Chemical process fault diagnosis method for adaptive kernel principal component analysis

Abstract

The invention discloses a chemical process fault diagnosis method for adaptive kernel principal component analysis. A suitable kernel function is selected; a kernel matrix and a corresponding covariance matrix are calculated; the covariance matrix is calculated to obtain a feature value; different thresholds are set according to the condition that whether a feature value is zero; the feature valueexceeding a threshold is selected as a kernel principal component model; a calculation statistical magnitude and a control limit are compared to determine fault occurrence. In addition, a sliding window with the proper length is added based on the kernel principal component analysis method based on a threshold and a kernel principal component model is extracted adaptively based on a threshold method; data in each sliding window are processed in a targeted manner and the factor of the fault occurrence is diagnosed, so that the fault diagnosis of the chemical process is processed adaptively.

Description

technical field [0001] The invention relates to the technical field of chemical production fault diagnosis, in particular to a chemical process fault diagnosis method based on self-adaptive kernel principal component analysis. Background technique [0002] Chemical process is one of the important process facilities in industrial society, and occupies an important position in economic development and social production needs. With the improvement of modern science and technology, the chemical process has become more and more complicated. A series of unexpected problems in the system process also followed, and the difficulty of process monitoring has also increased due to the influence of related problems such as the high complexity of the chemical process. Ensuring the normal operation of the chemical process is the key to achieving good economic benefits, and the improvement and effectiveness of fault detection and diagnosis methods is particularly important. In recent year...

AI Technical Summary

Problems solved by technology

However, the existing methods have certain difficulties in processing nonlinear data and real-time diagnosis, and cannot establish models in real time based on data, and the diagnostic accuracy is limited to a certain extent, which consumes a lot of manpower and material resources.

Images