基于TensorFlow的高压输电线路异物识别
|
摘要
针对传统异物识别准确率较低的问题,提出一种基于TensorFlow的深度卷积神经网络的异物识别模型。将巡检图像进行图像灰度化和尺寸压缩等预处理,并采用三维块匹配滤波(BM3D)算法进行图像去噪得到实验所需的训练数据。提出基于TensorFlow的深度卷积神经网络框架,通过使用框架中的TensorBoard模块设计深度卷积神经网络模型结构与优选模型参数,并针对ReLU激活函数与特征权重进行理论分析。实验结果表明,经过15次迭代训练后,深度卷积神经网络比传统的支持向量机(SVM)、极限学习机(ELM)和BP神经网络算法具有更强的巡检图像识别能力;与经典的LeNet-5和VGGNet模型以及相关文献中的模型相比,所提模型更具有优越性。
Aiming at the low accuracy rate of traditional foreign body identification,a foreign body identification mo-del based on TensorFlow-based deep CNN(Convolutional Neural Network) is proposed. The inspection image is pre-processed by image graying and size compression,and BM3 D algorithm is used for image denoising to get the training data needed in the experiment. A deep CNN framework based on TensorFlow is proposed. By using the TensorBoard module in the framework,the model structure is designed and parameters of the deep CNN are selected,and the ReLU activation function and feature weight are analyzed theoretically. The experimental results show that after fifteen times of iteration training,the deep CNN has better recognition ability than the traditional SVM,ELM and BP neural network;compared with the classical LeNet-5 model,VGGNet model and models in the related literatures,the proposed model has more advantages.
Aiming at the low accuracy rate of traditional foreign body identification,a foreign body identification mo-del based on TensorFlow-based deep CNN(Convolutional Neural Network) is proposed. The inspection image is pre-processed by image graying and size compression,and BM3 D algorithm is used for image denoising to get the training data needed in the experiment. A deep CNN framework based on TensorFlow is proposed. By using the TensorBoard module in the framework,the model structure is designed and parameters of the deep CNN are selected,and the ReLU activation function and feature weight are analyzed theoretically. The experimental results show that after fifteen times of iteration training,the deep CNN has better recognition ability than the traditional SVM,ELM and BP neural network;compared with the classical LeNet-5 model,VGGNet model and models in the related literatures,the proposed model has more advantages.
引文
[1] 杨方,白翠粉,张义斌. 能源互联网的价值与实现架构研究[J]. 中国电机工程学报,2015,35(14):3495-3502.YANG Fang,BAI Cuifen,ZHANG Yibin. Research on the value and implementation framework of energy internet[J]. Proceedings of the CSEE,2015,35(14):3495-3502.
[2] 胡毅,刘凯,吴田,等. 输电线路运行安全影响因素分析及防治措施[J]. 高电压技术,2014,40(11):3491-3499.HU Yi,LIU Kai,WU Tian,et al. Analysis of influential factors on operation safety of transmission line and countermeasures[J]. High Voltage Engineering,2014,40(11):3491-3499.
[3] 彭向阳,陈驰,饶章权,等. 基于无人机多传感器数据采集的电力线路安全巡检及智能诊断[J]. 高电压技术,2015,41(1):159-166.PENG Xiangyang,CHEN Chi,RAO Zhangquan,et al. Safety inspec-tion and intelligent diagnosis of transmission line based on unman-ned helicopter of multi sensor data acquisition[J]. High Voltage Engineering,2015,41(1):159-166.
[4] 彭向阳,钱金菊,吴功平,等. 架空输电线路机器人全自主巡检系统及示范应用[J]. 高电压技术,2017,43(8):2582-2591.PENG Xiangyang,QIAN Jinju,WU Gongping,et al. Full automatic inspection system and its demonstration application based on robot for overhead transmission lines[J]. High Voltage Engineering,2017,43(8):2582-2591.
[5] 白丽波,李春雷,祁瑞,等. 对内蒙古中西部地区输电线路鸟害的调查与分析[J]. 内蒙古石油化工,2015(3):43-44.BAI Libo,LI Chunlei,QI Rui,et al. Investigation and analysis of bird harms in the mid western of Inner Mongolia[J]. Inner Mongolia Petrochemical Industry,2015(3):43-44.
[6] 冯玲,黄新波,朱永灿. 基于图像处理的输电线路覆冰厚度测量[J]. 电力自动化设备,2011,31(10):76-80.FENG Ling,HUANG Xinbo,ZHU Yongcan. Transmission line icing thickness measuring based on image processing[J]. Electric Power Automation Equipment,2011,31(10):76-80.
