BP神经网络预测电极速度影响放电参数分析

doi:10.16180/j.cnki.issn1007-7820.2019.06.009

电子科技 ›› 2019, Vol. 32 ›› Issue (6): 43-48.doi: 10.16180/j.cnki.issn1007-7820.2019.06.009

BP神经网络预测电极速度影响放电参数分析

管胜¹,阮方鸣²,周奎¹,苏明²,王珩²,邓迪³,李佳⁴

1. 贵州大学大数据与信息工程学院,贵州贵阳 550025
2. 贵州师范大学大数据与计算机科学学院,贵州贵阳 550001
3. 贵州省机械电子产品质量监督检验院,贵州贵阳 550016
4. 深圳振华富电子有限公司,广东深圳 518109

收稿日期:2018-06-18 出版日期:2019-06-15 发布日期:2019-07-01
作者简介:管胜(1992-),男,硕士研究生。研究方向:电路与系统。|阮方鸣(1958-),男,博士,教授。研究方向:电磁兼容设计、静电放电、电磁生物效应、信息对抗与大数据安全。
基金资助:
贵州省静电与电磁防护科技创新人才团队(黔科合平台人才[2017]5653);2016年度中央引导地方科技发展专项资金项目(黔科中引地[2016]4006号)

Analysis of Discharge Parameters Affected by BP Neural Network Predicting Electrode Velocity

GUAN Sheng¹,RUAN Fangming²,ZHOU Kui¹,SU Ming²,WANG Heng²,DENG Di³,LI Jia⁴

1. School of Big Data and Information Engineering,Guizhou University,Guiyang 550025,China
2. School of Big Data and Computer Sciences,Guizhou Normal University,Guiyang 550001,China
3. Guizhou Machinery and Electronic Products Quality Supervision and Inspection Institute,Guiyang 550016,China
4. Shenzhen Zhenhua Fu Electronics Limited Company,Shenzhen 518109,China

Received:2018-06-18 Online:2019-06-15 Published:2019-07-01
Supported by:
Guizhou Province Electrostatic and Electromagnetic Protection Science and Technology Innovation Talent Team (Yankehe Platform Talent [2017] 5653);2016 Central Government Leading Local Science and Technology Development Special Fund Project (Zhongke Zhongdi [2016] No.4006)

摘要/Abstract

摘要：

文中结合小间隙放电的双过程模型,探讨电极移动引起放电场强和压强的变化对放电间隙内部相关因子的影响。文中同时利用BP神经网络预测分析电极移动速度对放电参数的影响。基于静电放电电极移动速度效应检测仪,不断改变电极移动速度,反复多次进行放电实验并统计试验数据。利用BP神经网络对已测实验数据进行训练、学习,从而预测不同速度与压强下对应的电流上升时间和峰值电流大小。实验结果表明,放电电流的上升时间与电极移动速度不存在相关性。根据新方法预测出的不同速度下的峰值电流和实际大小相比准确率更高。研究结果对探寻非接触式静电放电的规律和制定静电放电标准有一定的参考价值。

关键词: 静电放电, 电极移动速度, BP神经网络, 学习与训练, 预测, 规律

Abstract:

The dual-process model of small gap discharge was used to investigate the influence of the change of field intensity and pressure on the internal correlation factors of the discharge gap, and the BP neural network was applied to predict and analyze the influence of the electrode moving speed on the discharge parameters. Based on the electrostatic discharge electrode moving speed effect detector, the electrode moving speed was continuously changed, and the discharge experiment had been repeated several times to obtain and statistically calculated the test data. Meanwhile, BP neural network was used to train and learn the measured experimental data, so as to predict the current rise time and peak current at different speeds and pressures. The results showed that there was no correlation between the rising time of the discharge current and the moving speed of the electrode. According to the new method, the accuracy of peak current at different speeds was higher than that of the actual size. The research results was of great reference value in exploring the law of non-contact electrostatic discharge and the formulation of electrostatic discharge standards.

Key words: electrostatic discharge, electrode movement speed, BP neural network, learning and training, prediction, disciplinary

中图分类号:

TP183

管胜,阮方鸣,周奎,苏明,王珩,邓迪,李佳. BP神经网络预测电极速度影响放电参数分析[J]. 电子科技, 2019, 32(6): 43-48.

GUAN Sheng,RUAN Fangming,ZHOU Kui,SU Ming,WANG Heng,DENG Di,LI Jia. Analysis of Discharge Parameters Affected by BP Neural Network Predicting Electrode Velocity[J]. Electronic Science and Technology, 2019, 32(6): 43-48.

