Trend prediction method for degradation state of key parts of rotary machine

Abstract

The invention discloses a trend prediction method for degradation state of key parts of a rotary machine comprising the following steps: S1, collecting vibration signals in a certain time period at acertain rotating speed of the rotary machine based on equal interval time, and denoising the vibration signals; S2, calculating the average permutation entropy and nonlinearity of the vibration signalsequence according to the obtained vibration signal sequence, and forming a composite index time sequence; s3, fitting the composite exponential time sequence by adopting a nonlinear exponential function, and extracting to obtain a fitting function model; S4, subtracting a corresponding value on the fitting function model from the composite exponential time sequence to obtain a residual time sequence, and performing identification and residual prediction on the residual time sequence by adopting an extreme learning machine model; and S5, combining the fitting function model and the extreme learning machine to form a hybrid extreme learning machine prediction model, and realizing rotary machine degradation trend prediction. The invention can predict the degradation state of the key parts of the rotary machine, and is high in calculation speed and good in prediction effect.

Description

technical field [0001] The invention belongs to the technical field of state monitoring and life evaluation of mechanical systems, and in particular relates to a method for predicting the degradation state trend of key parts of rotating machinery. Background technique [0002] At present, many of the degradation state identification and evaluation methods of mechanical systems in my country are mainly based on online monitoring methods, which can better achieve a balance between safety and economy. Among the state monitoring of many mechanical systems, the vibration analysis method has the characteristics of fast diagnosis and online monitoring, and has been widely used in the state monitoring and fault diagnosis of rotating machinery. The existing vibration signal complexity measurement method has good computational efficiency and can quickly perceive the rapid change of the dynamic behavior of the object system from the vibration time series, but its value will produce rel...

AI Technical Summary

Problems solved by technology

The existing vibration signal complexity measurement method has good computational efficiency and can quickly perceive the rapid change of the dynamic behavior of the object system from the vibration time series, but its value will produce relatively drastic changes, which is not conducive to the long-term degradation of the mechanical system. Prediction of Process Trends

Images