基于图像增强的瓷质绝缘子灰密程度检测方法
|
摘要
由于雾天、光线较暗等恶劣现场条件下采集到的绝缘子图像清晰度与可读性较低,绝缘子目标及盘面区域色彩特征的提取较难,导致现有的可见光图像污秽检测方法不具备通用性,为此提出了一种基于图像增强的瓷质绝缘子灰密程度检测方法。先用改进的带颜色恢复的多尺度Retinex(MSRCR)算法对采集到的绝缘子图像进行增强,提高图像的清晰度和对比度;然后,采用二维最小误差法结合形态学滤波分割提取出绝缘子盘面区域,分别提取6个通道的均值、最大值、最小值等7个特征量并用Fisher准则函数筛选出分类能力较强的特征Smean,Smax,Svar作为灰密程度判别特征;最后,用思维进化算法(MEA)优化反向传播(BP)神经网络进行仿真预测。实验结果表明,概率神经网络和粒子群优化算法优化BP神经网络的判别准确率分别为88.00%和93.00%,而所提方法的准确率可达95.00%,可以准确判别恶劣条件下的绝缘子灰密程度。
It is difficult to gather the high-definition and readable images of insulators in bad conditions such as foggy day and dim light.The available contamination detection methods of visible images does not have generality due to the difficulty of extracting insulator objects and color features of surface region.Therefore,this paper proposes a image enhancement based detection method of non-soluble deposit density(NSDD)levels of porcelain insulators.Firstly,the improved multiple scale Retinex with color restoration(MSRCR)algorithm is used to enhance the clarity and contrast of the collected insulator images.Secondly,the two-dimensional minimum error algorithm and the morphological filter algorithm are combined to segment and extract the surface region of insulators.And seven characteristic values in six channels are extracted,such as mean value,maximum value,minimum value.Then the Smean,Smaxand Svar with highly classification ability are selected as the identify features of NSDD levels by using the Fisher criterion function.Finally,the back propagation(BP)neural network optimized by the mind evolutionary algorithm(MEA)is used for simulation and forecast.The experiment results show that the recognition accuracy rates of the probabilistic neural network algorithm and the BP neural network optimized by particle swarm optimization(PSO)algorithm are 88.00% and 93.00%,respectively.In comparison,the accuracy rate of the proposed method is 95.00%,which shows that it can accurately identify the NSDD levels of insulators in bad conditions.
It is difficult to gather the high-definition and readable images of insulators in bad conditions such as foggy day and dim light.The available contamination detection methods of visible images does not have generality due to the difficulty of extracting insulator objects and color features of surface region.Therefore,this paper proposes a image enhancement based detection method of non-soluble deposit density(NSDD)levels of porcelain insulators.Firstly,the improved multiple scale Retinex with color restoration(MSRCR)algorithm is used to enhance the clarity and contrast of the collected insulator images.Secondly,the two-dimensional minimum error algorithm and the morphological filter algorithm are combined to segment and extract the surface region of insulators.And seven characteristic values in six channels are extracted,such as mean value,maximum value,minimum value.Then the Smean,Smaxand Svar with highly classification ability are selected as the identify features of NSDD levels by using the Fisher criterion function.Finally,the back propagation(BP)neural network optimized by the mind evolutionary algorithm(MEA)is used for simulation and forecast.The experiment results show that the recognition accuracy rates of the probabilistic neural network algorithm and the BP neural network optimized by particle swarm optimization(PSO)algorithm are 88.00% and 93.00%,respectively.In comparison,the accuracy rate of the proposed method is 95.00%,which shows that it can accurately identify the NSDD levels of insulators in bad conditions.
引文
[1]黄新波,陈贵荣,王孝敬,等.输电线路在线监测与故障诊断[M].2版.北京:中国电力出版社,2014:206-232.HUANG Xinbo,CHEN Guirong,WANG Xiaojing,et al.Online monitoring and fault diagnosis of transmission line[M].2nd ed.Beijing:China Electric Power Press,2014:206-232.
