A chemical fault monitoring method based on generalized multi-block independent element analysis model

Abstract

The invention discloses a chemical fault monitoring method based on a generalized multi-block independent element analysis model, and aims to propose a generalized multi-block independent element analysis algorithm, which can implement non-Gaussian multi-block for overlapping and non-overlapping variable sub-block divisions Modeling, so as to use the generalized multi-block independent meta-analysis algorithm to implement distributed fault monitoring. In the process of implementing the modeling based on the independent element analysis algorithm, the method of the present invention simultaneously considers the uniqueness of each sub-block and the integrity between the sub-blocks, from the separation of the whole to the extraction of local sub-blocks, and then returns from the local sub-blocks to the whole Separate interleaved one-by-one extraction strategies. Therefore, the method of the present invention is a brand new non-Gaussian multi-block modeling and fault monitoring method. In addition, the superiority of the method of the present invention will be verified in specific implementation cases, thereby illustrating that the method of the present invention is a more preferred non-Gaussian distributed fault monitoring method.

Description

technical field [0001] The invention relates to a data-driven fault monitoring method, in particular to a chemical fault monitoring method based on a generalized multi-block independent element analysis model. Background technique [0002] Due to the wide application of computer technology in chemical industry production, process objects can be stored offline and measure massive amounts of data online, and modern industrial processes are gradually moving towards digital management. These data contain potential information that can reflect the operating status of the production process, and the use of sampling data to monitor the operating status of the process has been favored by many scholars. In the past ten years, both academia and industry have invested a lot of manpower and material resources in the research of fault monitoring technology. In the field of data-driven fault monitoring research, statistical process monitoring is the most studied method, among which Princ...

AI Technical Summary

Problems solved by technology

How to implement multi-block ICA modeling for this multi-block division result, and consider the interaction between blocks, has not yet been fully considered in literature or patents

The traditional multi-block principal component analysis algorithm also requires that the division of variable blocks does not overlap. Therefore, directly expanding multi-block principal component analysis into multi-block ICA algorithm cannot deal with the overlapping variable sub-block division.

Images