Evidence Theory Fault State Identification Method Based on Correlation Coefficient Distance and Iterative Improvement

Abstract

The present invention is based on the correlation coefficient distance and iterative improved evidence theory fault state identification method, including the steps: first, using multi-sensors to collect data signals during the operation of the equipment, so as to obtain multiple basic probability assignments of the current operation state of the equipment; second Second, calculate the distance between each BPA through the distance of the Correlation correlation coefficient and the distance of the Spearman correlation coefficient to generate a distance matrix; third, assign the corresponding weight to the evidence body based on the distance matrix; fourth, use the generated double weight The weighted average evidence is obtained by performing weighted correction on the original evidence body BPA; fifthly, the weighted average evidence is combined n-1 times according to the proposed iteratively improved new fusion rule to obtain the fusion result. The present invention utilizes the double distance function to optimize the evidence theory and at the same time introduces the idea of ​​iterative improvement to improve the combination rules of the evidence theory, thus solving the problem of information conflict, effectively improving the reliability of fault state identification, and accelerating the fusion convergence speed.

Description

technical field [0001] The invention relates to a fault diagnosis and state identification method, in particular to an evidence theory fault state identification method based on correlation coefficient distance and iterative improvement. Background technique [0002] With the rapid development of modern industry, the composition and structure of various large-scale equipment are increasingly complex. When the equipment fails, the maintenance cost of the equipment increases day by day, resulting in more and more serious losses caused by equipment failure, and even catastrophic damage. ACCIDENT. Using fault diagnosis technology to monitor the condition of equipment can effectively improve the stability of equipment operation, greatly reduce maintenance costs, and can determine the type and location of faults in time, avoiding major accidents from the root cause. . Therefore, the fault diagnosis and status identification of equipment has gradually become the focus of domestic...

AI Technical Summary

Problems solved by technology

The core of the D-S evidence theory is the Dempster evidence combination rule. Although it has excellent characteristics, there will be counterintuitive problems when using the D-S evidence theory to fuse conflicting data, which makes the final fusion result develop in an unreasonable direction and affects final diagnosis

Images