Chemical process fault detection method based on adaptive kernel principal component analysis

Abstract

The invention relates to a chemical process fault detection method based on adaptive kernel principal component analysis. The method comprises the following steps: S1. constructing an offline model according to historical data to obtain an Euclidean distance between kernel principal component load vectors in the historical data and a kernel principal component T of the historical data; S2. performing online monitoring based on online data, obtaining DVKPC, NDVKPC and AKPC of the online data in sequence in combination with the Euclidean distance between the kernel principal component load vectors in the historical data, and then calculating a T2 statistical magnitude and a control limit of the online data based on AKPC; and S3. judging whether the T2 statistical magnitude exceeds the control limit, if so, indicating a fault, or otherwise, returning to step S2. Compared with the prior art, by adaptively selecting the kernel principal component of an online data sample, the mutation information can be effectively focused to prevent the mutation features from being scattered or flooded, thereby reducing the fault detection false alarm rate and improving the fault detection performance.

Description

technical field [0001] The invention relates to the technical field of automatic detection, in particular to a chemical process fault detection method based on self-adaptive nuclear principal component analysis. Background technique [0002] With the development of complex and large-scale chemical industry production process, once a failure occurs in the chemical process, it will not only cause economic losses, but also may pollute the environment and even endanger personal safety. Therefore, it is necessary to detect faults in the chemical process. Generally, because the fault detection methods have their own constraints, and the chemical process is a complex nonlinear process, it is impossible for any fault detection method to accurately detect all the faults at one time. Therefore, the research focus of the fault detection method is how to effectively reduce the fault false alarm rate. [0003] Existing fault detection methods usually monitor the running status of chemic...

AI Technical Summary

Problems solved by technology

[0006] However, there are still some problems in the above-mentioned improved KPCA method: KPCA subjectively uses the kernel principal component with large variance for fault detection, in which the normal kernel principal component of the kernel component with large variance may overwhelm the variation kernel principal component, The kernel principal component with a small variance may also contain the variation kernel principal component, which will cause the variation features to be scattered into two spaces, which may easily cause the variation features to be scattered or submerged, and eventually lead to a high false positive rate of fault detection.

Images