[2]LIU Yutian,FAN Rui,TERZIJA V.Power system restoration:a literature review from 2006to 2016[J].Journal of Modern Power Systems and Clean Energy,2016,4(3):332-341.
[3]HUANG Xinbo,ZHANG Huiying,ZHANG Ye.Automatic identification and location technology of glass insulator selfshattering[J].Journal of Electronic Imaging,2017,26(6):1-12.
[4]HE J,GORUR R S.Flashover of insulators in a wet environment[J].IEEE Transactions on Dielectrics and Electrical Insulation,2017,24(2):1038-1044.
[5]赵伟强,黄新波,赵隆,等.输电线路绝缘子表面盐密在线监测系统[J].西安工程大学学报,2016,30(1):86-92.ZHAO Weiqiang,HUANG Xinbo,ZHAO Long,et al.The online monitoring system for insulator surface salt density of transmission lines[J].Journal of Xi’an Polytechnic University,2016,30(1):86-92.
[6]何慧雯,戴敏,张亚萍,等.污秽绝缘子泄漏电流在线监测及数据分析[J].高电压技术,2010,36(12):3007-3014.HE Huiwen,DAI Min,ZHANG Yaping,et al.Online monitoring and data analysis on leakage current of insulators[J].High Voltage Engineering,2010,36(12):3007-3014.
[7]李璟延,司马文霞,孙才新,等.绝缘子污秽度预测特征量提取与神经网络模型[J].电力系统自动化,2008,32(15):84-88.LI Jingyan,SIMA Wenxia,SUN Caixin,et al.Characteristics extraction for contamination forecast of insulators and the neural network model[J].Automation of Electric Power Systems,2008,32(15):84-88.
[8]梅红伟,曹彬,王耿耿,等.绝缘子表面局部等值盐密测量方法[J].电网技术,2016,40(4):1289-1294.MEI Hongwei,CAO Bin,WANG Genggeng,et al.Research on partial equivalent salt deposit density for insulator[J].Power System Technology,2016,40(4):1289-1294.
[9]HUANG Xinbo,CHENG Xie,LI Husheng.Equivalent salt deposit density optical fiber sensor for transmission lines in power grid[J].IEEE Sensors Journal,2017,17(1):91-99.
[10]张烨,黄新波,李菊清,等.视频图像处理在输电线路安防系统的应用[J].广东电力,2016,29(5):102-107.ZHANG Ye,HUANG Xinbo,LI Juqing,et al.Application of video and image processing in transmission line security system[J].Guangdong Electric Power,2016,29(5):102-107.
[11]田治仁,金立军.基于彩色可见光图像的绝缘子污秽等级判别[J].电工电能新技术,2015,34(9):70-74.TIAN Zhiren,JIN Lijun.Detection of insulator contamination grades based on digital image processing[J].Advanced Technology of Electrical Engineering and Energy,2015,34(9):70-74.
[12]ZHANG Wenfei,LIANG Jian,JU Haijuan,et al.Study of visibility enhancement of hazy images based on dark channel prior in polarimetric imaging[J].Optik-International Journal for Light and Electron Optics,2017,130:123-130.
[13]黄新波,李菊清,张烨,等.复杂环境下覆冰绝缘子识别检测技术[J].高电压技术,2017,43(3):891-899.HUANG Xinbo,LI Juqing,ZHANG Ye,et al.The research of recognition and detection technology of ice-covered insulators under complex environment[J].High Voltage Engineering,2017,43(3):891-899.
[14]陈向阳,谭礼健.基于自适应分数阶微分的医学图像增强算法[J].计算机应用研究,2017,34(11):1-8.CHEN Xiangyang,TAN Lijian.Medical image enhancement algorithm based on adaptive fractional order differentiation[J].Application Research of Computers,2017,34(11):1-8.
[15]刘振宇,江海蓉,徐鹤文.极端天气条件下低质图像增强算法研究[J].计算机工程与应用,2017,53(8):193-198.LIU Zhenyu,JIANG Hairong,XU Hewen.Low-quality image enhancement algorithms in extreme weather conditions[J].Computer Engineering and Applications,2017,53(8):193-198.
