An approach to power distribution fault diagnosis using a neural net based supervised clustering methodology

This paper discusses the use of a new neural network supervised clustering method to perform fault diagnosis for power distribution networks. The neural network performs fault type classification, faulted feeder and faulted phase identification, and fault impedance estimation for grounded and ungrounded distribution networks. These fault diagnosis decisions are performed on a feeder by feeder basis. The theoretical development of the neural net is presented. Also the effectiveness of the method is demonstrated using data generated by a fault simulation program specially designed to facilitate sensitivity studies of distribution systems. This work represents the first time a supervised clustering neural net has been used for distribution fault diagnosis.

An approach to power distribution fault diagnosis using a neural net based supervised clustering methodology Academic Article