Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Low Impedance Fault Identification and Classification Based on Boltzmann Machine Learning for HVDC Transmission Systems
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.
Low Impedance Fault Identification and Classification Based on Boltzmann Machine Learning for HVDC Transmission Systems
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.
Low Impedance Fault Identification and Classification Based on Boltzmann Machine Learning for HVDC Transmission Systems
Raheel Muzzammel (Autor:in) / Ali Raza (Autor:in)
2022
Aufsatz (Zeitschrift)
Elektronische Ressource
Unbekannt
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 , Production of electric energy or power. Powerplants. Central stations , TK1001-1841 , Renewable energy sources , TJ807-830
Metadata by DOAJ is licensed under CC BY-SA 1.0
Virtual Difference Voltage Scheme for Fault Detection in VSC-HVDC Transmission Systems
| DOAJ | 2020
AC fault ride through control strategy on inverter side of hybrid HVDC transmission systems
| DOAJ | 2019