图/表 14

图1

图2

图3

图4

图5

图6

图7

表1

图8

表2

图9

图10

表3

表4

参考文献 16

[1]	原青云, 张喜军, 刘尚合 , 等. 影响空气式静电放电特性的相关因素分析[J]. 高电压技术, 2010,36(10):2500-2506.
	Yuan Qingyun, Zhang Xijun, Liu Shanghe , et al. Analysis on the relative factors affecting the characteristics of air electrostatic discharge[J]. High Voltage Engineering, 2010,36(10):2500-2506.
[2]	阮方鸣, 章俊华, 陈辉林 , 等. 非接触静电放电测试低重复特性分析研究[J]. 电波科学学报, 2014,29(5):940-945.
	Ruan Fangming, Zhang Junhua, Chen Huilin , et al. Analysis and investigation of low repeatability of measurement results in non-contact mode ESD[J]. Chinese Journal of Radio Science, 2014,29(5):940-945.
[3]	朱利, 原青云, 周为平 . 环境因素对空气式静电放电的影响研究[ C].北京:静电防护与标准化学术交流会, 2012.
	Zhu Li, Yuan Qingyun, Zhou Weiping . Study on the influence of environmental factors on the air electrostatic discharge[ C].Beijing:Symposium on Electrostatic Protection and Standardization, 2012.
[4]	阮方鸣, 高攸刚, 石丹 , 等. 静电放电参数对电极速度的相关性与机理分析[J]. 电波科学学报, 2008,23(5):977-981.
	Ruan Fangming, Gao Yougang, Shi Dan , et al. Correlation investigation of discharge parameters with contact approach speed and its mechanism in human-metal electrostatic discharge[J]. Chinese Journal of Radio Science, 2008,23(5):977-981.
[5]	阮方鸣, 章俊华, 杨向东 , 等. 静电放电参数随电极移动速度和空气压强变化的特性分析[J].环境技术, 2014(s1):15-18.
	Ruan Fangming, Zhang Junhua, Yang Xiangdong , et al. Analysis of electrostatic discharge parameters as a function of electrode movement velocity and air pressure variation[J].Environmental Technology, 2014(s1):15-18.
[6]	Ruan F M, Meng Y, Xu Y B , et al. Relationship investigation of ESD parameters, air pressure variation and electrode approach speed[J].Journal of Network & Information Security, 2013(4):307-314.
[7]	吴勇, 刘国红, 顾立娟 , 等. 空气式静电放电的实验分析[J]. 高电压技术, 2011,37(1):131-135.
	Wu Yong, Liu Guohong, Gu Lijuan , et al. Experimental analysis of air-type electrostatic discharge[J]. High Voltage Technology, 2011,37(1):131-135.
[8]	周奎, 阮方鸣, 张景 , 等. 电极移动速度效应的空气动力学分析[J]. 电波科学学报, 2016,31(6):1060-1066.
	Zhou Kui, Ruan Fangming, Zhang Jing , et al. Air dynamics analysis on electrode moving speed effect[J]. Chinese Journal of Radio Science, 2016,31(6):1060-1066.
[9]	任正风 . MATLAB R2015b神经网络技术[M]. 北京: 清华大学出版社, 2016.
	Ren Zhengfeng. MATLAB R2015b neural network technology[M]. Beijing: Tsinghua University Press, 2016.
[10]	朱英 . 改进的BP神经网络预测模型及其应用[J]. 武汉理工大学学报:交通科学与工程版, 2012,36(6):1252-1255.
	Zhu Ying . Improved BP neural network prediction model and its application[J]. Journal of Wuhan University of Technology:Transportation Science and Engineering Edition, 2012,36(6):1252-1255.
[11]	苏宇逍 . 基于GA的BP神经网络在多目标优化中的应用[J]. 电子科技, 2015,28(6):51-56.
	Su Yuxiao . Application of BP neural network based on GA in multi-objective optimization[J]. Electronic Science and Technology, 2015,28(6):51-56.
[12]	孟洋, 阮方鸣, 庄宁 . 静电放电参数低重复特性分析[J]. 贵州师范大学学报:自然科学版, 2013,31(1):67-71.
	Meng Yang, Ruan Fangming, Zhuang Ning . Analysis of low repetition characteristics of electrostatic discharge parameters[J]. Journal of Guizhou Normal University:Natural Science, 2013,31(1):67-71.
[13]	原青云, 刘尚合, 张希军 , 等. IEC61000-4-2标准试验平台的局限性分析及其完善的探讨[J]. 高电压技术, 2011,37(1):118-123.
	Yuan Qingyun, Liu Shanghe, Zhang Xijun , et al. Limitations of the IEC61000-4-2 standard test platform and discussion of its perfection[J]. High Voltage Technology, 2011,37(1):118-123.
[14]	吴勇, 赵纪华, 顾立娟 , 等. 空气式静电放电的规律[J]. 河北师范大学学报:自然科学版, 2011,35(1):50-54.
	Wu Yong, Zhao Jihua, Gu Lijuan , et al. The law of air-type electrostatic discharge[J]. Journal of Hebei Normal University:Natural Science, 2011,35(1):50-54.
[15]	阮方鸣, 石丹, 高攸纲 , 等. 在小间隙放电中Bernoulli定理分析电极移动速度效应[J]. 电波科学学报, 2009,24(3):551-555.
	Ruan Fangming, Shi Dan, Gao Yougang , et al. Application of Bernoulli’s theorem for speed effect of electrode moving in short-gap electrostatic discharge[J]. Chinese Journal of Radio Science, 2009,24(3):551-555.
[16]	Bonisch S, Kalkner W, Pommerenke D . Modeling of short-gap ESD under consideration of different discharge mechanisms[J]. IEEE Transactions on Plasma Science, 2003,31(2):736-744. doi: 10.1109/TPS.2003.815823

