On-line fault diagnosis of distribution substations using hybrid cause-effect network and fuzzy rule-based method

A correct and rapid inference is required for practical use of an on-line f ault diagnosis in power substations. This paper proposes a novel approach f or on-line fault section estimations and fault types identification using t he hybrid cause-effect network/fuzzy rule-based method in distribution subs tations. A cause-effect network, which is well suited to parallel processin g, represents the functions of protective relays and circuit breakers for s election of faulted sections. Therefore the inference speed can be improved significantly In order to deal with the uncertainties involved in the proc ess of clarifying faults, a fuzzy rule-based method is derived. The propose d approach has been practically verified by testing on a typical Taiwan Pow er Company's (Taipower) secondary substation. The experimental results reve al that the correct and rapid diagnosis is obtained even for the fault doma ins involving multiple faults and failure operations of protective devices. Moreover, it is easy to implement and transplant into different substation s.