An integrated approach for real-time hazard mitigation in complex industrial processes

Modern engineering systems give paramount importance to safety in order to avoid or mitigate hazardous accidents which can lead to huge economic losses, environmental contamination, and human injuries. This paper proposes an integrated approach that uses both Hidden Markov Model and Bayesian Network to estimate an optimum safety-threshold for complex industrial processes. In order to estimate the safety threshold, the proposed approach considers different cost factors and the joint probabilities of multiple process variables leading to an accident. In addition to the system level threshold, it also estimates the safety-threshold for components. This helps in identifying the component that needs maintenance to enhance system performance and safety. Furthermore, it proposes a dynamic risk assessment methodology based on multiple real-time process variables. The optimum safety-thresholds are estimated using Genetic Algorithm which aims at minimizing the system running cost over a finite time horizon. A case study on Tennessee Eastman Chemical Process is presented to demonstrate the proposed methodology for optimizing process safety-threshold.