Prediction method for safety assessment of coal mill

Abstract

The invention relates to a prediction method for safety assessment of a coal mill. The method comprises steps of extracting key factor variables and corresponding expert scores from a historical database to form an original data set; performing data clustering simplification on the original data set; carrying out dimensionality reduction on the key factor variables under each cluster based on a principal component analysis strategy, and obtaining principal component factors under each cluster; combining principal component analysis and a long short-term memory neural network, taking principal component factors of the training samples as input variables of the long short-term memory neural network, taking corresponding coal mill operation safety scores as output variables, and establishing a prediction model of coal mill equipment safety evaluation; and evaluating the coal mill operation safety of the coal mill operation data based on the prediction model. Real-time online safety evaluation can be carried out on the running state of the coal mill, the running state of the coal mill is sensed in advance, intervention work is implemented, safety is improved, and the service life of the coal mill is prolonged.

Description

technical field [0001] The invention relates to the technical field of system operation evaluation algorithm optimization based on machine learning, in particular to a prediction method for coal mill safety evaluation. Background technique [0002] In the prior art, the research on the safety evaluation of coal mill equipment operation mainly analyzes the coal mill equipment operation safety from the perspective of coal mill equipment failure. For example, in the fault diagnosis based on the quantitative model, first determine the fault type of the coal mill under study, then establish the corresponding fault expression according to a certain type of fault type, and finally judge whether the fault occurs according to the fault expression. The precise establishment of the fault expression is The key to judging the operation performance of the coal mill; in the fault diagnosis based on the signal model, the signal generated during the operation of the coal mill is mainly ident...

AI Technical Summary

Problems solved by technology

For example, in the fault diagnosis based on the quantitative model, first determine the fault type of the coal mill under study, then establish the corresponding fault expression according to a certain type of fault type, and finally judge whether the fault occurs according to the fault expression. The precise establishment of the fault expression is The key to judging the operation performance of the coal mill; in the fault diagnosis based on the signal model, the signal generated during the operation of the coal mill is mainly identified based on the sensing measurement tool. The sensing measurement tool is the key to judging the operation performance of the coal mill. In addition, the sensor A large number of installation, use and subsequent maintenance will result in high costs, which is not conducive to the construction of economical power plants; in the fault diagnosis based on the historical data model, based on the historical operation data of the coal mill equipment, the fault of the coal mill is identified based on an intelligent algorithm Parameters and deep excavation of coal mill equipment failure model

[0003] The above-mentioned studies are mainly aimed at certain types of faults of coal mills, and the operating parameters of coal mills have nonlinear strong coupling characteristics. Changes in one parameter often cause changes in other parameters, resulting in the occurrence of various types of faults. Azimuth realizes the evaluation of the operation safety of coal mill equipment

Images