Deep Learning-Based Robust DC Fault Protection Scheme for Meshed HVDC Grids

作     者：Muhammad Zain Yousaf Hui Liu Ali Raza Ali Mustafa Muhammad Zain Yousaf;Hui Liu;Ali Raza;Ali Mustafa

作者机构：the School of Electrical EngineeringGuangxi UniversityNanning 530004China the School of Electrical EngineeringUniversity of LahoreLahore 39161Pakistan the School of Electrical EngineeringXi’an Jiaotong UniversityXi’an 710049China 

出 版 物：《CSEE Journal of Power and Energy Systems》 (中国电机工程学会电力与能源系统学报（英文）)

年 卷 期：2023年第9卷第6期

页      面：2423-2434页

核心收录：

学科分类：080802[工学-电力系统及其自动化] 0808[工学-电气工程] 08[工学] 

基　　金：the National Natural Science Foundation of China under Grant 51977041 

主　　题：High voltage direct current(HVDC) longshort-term-memory(LSTM) primary protection voltage source converters(VSC) 

摘      要：Fast and reliable detection of faults is a significant technical challenge in transient-based protection for a modular multi-level converter(MMC)based high voltage direct current(HVDC)*** is because existing protection schemes rely heavily upon setting a complicated protective threshold,the failure of which causes high DC-fault currents in HVDC grids,and MMC is prone to such strong transient *** this context,this paper proposes a DC-line fault diagnosis technique based on a tuned long-short-term memory(LSTM)algorithm to improve the response and accuracy of transient-based *** discrete wavelet transform(DWT)extracts the transient features of DC-line voltages in the frequency-time *** healthy and faulty samples are incorporated during training even by considering the noise *** training,numerous test samples are run to evaluate the proposed algorithm’s robustness under various fault *** results show the proposed algorithm can detect DC faults and has a high recognition accuracy of 98.6%.Compared to contemporary techniques,it can perform well to identify DC-line faults because of the efficient training of characteristic features.