[16]张雅媛.基于多尺度Retinex算法的彩色雾霾图像增强研究[J].包装学报,2016,8(3):60-65.ZHANG Yayuan.Research of haze color image enhancement based on multi-scale Retinex[J].Packaging Journal,2016,8(3):60-65.
[17]范九伦,雷博.灰度图像最小误差阈值分割法的二维推广[J].自动化学报,2009,35(4):386-393.FAN Jiulun,LEI Bo.Two-dimensional extension of minimum error threshold segmentation method for gray-level images[J].Acta Automatica Sinica,2009,35(4):386-393.
[18]陈明亮,陈成新,古建平.一种基于直方图的自适应分段线性变换法[J].国外电子测量技术,2015,34(2):36-38.CHEN Mingliang,CHEN Chengxin,GU Jianping.Adaptive piecewise linear transform method based on histogram[J].Foreign Electronic Measurement Technology,2015,34(2):36-38.
[19]张秀君,孙晓丽.分段线性变换增强的自适应方法[J].电子科技,2005(3):13-16.ZHANG Xiujun,SUN Xiaoli.A research on the piecewise linear transformation in adaptive IR image enhancement[J].IT AGE,2005(3):13-16.
[20]李宁,许树成,邓中亮.基于HSI色彩坐标相似度的彩色图像分割方法[J].现代电子技术,2017,40(2):30-33.LI Ning,XU Shucheng,DENG Zhongliang.Color image segmentation based on similarity in HSI color coordinate[J].Modern Electronics Technique,2017,40(2):30-33.
[21]缪慧司,梁光明,刘任任,等.基于HSI修正空间信息融合的彩色白细胞图像分割方法[J].生物医学工程学杂志,2016,33(2):303-307.MIAO Huisi,LIANG Guangming,LIU Renren,et al.Segmentation method of color white blood cell image based on HSI modified space information fusion[J].Journal of Biomedical Engineering,2016,33(2):303-307.
[22]王继东,庞文杰.Fisher判别分类法在光伏并网系统稳态电能质量评估中的应用[J].电力自动化设备,2017,37(3):50-54.WANG Jidong,PANG Wenjie.Application of Fisher discriminant analysis in steady-state power quality evaluation of grid-connected photovoltaic system[J].Electric Power Automation Equipment,2017,37(3):50-54.
[23]章浩伟,孙洋洋,刘颖,等.基于Fisher判别分析的多囊卵巢综合征中医证候分布规律[J].北京生物医学工程,2017,36(1):82-86.ZHANG Haowei,SUN Yangyang,LIU Ying,et al.Distribution regularity of TCM syndromes in patients with polycystic ovary syndrome based on Fisher discriminant analysis[J].Beijing Biomedical Engineering,2017,36(1):82-86.
[24]钱兆明,任高峰,褚夫蛟,等.基于PCA法和Fisher判别分析法的岩体质量等级分类[J].岩土力学,2016,37(增刊2):427-432.QIAN Zhaoming,REN Gaofeng,CHU Fujiao,et al.Rock mass quality classification based on PCA and Fisher discrimination analysis[J].Rock and Soil Mechanics,2016,37(Supplement 2):427-432.
[25]吴志攀,赵跃龙,罗中良,等.基于PSO-BP神经网络的车牌号码识别技术[J].中山大学学报(自然科学版),2017,56(1):46-52.WU Zhipan,ZHAO Yuelong,LUO Zhongliang,et al.License plate recognition technology based on PSO-BP neural network[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2017,56(1):46-52.
[26]余发山,康洪,张宏伟.基于PSO优化BP神经网络的液压钻机故障诊断[J].自动化仪表,2016(4):42-46.YU Fashan,KANG Hong,ZHANG Hongwei.Fault diagnosis for hydraulic drilling rig based on BP neural network optimized by PSO[J].Process Automation Instrumentation,2016(4):42-46.
