Unsupervised High Impedance Fault Detection Using Autoencoder and Principal Component Analysis

Detection of high impedance faults (HIFs) in power distribution networks remains a challenging task. Due to the low current magnitude and diverse characteristics of HIFs, conventional over-current relays are ineffective in detecting such faults. Machine learning-based methods have emerged as a promising solution, but most rely on supervised learning techniques to detect HIF by performing classifications that require a significant amount of HIF data that are difficult to acquire in the real world. As a result, the reliability and generalization of these models are limited when the load profiles and faults are not present in the training data. In this paper, we propose an unsupervised HIF detection framework that employs autoencoder and principal component analysis-based monitoring techniques to identify changes in the correlation structure within the current waveforms that deviate from normal loads. The performance of the proposed HIF detection method is tested using real data collected from a 4.16 kV distribution system and compared with results from a commercially available solution for HIF detection. The numerical results demonstrate the superiority of our proposed method over the commercially available HIF detection technique while ensuring high security by avoiding false detections during normal load conditions.