Multi-working-condition industrial monitoring method and device based on dictionary learning, equipment and medium

Abstract

The invention relates to a multi-working-condition industrial monitoring method based on dictionary learning. The method comprises the steps of acquiring label-free historical data containing a pure net value, measurement noise and an abnormal value; constructing an unsupervised dictionary learning model based on the label-free historical data; solving a dictionary, a sparse coding matrix and an abnormal value matrix according to the unsupervised dictionary learning model; dividing the dictionary into a plurality of sub-dictionaries according to the production condition information; and acquiring test data, and judging whether the test data is a fault point or not through the sub-dictionary. According to the method, the measurement noise can be suppressed, and the influence of the abnormalvalue is reduced, so that false alarm of faults in industrial monitoring is effectively prevented. Therefore, the accuracy of fault monitoring is improved, and the robustness of the monitoring methodto abnormal values and noise in data is ensured.

Description

technical field [0001] The present application relates to the field of industrial process monitoring, in particular to a dictionary learning-based multi-working-condition industrial monitoring method, device, equipment and medium. Background technique [0002] In modern industry, how to ensure production safety and improve product quality has important research value. It is against this background that process monitoring technology emerges. Most of the early process monitoring methods are based on mathematical models and knowledge-based monitoring. However, for the process industry, accurate mathematical mechanism models and complete expert knowledge are often difficult to obtain. Therefore, the process monitoring methods based on mathematical models and knowledge are usually difficult to be practically applied. [0003] With the widespread use of Distributed Control System (DCS) and various intelligent instruments in the process industry, a large amount of process data i...

AI Technical Summary

Problems solved by technology

[0005] Based on this, it is necessary to provide a multi-condition industrial monitoring method, device, equipment and medium based on dictionary learning to solve the problem of inaccurate monitoring of traditional industrial process monitoring methods

Images