Residual service life prediction method for large-scale equipment based on multi-parameter feature fusion

Abstract

The invention discloses a residual service life prediction method for large-scale equipment based on multi-parameter feature fusion. The method comprises the steps: obtaining multiple sensor time sequence parameters of large-scale equipment in a laboratory through a large-scale online monitoring system; performing regression analysis on the multi-parameter continuous values by using a ReliefF algorithm, and obtaining a parameter type with relatively large correlation with the equipment state through feature weight screening; performing data dimension reduction and feature extraction on the screened parameters based on a principal component analysis method, and obtaining a health index representing the operation state of the large-scale equipment through weight fusion; constructing an HMM model based on an expectation maximization algorithm, taking the health indexes as a training set for model training, and finding a grading model used for evaluating the equipment health state corresponding to the current health index; calculating an exponential likelihood value through a Viterbi algorithm to obtain a health index nearest to the likelihood value, and predicting an exponential difference by using a weighted average method to obtain a health state fitting curve; and calculating a residual service life prediction value of the large-scale equipment.

Description

Technical field: [0001] The invention relates to a method for predicting the remaining service life of large equipment, in particular to a method for predicting the remaining service life of large equipment based on multi-parameter feature fusion. Background technique: [0002] As chemical equipment used for polymer material processing or chemical research in university laboratories, it is very important to improve equipment reliability, reduce maintenance costs, and establish a large-scale equipment health maintenance management technology centered on the remaining service life. The remaining life prediction of large-scale equipment refers to predicting the remaining life of the equipment from healthy use to the failure threshold by analyzing the historical performance degradation process of the equipment, so as to realize early maintenance and avoid losses caused by downtime due to failure. [0003] Although the common service life prediction methods take into account the ...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the single parameter problem in the traditional method for predicting the service life of large-scale equipment, the present invention improves the existing large-scale equipment health state prediction method, and fuses various sensor parameters into a health index representing the performance state of the equipment through the ReliefF-PCA algorithm. By substituting the time-series health index, build an HMM state training model based on the EM algorithm, find the corresponding health state, use the Viterbi algorithm to calculate the likelihood value, and use the weighted average method to fit the health index, and then obtain the prediction of the equipment health state value

Images