Detection and classification of micro‐grid faults based on HHT and machine learning techniques

Abstract

This study presents a novel micro‐grid protection scheme based on Hilbert–Huang transform (HHT) and machine learning techniques. Initialisation of the proposed approach is done by extracting the three‐phase current signals at the targeted buses of different feeders. The obtained non‐stationary signals are passed through the empirical mode decomposition method to extract different intrinsic mode functions (IMFs). In the next step using HHT to the selected IMFs component, different needful differential features are computed. The extracted features are further used as an input vector to the machine learning models to classify the fault events. The proposed micro‐grid protection scheme is tested for different protection scenarios, such as the type of fault (symmetrical, asymmetrical and high impedance fault), micro‐grid structure (radial and mesh) and mode of operation (islanded and grid connected) and so on. Three different machine learning models are tested and compared in this framework: Naive Bayes classifier, support vector machine and extreme learning machine. The extensive simulated results from a standard IEC micro‐grid model prove the effectiveness and reliability of the proposed micro‐grid protection scheme.