Detection method for abnormal state of multi-mode industrial process, system thereof and equipment

Abstract

The invention belongs to the field of process monitoring, particularly relates to a detection method for abnormal state of a multi-mode industrial process, a system and equipment, and aims to solve the problem of insufficient detection precision of an abnormal production state reflected by an abnormal change trend of a monitored multi-dimensional variable in a complex industrial production process. The method comprises the following steps: acquiring state monitoring data; preprocessing the state monitoring data to obtain preprocessed data; segmenting the preprocessed data, and constructing an augmented matrix used for describing the state of the production process at the t moment as a first matrix; calculating detection results under set abnormal indexes set and sbt based on errors between the matrixes; carrying out filtering processing on the obtained detection result; and if the value corresponding to the filtered detection result is greater than any one of two pre-acquired alarm thresholds, performing early warning. According to the invention, the detection precision of abnormal state detection in the multi-mode industrial process is improved.

Description

technical field [0001] The invention belongs to the field of process monitoring, and in particular relates to a detection method, system and equipment for abnormal states of multi-modal industrial processes. Background technique [0002] Modern industrial production lines are becoming more and more complex. If abnormal phenomena in the production process cannot be detected, diagnosed and eliminated in time, it may lead to equipment damage, product quality decline, and even serious production accidents and casualties. Nowadays, a large number of sensors have been used to monitor the production process, and sufficient monitoring data can be collected from the production process. Using these data, a data-driven model can be built to realize real-time monitoring of the production process and automatic detection of abnormal states. The relevant research has great research significance and application value. [0003] Most of the existing process monitoring algorithms are aimed a...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem of insufficient detection accuracy of the abnormal production state reflected by the abnormal change trend of the monitored multidimensional variable in the complex industrial production process including multiple operating modes, In the first aspect of the present invention, a method for detecting an abnormal state of a multimodal industrial process is proposed, the method comprising:

Images