A Framework for Fault Diagnosis using Continuous Bayesian Network and Causal Inference

Fault diagnosis in industrial facilities has traditionally been done using rule-based approaches, heuristics or expert-knowledge. Bayesian network provides a flexible and data-driven alternative that can reason under uncertainty. Most of the data being generated by sensors in industrial setups are continuous and the underlying data-generating models are essentially non-linear. This paper employs Bayesian network and proposes a framework that learns parameters of probability density functions of a continuous Bayesian network using neural network/s without requiring assumption of linear Gaussian model or discretization of continuous data. Moreover, an expression of probability query using learned parametric density functions and causal-inference based mathematical formulation of two tasks related to fault diagnosis –in the context of industrial plants– namely root-cause-analysis and identification of most-influential-path in Bayesian network have been provided.