Machine learning method used for electrolytic-cell fault early-warning and application thereof

Abstract

The invention provides a machine learning method used for electrolytic-cell fault early-warning. The method is used for establishing an anticipation model for electrolytic-cell faults. A main processof the method includes: extracting detection point sequence data; preprocessing the data; inputting a training data set to a GMM clustering model; defining abnormality discrimination rules; optimizingdiscrimination parameters; improving the GMM clustering model; and evaluating a fitting effect of the trained model. The invention also provides an application of the machine learning method used forelectrolytic-cell fault early-warning. A main process of the application includes: extracting new detection point sequence data; preprocessing the data; predicting a time sequence; and carrying out early-warning fault judgment of the trained model. According to the method and the application, benumbing of traditional conditional value alarming on operators can be effectively reduced, experiencedoperators can be replaced for judging the faults, and error judgment of human factors can be avoided.

Description

technical field [0001] The invention relates to the technical field of clustering and prediction methods of machine learning, in particular to a machine learning method and application thereof for early warning of operating parameter failures of electrolyzer equipment, and is suitable for electrolyzer equipment whose operating parameters can be automatically collected and transmitted. Background technique [0002] At present, in the maintenance of production equipment, most enterprises still stay in the preventive maintenance of equipment, which consumes a lot of manpower and material resources, and once the problem is found, the problem has already occurred, causing chain parking and bringing great losses to production. However, in the production of modern chemical enterprises, the automation of production data measurement has been realized. The production and consumption data can be transmitted to the DCS system through sensing equipment, and the operation data (flow, press...

AI Technical Summary

Problems solved by technology

However, if a single operation data occasionally exceeds the threshold, it does not necessarily cause damage to the equipment. Too many false alarms can easily paralyze the operator. Correlation, before the failure occurs, it is of great significance to predict the upcoming problems of the equipment based on the abnormality of the operating parameters of the equipment

Images