original data becomes variable after mapping from the input space to the high-dimensional feature space Redundant, and the kernel matrix is ​​a square matrix with the size of the sample number

As the number of samples increases, the amount of calculation continues to increase, and in industrial processes, the number of samples is often huge, so it is difficult to extract the nonlinear relationship between variables with the original KPCA, which may cause fault diagnosis An error occurred

Images