Characterization of underground cable incipient behavior using time-frequency multi-resolution analysis and artificial neural networks

This paper presents preliminary work of a research project with a long-term goal to develop an on-line, non-destructive underground cable monitoring system that can not only detect incipient faults but also predict the remaining life of the cable lateral. The results presented in this paper help identify and characterize possible incipient faults occurring in underground cable laterals being monitored on-line. In this paper, two experimental setups designed and deployed for on-line monitoring of underground cable lateral to record data are presented. An analysis procedure of the recorded data implementing a time-frequency multi-resolution technique is presented. The results of using an artificial neural network for pattern identification of the recorded data are also presented.