ARIMA Model-based Safety Risk Prediction for an Aircraft Type

In order to study the safety of aviation operations, an ARIMA model was often used to forecast the safe operation of a certain type of aircraft. Based on the event type, number of events, event level, flight time and number of takeoffs and landings, a risk value prediction index system was established and the risk situation was predicted by time series analysis. The risk values and time were selected for statistical analysis, and an autoregressive moving average model (ARIMA) was constructed. Smoothness tests, white noise tests, identification and ranking of the model, diagnostic tests and parameter estimation were performed, and the ARIMA(1,1,2) model was finally constructed. The results show that the model fits the historical series of risk better and obtains good prediction accuracy. The short-term (7 months) prediction value of the model is generally consistent with the risk variation trend of this type of aircraft, and the prediction accuracy is acceptable. The study can provide data basis for airline safety operation trend analysis and judgment, and can also help airlines to develop targeted risk prevention and control plans.