浏览全部资源
扫码关注微信
收稿：2020-11-17，
修回：2021-1-7，
录用：2021-1-14，
纸质出版：2021-11-16
移动端阅览
目的
2
在电力系统中，准确地识别绝缘子目标是保障输电线路正常运行的重要前提。针对传统方法无法自动提取绝缘子特征，以及深度学习网络提取绝缘子语义信息不足的问题，提出了一种基于改进多尺度网络的绝缘子识别模型，同时满足自动识别和增强语义信息的要求。
方法
2
改进工作主要分为3部分，首先，采用特征融合的方法，增强特征提取网络生成的特征图的语义信息；其次，特征提取后，为了避免经过多次卷积、池化操作，较小尺度绝缘子语义信息损失严重，因此，扩大网络中的小尺度特征图，进一步丰富较小尺度绝缘子的语义信息；最后，为了更好地识别尺度差异较大的绝缘子，改进锚点框的参数。完成改进工作后，通过边框回归得到绝缘子的准确位置信息，最终识别出绝缘子。
结果
2
实验数据集由复合、玻璃和陶瓷3种材质的绝缘子构成，共有4 350幅图像。在实验数据集上进行识别，实验结果与3种不同结构的多尺度网络模型相比，模型结构最优，识别准确率为96.28%，与传统的Faster RCNN（faster region convolutional neural network）、改进的Faster RCNN等方法相比，识别准确率提高了1.98%~11.99%不等。
结论
2
本文提出的改进模型使绝缘子识别准确率显著提高，为之后的输电线路检测工作夯实基础。
Objective
2
The insulator is the key component in transmission lines. Insulators are numerous and widely distributed in transmission lines. They operate in the field for a long time. Affected by high voltage and complex climate
faults
such as defects and cracks
occur easily. Faults have serious consequences and entail economic losses. Therefore
the insulator components in aerial images need to be identified efficiently and accurately to provide a basis for fault diagnosis and other related work. Traditional insulator recognition methods include threshold segmentation based on target features and recognition algorithms based on image enhancement. These methods need features to be designed manually
but manual selection of labeled features is prone to errors or false checks
and the recognition efficiency and accuracy are low. Hence
this approach cannot fully meet actual needs. Compared with traditional methods
such as image segmentation and image enhancement
deep learning extracts insulator features automatically by using a machine
and it is more accurate and faster than manual extraction.Researchers have used the popular algorithm faster region convolutional neural network(Faster RCNN) to identify insulators and generated proposal regions in the last feature layer by convolution to identify insulator targets. This algorithm results in an insufficient number of feature maps to be identified
and the small scale leads to weak semantic information of insulators
which easily causes misdetection and even non-detection. When the single-shot multi-box detector and "you only look once" use a fixed-size convolution kernel to identify insulators with a large scale difference
the semantic information of insulator features with a relatively small scale is reduced
which easily causes small-scale insulation misdetection.
Method
2
An insulator recognition model based on the improved scale-transferrable network is proposed to address the problems that traditional methods cannot automatically extract insulator features and that the deep learning network is insufficient to extract insulator semantic information. This model meets the requirements of automatic recognition and semantic information enhancement. The length and width of the insulator images are limited to 300×300 pixels. The preprocessed insulator images are outputted to the backbone network Densenet-169. Densenet-169 completes the feature extraction of the insulator images. The improvement work in this study is mainly divided into three parts. First
the feature integration method is used to enhance the semantic information of the feature map generated by Densenet-169. Second
after feature extraction
the semantic information loss of the small-scale insulator becomes serious; therefore
the small-scale feature map in the network is expanded to further enrich the semantic information. Lastly
the parameters of the anchor box are improved to effectively identify the insulator with a large-scale difference. After the improvement work is completed
the accurate position information of the insulator is obtained through bounding box regression
and the insulator is identified.
Result
2
The experimental data set is composed of composite
glass
and ceramic insulators. The images have a total of 4 350
which include 2 000 composite
1 350 glass
and 1 000 ceramic insulator images. The scale of each image is preprocessed as 300×300 pixels
and the training and test sets are divided randomly(3 250 and 1 100
respectively). Experimental results show that the model structure is improved
and the recognition accuracy is 96.28%. The improvement in recognition accuracy ranges from 1.98% to 11.99% relative to the traditional Faster RCNN
improved Faster RCNN
and improved region-based fully convolutional neural network(R-FCN).
