Aero-engine residual life prediction method based on data enhancement

Abstract

The invention discloses an aero-engine residual life prediction method based on data enhancement, and provides a multi-path feature fusion network model and a data enhancement algorithm. Firstly, the number of samples of a data set is increased through a data enhancement mode, so that the prediction accuracy is improved; secondly, a multi-path feature fusion prediction model is constructed, and two different paths are selected to extract features: the first path inputs data into a convolutional neural network (CNN) and a gating cycle unit (GRU), and spatial features and time sequence features are extracted respectively; and the second path directly inputs the data into a long short-term memory (LSTM) network to obtain time sequence characteristics. And finally, fusing the output features of the two paths, and inputting the fused output features into a full-connection layer for RUL prediction. Compared with an existing network model, the residual life prediction precision of the equipment can be effectively improved, and the method has practical application value.

Description

technical field [0001] The invention relates to a method for predicting the remaining life of an aero-engine, in particular to a method for predicting the remaining life of an aero-engine based on data enhancement and a multi-path feature fusion model. Background technique [0002] Turbofan engine, as the "heart" of various aircraft systems in the aviation field, its performance changes can directly affect the safe operation of the aircraft. However, due to the daily work of aviation turbofan engines in the environment of high temperature, high pressure and high vibration speed, accidents and failures are prone to occur with the increase of working time. Therefore, it is of great significance to predict the remaining life (RUL) of aviation turbofan engines and change the regular maintenance to active maintenance for reducing flight safety accidents and saving equipment maintenance costs. [0003] At present, the remaining life prediction methods can be roughly divided into ...

AI Technical Summary

Problems solved by technology

Most of the existing deep learning models are based on a single model, which cannot mine and comprehensively consider various features, and the generalization performance is poor.

In addition, in terms of degradation data, there are few existing performance degradation data sets, which cannot meet the needs of deep learning models for a large amount of training data, making the accuracy of existing deep learning life prediction models low

Images