Research on Electric Shock Identification Based on Feature Overlap Analysis and Bayes-Random Forest

doi:10.3969/j.issn.1008-0198.2024.01.005

Abstract

Abstract: In response to the difficulty in identifying biological electric shocks caused by feature aliasing in low-voltage distribution systems, a Bayesian-random forest based method for identifying electric shock caused by characteristic overlap in low-voltage distribution systems is proposed. Firstly, the current waveforms of five types of electric shocks, including a non-living organism control group, are analyzed to study the overlap of the same shock characteristics in different categories. Secondly, the Bayesian optimization algorithm is used to optimize the hyper-parameters of the random forest model. The random forest is fitted with real samples using bagging, describing the operation of the ensemble identification mechanism and the specific implementation process of the method. Furthermore, the method is validated on 136 802 test samples containing five types, achieving an overall accuracy of 96.276%. Finally, a comparison with existing methods demonstrates the superiority of the proposed method in electric shock identification.

Key words: biological electric shock identification, random forest, feature overlap

CLC Number:

TM77

WU Cong, LIU Mouhai, ZHOU Can, HUANG Rui, TONG Haixin, LU Jin. Research on Electric Shock Identification Based on Feature Overlap Analysis and Bayes-Random Forest[J]. Hunan Electric Power, 2024, 44(1): 32-37.

References

[1] 李天友,郭峰.低压配电的触电保护技术及其发展[J].供用电,2019,36(12):2-8.
[2] 张军伟,李奎,王卿粹,等.复杂波形剩余电流保护器的设计[J].低压电器,2012(20):20-24.
[3] 李奎,戴逸华,牛峰,等.基于触发角识别的脉动直流剩余电流有效值检测方法[J].电力自动化设备,2017,37(5):80-84.
[4] 李奎,陆俭国,岳大为,等.漏电信号的识别技术及其方法[J].低压电器,2008(23):1-4,10.
[5] 李倩,李奎,王尧,等.脉动直流剩余电流下AC型漏电断路器动作特性分析[J].河南理工大学学报(自然科学版),2020,39(3):100-107.
[6] 夏越,杜松怀,李春兰,等.中国剩余电流保护技术与装置的发展趋势[J].农业工程学报,2010,26(增刊2):151-155.
[7] 武一,李奎,岳大为,等.消除剩余电流保护动作死区的理论与方法[J].电工技术学报,2008,23(6):44-49.
[8] 关海鸥,杜松怀,苏娟,等.一种触电信号的自动快速检测模型[J].电网技术,2013,37(8):2328-2335.
[9] 韩晓慧,杜松怀,苏娟,等.触电信号暂态特征提取及故障类型识别方法[J].电网技术,2016,40(11):3591-3596.
[10] 韩晓慧,杜松怀,苏娟,等.基于参数优化的最小二乘支持向量机触电电流检测方法[J].农业工程学报,2014,30(23):238-245.
[11] 关海鸥,杜松怀,李春兰,等.基于有限脉冲反应和径向基神经网络的触电信号识别[J].农业工程学报,2013,29(8):187-194.
[12] 王金丽,刘永梅,杜松怀,等.基于剩余电流固有模态能量特征的生物触电故障诊断模型[J].农业工程学报,2016,32(21):202-208.
[13] 关海鸥,李伟凯,杜松怀,等.基于Hilbert-Huang变换的生物触电电流检测模型[J].农业工程学报,2017,33(14):202-209.
[14] 祁广云,李磊,关海鸥,等.生物触电信号高阶统计特征描述及分析方法[J].江苏大学学报(自然科学版),2017,38(2):173-178,185.
[15] 关海鸥,刘梦,李春兰,等.基于小波包变换和量子神经网络的触电故障类型识别模型[J].农业工程学报,2018,34(5):183-190.
[16] 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.
[17] 王阳,许志红,郭清滔.基于奇异值差分谱熵复杂度的生物触电信号识别研究[J].供用电,2019,36(12):9-16,21.
[18] WU S, LIN S Y, GUO M F. Application of WE-AE-BP method to electric shock faults identification in the low-voltage distribution network[C]//2020 IEEE 1st China International Youth Conference on Electrical Engineering (CIYCEE). Wuhan,China.IEEE, 2020: 1-6.
[19] WEI Z F, GUO M F. Artificial intelligence recognition method of living body electric shock in low voltage distribution networks[C]//2020 IEEE 1st China International Youth Conference on Electrical Engineering(CIYCEE).Wuhan,China.IEEE,2020: 1-7.
[20] 刘永梅,杜松怀,盛万兴.基于SVM-神经网络融合反馈的触电电流检测方法[J].电网技术,2020,44(5):1972-1977.