Research on Aviation Safety Prediction Based on Multivariate Grey Model Optimized by Genetic Algorithm

Considered that the causal mechanism of aviation accidents is complex and has many causal factors with strong grey characteristics, while the traditional grey prediction model is only applicable to single variable and has low accuracy, a new method of aviation safety prediction is proposed based on a multivariate grey model optimized by genetic algorithm. Firstly, the SHEL analysis model is used to determine the causes of aviation safety and and further screening for key causal factors. Secondly, a multivariate grey MGM(1, n, GA(r)) aviation safety prediction model is constructed by taking human factors, environmental factors, equipment and facilities factors, external influencing factors, and forced reporting events as the research objects, and genetic algorithm is used to search the optimal solution of grey model parameters. Finally, the simulation example shows that the proposed method is more applicable and has higher prediction accuracy and advantages in aviation safety short time prediction than the traditional grey model.