Low Impedance Fault Identification and Classification Based on Boltzmann Machine Learning for HVDC Transmission Systems

Abstract

Identification and classification of DC faults are considered as fundamentals of DC grid protection. A sudden rise of DC fault current must be identified and classified to immediately operate the corresponding interrupting mechanism. In this paper, the Boltzmann machine learning (BML) approach is proposed for identification and classification of DC faults using travelling waves generated at fault point in voltage source converter based high-voltage direct current (VSC-HVDC) transmission system. An unsupervised way of feature extraction is performed on the frequency spectrum of the travelling waves. Binomial class logistic regression (BCLR) classifies the HVDC transmission system into faulty and healthy states. The proposed technique reduces the time for fault identification and classification because of reduced tagged data with few characteristics. Therefore, the faults near or at converter stations are readily identified and classified. The performance of the proposed technique is assessed via simulations developed in MATLAB/Simulink and tested for pre-fault and post-fault data both at VSC1 and VSC2, respectively. Moreover, the proposed technique is supported by analyzing the root mean square error to show practicality and realization with reduced computations.

Keywords

• Binary class logistic regression (BCLR)
• Boltzmann machine learning (BML)
• DC grid protection
• fault identification and classification
• voltage source converter based high-voltage direct current (VSC-HVDC) transmission system