Abstract：Current electric shock detection methods are primarily designed to address faults between the live wire and the ground wire, mainly relying on monitoring changes in residual current to identify issues. However, in the case of a neutral-to-live electric shock fault, the fault circuit often does not cause a significant change in the residual current. This presents a considerable challenge for existing detection methods when it comes to identifying neutral-to-live electric shock incidents. To address the aforementioned issues, a low-voltage neutral-to-live electric shock faults detection method based on dynamic fault characteristics and a light gradient boosting machine has been proposed. Firstly, a 1:1 prototype experimental platform for a low-voltage distribution network was established in a real system. Under various operating scenarios involving multiple household loads, experiments reproducing live neutral shock faults were conducted alongside control experiments using a sliding resistor to replace the electrically shocked body. A substantial amount of experimental samples representing both fault and normal operating states was collected, creating a comprehensive database. Secondly, the complexity of neutral-to-live electric shock faults is assessed based on the interference of load current on fault current. A fault circuit electrical equivalent model is established by considering the dynamic resistance and breakdown arcs at the dual contact points of the neutral-to-live shock, in conjunction with biological dynamic impedance. The impact of fault current on the main circuit current is analyzed. Finally, features of the main circuit current are extracted from the perspective of magnitude and high-frequency components, and the temporal changes of individual features before and after the occurrence of faults are compared. Given the difficulty in clearly distinguishing between fault and non-fault states based on individual features alone, along with the fact that these features exhibit varying sensitivity to both states, a multidimensional representation of the system state is employed. Following an ensemble computational approach, a lightweight gradient boosting machine model is developed, leveraging its uni-directional gradient sampling method and ensemble operation mechanism to accurately classify the two states. The proposed method was evaluated on a test dataset consisting of 50 666 samples, achieving an overall accuracy of 96.82%. Specifically, the identification accuracy for 35 831 normal samples was 97.50%, while the accuracy for 14 835 neutral-to-live electric shock faults was 95.17%. The test results indicated that the proposed method could accurately distinguish neutral-to-live electric shock faults from normal operating conditions, including those in the control group with the sliding rheostat added, even when the fault information was significantly obscured by high load currents. Compared to existing methods, the proposed approach shows an advantage in accurately detecting low-voltage neutral-to-live electric shock faults. The following conclusions can be drawn from the analysis: (1) By incorporating the time-varying impedance of biological tissues, variations in contact resistance, and breakdown arcs, the dynamic characteristics of faults were examined, revealing two effects of neutral-to-live electric shock faults on the main circuit current: changes in current magnitude and variations in high-frequency components. These findings served as the basis for constructing feature vectors. (2) The contribution of individual features to distinguishing between neutral-to-live electric shock faults and normal operating conditions is limited, resulting in significant inter-class ambiguity that can easily disrupt the sample fitting performance of traditional pattern recognition models. However, if features can exhibit a certain degree of sensitivity across different classes, the combination of multidimensional features can facilitate comprehensive discrimination. (3) Due to its inherent resilience to disturbances, the ensemble model can effectively mitigate interference caused by inter-class ambiguity and demonstrate strong generalization capabilities.
