1 State Grid Jiangxi Electric Power Research Institute, Nanchang 330000, China
2 Department of Electric Engineering, Tsinghua University, Beijing 100084, China
Show less
文章历史+
Received
Published
Revised
2025-10-09
2026-05-08
2025-11-27
Online Date
2026-08-06
PDF (5861K)
摘要
为提升接地网腐蚀与断点量化评估的准确性,提出一种常春藤优化算法(IVY)与卷积神经网络-双向长短时记忆网络(convolutional neural networks-bidirectional long short-term memory,CNN-BiLSTM)深度学习模型相结合的瞬变电磁视电阻率反演方法,实现了对接地网瞬变电磁信号的高精度反演。传统瞬变电磁反演方法如“烟圈”理论虽能实现快速成像,但反演精度有限;而常规CNN-BiLSTM混合模型虽能同时捕捉时空特征,但在网络超参数优化方面存在不足。通过引入IVY算法对CNN-BiLSTM模型的超参数进行自适应优化,显著提升了模型性能。通过一维正演模拟构建包含多种地电参数的训练样本库,利用IVY-CNN-BiLSTM混合模型挖掘瞬变电磁信号与视电阻率间的深层映射关系,实现端到端的高精度反演。反演结果表明,所提方法反演结果与真实值的拟合优度优于0.95,性能显著优于传统CNN、CNN-BiLSTM等算法,能够为接地网状态的无损量化评估与可视化诊断提供可靠依据。实验验证表明,所提方法在接地网腐蚀诊断中的准确度和可靠性远超传统反演方法,为变电站接地网状态监测提供了一种新的技术途径。
Abstract
To enhance the accuracy of corrosion and breakpoint quantification in grounding grids, an inversion method based on transient electromagnetic apparent resistivity was proposed by combining the IVY optimization algorithm with a convolutional neural networks-bidirectional long short-term memory(CNN-BiLSTM) deep learning model. Through this approach, high-precision inversion of transient electromagnetic signals from grounding grids was achieved. Traditional transient electromagnetic inversion methods, such as the “smoke ring” theory, enable rapid imaging but suffer from limited inversion accuracy, while conventional CNN-BiLSTM hybrid models can capture spatiotemporal features but lack effective hyperparameter optimization. The IVY algorithm was introduced to adaptively optimize the hyperparameters of the CNN-BiLSTM model, thereby significantly improving its performance. A one-dimensional forward simulation was conducted to construct a training dataset containing various geoelectrical parameters, and the IVY-CNN-BiLSTM hybrid model was employed to extract the deep mapping relationship between transient electromagnetic signals and apparent resistivity, realizing end-to-end high-precision inversion. The inversion results demonstrated that the proposed method achieved a coefficient of determination exceeding 0.95 with the true values and outperformed traditional CNN and CNN-BiLSTM algorithms. The proposed approach provides a reliable basis for nondestructive quantitative evaluation and visual diagnosis of grounding grid conditions. Experimental validation confirmed that the proposed method exhibited much higher accuracy and reliability in grounding grid corrosion diagnosis than conventional inversion methods, offering a novel technical route for substation grounding grid condition monitoring.
$\Delta \boldsymbol{G}_{r i}=\left\{\begin{array}{ll} \operatorname{Hdiv}\left[\boldsymbol{I}_{i},\left(\boldsymbol{I}_{\max }-\boldsymbol{I}_{\min }\right)\right], & \text { Iter }=1 \\ \mathbf{r a n d}^{2} \odot[\boldsymbol{N}(1, M) \odot \Delta \boldsymbol{G} r i], & \text { Iter }>1 \end{array}\right.$
HeYifan, XuHengchang, TangLiangliang, et al. Non-destructive detection system of grounding grids based on virtual lock-in amplifiers[J]. China Measurement & Test, 2020, 46(3): 84-90.
DongGuanliang, BaiYu, LiYongheng, et al. Simulation design and test of U-shaped transmitting coil[J]. China Measurement & Test, 2025, 51(10): 130-137.
[5]
DurhamN, ZhaoJ, BridgesG, et al. Acoustic guided wave detection of grounding rod corrosion: equivalent circuit model and implementation[J]. Smart Materials Structures, 2020, 29(5): 055040.
PengLisha, SunHongyu, LiShisong, 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.
DuanShaohui, ZongWei, ZhouLingjie, et al. Research of the short-circuit current of transmission line on potential rise of buried pipeline and its suppression method[J]. Electrical Measurement & Instrumentation, 2024, 61(3): 89-94.
[10]
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.
[11]
ZhangJiahui. The study of grounding grid corrosion electrochemical measurement method[D]. Chongqing: Chongqing University, 2016.
HongHaitao, PengMinfang, WangGuangrong, 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. Zhangjiajie: Chinese Society of Electrical Engineering, 2007: 425-428.
YangMeijia, LiuBaozhu. An improved algorithm for forming Z-matrix of power grid containing large amount of grounded-branches[J]. Power System Protection and Control, 2010, 38(22): 161-165.
XiaoLeishi, ZhangBo, LiQian, et al. Connection mode of distributed equipotential grounding grid and main grounding grid[J]. High Voltage Engineering, 2015, 41(12): 4226-4232.
LiuYugen, ChenChao. 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.
ZhuNan, DongYi, GuoKai, et al. Bayes rapid discrimination of goaf types based on multi-parameter TEM data[J]. Science Technology and Engineering, 2025, 25(29): 12364-12371.
GuoSongwei, YanQiang. Application of transient electromagnetic methods in water exploration of the west of Ming’an Town in Wu-lateqianqi, Inner Mongolia[J]. Science Technology and Engineering, 2020, 20(7): 2564-2572.
[26]
TatematsuA, YamanakaA. 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.
WangWendong, HuXuquan, XuZhengyu, et al. Topology detecting method of grounding grids based on morphological filtration[J]. Transactions of China Electrotechnical Society, 2021, 36(17): 3685-3692.
LuanHui, XuChang, LiuNannan, 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.
[31]
WangQ, WangH, WuM, 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). Xi’an: IEEE, 2018: 394-397.
GaoMingliang, YuShengbao, ZhengJianbo, et al. Research of resistivity imaging using neural network based on immune genetie algorithm[J]. Chinese Journal of Geophysics, 2016, 59(11): 4372-4382.
ChenLi, YuJing, FanDandan, et al. Research on time difference prediction of ultrasonic gas meter based on CNN-Attention-GRU[J]. China Measurement & Test, 2025, 51(12): 104-111.