Human Factor Quantitative Analysis Based on OHFAM and Bayesian Network

Abstract

Occurrence Human Factors Analysis Model is developed for China civil aviation based on the Human Factors Analysis and Classification System (HFACS) and the actual operation conditions and characteristics of China civil aviation to enhance the classification, analysis and utilization of safety information. In addition, to generate a model which can provides quantitative analysis supportive in aviation incident analysis, a human factor analysis model based on OHFAM and Bayesian network is established. This model constructed by combing hill-climbing search method with CH score function is a Bayesian network which uses three layers nodes to represent causality between human factors and incidents. The specific impact degree of human factors on aviation incidents is represented by conditional probability parameters of the model. It is useful in aviation incident analyses and deductions. © Springer International Publishing Switzerland 2014.