Fault diagnosis of electrical power systems using soft computing
- Additional Document Info
- View All
Monitoring of electric power systems is particularly challenging due to the presence of dynamic load changes of network nodes, as well as the presence of both continuous and discrete variables, noisy information and lack of data. The need to develop more powerful approaches has been recognized, and hybrid techniques that combine several reasoning methods start to be used. A fault diagnosis framework that is able to locate the set of nodes involved in multiple fault events is proposed. A methodology based on the system history data combining an AutoAssociative Neural Network (AANN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS) detects faulty nodes, type of faults and time when the faults appear. © 2013 IFAC.