This paper proposes a dynamic economic risk analysis methodology for process systems. The Bayesian Tree Augmented Naïve Bayes (TAN) algorithm is applied to model the precise and concise probabilistic dependencies that exist among key operational process variables to detect faults and predict the time dependent probability of system deviation. The modified inverted normal loss function is used to define system economic losses as a function of process deviation. The time dependent probability of system deviation owing to an abnormal event is constantly updated based on the present state of the relevant process variables. The integration of real time probability of system deviation with potential losses provides the risk profile of the system at any instant. This risk profile can be used as the basis for operational decision making and also to activate the emergency safety system. The proposed methodology is tested and verified using the Richmond refinery accident.
- Dynamic failure prediction
- Economic consequences
- Loss functions
- Process safety
- Structure learning of Bayesian network from data and risk analysis