Setting up new standards in aviation industry with the help of artificial intelligent – machine learning application

Abstract

In these times, dominated by innovation, technology is an important asset in optimizing maintenance, aircraft operations and even the investigation process of aviation accidents, with unprecedented results so far. All the information related to an aircraft, generated over time, can be included in a database, in order to be analyzed for better technical insights. The same approach can be applied in analyzing evidence and reports generated after an aircraft accident occurred. Aircraft investigation involves tones of hard-working hours and evidence analysis. This research aims to identify a new tool to improve the investigation process of aircraft incidents caused by human factors errors. Using artificial intelligence to process the resulted evidence during the aircraft accidents investigation, will shed light on the root cause of the incident much faster. Accelerating an investigation means huge benefits for all parties involved. In this sense, a proof-of-concept software has been developed to emphasize the power of artificial intelligent in the aircraft accidents investigation. Using machine learning algorithms, a program was trained with data, to develop an application capable of automatically determining the root cause of an accident based on witness statements. All data was derived from the Aviation Safety Reporting System database from the U.S, which was queried for incidents, occurred between 2000 and 2020. This application is not only about automating a stage in an aircraft accident investigation, is rather about setting up new standards in aviation industry with the help of artificial intelligence.