[7] 金立军,姚春羽,闫书佳,等. 基于航拍图像的输电线路异物识别[J]. 同济大学学报(自然科学版),2013,41(2):277-281.JIN Lijun,YAO Chunyu,YAN Shujia,et al. Recognition of extra mat-ters on transmission lines based on aerial images[J]. Journal of Tongji University(Natural Science),2013,41(2):277-281.
[8] WANG Wanguo,ZHANG Jingjing,HAN Jun,et al. Broken strand and foreign body fault detection method for power transmission line based on unmanned aerial vehicle image[J]. Journal of Computer Applications,2015,35(8):2404-2408.
[9] JIAO S,WANG H. The research of transmission line foreign body detection based on motion compensation[C]∥First International Conference on Multimedia and Image Processing. Bandar Seri Begawan,Brunei Darussalam:IEEE,2016:10-14.
[10] 张施令,姚强. 基于WNN-GNN-SVM组合算法的变压器油色谱时间序列预测模型[J]. 电力自动化设备,2018,38(9):1-6.ZHANG Shiling,YAO Qiang. Predicting model of transformer DGA time series based on WNN-GNN-SVM combined algorithm[J]. Electric Power Automation Equipment,2018,38(9):1-6.
[11] 陈振,肖先勇,李长松,等. 基于代价敏感极端学习机的电力系统暂态稳定评估方法[J]. 电力自动化设备,2016,36(2):118-123.CHEN Zhen,XIAO Xianyong,LI Changsong,et al. Power system transient stability assessment based on cost-sensitive extreme learning machine[J]. Electric Power Automation Equipment,2016,36(2):118-123.
[12] SENNI L,RICCI M,PALAZZI A,et al. On-line automatic detection of foreign bodies in biscuits by infrared thermography and image processing[J]. Journal of Food Engineering,2014,128(128):146-156.
[13] SILVER D,HUANG A,MADDISON C J,et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature,2016,529(7587):484-489.
[14] SILVER D,SCHRITTWIESER J,SIMONYAN K,et al. Mastering the game of Go without human knowledge[J]. Nature,2017,550(7676):354-359.
[15] CHEN Y H,KRISHNA T,EMER J S,et al. Eyeriss:an energy-efficient reconfigurable accelerator for deep convolutional neural networks[J]. IEEE Journal of Solid-State Circuits,2017,52(1):127-138.
[16] ABADI M,AGARWAL A,BARHAM P,et al. TensorFlow:large-scale machine learning on heterogeneous distributed systems[J]. IEEE Transactions on Medical Imaging,2018,37(6):1322-1332.
[17] KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet classification with deep convolutional neural networks[C]∥International Conference on Neural Information Processing Systems. [S.l.]:Curran Associates Inc,2012:1097-1105.
[18] HE K,SUN J. Convolutional neural networks at constrained time cost[C]//Computer Vision and Pattern Recognition. Boston,MA,USA:IEEE,2014:5353-5360.
[19] 师飘. 输电线路上鸟巢的检测算法研究[D]. 北京:北京交通大学,2017.SHI Piao. Research on algorithms of bird nest detection on power line[D]. Beijing:Beijing Jiaotong University,2017.
[20] 焦圣喜,王海洋. 基于ORB算法的输电线路异物识别研究[J]. 科学技术与工程,2016,16(27):236-240.JIAO Shengxi,WANG Haiyang. The recognition and tracking of fo-reign body on transmission line based on ORB algorithm[J]. Science Technology and Engineering,2016,16(27):236-240.
[2] 胡毅,刘凯,吴田,等. 输电线路运行安全影响因素分析及防治措施[J]. 高电压技术,2014,40(11):3491-3499.HU Yi,LIU Kai,WU Tian,et al. Analysis of influential factors on operation safety of transmission line and countermeasures[J]. High Voltage Engineering,2014,40(11):3491-3499.
[3] 彭向阳,陈驰,饶章权,等. 基于无人机多传感器数据采集的电力线路安全巡检及智能诊断[J]. 高电压技术,2015,41(1):159-166.PENG Xiangyang,CHEN Chi,RAO Zhangquan,et al. Safety inspec-tion and intelligent diagnosis of transmission line based on unman-ned helicopter of multi sensor data acquisition[J]. High Voltage Engineering,2015,41(1):159-166.