[27]杨凌霄,朱亚丽.基于概率神经网络的高压断路器故障诊断[J].电力系统保护与控制,2015,43(10):62-67.YANG Lingxiao,ZHU Yali.High voltage circuit breaker fault diagnosis of probabilistic neural network[J].Power System Protection and Control,2015,43(10):62-67.
[28]张代磊,黄大年,张冲.基于遗传算法优化的BP神经网络在密度界面反演中的应用[J].吉林大学学报(地球科学版),2017,47(2):580-588.ZHANG Dailei,HUANG Danian,ZHANG Chong.Application of BP neural network based on genetic algorithm in the inversion of density interface[J].Journal of Jilin University(Earth Science Edition),2017,47(2):580-588.
[29]GAO J L.Modeling of photovoltaic cell based on BP neural networks improved by MEA[J].Applied Mechanics and Materials,2012,217/218/219:809-814.
[30]张以帅,赖惠鸽,李勇,等.基于MEA优化BP神经网络的天然气短期负荷预测[J].自动化与仪表,2016(5):15-19.ZHANG Yishuai,LAI Huige,LI Yong,et al.Short-term gas load forecasting based on MEA optimized BP neural network[J].Automation&Instrumentation,2016(5):15-19.
[31]HUANG Xinbo,ZHANG Fei,LI Husheng,et al.An online technology for measuring icing shape on conductor based on vision and force sensors[J].IEEE Transactions on Instrumentation and Measurement,2017,66(12):3180-3189.
[32]张烨,冯玲,穆靖宇,等.输电线路绝缘子覆冰厚度图像识别算法[J].电力系统自动化,2016,40(21):195-202.DOI:10.7500/AEPS20160116007.ZHANG Ye,FENG Ling,MU Jingyu,et al.Image identification algorithm of icing thickness for insulator in power transmission lines[J].Automation of Electric Power Systems,2016,40(21):195-202.DOI:10.7500/AEPS20160116007.
[2]LIU Yutian,FAN Rui,TERZIJA V.Power system restoration:a literature review from 2006to 2016[J].Journal of Modern Power Systems and Clean Energy,2016,4(3):332-341.
[3]HUANG Xinbo,ZHANG Huiying,ZHANG Ye.Automatic identification and location technology of glass insulator selfshattering[J].Journal of Electronic Imaging,2017,26(6):1-12.
[4]HE J,GORUR R S.Flashover of insulators in a wet environment[J].IEEE Transactions on Dielectrics and Electrical Insulation,2017,24(2):1038-1044.
[5]赵伟强,黄新波,赵隆,等.输电线路绝缘子表面盐密在线监测系统[J].西安工程大学学报,2016,30(1):86-92.ZHAO Weiqiang,HUANG Xinbo,ZHAO Long,et al.The online monitoring system for insulator surface salt density of transmission lines[J].Journal of Xi’an Polytechnic University,2016,30(1):86-92.
[6]何慧雯,戴敏,张亚萍,等.污秽绝缘子泄漏电流在线监测及数据分析[J].高电压技术,2010,36(12):3007-3014.HE Huiwen,DAI Min,ZHANG Yaping,et al.Online monitoring and data analysis on leakage current of insulators[J].High Voltage Engineering,2010,36(12):3007-3014.
[7]李璟延,司马文霞,孙才新,等.绝缘子污秽度预测特征量提取与神经网络模型[J].电力系统自动化,2008,32(15):84-88.LI Jingyan,SIMA Wenxia,SUN Caixin,et al.Characteristics extraction for contamination forecast of insulators and the neural network model[J].Automation of Electric Power Systems,2008,32(15):84-88.
[8]梅红伟,曹彬,王耿耿,等.绝缘子表面局部等值盐密测量方法[J].电网技术,2016,40(4):1289-1294.MEI Hongwei,CAO Bin,WANG Genggeng,et al.Research on partial equivalent salt deposit density for insulator[J].Power System Technology,2016,40(4):1289-1294.