Conclusion
2
The improved model increases the accuracy of insulator identification significantly and lays a solid foundation for subsequent transmission line detection work. Considering that the total number of anchor boxes is increased due to the improved scaling module
the compression parameters will be considered in future work to reduce the calculation.
Cheng H Y, Zhai Y J and Chen R. 2019. Faster R-CNN based recognition of insulators in aerial images. Modern Electronics Technique, 42(2): 98-102
程海燕, 翟永杰, 陈瑞. 2019. 基于Faster R-CNN的航拍图像中绝缘子识别. 现代电子技术, 42(2): 98-102 [DOI: 10.16652/j.issn.1004-373x.2019.02.023]
Huang G, Liu Z, Laurens V and Weinberger K Q. 2017. Densely Connected Convolutional Networks//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Hawaii, USA: IEEE: 2261-2269[ DOI: 10.1109/CVPR.2017.243 http://dx.doi.org/10.1109/CVPR.2017.243 ]
Huang X B, Yang L Y, Zhang Y, Cao W and Li L C. 2018. Image enhancement based detection method of non-soluble deposit density levels of porcelain insulators. Automation of Electric Power Systems, 42(14): 151-157
黄新波, 杨璐雅, 张烨, 曹雯, 李立浧. 2018. 基于图像增强的瓷质绝缘子灰密程度检测方法. 电力系统自动化, 42(14): 151-157 [DOI: 10.7500/AEPS20170614017]
Huang X N and Zhang Z L. 2010. A method to extract insulator image from aerial image of helicopter patrol. Power System Technology, 34(1): 194-197
黄宵宁, 张真良. 2010. 直升机巡检航拍图像中绝缘子图像的提取算法. 电网技术, 34(1): 194-197 [DOI: 10.13335/j.1000-3673.pst.2010.01.027]
Ji Z, Kong Q K, Wang H R and Pang Y W. 2019. Small and dense commodity object detection with multi-scale receptive field attention//Proceedings of the 27th ACM International Conference on Multimedia. Nice, France: Association for Computing Machinery: 1349-1357[ DOI: 10.1145/3343031.3351064 http://dx.doi.org/10.1145/3343031.3351064 ]
Jin Y L and Ge F Y. 2020. Pedestrian detection in full-time automatic driving based on FPN fusion architecture. Industrial Control Computer, 33(6): 59-60, 63
金彦亮, 葛飞扬. 2020. 基于FPN融合的全时段自动驾驶中行人检测. 工业控制计算机, 33(6): 59-60, 63 [DOI: 10.3969/j.issn.1001-182X.2020.06.024]
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C Y and Berg A C. 2016. SSD: single shot MultiBox detector//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, the Netherlands: 21-37[ DOI: 10.1007/978-3-319-46448-0_2 http://dx.doi.org/10.1007/978-3-319-46448-0_2 ]
Liu Z, Zhang L M, Geng M X, Yao J, Zhang J L and Hu Y F. 2019. Object detection of high-voltage cable based on improved Faster R-CNN. CAAI Transactions on Intelligent Systems, 14(4): 627-634
刘召, 张黎明, 耿美晓, 么军, 张金禄, 胡益菲. 2019. 基于改进的Faster R-CNN高压线缆目标检测方法. 智能系统学报, 14(4): 627-634 [DOI: 10.11992/tis.201905026]
Lu J Z, Xie P K, Fang Z and Jiang Z L. 2018. Electric field simulation and sheds optimization of anti-icing and anti-lightning insulator under heavy icing condition. Electric Power Automation Equipment, 38(3): 199-204
陆佳政, 谢鹏康, 方针, 蒋正龙. 2018. 重覆冰条件下防冰防雷绝缘子电场仿真与伞裙优化. 电力自动化设备, 38(3): 199-204 [DOI: 10.16081/j.issn.1006-6047.2018.03.027]
Ma Q, Yang Y H, Liu W Y, Qi Z and Guo J Z. 2005. Power system transient stability assessment based on combined support vector machine based on multi input feature integration. Proceedings of The CSEE, 25(6): 17-23
