Removal of Interference in Partial Discharge Signals Using Type 2 Fuzzy Logic Controller

A frequent investigative method for judging the state of insulation in high-voltage equipment is the partial discharge (PD) test. External interference frequently adversely the measured PD signals. The type-2 fuzzy inference system (FIS) tuned with particle swarm optimization (PSO), an artificial intelligence (AI) technology, is used to de-noise the PD signals in this study. By using PSO, upper and lower membership function parameters are tuned automatically. The proposed method's statistical metrics- Compared to the Fast Fourier Transform and Wavelet Transform-are determined, including the signal-to-noise ratio, cross-correlation coefficient, pulse amplitude distortion, mean square error, and noise level reduction. Compared to the genetic algorithm and PSO, the type-2 FIS algorithm performs better than the others in terms of durability and computational cost.