[9]HUANG Xinbo,CHENG Xie,LI Husheng.Equivalent salt deposit density optical fiber sensor for transmission lines in power grid[J].IEEE Sensors Journal,2017,17(1):91-99.
[10]张烨,黄新波,李菊清,等.视频图像处理在输电线路安防系统的应用[J].广东电力,2016,29(5):102-107.ZHANG Ye,HUANG Xinbo,LI Juqing,et al.Application of video and image processing in transmission line security system[J].Guangdong Electric Power,2016,29(5):102-107.
[11]田治仁,金立军.基于彩色可见光图像的绝缘子污秽等级判别[J].电工电能新技术,2015,34(9):70-74.TIAN Zhiren,JIN Lijun.Detection of insulator contamination grades based on digital image processing[J].Advanced Technology of Electrical Engineering and Energy,2015,34(9):70-74.
[12]ZHANG Wenfei,LIANG Jian,JU Haijuan,et al.Study of visibility enhancement of hazy images based on dark channel prior in polarimetric imaging[J].Optik-International Journal for Light and Electron Optics,2017,130:123-130.
[13]黄新波,李菊清,张烨,等.复杂环境下覆冰绝缘子识别检测技术[J].高电压技术,2017,43(3):891-899.HUANG Xinbo,LI Juqing,ZHANG Ye,et al.The research of recognition and detection technology of ice-covered insulators under complex environment[J].High Voltage Engineering,2017,43(3):891-899.
[14]陈向阳,谭礼健.基于自适应分数阶微分的医学图像增强算法[J].计算机应用研究,2017,34(11):1-8.CHEN Xiangyang,TAN Lijian.Medical image enhancement algorithm based on adaptive fractional order differentiation[J].Application Research of Computers,2017,34(11):1-8.
[15]刘振宇,江海蓉,徐鹤文.极端天气条件下低质图像增强算法研究[J].计算机工程与应用,2017,53(8):193-198.LIU Zhenyu,JIANG Hairong,XU Hewen.Low-quality image enhancement algorithms in extreme weather conditions[J].Computer Engineering and Applications,2017,53(8):193-198.
[16]张雅媛.基于多尺度Retinex算法的彩色雾霾图像增强研究[J].包装学报,2016,8(3):60-65.ZHANG Yayuan.Research of haze color image enhancement based on multi-scale Retinex[J].Packaging Journal,2016,8(3):60-65.
[17]范九伦,雷博.灰度图像最小误差阈值分割法的二维推广[J].自动化学报,2009,35(4):386-393.FAN Jiulun,LEI Bo.Two-dimensional extension of minimum error threshold segmentation method for gray-level images[J].Acta Automatica Sinica,2009,35(4):386-393.
[18]陈明亮,陈成新,古建平.一种基于直方图的自适应分段线性变换法[J].国外电子测量技术,2015,34(2):36-38.CHEN Mingliang,CHEN Chengxin,GU Jianping.Adaptive piecewise linear transform method based on histogram[J].Foreign Electronic Measurement Technology,2015,34(2):36-38.
[19]张秀君,孙晓丽.分段线性变换增强的自适应方法[J].电子科技,2005(3):13-16.ZHANG Xiujun,SUN Xiaoli.A research on the piecewise linear transformation in adaptive IR image enhancement[J].IT AGE,2005(3):13-16.
[20]李宁,许树成,邓中亮.基于HSI色彩坐标相似度的彩色图像分割方法[J].现代电子技术,2017,40(2):30-33.LI Ning,XU Shucheng,DENG Zhongliang.Color image segmentation based on similarity in HSI color coordinate[J].Modern Electronics Technique,2017,40(2):30-33.
[21]缪慧司,梁光明,刘任任,等.基于HSI修正空间信息融合的彩色白细胞图像分割方法[J].生物医学工程学杂志,2016,33(2):303-307.MIAO Huisi,LIANG Guangming,LIU Renren,et al.Segmentation method of color white blood cell image based on HSI modified space information fusion[J].Journal of Biomedical Engineering,2016,33(2):303-307.
