Flight control system data prediction and auxiliary diagnosis method based on LSTM neural network

Abstract

The invention belongs to the technical field of flight control data processing, and relates to a flight control system data prediction and auxiliary diagnosis method based on an LSTM neural network. The method provided by the invention mainly comprises the steps that multi-dimensional key data of a flight control system are extracted; a preset time period is a time series consisting of a number of time intervals of the same time step; based on the data of flight control within the preset time period, standardization processing is carried out to generate a flight control data vector group corresponding to each time interval; the generated time series data vector group is input into the LSTM neural network for training, so that the LSTM neural network learns from the data and acquires analysis and processing capability for the data; and finally, a new predictive data vector group is input to the trained LSTM neural network, and the flight control data are analyzed and processed to predict the future value of the key data of the flight control system and assist in fault diagnosis.

Description

technical field [0001] The invention belongs to the technical field of flight control data processing, and relates to a data prediction and auxiliary diagnosis method of a flight control system based on an LSTM neural network. Background technique [0002] The structure of the aircraft is complex and there are many parts, any failure of a tiny part may lead to an irreparable accident. Therefore, data prediction and fault diagnosis of flight control system are very important for flight safety. The traditional data prediction method of the flight control system is manual analysis, that is, the maintenance personnel perform health assessment and fault diagnosis on the flight control system. However, the flight control system receives and stores the sensor data of various parts of the aircraft, and various data are correlated and coupled, which must be analyzed by experienced maintenance experts, and it takes a long time to meet the current maintenance needs of multiple sorties...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a flight control system data prediction and auxiliary diagnosis method based on LSTM neural network, to solve the problem of relying on expert experience and analysis consumption in the existing method mentioned in the above background technology to process complex coupled multi-dimensional data of the flight control system. long time, unsatisfactory forecasting effect, etc.

The invention adopts the method of deep learning, and uses the powerful computing power of the computer to analyze the complex coupled multi-dimensional data of the flight control system, which can better solve the problems of traditional methods relying on expert experience, time-consuming analysis, and unsatisfactory prediction results.

Images