| 159 | 0 | 90 |
| 下载次数 | 被引频次 | 阅读次数 |
接地网在电力系统中起到关键的保护作用，是保障系统安全稳定运行的重要基础设施。因此，迫切需要对其受到土壤腐蚀发生的腐蚀或断裂情况进行量化评估。瞬变电磁检测法能够克服传统检测方法需要断电或开挖的不足，但基于该方法进行接地网腐蚀与断点量化评估依赖于准确的视电阻率，现阶段基于烟囱模型的视电阻率反演方法存在准确度较低的问题，该文提出一种CNN-GRU-Attention算法的接地网视电阻率反演方法。首先通过瞬变电磁一维正演模型建立包含多种工况的瞬变电磁信号数据库，随后将数据输入所构建的CNN-GRU-Attention神经网络模型中进行训练，进而实现测点处视电阻率的高精度反演。与传统的CNN、CNN-GRU等算法相比，所提方法在反演准确性方面表现更优，拟合精度达到90%以上，能够显著提升接地网视电阻率的估算精度，为后续视电阻率成像以及腐蚀程度的定量评估奠定坚实基础。
Abstract：The grounding grid plays a critical protective role in power systems and serves as essential infrastructure for ensuring safe and stable operation. Therefore, it is crucial to quantitatively assess corrosion or breakage caused by prolonged exposure to soil environments. The transient electromagnetic(TEM) detection method overcomes the limitations of traditional techniques that require power outages or excavation. However,the effectiveness of corrosion and discontinuity assessment based on the TEM method depends on the accuracy of apparent resistivity inversion. Current approaches relying on chimney models often suffer from low accuracy. To address this issue, this paper proposes a CNN-GRU-Attention-based method for apparent resistivity inversion of grounding grids. A one-dimensional TEM forward model is used to generate a comprehensive dataset under various conditions, which is then fed into a CNN-GRU-Attention neural network for training. The proposed method achieves high-precision inversion of apparent resistivity at measurement points. Compared with traditional CNN and CNN-GRU models, the proposed approach demonstrates superior performance, achieving inversion accuracy exceeding 90%. This significantly enhances the estimation precision of apparent resistivity and provides a solid foundation for subsequent resistivity imaging and quantitative evaluation of grounding grid corrosion.
[1]何毅帆,徐恒昌,汤亮亮,等.基于虚拟锁相放大器的接地网无损检测系统[J].中国测试, 2020, 46(3):84-90.HE Y F, XU H C, TANG L L, et al. Non-destructive detection system of grounding grids based on virtual lock-in amplifiers[J]. China Measurement&Test, 2020, 46(3):84-90.
[2]董冠良,白羽,李永恒,等. U形发射线圈仿真设计与测试[J].中国测试, 2025, 51(10):130-137.DONG G L, BAI Y, LI Yo H, et al. Simulation design and test of U-shaped transmitting coil[J]. China Measurement&Test,2025, 51(10):130-137.
[3]DURHAM N, ZHAO J, BRIDGES G, et al. Acoustic guided wave detection of grounding rod corrosion:equivalent circuit model and implementation[J]. Smart Materials Structures,2020, 29(5):055040.
[4]彭丽莎,孙洪宇,李世松,等.高压输电杆塔接地极腐蚀缺陷混频SH导波检测方法[J].电工技术学报, 2025, 40(2):376-386.PENG L S, SUN H Y, LI S S, et al. Mix-frequency SH guided wave corrosion defects detection method for high voltage transmission tower grounding electrode[J]. Transactions of China Electrotechnical Society, 2025, 40(2):376-386.
[5]段绍辉,宗伟,周灵杰,等.输电线路短路电流对埋地管道电位抬升及抑制方法研究[J].电测与仪表, 2024, 61(3):89-94.DUAN S H, ZONG W, ZHOU L J, et al. Research of the shortcircuit current of transmission line on potential rise of buried pipeline and its suppression method[J]. Electrical Measurement&Instrumentation, 2024, 61(3):89-94.
[6]张佳慧.接地网腐蚀的电化学测量方法研究[D].重庆:重庆大学, 2016.ZHANG J H. The study of grounding grid corrosion electrochemical measurement method[D]. Chongqing:Chongqing University , 2016.
[7]洪海涛,彭敏放,王光荣,等.基于恒电位法的接地网智能监测系统研究[C]//电工理论与新技术学术年会论文集,2007.HONG H T, PENG M F, WANG G R, et al. An intelligent system for monitoring grounding grids based on permanent potential method[C]//Annual National Conference of Electrical Theory and New Technologies Conference Proceedings, 2007.
[8]杨美佳,刘宝柱.针对大量接地支路电网形成节点阻抗矩阵的改进算法[J].电力系统保护与控制, 2010, 38(22):161-165.YANG M J, LIU B Z. An improved algorithm for forming Zmatrix of power grid containing large amount of groundedbranches[J]. Power System Protection and Control, 2010,38(22):161-165.
