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

Muhammad Zain Yousaf; Hui Liu; Ali Raza; Ali Mustafa

doi:10.17775/CSEEJPES.2021.03550

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

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

Regular Papers | 更新时间：2026-10-15

- Deep Learning-Based Robust DC Fault Protection Scheme for Meshed HVDC Grids
- CSEE Journal of Power and Energy Systems Vol. 9, Issue 6, Pages: 2423-2434(2023)
- 作者机构：
  
  1. School of Electrical Engineering, Guangxi University,Nanning,China
  2. School of Electrical Engineering, University of Lahore,Lahore,Pakistan
  3. School of Electrical Engineering, Xi'an Jiaotong University,Xi'an,China
- 作者简介：
- 基金信息：
- DOI：10.17775/CSEEJPES.2021.03550
  CLC：
- Published：01 November 2023
- 稿件说明：
移动端阅览
Muhammad Zain Yousaf, Hui Liu, Ali Raza, et al. Deep Learning-Based Robust DC Fault Protection Scheme for Meshed HVDC Grids[J]. CSEE Journal of Power and Energy Systems, 2023, 9(6): 2423-2434.
DOI：

Muhammad Zain Yousaf, Hui Liu, Ali Raza, et al. Deep Learning-Based Robust DC Fault Protection Scheme for Meshed HVDC Grids[J]. CSEE Journal of Power and Energy Systems, 2023, 9(6): 2423-2434. DOI： 10.17775/CSEEJPES.2021.03550.

摘要

Abstract

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) system. This 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 currents. In 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 protection. The discrete wavelet transform (DWT) extracts the transient features of DC-line voltages in the frequency-time domain. Many healthy and faulty samples are incorporated during training even by considering the noise influence. After training

numerous test samples are run to evaluate the proposed algorithm's robustness under various fault conditions. Test 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.

关键词

Keywords

references

29. D. P. Kingma and J. Ba, “Adam: a method for stochastic optimization,” arXiv preprint arVix: 1412.6980, Dec. 2014, pp. 273–297. [Online ] . Available: https://doi.org/10.48550/arXiv.1412.6980.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Detection Framework for Few-Shot Voltage Disturbances in Power Systems Using Evaluation Learning

Real-Time Dispatch via Expert Knowledge Driven Deep Reinforcement Learning

Interpretable Multi-Agent Reinforcement Learning for Continuous Double Auction-Based P2P Energy Trading

Current Balancing Control Approach for Paralleled MMC Groups in Hybrid LCC/VSC Cascaded HVDC System

Data-Driven Approach for Electromagnetic Transient Recognition Using Transfer Learning

Related Author

Wenxia Sima

Han Zhang

Ming Yang

Liangcheng Cheng

Jiahao Yan

Jianguo Yao

Shengchun Yang

Wenbo Mao

Related Institution

State Key Laboratory of Power Transmission Equipment & System Security and New Technology, Chongqing University

China Electric Power Research Institute

College of Electrical and Electronics Engineering, North China Electric Power University

School of Electrical and Information Engineering, University of Sydney

State Key Laboratory for Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University

AI问答

⁰