[22]王继东,庞文杰.Fisher判别分类法在光伏并网系统稳态电能质量评估中的应用[J].电力自动化设备,2017,37(3):50-54.WANG Jidong,PANG Wenjie.Application of Fisher discriminant analysis in steady-state power quality evaluation of grid-connected photovoltaic system[J].Electric Power Automation Equipment,2017,37(3):50-54.
[23]章浩伟,孙洋洋,刘颖,等.基于Fisher判别分析的多囊卵巢综合征中医证候分布规律[J].北京生物医学工程,2017,36(1):82-86.ZHANG Haowei,SUN Yangyang,LIU Ying,et al.Distribution regularity of TCM syndromes in patients with polycystic ovary syndrome based on Fisher discriminant analysis[J].Beijing Biomedical Engineering,2017,36(1):82-86.
[24]钱兆明,任高峰,褚夫蛟,等.基于PCA法和Fisher判别分析法的岩体质量等级分类[J].岩土力学,2016,37(增刊2):427-432.QIAN Zhaoming,REN Gaofeng,CHU Fujiao,et al.Rock mass quality classification based on PCA and Fisher discrimination analysis[J].Rock and Soil Mechanics,2016,37(Supplement 2):427-432.
[25]吴志攀,赵跃龙,罗中良,等.基于PSO-BP神经网络的车牌号码识别技术[J].中山大学学报(自然科学版),2017,56(1):46-52.WU Zhipan,ZHAO Yuelong,LUO Zhongliang,et al.License plate recognition technology based on PSO-BP neural network[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2017,56(1):46-52.
[26]余发山,康洪,张宏伟.基于PSO优化BP神经网络的液压钻机故障诊断[J].自动化仪表,2016(4):42-46.YU Fashan,KANG Hong,ZHANG Hongwei.Fault diagnosis for hydraulic drilling rig based on BP neural network optimized by PSO[J].Process Automation Instrumentation,2016(4):42-46.
[27]杨凌霄,朱亚丽.基于概率神经网络的高压断路器故障诊断[J].电力系统保护与控制,2015,43(10):62-67.YANG Lingxiao,ZHU Yali.High voltage circuit breaker fault diagnosis of probabilistic neural network[J].Power System Protection and Control,2015,43(10):62-67.
[28]张代磊,黄大年,张冲.基于遗传算法优化的BP神经网络在密度界面反演中的应用[J].吉林大学学报(地球科学版),2017,47(2):580-588.ZHANG Dailei,HUANG Danian,ZHANG Chong.Application of BP neural network based on genetic algorithm in the inversion of density interface[J].Journal of Jilin University(Earth Science Edition),2017,47(2):580-588.
[29]GAO J L.Modeling of photovoltaic cell based on BP neural networks improved by MEA[J].Applied Mechanics and Materials,2012,217/218/219:809-814.
[30]张以帅,赖惠鸽,李勇,等.基于MEA优化BP神经网络的天然气短期负荷预测[J].自动化与仪表,2016(5):15-19.ZHANG Yishuai,LAI Huige,LI Yong,et al.Short-term gas load forecasting based on MEA optimized BP neural network[J].Automation&Instrumentation,2016(5):15-19.
[31]HUANG Xinbo,ZHANG Fei,LI Husheng,et al.An online technology for measuring icing shape on conductor based on vision and force sensors[J].IEEE Transactions on Instrumentation and Measurement,2017,66(12):3180-3189.
[32]张烨,冯玲,穆靖宇,等.输电线路绝缘子覆冰厚度图像识别算法[J].电力系统自动化,2016,40(21):195-202.DOI:10.7500/AEPS20160116007.ZHANG Ye,FENG Ling,MU Jingyu,et al.Image identification algorithm of icing thickness for insulator in power transmission lines[J].Automation of Electric Power Systems,2016,40(21):195-202.DOI:10.7500/AEPS20160116007.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |