Bayes Theorem, Causality and Building Blocks for Bayesian Networks
G. Unnikrishnan · 2020
This chapter covers the basics of probability, Bayes Theorem and the nature of causality. It introduces the application of the Bayes Theorem to cause and effect and thereby the understanding of incidents and accidents. A Bayesian Networks (BN) is a directed acyclic graph in which the nodes represent the system variables and the arcs symbolize the dependencies or the cause–effect relationships among the variables. The BN basically describes the joint probabilities of the events and can be used for several types of analysis. Sensitivity to findings uses two types of measures: entropy reduction or mutual information for discrete variables and variance reduction for continuous variables. Oil and separator, atmospheric hydrocarbon storage tanks and hydrocarbon pipelines have Loss Of Containment (LOC) scenarios that can lead to high consequence accidents. LOC of the compressor itself is very rare, and therefore damage is considered as a major hazard for compressor.