马骞, 杨以涵, 刘文颖, 齐郑, 郭金智. 2005. 多输入特征融合的组合支持向量机电力系统暂态稳定评估. 中国电机工程学报, 25(6): 17-23 [DOI: 10.3321/j.issn:0258-8013.2005.06.004]
Peng X Y, Liu Y, Wang K, Zhang B Y, Qian J J, Chen C and Yang B S. 2019. An automatically locating method for insulator object based on CNNs. Geomatics and Information Science of Wuhan University, 44(4): 563-569
彭向阳, 刘洋, 王柯, 张泊宇, 钱金菊, 陈驰, 杨必胜. 2019. 利用卷积神经网络进行绝缘子自动定位. 武汉大学学报(信息科学版), 44(4): 563-569 [DOI: 10.13203/j.whugis20170175]
Redmon J, Divvala S, Girshick R and Farhadi A. 2016. You only look once: unified, real-time object detection//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 779-788[ DOI: 10.1109/CVPR.2016.91 http://dx.doi.org/10.1109/CVPR.2016.91 ]
Wang D W and Li Y D. 2020. Insulator object detection based on image deblurring by WGAN. Electric Power Automation Equipment, 40(5): 188-194
王德文, 李业东. 2020. 基于WGAN图片去模糊的绝缘子目标检测. 电力自动化设备, 40(5): 188-194 [DOI: 10.16081/j.epae.202003020]
Xie X Y, Zhou J H and Zhang Y J. 2020. Application and challenge of deep learning in ubiquitous power Internet of things. Electric Power Automation Equipment, 40(4): 77-87
谢小瑜, 周俊煌, 张勇军. 2020. 深度学习在泛在电力物联网中的应用与挑战. 电力自动化设备, 40(4): 77-87 [DOI: 10.16081/j.epae.202002008]
Yang F, Wang G J, Peng X S, Wen J Y, Chen Q J, Yang G Y and Li C H. 2018. Partial discharge pattern recognition of high-voltage cables based on convolutional neural network. Electric Power Automation Equipment, 38(5): 123-128
杨帆, 王干军, 彭小圣, 文劲宇, 陈清江, 杨光垚, 李朝晖. 2018. 基于卷积神经网络的高压电缆局部放电模式识别. 电力自动化设备, 38(5): 123-128 [DOI: 10.16081/j.issn.1006-6047.2018.05.018]
Zhang Q, Wang J P and Li W T. 2019. Insulator state detection of convolutional neural networks based on feedback mechanism. Transactions of China Electrotechnical Society, 34(16): 3311-3321
张倩, 王建平, 李帷韬. 2019. 基于反馈机制的卷积神经网络绝缘子状态检测方法. 电工技术学报, 34(16): 3311-3321 [DOI: 10.19595/j.cnki.1000-6753.tces.180962]
Zhao W Q, Cheng X F, Zhao Z B and Zhai Y J. 2020. Insulator recognition based on attention mechanism and Faster RCNN. CAAI Transactions on Intelligent Systems, 15(1): 92-98
赵文清, 程幸福, 赵振兵, 翟永杰. 2020. 注意力机制和Faster RCNN相结合的绝缘子识别. 智能系统学报, 15(1): 92-98 [DOI: 10.11992/tis.201907023]
Zhao Z B, Cui Y P, Qi Y C, Du L Q, Zhang K and Zhai Y J. 2019. Detection method of insulator in aerial inspection image based on modified R-FCN. Computer Science, 46(3): 159-163
赵振兵, 崔雅萍, 戚银城, 杜丽群, 张珂, 翟永杰. 2019. 基于改进的R-FCN航拍巡线图像中的绝缘子检测方法. 计算机科学, 46(3): 159-163 [DOI: 10.11896/j.issn.1002-137X.2019.03.024]
Zhao Z B, Qi H Y, Qi Y C, Zhang K, Zhai Y J and Zhao W Q. 2020. Detection method based on automatic visual shape clustering for pin-missing defect in transmission lines. IEEE Transactions on Instrumentation and Measurement, 69(9): 6080-6091[DOI: 10.1109/TIM.2020.2969057]
Zhou P, Ni B B, Geng C, Hu J G and Xu Y. 2018. Scale-transferrable object detection//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 528-537[ DOI: 10.1109/CVPR.2018.00062 http://dx.doi.org/10.1109/CVPR.2018.00062 ]
Zou H L and Lu L. 2019. Object detection of aerial insulator images based on residual-FPN optimization. Instrumentation Technology, (10): 13-16
邹汉凌, 陆丽. 2019. 基于Residual-FPN优化的航拍绝缘子目标识别. 仪表技术, (10): 13-16 [DOI: 10.19432/j.cnki.issn1006-2394.2019.10.004]
相关作者
相关机构
京公网安备11010802024621
