Evidence theory fault state identification method based on correlation coefficient distance and iterative improvement

Abstract

The invention discloses an evidence theory fault state identification method based on correlation coefficient distance and iterative improvement, and the method comprises the steps: 1, collecting a data signal of equipment in an operation process through a plurality of sensors, and obtaining a plurality of basic probability assignments of the current operation state of the equipment; 2, calculating the distance between BPAs according to a Correlation coefficient distance and a Spearman correlation coefficient distance, and generating a distance matrix; 3, allocating corresponding weights to evidence bodies based on the distance matrix; 4, performing weighted correction on an original evidence body BPA by utilizing the generated double weights to obtain weighted average evidence; 5, combining the weighted average evidences for n-1 times according to the proposed iterative improved new fusion rule, and obtaining a fusion result. According to the method, the evidence theory combination rule is improved by introducing the idea of iterative improvement while the evidence theory is optimized by utilizing the double-distance function, so that the problem of information conflict is solved,the reliability of fault state recognition is effectively improved, and the fusion convergence speed is increased.

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 each large-scale equipment is becoming more and more complex. When it breaks down, the maintenance cost of the equipment will increase day by day, which will lead to more and more serious losses caused by equipment failure, and even cause 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 the fault in time, avoiding major accidents from the root cause occur. Therefore, equipment fault diagnosis and state identification have gradually become the ...

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