Tuning of fault semantic network using Bayesian theory for probabilistic fault diagnosis in process industry

Investigating complex interaction patterns among multiple process variables (PVs) is an important task for fault propagation analysis and calculation of final risks. This paper demonstrates a robust method to estimate interaction strengths among process variables. The method is based on dynamic fault semantic networks (FSN) combined with Bayesian belief theory for probabilistic tuning of the fault semantic network. The effectiveness and feasibility of the proposed technique is verified on simulated data emanating from Tennessee Eastman (TE) process. The extracted patterns of interaction structure among PVs aid to uncover the polishing mechanisms and provide more insights to investigate fault propagation scenarios.