电极速度/m·s^-1	实际电流/A	预测电流/A	预测正确率
0.11	1.884	1.85	98.20%
0.16	2.089	2.109	99.04%
0.23	2.181	2.11	96.74%
0.29	2.231	2.31	96.46%
0.39	2.56	2.48	96.88%

电极速度/m·s^-1	实际电流/A	预测电流/A	预测正确率
0.49	2.601	2.669 4	97.37%
0.51	2.632	2.658 1	99.01%
0.54	2.593	2.630 8	98.54%
0.57	2.522	2.596 6	97.04%
0.6	2.465	2.559 4	96.17%

BP神经网络预测电极速度影响放电参数分析

Analysis of Discharge Parameters Affected by BP Neural Network Predicting Electrode Velocity

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 16

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	冯先丁,魏镜弢,吴张永,钱杰,浦友尚. 基于PCA-PSO-SVM的球磨机负荷预测研究[J]. 电子科技, 2022, 35(1): 29-34.
[2]	孟晓姣,张世巍,李小健,李敏玥,宋丙鑫,路宏敏. 一种基于BP神经网络的车载通信设备性能评估方法[J]. 电子科技, 2021, 34(5): 24-28.
[3]	宋丙鑫,路宏敏,李敏玥,孟晓姣,万健鹏. 一种车载通信设备电磁兼容性预测方法[J]. 电子科技, 2021, 34(5): 7-12.
[4]	朱成名,魏云冰,蒋成成,朱健安. 基于PSO-BP神经网络的风电功率备用容量估计模型[J]. 电子科技, 2021, 34(12): 36-41.
[5]	王洪亮,陈新源,赵雨梦. 基于集合经验模态分解和ARIMA-GRNN的负荷预测方法[J]. 电子科技, 2021, 34(12): 42-48.
[6]	朱健安,魏云冰,朱鹏杰,蒋成成,朱成名. 基于优化灰色傅里叶残差修正的中长期负荷预测[J]. 电子科技, 2021, 34(12): 49-55.
[7]	任磊,付子义,雷海勋. 有源电力滤波器改进电流预测无差拍控制方法[J]. 电子科技, 2021, 34(11): 67-74.
[8]	朱轶峰. 基于WiFi-BP的室内定位算法[J]. 电子科技, 2020, 33(8): 74-79.
[9]	金鑫,冯毅,尤雪汐,王佳欣. 基于机器学习的信息安全设备调配保障技术研究[J]. 电子科技, 2020, 33(8): 80-86.
[10]	付新贺,袁永旭. 基于灰色预测算法的图情数据分析技术[J]. 电子科技, 2020, 33(7): 67-70.
[11]	刘义民,刘韬,陈庆. CHMM和AR模型在轴承性能退化评估与预测中的应用[J]. 电子科技, 2020, 33(5): 58-65.
[12]	许凤翔. 一种改进相似度的协同过滤算法实现[J]. 电子科技, 2020, 33(2): 54-59.
[13]	杨海柱,江昭阳,李梦龙,康乐. 基于改进人工鱼群-蛙跳算法优化LSSVM参数短期负荷预测[J]. 电子科技, 2020, 33(12): 67-74.
[14]	祁鑫,王福忠,张丽,王瑞,王晓慧. 基于SVD-LSTM的高校学生宿舍空调负荷预测[J]. 电子科技, 2020, 33(11): 59-66.
[15]	罗小龙,刘子龙. 基于快速编码单元划分和自适应模式决策的HEVC效率改进算法[J]. 电子科技, 2020, 33(10): 21-25.