Unsupervised High Impedance Fault Detection Using Autoencoder and Principal Component Analysis

TL;DR

This work tackles the challenge of detecting high impedance faults in power distribution networks, where low fault currents hinder traditional protection. It proposes an unsupervised framework that combines an autoencoder (AE) with principal component analysis (PCA) to monitor changes in the correlation structure of current waveforms from a single location, avoiding the need for labeled fault data. By augmenting univariate current measurements into a multivariate data matrix, the AE extracts nonlinear correlations, and PCA analyzes reconstruction-error residuals to establish robust fault-detection thresholds via $T^2$, SPE, and the combined index $\varphi$. Real-world experiments on a 4.16 kV feeder show that AE+PCA detects more HIF events than a commercial solution while maintaining zero false alarms on normal loads, highlighting its practical impact for grid protection and reliability.

Abstract

Detection of high impedance faults (HIF) has been one of the biggest challenges in the power distribution network. The low current magnitude and diverse characteristics of HIFs make them difficult to be detected by over-current relays. Recently, data-driven methods based on machine learning models are gaining popularity in HIF detection due to their capability to learn complex patterns from data. Most machine learning-based detection methods adopt supervised learning techniques to distinguish HIFs from normal load conditions by performing classifications, which rely on a large amount of data collected during HIF. However, measurements of HIF are difficult to acquire in the real world. As a result, the reliability and generalization of the classification methods are limited when the load profiles and faults are not present in the training data. Consequently, this paper proposes an unsupervised HIF detection framework using the autoencoder and principal component analysis-based monitoring techniques. The proposed fault detection method detects the HIF by monitoring the changes in correlation structure within the current waveforms that are different from the 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 that the proposed method outperforms the commercially available HIF detection technique while maintaining high security by not falsely detecting during load conditions.

Figures (7)

• Figure 1: Workflow of the proposed HIF detection method.
• Figure 2: RMS currents of normal load.
• Figure 3: Current waveform of the normal load and the waveform during the HIF.
• Figure 4: Detection result of normal load.
• Figure 5: Detection result of HIF on grass.