Fault detection and classification of an HVDC transmission line using a heterogenous multi‐machine learning algorithm

Abstract

This paper presents a novel integrated multi-Machine Learning (ML) system architecture for the protection of bipolar HVDC transmission line in which different ML models of Support Vector Machine (SVM) and K-Nearest Neighbours (KNN) are used for fault detection and classification. The KNN fault type classifier is designed as a dual-purpose module, which not only detects the fault type but also acts as a redundant module for unsure fault declaration from the startup unit. Gradients and standard deviations of DC current, voltage, harmonic current, and a correlation coefficient between the aerial and zero modes of DC current are appropriate feature vector extracted from single-end signal measurement. Overall, 154 training cases and 53 main test cases are obtained by simulating various fault and non-fault states on a ±650 kV-1000 km Current Source Converter (CSC)-HVDC using an EMTDC/PSCAD platform. The ML modules are trained in MATLAB and tested under different severe conditions with a total of 2220 test cases. Thanks to the appropriate feature vector and the proposed system architecture, the obtained results show that the proposed algorithm is effective enough to detect and distinguish a variety of internal faults and pseudo-faults/external faults. Also, it needs low training data requirements.

Design of automatic up-and-down system of transmission line hardware crimping quality inspection robot

“…The improved S-shaped trajectory planning method ensures that the planned path distance is shortest, and when the robot encounters obstacles, the software system can quickly plan the turning path and effectively avoid obstacles [8][9] .…”

Heterogeneous Multi-ml Approach Implemented in Hvdc Transmission Line

“…The given method makes no direct use of threshold values, and the classification and detection procedure is determined by the similarity of standard deviations and gradients among query samples' signals and training examples. [3] Also there are some different techniques in different papers that use one algorithm but are not giving better results than this heterogeneous algorithm.…”

“…Through the proposed system design, this innovative combination of two separate machine learning models is a fresh start and contribution to machine learning to give solutions for power system challenges. [3] The second solution is to use ANN to detect transmission line faults. Because it is a programming approach capable of solving problems (linear or nonlinear), artificial neural networks (ANN) may be used efficiently for defect classification and detection.…”

Calculated DC resistance‐based pilot protection scheme for bipolar high‐voltage direct current transmission lines

“…Compared with the HVAC technology, the high-voltage direct current (HVDC) technology is evaluated as a preferential choice for long-distance asynchronous systems connection and largepower transmission. It has many advantages such as lower power loss, higher operational reliability and better power control flexibility etc [1][2][3]. The line protection scheme is expected to reduce the forced outage hours for each DC system, promoting the stability and reliability of power systems.…”