Calculation method for performance interval of production device

Abstract

The invention discloses a calculation method for a performance interval of a production device, and relates to the research of an evaluation method for calculating the performance interval of the device according to interval and running real-time monitoring data. Compared with a conventional clustering algorithm, the method has the advantages that a clustering result is more accurate and the precision is higher; the influence of indexes in actual production on device performance is considered, and a weight of the index with relatively high influence is highlighted, so that a final performanceclustering center better meets an actual running condition of the device; by defining a maximum clustering radius on a mathematic level, differing from fuzzy division of other types, accurate performance interval division is obtained; the size of a collection window on the specific mathematic level is defined, and only when data in the collection window is all divided in a same interval, device performance status evaluation can be obtained, so that the evaluation accuracy is defined, and the influence of individual interference data on an evaluation result is avoided.

Description

technical field [0001] The invention relates to an evaluation method for modeling equipment performance interval division based on historical data of equipment operation, and calculating and judging the performance interval condition of the equipment according to the interval and real-time operation monitoring data. Background technique [0002] With the development of industrial technology and the expansion of the scale of manufacturing enterprises, manufacturing technology has gradually developed from semi-manual and semi-mechanized to a fully mechanized and intelligent direction. Highly complex and expensive equipment is more and more widely used in enterprise production lines. superior. The operation of the manufacturing equipment of "flow production type" enterprises has the characteristics of high safety requirements and continuous production. Once the equipment performance declines or fails, it will not only increase the maintenance cost of the enterprise, but also ha...

AI Technical Summary

Problems solved by technology

This method aims at the disadvantage of using the K-means algorithm to analyze the same effect of each index attribute of the equipment in the clustering of the division performance interval, resulting in the problem of low accuracy of interval clustering and the information entropy method only based on data information and ignores the index interval. Correlation and other issues, combined with CRITIC and information entropy methods to obtain the comprehensive weight of each index, and then cluster the focus through multi-index clustering to obtain the division of equipment performance intervals;

Images