Fault Location Detection in Underground Cables based on Wavelet-ANFIS Approach

Abstract

Due to the difficulties experienced in identifying the exact location of underground cable faults, it is therefore evident that there is a need to employ optimal methods that will have the capability to swiftly identify the fault location and henceforth reduce the downtime of the system. This paper presents a study that combines both Wavelet Transform and Adaptive Neuro-Fuzzy Inference System (ANFIS) technique for fault location in underground cables. A 9 km, 11 kV, 50 Hz transmission line was developed, and a single line to ground fault was simulated at different line locations. The wavelet transform was used to extract noteworthy features that were subsequently utilised as inputs for training and testing the Adaptive Neuro-Fuzzy Inference System (ANFIS). The results obtained from the ANFIS were compared with the actual simulated test values. From the results obtained, the technique was able to achieve a 99.94% accuracy in fault location.