Dimensionless index based fault diagnosis method for rotating machinery

Abstract

The present invention discloses a dimensionless index based fault diagnosis method for rotating machinery. The method comprises the following steps: (1) acquiring fault type signal data; (2) performing dimensionless index calculation; (3) performing sample processing to form a data set; (4) using a Kolmogorov-Smirnov test method, and using a kstest2 function in matlab to acqurie similarity between a to-be-tested sample and the known data set, so as to obtain a basic belief function; (5) performing corrected D-S data fusion by using an evidence combination method based on a weight coefficient and collision probability redistribution; and (6) analyzing a fusion result and making a decision. According to the technical scheme provided by the present invention, by using the dimensionless index, K-S and D-S combined rotating machinery fault evidence combination diagnosis method, a large number of fault signal characteristic values can be extracted; by using the K-S method, the rotating machinery fault evidence combination diagnosis is implemented more reliably; and by using a more reliable and reasonable fusion result, decision-making risk is reduced.

Description

technical field [0001] The technical solution relates to a data processing method, in particular to a fault diagnosis method for rotating machinery. Background technique [0002] Large-scale rotating machinery equipment (such as steam turbines, rotating bearings, fans, compressors, etc.) is the key equipment in important engineering fields such as petroleum, chemical industry, metallurgy, machinery manufacturing, aerospace, etc. Continuous development in the direction of serialization and precision requires higher safety and reliability of these devices. [0003] However, when the petrochemical rotating mechanical equipment fails, the vibration monitoring signal often contains a large amount of non-linear, random, and non-traversable information, which brings great difficulties to the analysis of the fault signal. [0004] The existing technology often uses the probability density function of the vibration signal of the petrochemical rotating machinery equipment to deduce t...

AI Technical Summary

Problems solved by technology

However, in the actual information fusion system, due to natural environment interference or human interference, etc., the evidence bodies provided by the sensors often conflict with each other.

Images