[1] 张璐, 陈雪寒, 唐巍, 等. 低压配电台区移动柔性互联: 可行性分析、应用场景及展望[J]. 电力系统自动化, 2025, 49(5): 1-12. Zhang Lu, Chen Xuehan, Tang Wei, et al.Mobile flexible interconnection in low-voltage distribution station areas: feasibility analysis, application scenarios and prospects[J]. Automation of Electric Power Systems, 2025, 49(5): 1-12. [2] 盛德杰, 王尧, 邢云琪, 等. 基于磁流体动力学仿真的低压交流串联故障电弧致火风险研究[J]. 电工技术学报, 2025, 40(10): 3326-3338. Sheng Dejie, Wang Yao, Xing Yunqi, et al.Research on fire risk of low voltage AC series fault arc based on magnetohydrodynamics simulation[J]. Transactions of China Electrotechnical Society, 2025, 40(10): 3326-3338. [3] 郭莹霏, 池源, 王强钢, 等. 面向多元负荷和优质供电的虚拟增容配电变压器: 概念、应用与展望[J]. 电工技术学报, 2024, 39(21): 6666-6686, 6803. Guo Yingfei, Chi Yuan, Wang Qianggang, et al.Virtual capacity-enhanced distribution transformer for diverse loads and quality power supply: concepts, applications, and prospects[J]. Transactions of China Electrotechnical Society, 2024, 39(21): 6666-6686, 6803. [4] 何志鹏, 李伟林, 邓云坤, 等. 低压交流串联故障电弧辨识方法[J]. 电工技术学报, 2023, 38(10): 2806-2817. He Zhipeng, Li Weilin, Deng Yunkun, et al.The detection of series AC arc fault in low-voltage distribution system[J]. Transactions of China Elec- trotechnical Society, 2023, 38(10): 2806-2817. [5] 叶豪, 李春兰, 高阁, 等. 基于多因素的动物触电电流特征试验与分析[J]. 江苏大学学报(自然科学版), 2020, 41(1): 39-45. Ye Hao, Li Chunlan, Gao Ge, et al.Experiment and analysis of animal electric shock current characteri- stics based on multiple factors[J]. Journal of Jiangsu University (Natural Science Edition), 2020, 41(1): 39-45. [6] 裴艳萍, 李琰, 陈江华, 等. 与爱“童”行, “电小青”筑梦未来[C]//全国电力能源优秀党建典型案例论文集, 2024: 359. [7] 朱丽娇, 程晋然, 尹兴坚. 基于感应电压触电事件分析的35kV单芯电缆护层接地方式研究[J]. 电气技术, 2023, 24(11): 81-84. Zhu Lijiao, Cheng Jinran, Yin Xingjian.Research on the grounding method of 35kV single core cable sheath in subway based on the analysis of induced voltage electric shock events[J]. Electrical Engin- eering, 2023, 24(11): 81-84. [8] 汪自虎, 王文天, 惠慧, 等. 基于近邻成分分析与优化核极限学习机的光伏接入配电网漏电识别[J]. 高压电器, 2024, 60(6): 203-211. Wang Zihu, Wang Wentian, Hui Hui, et al.Leakage recognition method of photovoltaic connected to distribution network based on neighborhood com- ponent analysis and optimized kernel extreme learning machine[J]. High Voltage Apparatus, 2024, 60(6): 203-211. [9] 肖湘奇, 肖宇, 黄瑞, 等. 基于随机森林算法的低压系统漏电检测技术研究[J]. 电力科学与技术学报, 2024, 39(3): 38-47, 115. Xiao Xiangqi, Xiao Yu, Huang Rui, et al.Research on leakage detection technology of low-voltage power system based on random forest algorithm[J]. Journal of Electric Power Science and Technology, 2024, 39(3): 38-47, 115. [10] Parise G.A new summary on the IEC protection against electric shock[J]. IEEE Transactions on Industry Applications, 2013, 49(2): 1004-1011. [11] LaRocca R L. Personnel protection devices for use on appliances[J]. IEEE Transactions on Industry Appli- cations, 1992, 28(1): 233-238. [12] Liew A C.Nuisance trippings of residual current circuit breakers or ground fault protectors of power sources connected to computer and electronic loads[J]. Electric Power Systems Research, 1990, 20(1): 23-30. [13] 徐浩, 王欣阳, 魏云冰, 等. 基于最小二乘法的活体触电动态阻抗分析[J]. 