Knowledge representation and uncertainty management: applying Bayesian belief networks to a safety assessment expert system
Baofeng Guo · 2004
We discuss knowledge representation and uncertainty management based on Bayesian belief networks (BBNs). Firstly, we carry out an investigation to the identified problems that occurs during applying safety standards. We conclude that most of these problems originate from the uncertainty nature in safety assessment. Then we provide an in-depth argument to explain why BBNs can deal with these problems, and offer an efficient approach for knowledge representation and uncertainty management for safety assessment. Finally, we present a BBN-based decision-supporting expert system that can be used to assess the implementing quality of overall safety requirement within safety standard IEC 61508. This BBN prototype is based on a systematic identification of failure modes, and modelling of their impacts on the final systems. Other phases of safety-related systems development life cycles are particularly appropriate candidates for this type of analysis.