A multiphase dynamic Bayesian networks methodology for the determination of safety integrity levels

A novel safety integrity levels (SILs) determination methodology based on multiphase dynamic Bayesian networks (MDBNs) for safety instrumented systems is proposed. Proof test interval phase and proof test phase are modeled separately using dynamic Bayesian networks, and integrated together to form the MDBNs. The unified structure models of MDBNs for k-out-of-n architectures are constructed, and the procedures of automatic creation of conditional probability tables are developed. The target failure measures, that is, probability of failure on demand, average probability of failure on demand, probability of failing safely, average probability of failing safely, and SIL of safety instrumented systems operating in a low demand mode, are evaluated using the proposed MDBNs. The effects of time interval of MDBNs, common cause weight, imperfect proof test and repair on model precision are researched. User-friendly SIL determination software is developed by using MATLAB GUI to assist engineers in determining the SIL value. (C) 2016 Elsevier Ltd. All rights reserved.