Civil Aircraft Hard Landing Prediction Based on PSO-ARIMA Model

The hard landing incident seriously affects the safety of the aircraft during the landing phase. In this paper, a hard landing prediction model is proposed, which is improved based on the Autoregressive Integrated Moving Average Model (ARIMA) using the Particle Swarm Optimization (PSO) algorithm. In comparison to the ARIMA model, introducing the PSO algorithm can find the optimum combination of parameters for the model and improve the prediction accuracy. For the vertical acceleration series during the landing intervals, the stationarity test and white noise test of the data are performed to determine the applicability of the ARIMA model. The PSO algorithm with a targeted fitness function to determine the model order. The results of the experiments show that PSO-ARIMA model is better than the ARIMA model in terms of Mean Square Error (MSE), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), with 34.38%, 22.12% and 23.94% descent, respectively.