An integration of neural networks and fuzzy logic for power systems diagnosis

The authors present a hybrid AI system, integrating neural networks and fuzzy logic, to be used as an operator´s aid in the diagnosis of faults in power systems and in their training. Once the faults are indicated by the neural network, the fuzzy logic subsystem analyzes the results and gives an explanation for them. The hybrid system can handle single, novel, noisy and multiple faults and is portable to be used in operating systems DOS and UNIX. The authors present, in detail, a case example of a simplified power system generation plant. The results obtained demonstrate that this hybrid system is a very powerful and reliable method for the solution of existing problems in power system fault diagnosis