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.

Modern industrial processes are highly instrumented with more frequent recording of data. This provides abundant data for safety analysis; however, these data resources have not been well used. This paper presents an integrated dynamic failure prediction analysis approach using principal component analysis (PCA) and the Bayesian network (BN). The key process variables that contribute the most to process performance variations are detected with PCA, while the Bayesian network is adopted to model the interactions among these variables to detect faults and predict the time-dependent probability of system failure. The proposed integrated approach uses big data analysis. The structure of BN is learned using past historical data. The developed BN is used to detect faults and estimate system failure risk. The risk is updated subsequently as new process information is collected. The updated risk is used as a decision-making parameter. The proposed approach is validated through a case of a crude oil distillation unit operation. (Figure Presented).

Complex and non-linear relationships exist among process variables in a process operation. Owing to these complex and non-linear relationships potential accident modelling using an analytical technique is proving to be not very effective. The artificial neural network (ANN) is a powerful computational tool that assists in modelling complex and nonlinear relationships. This relationship has good potential to be generalized and used for subsequent failure analysis. This paper integrates ANNs with probabilistic analysis to model a process accident. A multi-layer perceptron (MLP) is used to define the relationship among process variables. The defined relationship is used to model a process accident considering logical and casual dependence of the variables. The predicted accident probability is subsequently used to estimate the likelihoods of failure to the process unit. A backward propagation technique is used to dynamically update the variable states and the failure probabilities accordingly. Integrating ANN with a probabilistic approach provides an efficient and effective way to estimate process accident probability as a function of time and thus the risk can be easily predicted upon quantifying the damage. The updating mechanism of the approach makes the model adaptive and captures evolving process conditions. The proposed integrated approach is applied to the Tennessee process system as a case study.

With the increasing complexity of the hazardous process operation, potential accident modelling is becoming challenging. In process operation accidents, causation is a function of nonlinear interactions of various factors. Traditional accident models such as the fault tree represent cause and effect relationships without considering the dependency and nonlinear interaction of the causal factors. This paper presents a new non-sequential barrier-based process accident model. The model uses both fault and event tree analysis to study the cause-consequence relationship. The dependencies and nonlinear interaction among failure causes are modelled using a Bayesian network (BN) with various relaxation strategies. The proposed model considers six prevention barriers in the accident causation process: design error, operational failure, equipment failure, human failure and external factor prevention barriers. Each barrier is modelled using BN and the interactions within the barrier are also modelled using BN. The proposed model estimates the lower and upper bounds of prevention barriers failure probabilities, considering dependencies and non-linear interaction among causal factors. Based on these failure probabilities, the model predicts the lower and upper bounds of the process accident causation probability. The proposed accident model is tested on a real life case study.