Deep Learning-Based Approach for Civil Aircraft Hazard Identification and Prediction

Abstract

Safety is an eternal issue in the civil aviation transportation. Once a civil aviation accident occurs, it will cause great casualties and economic losses. In order to ensure the civil aviation safety, the hazard identification and prediction of civil aircraft should be effectively and accurately realized. The civil aircraft uses Aircraft Communications Addressing and Reporting System (ACARS) to interact with the ground during flight. The data generated by ACARS has a simple structure and strong timeliness. In view of the advantages of ACARS data, a hazard identification and prediction method based on support vector machine optimized by particle swarm optimization (PSO-SVM) and long short term memory (LSTM) neural networks which uses ACARS report as analysis data is proposed. First, in order to reduce the identification and prediction time cost, the SVM-based recursive feature elimination method with cross-validation algorithm (SVM-RFECV) is used to select the characteristic parameters. Then, the SVM optimized by PSO is used to identify hazard based on the selected parameters. According to the identification results, the LSTM is used to predict the trend of the selected parameters to realize hazard prediction. An A13 report of APU generated by ACARS is selected as analysis data for hazard identification and predication in this paper. The analysis results show that the proposed identification method based on PSO-SVM and SVM-RFECV has high identification speed and accuracy. The proposed prediction method based on LSTM has the best prediction performance. The proposed method can effectively identify hazards and accurately predict the trend of parameters to improve the safety of aircraft. INDEX TERMS Aviation safety, hazard identification, hazard prediction, deep learning, long short term memory (LSTM).

E-Pilots: A System to Predict Hard Landing During the Approach Phase of Commercial Flights

“…Although there is a lot of work addressing the prediction of flight landing incidents [9]- [12] and other unsafety situations [13]- [16], the prediction of hard landing accidents have been less researched. Furthermore, most of the existing works focus on the prediction of HL for unmanned aerial vehicles (UAV), which dynamical features and flying protocols are completely different from the ones of commercial flights.…”

Risk identification of civil aviation engine control system based on particle swarm optimization-mean impact value-support vector machine

“…17 The PSO algorithm is adopted to optimize the parameters c and γ of SVM model in order to improve the learning ability and convergence speed of the model. 18…”

“…17 The PSO algorithm is adopted to optimize the parameters c and γ of SVM model in order to improve the learning ability and convergence speed of the model. 18 The PSO algorithm assumes that m particles form a population in a n-dimensional target search space. 19,20 The position of the uth particle in the n-dimensional search space is denoted as x u q ðq ¼ 1; 2,/,nÞ , and the position of each particle is a potential solution.…”

Application of Combination Forecasting Model in Aircraft Failure Rate Forecasting

“…In recent years, with the mature development and application of deep learning methods such as Long short-term memory (LSTM) neural network technology [ 19 ] and convolution neural network (CNN) technology [ 20 ], some researchers have conducted valuable research in the field of aircraft failure rate prediction because of its advantages in data feature extraction. However, the deep learning model has theoretical limitations, resulting in many deficiencies in practical applications, such as large training samples, time-consuming, complex structure, difficult to determine its structural parameters, and premature convergence.…”

“…Regression analysis [1], time series [2,3], mathematical statistics [4], Weibull distribution statistics [5], Bayesian [6] Grey model GM (1, 1) [7][8][9], Verhulst [10] Machine learning model Artificial neural network (ANN) [11], BP neural network [12][13][14], generalized regression neural network (GRNN) [15], support vector machine (SVM) [16], least squares support vector machine (LS-SVM) [17], random forest [18] Deep learning model Long short-term memory (LSTM) [19], convolutional neural network (CNN) [20] Combined model…”