Insulator State Detection of Convolutional Neural Networks Based on Feedback Mechanism
Zhang Qian1, Wang Jianping1, Li Weitao1,2
1. School of Electric Engineering and Automation Hefei University of Technology Hefei 230009 China; 2. State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang 110004 China
Abstract As an important equipment on the transmission line, the conditions of insulators directly affect the safe operation of power grid. Therefore, it is important and necessary to detect the insulator state automatically and accurately. However, existing detection models with constant feature space have drawbacks for distinctive samples, and it is complex to extract insulator image features. Thus, a method for insulator state detection based on convolutional neural network and feedback mechanism is explored in this paper, which imitates the human cognition process with repetitive comparison and inference from simple to fine. Firstly, according to the characteristics of the insulator samples, the network structure of LeNet-5 is improved by employing stochastic configuration networks (SCNs) and the feedback mechanism, and the alternate optimization strategy is adopted to optimize the parameters of the convolution neural network. Secondly, based on the entropy theory, the semantic error entropy measurement index is established to evaluate the uncertainty of the insulator detection results in real time to overcome the posterior evaluation. Finally, according to the evaluation results of semantic error information entropy measurement index, the feedback mechanism is constructed to adjust the size and number of the convolution kernels to extract the refined features for the repeated comparison and inference. The experimental results show that the improved convolution neural network model has a superior accuracy in insulator state detection.
Zhang Qian,Wang Jianping,Li Weitao. Insulator State Detection of Convolutional Neural Networks Based on Feedback Mechanism[J]. Transactions of China Electrotechnical Society, 2019, 34(16): 3311-3321.
[1] Lopes F V, Dantas K M, Silva K M, et al.Accurate two-terminal transmission line fault location using traveling waves[J]. IEEE Transactions on Power Delivery, 2018, 33(2): 873-880. [2] Eroğlu H, Aydin M.Solving power transmission line routing problem using improved genetic and artificial bee colony algorithms[J]. Electrical Engineering, 2018, 100(3): 2103-2116. [3] Costa, Monti F B, AntonelloLopes, et al. Two- terminal traveling wave-based transmission line protection[J]. IEEE Transactions on Power Delivery, 2017, 32(3): 1382-1393. [4] 吕玉坤, 赵伟萍, 庞广陆, 等. 典型伞型瓷及复合绝缘子积污特性模拟研究[J]. 电工技术学报, 2018, 33(1): 209-216. Lü Yukun, Zhao Weiping, Pang Guanglu, et al.Simulation of contamination deposition on typical shed porcelain and composite insulators[J]. Transa- ctions of China Electrotechnical Society, 2018, 33(1): 209-216. [5] 律方成, 刘宏宇, 汪佛池, 等. 高速气流条件下污秽颗粒在复合绝缘子表面的沉积判据[J]. 电工技术学报, 2017, 32(1): 206-213. Lü Fangcheng, Liu Hongyu, Wang Fochi, et al.Deposit criterion of pollution particles on composite insulators surface under high speed aerosol[J]. Transactions of China Electrotechnical Society, 2017, 32(1): 206-213. [6] 蒋兴良, 潘杨, 汪泉霖, 等. 基于等效直径的复合绝缘子覆冰特性与结构参数分析[J]. 电工技术学报, 2017, 32(7): 190-196. Jang Xinliang, Pan Yang, Wang Quanlin, et al.Research on icing characteristics of composite insulator and structural parameter analysis based on equivalent diameter[J]. Transactions of China Elec- trotechnical Society, 2017, 32(7): 190-196. [7] 杨凯, 张认成, 杨建红, 等. 基于分形维数和支持向量机的串联电弧故障诊断方法[J]. 电工技术学报, 2016, 31(2): 70-77. Yang Kai, Zhang Rencheng, Yang Jianhong, et al.Series arc fault diagnostic method based on fractal dimension and support vector machine[J]. Transa- ctions of China Electrotechnical Society, 2016, 31(2): 70-77. [8] 程学珍, 林晓晓, 朱春华, 等. 基于时序信息的模糊Petri网电网故障诊断方法[J]. 电工技术学报, 2017, 32(14): 229-237. Cheng Xuezhen, Lin Xiaoxiao, Zhu Chunhua, et al.Power system fault analysis based on hierarchical fuzzy Petri net considering time association character[J]. Transactions of China Electrotechnical Society, 2017, 32(14): 229-237. [9] 律方成, 戴日俊, 王胜辉, 等. 