New Type of Aeronautical Risk Assessment: Performance of Kohonen SelfOrganizing Maps in Identifying Brazilian Aircraft with Greater Associated Risks

The purpose of this paper is to present a new way assessing aeronautical risk using configuration Kohonen Self-Organizing Maps (SOM) identify the Brazilian aircrafts more likely be involved in accidents and riskiest aircrafts. technique described classified as predictive for managing risks, according DOC 9859, can used both context prevention investigation accidents/incidents, well insurance industry. Using technique, it was possible 147 aircraft with highest associated probabilities occurrence accidents, 180 risks. Five years after identification, respective percentages accidents/incidents were 34% 27%. application help achieve objective community determining what, where, when next and/or incidents will occur. Another aspect work demonstrate that data collected by national civil aviation agency Brazil implement methodology management safety aviation.