电气工程学报, 2023, 18(3): 268-276. Xu Hao, Wang Xinyang, Wei Yunbing, et al.Dynamic impedance analysis of live electrocution based on least squares method[J]. Journal of Elec- trical Engineering, 2023, 18(3): 268-276. [14] Freschi F.High-frequency behavior of residual current devices[J]. IEEE Transactions on Power Delivery, 2012, 27(3): 1629-1635. [15] Christie R D, Zadehgol H, Habib M M.High impedance fault detection in low voltage networks[J]. IEEE Transactions on Power Delivery, 1993, 8(4): 1829-1836. [16] Czapp S.Elimination of the negative effect of earth fault current higher frequency on tripping of residual current devices[J]. Elektronika Ir Elektrotechnika, 2009, 91(3): 85-88. [17] 王欣阳, 魏云冰, 徐浩. 基于FFT和三次Hermite插值的人体触电判据初探[J]. 电气工程学报, 2023, 18(1): 133-142. Wang Xinyang, Wei Yunbing, Xu Hao.Preliminary study on the human body electric shock criterion based on FFT and cubic Hermite interpolation[J]. Journal of Electrical Engineering, 2023, 18(1): 133-142. [18] Han Xiaohui, Du Songhuai, Su Juan, et al.Electric shock fault diagnosis of low-voltage residual current- operated protective device[J]. IEEJ Transactions on Electrical and Electronic Engineering, 2018, 13(2): 180-186. [19] Han Xiaohui, Sheng Wanxing, Du Songhuai, et al.Novel protection scheme for residual current device- based electric fault time detection and touch current identification[J]. IET Generation, Transmission & Distribution, 2017, 11(10): 2478-2488. [20] 韩晓慧, 杜松怀, 李振, 等. 基于泄漏电流时频奇异谱和模糊聚类的触电故障诊断[J]. 农业工程学报, 2018, 34(4): 217-222. Han Xiaohui, Du Songhuai, Li Zhen, et al.Diagnosis of electric shock fault based on time-frequency singular value spectrum of leakage current and fuzzy clustering[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(4): 217-222. [21] Zhao Heng, Xiao Xianyong, Sun Qiuqin.Identifying electric shock in the human body via α dispersion[J]. IEEE Transactions on Power Delivery, 2018, 33(3): 1107-1114. [22] 李春兰, 罗杰, 王长云, 等. 基于循环谱特征和聚类分析的触电识别[J]. 电工技术学报, 2021, 36(22): 4677-4687. Li Chunlan, Luo Jie, Wang Changyun, et al.Electric shock recognition method based on cyclic spectrum features and cluster analysis[J]. Transactions of China Electrotechnical Society, 2021, 36(22): 4677-4687. [23] 蔡智萍, 郭谋发, 魏正峰. 基于BP神经网络的低压配电网生命体触电识别方法研究[J]. 电网技术, 2022, 46(4): 1614-1623. Cai Zhiping, Guo Moufa, Wei Zhengfeng.Research on recognition method of living body shock in low-voltage distribution network based on BP neural network[J]. Power System Technology, 2022, 46(4): 1614-1623. [24] Yang Gengjie, Quan Shengxin, Gao Wei.A new- designed biological electric shock identification method in low-voltage distribution network[J]. IEEE Transactions on Power Delivery, 2023, 38(3): 1558-1568. [25] 高伟, 饶俊民, 全圣鑫, 等. 不均衡小样本下多特征优化选择的生命体触电故障识别方法[J]. 电工技术学报, 2024, 39(7): 2060-2071. Gao Wei, Rao Junmin, Quan Shengxin, et al.Biological electric-shock fault identification method based on multi-feature optimization selection under unbalanced small sample[J]. Transactions of China Electrotechnical Society, 2024, 39(7): 2060-2071. [26] Tong Haixin, Zeng Xiangjun, Yu Kun, et al.Research on the identification method of series arc fault based on the feature sensitivity analysis and the TVA coefficient optimized random forest[J]. IEEE Transa- ctions on Power Delivery, 2024, 39(2): 751-762. [27] 李理, 喻锟, 曾祥君, 等. 基于发电机定子接地燃弧电阻变化特征的主动降压熄弧机理与抑制方法[J]. 电工技术学报, 2024, 39(17): 5379-5393. Li Li, Yu Kun, Zeng Xiangjun, et al.Mechanism and suppression method of active arc extinguishing based on the variation characteristics of arc resistance of stator[J]. Transactions of China Electrotechnical Society, 2024, 39(17): 5379-5393. [28] Ke Guolin, Meng Qi, Finley T, et al.LightGBM: a highly efficient gradient boosting decision tree[C]// 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, 2017: 1-9.
2025, Vol. 40 
