A neural net based approach for fault diagnosis in distribution networks

This paper discusses the application of field data to a new supervised clustering-based arcing distribution fault diagnosis method. The fault diagnosis method can perform three functions that provide preliminary fault location information for grounded and ungrounded power distribution systems: fault detection, faulted type classification, and faulted phase identification. It contains two main modules: a preprocessor and a pattern classifier which was implemented as a supervised clustering-based neural net. The inputs to the fault diagnosis method are the three phase and neutral currents for a feeder. The preprocessor computes a vector of statistical features from the phase currents and passes them to the neural net pattern classifier. The neural net determines the features pattern as normal or faulted. If detected as faulted, the neural net also identifies the fault type and classifies the faulted phase. Field studies were conducted in which the fault diagnosis method was trained and tested with normal and faulted phase currents generated from data recorded by events staged in the field for two, four-wire systems. The fault diagnosis method was highly successful during tests to validate the fault detection and identification functions. Also the fault diagnosis method was able to recognize the difference between faulted test patterns and fault-like test patterns representing line switching and load tap changer operations. Further the clustering-based fault diagnosis approach was evaluated using simulated data generated for a 3-feeder ungrounded system