基于紫外成像图像信息的绝缘子表面放电量化方法[J]. 电工技术学报, 2012, 27(2): 261-268. Lü Fangcheng, Dai Rijun, Wang Shenghui, et al.Study of insulator surface discharge quantification method based on ultraviolet imaging information[J]. Transactions of China Electrotechnical Society, 2012, 27(2): 261-268. [10] 李和明, 王胜辉, 律方成, 等. 基于放电紫外成像参量的绝缘子污秽状态评估[J]. 电工技术学报, 2010, 25(12): 22-29. Li Heming, Wang Shenghui, Lü Fangcheng, et al.Contamination condition evaluation of insulators based on discharge ultraviolet imaging parametres[J]. Transactions of China Electrotechnical Society, 2010, 25(12): 22-29. [11] Reddy M J B, Chandra B K, Mohanta D K. A DOST based approach for the condition monitoring of 11kV distribution line insulators[J]. IEEE Transactions on Dielectrics & Electrical Insulation, 2011, 18(2): 588-595. [12] Murthy V S, Tarakanath K, Mohanta D K, et al.Insulator condition analysis for overhead distribution lines using combined wavelet support vector machine (SVM)[J]. IEEE Transactions on Dielectrics & Electrical Insulation, 2010, 17(1): 89-99. [13] Hinton G E, Osindero S, Teh Y W.A fast learning algorithm for deep belief nets[J]. Neural Computation, 2014, 18(7): 1527-1554. [14] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al.Deep residual learning for image recognition[C]// IEEE Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016: 770-778. [15] Schmidhuber J.Deep learning in neural networks: an overview[J]. Neural Netw, 2014, 61: 85-117. [16] Lecun Y, Bengio Y, Hinton G.Deep learning[J]. Nature, 2015, 521(7553): 436-444. [17] Bronstein M M, Bruna J, Lecun Y, et al.Geometric deep learning: going beyond euclidean data[J]. IEEE Signal Processing Magazine, 2017, 34(4): 18-42. [18] Ren Shaoping, He Kaiming, Girshick R, et al.Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 39(6): 1137-1149. [19] Girshick R.Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015: 1440-1448. [20] Wang Dianhui, Li Ming.Stochastic configuration networks: fundamentals and algorithms[J]. IEEE Transactions on Cybernetics, 2017, 47(10): 3466-3479. [21] 滕书华, 鲁敏, 张军, 等. 信息系统中的熵理论和信息粒度[J]. 计算机工程与科学, 2012, 34(4): 94-101. Teng Shuhua, Lu Min, Zhang Jun, et al.Entropy theory and information granularity in information systems[J]. Computer Engineering & Science, 2012, 34(4): 94-101. [22] Li Weitao, Wang Dianhui, Chai Tianyou.Flame image-based burning state recognition for sintering process of rotary kiln using heterogeneous features and fuzzy integral[J]. IEEE Transactions on Industrial Informatics, 2012, 8(4): 780-790. [23] 范玉华, 秦世引. 基于潜在语义分析的场景分类优化决策方法[J]. 计算机辅助设计与图形学学报, 2013, 25(2): 175-182. Fang Yuhua, Qin Shiyin.Optimizing decision for scene classification based on latent semantic analysis[J]. Journal of Computer-Aided Design and Computer Graphics, 2013, 25(2): 175-182. [24] Ma Miao, Chen Fang, Guo Min, et al.A recognition method based on improved LeNet_5 for street view house numbers[J]. Journal of Yunnan University, 2016, 38(2): 197-203. [25] 李帷韬, 曹仲达, 朱程辉, 等. 基于深度集成学习的青梅品级智能反馈认知方法[J]. 农业工程学报, 2017, 33(23): 276-283. Li Weitao, Cao Zhongda, Zhu Chenghui.Research on greengage quality intelligent feedback cognition method with cognitive result entropy measurement index constraint[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(23): 276-283. [26] 王伟凝, 王励, 赵明权, 等. 基于并行深度卷积神经网络的图像美感分类[J]. 自动化学报, 2016, 42(6): 904-914. Wang Weining, Wang Li, Zhao Mingquan, et al.Image aesthetic classification using parallel deep convolutional neural networks[J]. Acta Automatica Sinica, 2016, 42(6): 904-914. [27] Luo Juan, Gwun O.A comparison of SIFT, PCA-SIFT and SURF[J]. International Journal of Image Processing, 2013, 3(4): 143-152. [28] Singh G, Chhabra I.Effective and fast face recognition system using complementary OC-LBP and HOG feature descriptors with SVM classifier[J]. Journal of Information Technology Research, 2018, 11(1): 91-110.
2019, Vol. 34 