[9]肖磊石,张波,李谦,等.分布式等电位接地网与变电站主接地网连接方式[J].高电压技术, 2015, 41(12):4226-4232.XIAO L S, ZHANG B, LI Q, et al. Connection mode of distributed equipotential grounding grid and main grounding grid[J]. High Voltage Engineering, 2015, 41(12):4226-4232.
[10]刘渝根,陈超.基于人工蜂群算法优化支持向量机的接地网腐蚀速率预测模型[J].电力自动化设备, 2019, 39(5):182-186,200.LIU Y G, CHEN C. Corrosion rate prediction model of grounding grid based on support vector machine optimized by artificial bee colony algorithm[J]. Electric Power Automation Equipment, 2019, 39(5):182-186,200.
[11]施会,王丰华,胡徐铭,等.变电站接地网电磁诊断法的试验研究[J].电测与仪表, 2018, 55(16):6-12.SHI H, WANG F H, HU X M, et al. Experimental studies on substation grounding grid fault diagnosis using electromagnetic diagnosis method[J]. Electrical Measurement&Instrumentation, 2018, 55(16):6-12.
[12]韩欣月,邓长征,付添,等.基于MWOA-Elman神经网络的接地网瞬变电磁缺陷识别[J].广西师范大学学报(自然科学版), 2023, 41(3):53-66.HAN Xi Y, DENG C Z, FU T, et al. Transient electronmagnetic defect identification of grounding grid based on MWOA-Elman neural network[J]. Journal of Guangxi Normal University(Natural Science Edition), 2023, 41(3):53-66.
[13]韦瑞尧,王熙俊,吴华成,等.变电站接地网腐蚀诊断研究进展及其应用[J].东北电力技术, 2024, 45(5):16-21.WEI R Y, WANG X J, WU H C, et al. Research progress and application of grounding network corrosion diagnosis in substations[J]. Northeast Electric Power Technology, 2024,45(5):16-21.
[14]Tatematsu A, Yamanaka A. Three-dimensional FDTD-based simulation of lightning-induced surges in secondary circuits with shielded control cables over grounding grids in substations[J]. IEEE Transactions on Electromagnetic Compatibility, 2023, 65(2):528-538.
[15]王文东,胡绪权,徐正玉,等.基于形态滤波的接地网拓扑检测[J].电工技术学报, 2021, 36(17):3685-3692.WANG W D, HU X Q, XU Z Y, et al. Topology detecting method of grounding grids based on morphological filtration[J]. Transactions of China Electrote Chnical Society,2021, 36(17):3685-3692.
[16]栾卉,徐畅,刘南南,等.基于COMSOL Multiphysics的瞬变电磁法接地网故障诊断仿真研究[J].实验室研究与探索,2017, 36(1):108-111.LUAN H, XU C, LIU N N, et al. A simulation research on fault diagnosis of grounding grids by transient electromagnetic method based on COMSOL Multiphysics[J]. Research and Exploration in Laboratory, 2017, 36(1):108-111.
[17]WANG Q, WANG H, WU M , et al. Research on noise suppression method for transient electromagnetic signal[C]//2018 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference(IMCEC), IEEE, 2018.
[18]高明亮,于生宝,郑建波,等.基于IGA算法的电阻率神经网络反演成像研究[J].地球物理学报, 2016, 59(11):4372-4382.GAO M L, YU S B, ZHENG J B, et al. Research of resistivity imaging using neural network based on immune genetie algorithm[J]. Chinese Journal of Geophysics, 2016, 59(11):4372-4382.
[19]白宇,薛贵军,谢文举,等.改进GJO优化CNN-BiLSTM的热负荷预测模型[J].中国测试, 2025, 51(4):82-90.BAI Y, XUE G J, XIE W J, et al. Improved GJO optimized CNN-BiLSTM heat load prediction model[J]. China Measurement&Test, 2025, 51(4):82-90.
[20]陈丽,禹静,樊丹丹,等.融合CNN-Attention-GRU的超声波燃气表时差预测方法研究[J].中国测试, 2025, 51(12):104-111.CHEN L, YU J, FAN D D, et al. Research on time difference prediction method of ultrasonic gas meter based on CNNAttention-GRU[J]. China Measurement&Test, 2025, 51(12):104-111.
基本信息:
DOI：10.11857/j.issn.1674-5124.2025070055
中图分类号:TM862;TP183
引用信息:
[1]黄松岭,蒋超凡,彭丽莎,等.基于CNN-GRU-Attention算法的接地网视电阻率反演方法[J].中国测试,2026,52(01):18-24+34.DOI:10.11857/j.issn.1674-5124.2025070055.
基金信息:
国网江西省电力有限公司科技项目（52182025000K）; 国家自然科学基金项目（U23B20113,52477008）
2026-01-23
2026-01-23