Aero-engine life prediction method based on long-term and short-term memory network

Abstract

The invention discloses an aero-engine life prediction method based on a long-term and short-term memory network. The method comprises the steps of dividing the historical data of an engine into a training set, a test set and a verification set; adding a residual life label to each period of the aero-engine in the training set and carrying out preprocessing; designing and training an aero-engine residual life model based on a convolutional neural network and a long short-term memory network; putting the data of the test set into a trained model to obtain an MAE value and an MSE value of the test set in model training; comparing the residual life label obtained in the test set with a real residual life data set to obtain corresponding goodness of fit verification prediction accuracy and feasibility of the method; and packaging the model with the highest accuracy into a computing unit, and visualizing a prediction result. The neural network provided by the invention is high in portability, high in prediction speed and high in prediction precision, the prediction process and result can be completely visualized, and the operation is convenient and simple.

Description

technical field [0001] The invention belongs to the technical field, and in particular relates to an aero-engine life prediction method based on a long-short-term memory network. Background technique [0002] As the core component of the aircraft, the stability and reliability of the aero-engine directly determine the safety performance of the aircraft. Therefore, the engine must be carefully inspected and repaired before each aircraft takes off, but this maintenance method undoubtedly increases the operating cost of the airline to a certain extent. [0003] In order to ensure that the aircraft can fly safely and reduce the maintenance cost of the aircraft, the British CAA proposed Prognostics and Health Management (PHM) in the 1880s. The remaining useful life (Remaining Useful Life, RUL) is defined as the time period from the current point to the failure of the device. If the remaining life of the aero-engine can be predicted in advance and accurately, reasonable maintena...

AI Technical Summary

Problems solved by technology

With the rapid development of deep learning, the accuracy of these traditional life prediction methods can no longer meet the needs of people in some fields.

Images