Fault diagnosis of micro energy grids using Bayesian belief network and adaptive neuro-fuzzy interference system

Abstract

Safety assessment of complex systems such as micro energy grids has lately become an interesting open research field. In this article, fault diagnosis for a micro energy grid in the occurrence of incomplete data and expert knowledge is discussed. A hybrid technique of Bayesian belief networks and adaptive-network-based fuzzy inference system is proposed for fault diagnosis and safety assessment of micro energy grid under uncertainty conditions and incomplete system's information. Merging adaptive-network-based fuzzy inference system with Bayesian belief networks contributes to a reduction of the information required for micro energy grid fault diagnosis when compared with each method separately. Where each method has different capability on capturing safety related information. The proposed hybrid approach helps operation crew to make the optimum decision. The approach depends on expert's knowledge more than the data from instrumentation and control system. The demonstrative example of a micro energy grids safety assessment is validated in this study.