Evaluation of multi-channel data calibration for substation protection measurement loops based on GA-BiLSTM

WEI Shengtai; BU Xinlian; HUANG Yujie; ZHOU Jian; LI Zhenxing

doi:10.11930/j.issn.1004-9649.202510017

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Evaluation of multi-channel data calibration for substation protection measurement loops based on GA-BiLSTM

更新时间：2026-07-31

- Evaluation of multi-channel data calibration for substation protection measurement loops based on GA-BiLSTM
- Vol. 59, Issue 7, Pages: 214-222(2026)
- 作者机构：
  
  1. 国网江苏省电力有限公司靖江市供电分公司
  2. 三峡大学电气与新能源学院
- 作者简介：
- 基金信息：
  
  This work is supported by Science and Technology Project of State Grid Jiangsu Electric Power Co., Ltd. (No.B3107025520M)
- DOI：10.11930/j.issn.1004-9649.202510017
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
魏圣泰, 卜鑫链, 黄钰杰, 等. 基于GA-BiLSTM的变电站保护测量回路多通道数据校核评估[J]. 中国电力, 2026, 59(7): 214−222.

WEI Shengtai, BU Xinlian, HUANG Yujie, et al. Evaluation of multi-channel data calibration for substation protection measurement loops based on GA-BiLSTM[J]. 2026, 59(7): 214-222.
魏圣泰, 卜鑫链, 黄钰杰, 等. 基于GA-BiLSTM的变电站保护测量回路多通道数据校核评估[J]. 中国电力, 2026, 59(7): 214−222. DOI： 10.11930/j.issn.1004-9649.202510017

WEI Shengtai, BU Xinlian, HUANG Yujie, et al. Evaluation of multi-channel data calibration for substation protection measurement loops based on GA-BiLSTM[J]. 2026, 59(7): 214-222. DOI： 10.11930/j.issn.1004-9649.202510017.

摘要

针对变电站二次保护测量回路误差存在影响测量精度，导致保护灵敏度降低并进一步影响保护可靠动作的问题，提出了基于遗传算法（genetic algorithm，GA）优化的双向长短期记忆神经网络（bi-directional long short-term memory，BiLSTM）的多通道数据校核评估方法，该方法确保了测量精度并丰富了多通道信息可用性。以多通道数据组间的相对偏差建立初始数据集，进一步设立对应的分类原则。算例分析表明，对比其他网络模型，所提多通道评估模型准确率可达到97%，有较大提升。

Abstract

In order to rectify the problem of measurement inaccuracies in secondary protection measurement circuits at substations

which undermine measurement precision

diminish protection sensitivity

and consequently impair the reliable operation of protective devices

this paper puts forth a multi-channel data verification and evaluation methodology founded on a bidirectional long short-term memory (BiLSTM) network that has been refined through a genetic algorithm (GA). This proposed methodology aims to guarantee measurement accuracy and to augment the usability of multi-channel information. An initial dataset is established based on relative deviations between multi-channel data groups

followed by the formulation of corresponding classification principles. Case study analysis demonstrates that compared to other network models

the GA-BiLSTM multi-channel evaluation model achieves an accuracy rate of 97%

representing a significant improvement.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Joint optimization planning of offshore wind farm collection and export system

Distribution network voltage fluctuation source localization based on Bayesian-optimized XGBoost

Novel pilot protection scheme for active distribution networks based on positive sequence fault component impedance characteristics

Evaluation of comprehensive performance and power generation economy of constructive super-long gravity heat pipe

Pricing strategy for flexible distribution networks guided by mobile energy storage

Related Author

No data

Related Institution

No data

AI问答

⁰