PURPOSE: The probability of being injured or killed from occupational incident is much higher than process mishap in the oil and gas industry. The aim of this study was to establish a model for predicting the probability of occupational fall incident using Bayesian networks.
METHODS: The study was performed in a selected number of oil refineries. Bayesian network variables (n = 18) were identified using literature as well as expert knowledge. These contributing factors were categorized in four layers (organizational, supervisory, preconditions, and unsafe acts) according to the Swiss cheese model. Causal relationships among contributing factors were determined by using expert judgment in combination with Dempster-Shafer theory. The conditional probability table of each contributing factor was measured using a questionnaire.
RESULTS: Prior probability of fall event was 5.34% (53 cases per 1000 operational workers in 12-month). The posterior probability predicted that using fall protection devices and safe working platform will decrease more than half (58%) of fall occupational incidents.
CONCLUSION: Bayesian Network's features including graphical representation, easy belief updating, performance testing, and sensitivity analysis facilitate the process of predicting occupational incident probability including fall events. Proposed approach is a step toward quantitative risk analysis of occupational incidents.
Language: en
Keywords
Bayesian network; Fall incident; Incident prediction; Oil industry