Method and system for calculating residual service life of mechanical device in multiple working conditions

Abstract

The invention provides a method and a system for calculating residual service life of a mechanical device in multiple working conditions. The method comprises the steps of obtaining historical data and current data of the mechanical device, and forming an original training data set of a Gaussian process regression model; building the Gaussian process regression model corresponding to a current state of the mechanical device according to the original training data set; predicting an eigenvalue representing a running state of the mechanical device according to the obtained Gaussian process regression model, thereby obtaining a prediction value corresponding to the residual service life; judging whether the obtained prediction value exceeds a set threshold or not; if yes, performing calculation to obtain current residual service life; and if not, including the obtained prediction value in the training data set to form a new training data set, optimizing or automatically generating a new Gaussian process regression model according to the new training data set, and predicting the eigenvalue according to the optimized or automatically generated new Gaussian process regression model, until the prediction value exceeds the set threshold.

Description

technical field [0001] The invention relates to the field of life prediction of mechanical equipment, and in particular to a method and system for calculating the remaining service life of mechanical equipment under multiple working conditions. Background technique [0002] Mechanical equipment (such as an engine on an aircraft) state prediction and remaining useful life (Remaining Useful Life, RUL for short) calculation is a technology that calculates its future use state based on the past and current state of mechanical equipment. A set of efficient and reliable state prediction and remaining service life calculation method has an extremely important guiding role in the maintenance service of mechanical equipment. Based on the results of predictive calculations, the future health status or decline of mechanical equipment can be effectively grasped, so that reasonable decisions can be made in advance, either by timely arranging mechanical equipment maintenance, or by replac...

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the fact that the existing prediction method cannot accurately predict the remaining service life of mechanical equipment operating under multiple working conditions, the present invention provides a method and system for calculating the remaining service life of mechanical equipment under multiple working conditions

Images