[4] 彭向阳,钱金菊,吴功平,等. 架空输电线路机器人全自主巡检系统及示范应用[J]. 高电压技术,2017,43(8):2582-2591.PENG Xiangyang,QIAN Jinju,WU Gongping,et al. Full automatic inspection system and its demonstration application based on robot for overhead transmission lines[J]. High Voltage Engineering,2017,43(8):2582-2591.
[5] 白丽波,李春雷,祁瑞,等. 对内蒙古中西部地区输电线路鸟害的调查与分析[J]. 内蒙古石油化工,2015(3):43-44.BAI Libo,LI Chunlei,QI Rui,et al. Investigation and analysis of bird harms in the mid western of Inner Mongolia[J]. Inner Mongolia Petrochemical Industry,2015(3):43-44.
[6] 冯玲,黄新波,朱永灿. 基于图像处理的输电线路覆冰厚度测量[J]. 电力自动化设备,2011,31(10):76-80.FENG Ling,HUANG Xinbo,ZHU Yongcan. Transmission line icing thickness measuring based on image processing[J]. Electric Power Automation Equipment,2011,31(10):76-80.
[7] 金立军,姚春羽,闫书佳,等. 基于航拍图像的输电线路异物识别[J]. 同济大学学报(自然科学版),2013,41(2):277-281.JIN Lijun,YAO Chunyu,YAN Shujia,et al. Recognition of extra mat-ters on transmission lines based on aerial images[J]. Journal of Tongji University(Natural Science),2013,41(2):277-281.
[8] WANG Wanguo,ZHANG Jingjing,HAN Jun,et al. Broken strand and foreign body fault detection method for power transmission line based on unmanned aerial vehicle image[J]. Journal of Computer Applications,2015,35(8):2404-2408.
[9] JIAO S,WANG H. The research of transmission line foreign body detection based on motion compensation[C]∥First International Conference on Multimedia and Image Processing. Bandar Seri Begawan,Brunei Darussalam:IEEE,2016:10-14.
[10] 张施令,姚强. 基于WNN-GNN-SVM组合算法的变压器油色谱时间序列预测模型[J]. 电力自动化设备,2018,38(9):1-6.ZHANG Shiling,YAO Qiang. Predicting model of transformer DGA time series based on WNN-GNN-SVM combined algorithm[J]. Electric Power Automation Equipment,2018,38(9):1-6.
[11] 陈振,肖先勇,李长松,等. 基于代价敏感极端学习机的电力系统暂态稳定评估方法[J]. 电力自动化设备,2016,36(2):118-123.CHEN Zhen,XIAO Xianyong,LI Changsong,et al. Power system transient stability assessment based on cost-sensitive extreme learning machine[J]. Electric Power Automation Equipment,2016,36(2):118-123.
[12] SENNI L,RICCI M,PALAZZI A,et al. On-line automatic detection of foreign bodies in biscuits by infrared thermography and image processing[J]. Journal of Food Engineering,2014,128(128):146-156.
[13] SILVER D,HUANG A,MADDISON C J,et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature,2016,529(7587):484-489.
[14] SILVER D,SCHRITTWIESER J,SIMONYAN K,et al. Mastering the game of Go without human knowledge[J]. Nature,2017,550(7676):354-359.
[15] CHEN Y H,KRISHNA T,EMER J S,et al. Eyeriss:an energy-efficient reconfigurable accelerator for deep convolutional neural networks[J]. IEEE Journal of Solid-State Circuits,2017,52(1):127-138.
[16] ABADI M,AGARWAL A,BARHAM P,et al. TensorFlow:large-scale machine learning on heterogeneous distributed systems[J]. IEEE Transactions on Medical Imaging,2018,37(6):1322-1332.
[17] KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet classification with deep convolutional neural networks[C]∥International Conference on Neural Information Processing Systems. [S.l.]:Curran Associates Inc,2012:1097-1105.
[18] HE K,SUN J. Convolutional neural networks at constrained time cost[C]//Computer Vision and Pattern Recognition. Boston,MA,USA:IEEE,2014:5353-5360.
[19] 师飘. 输电线路上鸟巢的检测算法研究[D]. 北京:北京交通大学,2017.SHI Piao. Research on algorithms of bird nest detection on power line[D]. Beijing:Beijing Jiaotong University,2017.
[20] 焦圣喜,王海洋. 基于ORB算法的输电线路异物识别研究[J]. 科学技术与工程,2016,16(27):236-240.JIAO Shengxi,WANG Haiyang. The recognition and tracking of fo-reign body on transmission line based on ORB algorithm[J]. Science Technology and Engineering,2016,16(27):236-240.