TY - JOUR
T1 - A data-based comparison of BN-HRA models in assessing human error probability
T2 - An offshore evacuation case study
AU - Abrishami, Shokoufeh
AU - Khakzad, Nima
AU - Hosseini, Seyed Mahmoud
PY - 2020
Y1 - 2020
N2 - Bayesian Network (BN) has been increasingly exploited to improve different aspects of Human Reliability Analysis (HRA), resulting in a new generation of HRA techniques, known as BN-HRA models. However, validating and evaluating the accuracy of BN-HRA models is still a challenging task. In this study, we have assessed and compared the performance of some of well-known BN-HRA techniques using human performance data obtained from an offshore evacuation simulation. Based on the role of data in quantifying the BN-HRA models, three categories of BN-HRA models have been considered: (i) BN-CREAM and BN-SPARH, which are based on predefined rules (rule-based methods), (ii) Bayesian Parameter Learning (BPL), which is entirely based on the available data (data-based method), and (iii) BN-SLIM model which is based on both the available data and the predefined rules (hybrid method). The results of the present study show that the data-based methods, i.e., BN-SLIM and BPL, in general outperform the rule-based methods. Cross-validation analysis further demonstrates the superiority of BN-SLIM over BPL, particularly in case of data scarcity.
AB - Bayesian Network (BN) has been increasingly exploited to improve different aspects of Human Reliability Analysis (HRA), resulting in a new generation of HRA techniques, known as BN-HRA models. However, validating and evaluating the accuracy of BN-HRA models is still a challenging task. In this study, we have assessed and compared the performance of some of well-known BN-HRA techniques using human performance data obtained from an offshore evacuation simulation. Based on the role of data in quantifying the BN-HRA models, three categories of BN-HRA models have been considered: (i) BN-CREAM and BN-SPARH, which are based on predefined rules (rule-based methods), (ii) Bayesian Parameter Learning (BPL), which is entirely based on the available data (data-based method), and (iii) BN-SLIM model which is based on both the available data and the predefined rules (hybrid method). The results of the present study show that the data-based methods, i.e., BN-SLIM and BPL, in general outperform the rule-based methods. Cross-validation analysis further demonstrates the superiority of BN-SLIM over BPL, particularly in case of data scarcity.
KW - Bayesian parameter learning
KW - BN-CREAM
KW - BN-SLIM
KW - BN-SPARH
KW - Human reliability assessment
KW - k-fold cross validation
UR - http://www.scopus.com/inward/record.url?scp=85086631972&partnerID=8YFLogxK
U2 - 10.1016/j.ress.2020.107043
DO - 10.1016/j.ress.2020.107043
M3 - Article
AN - SCOPUS:85086631972
SN - 0951-8320
VL - 202
JO - Reliability Engineering and System Safety
JF - Reliability Engineering and System Safety
M1 - 107043
ER -