基于 Canny算子的简化 PCNN电力故障区域提取方法

冯振新; 许晓路; 周东国; 江翼; 丁国成

红外技术, 2019, 41 (7): 634, 网络出版: 2019-08-13

基于 Canny算子的简化 PCNN电力故障区域提取方法

Fault Region Extraction of Electrical Equipments in Infrared Images by Pulse-coupled Neural Network Method with Canny Operator

论文大纲

冯振新 ^1,*许晓路 ¹周东国 ²江翼 ¹丁国成 ¹

作者单位

¹ 国网电力科学研究院武汉南瑞有限责任公司，湖北武汉 430074

² 武汉大学电气与自动化学院，湖北武汉 430072

脉冲耦合神经网络电力设备故障红外图像 Canny算子 Pulse-coupled neural network，electronical equipme

摘要

为了较好地实现电力设备红外图像故障区域提取，提出了一种基于 Canny算子边界检测的脉冲耦合神经网络( Pulse-coupled Neural Network，PCNN)红外图像区域提取方法。在该方法中，首先以 PCNN模型同步点火特性为基础，通过优化原始 PCNN模型内在的参数，使得模型迭代过程中将图像转换成为时间点火序列，然后引入 Canny边界检测算子并结合区域灰度特性，获取最佳时刻的脉冲输出信息，实现红外图像中热故障区域的有效提取。最后通过真实红外故障图像测试，验证了文中方法的有效性和适用性，同时方便了后续的特征提取与识别。

Abstract

To implement the extraction of fault regions from infrared images of electronic equipment, in this study, we present a pulse-coupled neural network (PCNN) infrared image region extraction method, which is based on the cooperation of the Canny algorithm. In this method, by using the synchronous pulse characteristics of the original PCNN model, several parameters are simplified to enable the PCNN model to generate time series through iterations. Meanwhile, the canny method is used to improve the ability of the PCNN model to segment infrared images efficiently and extract effective thermal fault regions. Experimental results show that the proposed method has the ability to obtain good segmentation performance and can be suitable for further feature extraction and recognition.

参考文献

[1] Jadin M S, Taib S. Recent progress in diagnosing the reliability of electrical equipment by using infrared thermography[J]. Infrared Physics & Technology, 2012, 55(4): 236-245.

[2] 杨先明, 叶玉堂, 方亮, 等. 红外电路故障检测系统 [J].红外与激光工程, 2006, 35(3): 262-266. YANG Xiaoming, YE Yutang, FANG Liang, et al. Infrared detection tester for electronic circuit[J]. Infrared and Laser Engineering, 2006,35(3): 262-265.

[3] 芦竹茂, 王天正, 俞华, 等. 基于红外图像分析的电力设备热故障检测技术研究[J]. 现代电子技术, 2017, 40(11): 123-126. LU Zhumang, WANG Tianzheng, YU Hua, et al. Research on electrical equipment thermal fault detection technology based on infrared image analysis[J]. Modern Electronics Technique, 2017, 40(11): 123-126.

[4] 井金剑, 翟春艳, 李书臣, 等. 基于红外图像识别的电气设备故障诊断[J].电子设计工程 , 2014, 22(12): 171-173. JING Jinjian, ZHAI Chunyan, LI Shuchen, et al. Fault diagnosis of electrical equipment based on infrared image recognition[J]. Electronic Design Engineering, 2014, 22(12): 171-173.

[5] 梁利利. 变电站红外图像的识别与故障诊断 [D].西安: 西安科技大学, 2010. LIANG Lili. Substation infrared image recognition and fault diagnosis[D]. Xi’an: Xi’an University, 2010.

[6] 孙伟, 王宏飞 , 邵锡军 . 基于改进分水岭算法的红外图像分割 [J].红外与激光工程, 2006, 35(Z5): 31-37. SUN Wei, WANG Hongfei, SHAO Xijun. Infrared target segmentation method based on improved watershed algorithms[J]. Infrared and Lazer Engineering, 2006, 35(Z5): 31-37.

[7] 靳璐, 付梦印 . 基于遗传模糊核聚类的图像分割 [J]. 模式识别与人工智能, 2013, 26(2): 205-210. JIN Lu, FU Mengyin. Image segmentation based on genetic kernel fuzzy c-means clustering algorithm[J]. PR &AI, 2013, 26(2): 205-210..

[8] 孙怡, 吴邦树, 刘仪卜, 等. 基于红外图像处理的电气设备故障诊断方法[J].机电工程技术 , 2016, 45(6): 58-61. SUN Yi, WU Bangshu, LIU Yibu, et al. Method of default diagnoising of electric equipments based on infrared image processing[J]. Mechanical & Electrical, 2016, 45(6): 58-61.

[9] 梁利利. 变电站红外图像的识别与故障诊断 [D].西安: 西安科技大学, 2010. LIANG Lili. Substation infrared image recognition and fault diagnosis[D]. Xi’an: Xi’an University, 2010.

[10] 门洪, 于加学, 秦蕾. 基于 CA和 OTSU的电气设备红外图像分割方法[J].电力自动化设备 , 2011, 31(9): 93-95. MEN Hong, YU Jiaxue, QIN Lei. Segmentation of electric equipment infrared image based on CA and OTSU[J]. Electric Power Automation Equipment, 2011, 31(9): 93-95.

[11] 王如意. 变电站电力设备红外图像分割技术研究 [D].西安: 西安科技大学, 2011. WANG Ruyi. Research of infrared segmentation for power equipment[D]. Xi’an: XiDian University, 2011.

[12] 付强, 姚建刚, 李唐兵, 等. 基于红外图像的绝缘子串钢帽和盘面区域自动提取方法[J].红外技术 , 2016, 38(11): 969-974, 979. FU Jiang, YAO Jiangang, LI Tangbing. The automatic extraction method of the insulator string’s steel caps and disks area based on infrared image[J]. Infrared Technology, 2016, 38(11): 969-974, 979.

[13] 刘琼, 马义德, 钱志柏 , 等. 一种基于交叉熵的改进型 PCNN图像自动分割新方法[J].中国图象图形学报, 2005, 10(5): 579-585. LIU Qing, MA Yide, QIAN Zhibai. Automated image segmentation using improved PCNN model based on Cross-entropy[J]. Journal of Image and Graphics, 2005, 10(5): 579-585

[14] Cope P K, Rockett P I. Efficacy of Gaussian smoothing in Canny edge detector[J]. Electronic Letters, 2000, 36(19): 1615-1616.

[15] 马义德. 脉冲耦合神经网络原理及其应用 [M].北京: 科学出版社 , 2006. MA Yide. Applications of Pulse-coupled Neural Networks[M]. Beijing: Science Press, 2006.

[16] Menardi G. A review on modal clustering[J]. International Statistical Review, 2016, 84(3): 413-433.

冯振新, 许晓路, 周东国, 江翼, 丁国成. 基于 Canny算子的简化 PCNN电力故障区域提取方法[J]. 红外技术, 2019, 41(7): 634. FENG Zhengxin, XU Xiaolu, ZHOU Dongguo, JIANG Yi, DING Guocheng. Fault Region Extraction of Electrical Equipments in Infrared Images by Pulse-coupled Neural Network Method with Canny Operator[J]. Infrared Technology, 2019, 41(7): 634.

基于 Canny算子的简化 PCNN电力故障区域提取方法

关于本站 Cookie 的使用提示

全站搜索

基于 Canny算子的简化 PCNN电力故障区域提取方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索