Pattern recognition of partial discharge in XLPE cables using a neural network

This paper describes an experimental study of pattern recognition of partial discharge (PD) in a crosslinked polyethylene (XLPE) cable by using a neural network (NN) system. The NN system was a three-layer artificial neural system with feedforward connections, and its learning method was a backpropagation algorithm incorporating an external teacher signal. Input information for the NN was a combination of the discharge magnitude, the number of pulse counts and the phase angle of applied voltage in which PD is produced. PD measurement was carried out using a PD pulse recorder for a 66 kV XLPE cable with an artificial defect under a 38 kV ac applied voltage. After learning 30 typical input patterns, the NN discriminated unknown patterns with 90% correct responses. The time duration including measuring time required for the NN to discriminate PD signal was 30 s. In a long-term performance test of a 66 kV XLPE cable with an artificial defect, the NN-based alarm processor was able to recognize the presence of PD 1 h before breakdown of the cable, and successfully alerted the operator.