Abstract:

The state of health of an electrical cable may be difficult to know, without destructive or very expensive tests. To overcome this, partial discharge (PD) measurements have been proposed as a relatively economic and simple-to-apply experimental technique for retrieving information on the state of health of an electrical cable. The retrieval is based on a relationship between PD measurements and the health of the cable. Given the difficulties in capturing such relationship by analytical models, empirical modeling techniques based on experimental data have been propounded. In this view, a set of PD measurements have been collected by Enea Ricerca sul Sistema Elettrico-ERSE during past campaigns, for building a diagnostic system of electrical cable health state. These experimental data may contain contradictory information which remarkably reduces the performance of the state classifier, if not a priori identified and possibly corrected. In the present paper, a novel technique based on the Adaboost algorithm is proposed for identifying contradictory PD patterns within an a priori analysis aimed at improving the diagnostic performance. Adaboost is a bootstrap-inspired, ensemble-based algorithm which has been effectively used for addressing classification problems.
Received on March 30, 2010, revised on August 1, 2010
References: 13