Research on Civil Aviation Passenger Transportation Accident Symptoms Based on Deep Learning

Abstract

Abstract In the process of civil aviation safety production, countries and organizations have unified the establishment of a mandatory accident reporting system. In addition, in order to prevent aviation accidents and accident symptoms to the maximum extent, and to obtain as detailed information as possible in the first time when accidents, accident symptoms and other civil aviation unsafe incidents occur, Countries and organizations should also establish a non-punitive voluntary aviation incident reporting system to complement this. NASA in the 1970s began to establish the aviation voluntary reporting system, the system ASRS later became the world’s first implementation of the aviation safety voluntary reporting system. This paper is a comprehensive study on the voluntary reporting system for civil aviation safety. By using data mining technology, the 6W structured expression model of aviation safety accident report is established on the basis of ASRS system for aviation safety accident report, and the information of different dimensions and different data structures is studied completely and systematically. According to the data types in the 6W structured representation model, two data mining methods of multi-dimension analysis and text classification are selected.