Industrial process visual monitoring method based on data dependence kernel discriminant analysis

Abstract

The invention discloses a polyethylene process visual monitoring method based on data dependence kernel discriminant analysis, and the method comprises the steps: firstly collecting normal working condition data and abnormal working condition data of an industrial process, building intra-class compactness and inter-class separation degree, building a space structure constraint term based on t distribution similarity and KL divergence, and then establishing a data dependence kernel discriminant analysis optimization function, then using an interior point method to carry out calculation to obtain a model numerical solution, and adopting Delauni triangulation to establish a visual process monitoring model. Compared with a traditional algorithm, the method has the advantages that the accuracy of process monitoring can be greatly improved, and a more visual system running state and an abnormal track can be provided for process operators.

Description

technical field [0001] The invention belongs to the field of industrial process control, in particular to an industrial process visualization monitoring method based on data-dependent kernel discriminant analysis. Background technique [0002] Process monitoring is a kind of technology to ensure industrial process safety, improve product quality, and reduce energy consumption and pollution. Due to the large number of applications of distributed control systems, a large amount of process data can be easily collected nowadays, and data-driven process monitoring technology is more and more popular because of its characteristics of easy deployment and implementation, good generalization ability and dependence on process knowledge. focus on. Humans are naturally exposed to a variety of visual stimuli; compared to other information, visual information is more intuitive, richer in content, and easier for operators to understand. Therefore, there is an urgent realistic demand for ...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of the existing data-driven industrial process visualization monitoring method, the present invention provides a kind of industrial process visualization monitoring method based on data-dependent kernel discriminant analysis, and the specific technical scheme is as follows:

Images