Method, device and equipment for predicting residual service life of magnetic levitation system and medium

Abstract

The invention discloses a method, device and equipment for predicting the residual service life of a magnetic levitation system and a medium, and the method comprises the steps: extracting time domainfeatures and frequency domain features from a levitation gap signal of a target magnetic levitation system, and obtaining a corresponding feature set; calculating a Spearman grade correlation coefficient corresponding to each feature in the feature set to determine monotonicity of each feature; clustering monotonicity of features in the feature set based on a hierarchical clustering method, and screening out target features from clustering results; calculating a health index threshold value corresponding to the target magnetic levitation system by utilizing the target characteristics; determining initial time suitable for predicting the starting life of the target magnetic levitation system by utilizing a pre-constructed exponential decay model; and based on the exponential decay model, predicting the remaining service life of the target magnetic levitation system by using the health index threshold and the initial time. According to the invention, the health index threshold and the exponential decay model are used for life prediction, and the accuracy of life prediction of the magnetic levitation system is improved.

Description

technical field [0001] The invention relates to the application field of a magnetic levitation system, in particular to a method, device, equipment and medium for predicting the remaining service life of a magnetic levitation system. Background technique [0002] At present, the maglev system is an emerging application technology, and the transportation field is one of the important directions of its development. However, once an accident occurs, it will bring inevitable losses. So how to accurately realize the remaining service life of the maglev system (Remaining Useful Life , RUL) prediction is a widespread concern at present. [0003] In the existing technology, the remaining service life of the maglev system can be predicted by establishing a physical model, but because the complex system usually consists of many parts and has a complex structure, the physical failure process becomes complicated and difficult to capture, so it is usually difficult Building accurate phy...

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, the remaining service life of the maglev system can be predicted by establishing a physical model, but because the complex system usually consists of many parts and has a complex structure, the physical failure process becomes complicated and difficult to capture, so it is usually difficult Building accurate physical models for complex systems reduces the accuracy of remaining useful life predictions

In addition, in the existing technology, the remaining service life can be predicted by the data-driven method, but this method needs to predict the development of the degradation index before the remaining service life prediction, which leads to the burden of finding a suitable projection model and reduces the remaining service life. Accuracy of Lifetime Prediction

Images