Defect Identification Detection Research for Insulator of Transmission Lines Based on Deep Learning

Abstract

Traditional method of insulator defect identification is manually operated, which has low efficiency and high cost. Therefore, an automatic method of insulator defect identification is proposed in this paper. Firstly, image segmentation was operated by classification method of Random Forest (RF) to realize the object recognition of the insulator. Then, the method of Convolutional Neural Network (CNN) was adopted to classify the normal and defect states of insulators, and finally, the location of self-explosion defect identification was realized by Faster Region-Convolutional Neural Network (Faster R-CNN). A large number of images of insulators taken by Unmanned Aerial Vehicle (UAV) were used as experimental data to verify the method. The results show that the method in this paper could efficiently identify the defects of insulators, and the recognition rate reached 89.0%. The results can provide some references for the research of insulator defect identification of transmission lines.

Insulators’ Identification and Missing Defect Detection in Aerial Images Based on Cascaded YOLO Models

“…Target detection Detection effect Faster R-CNN [20] Insulators and their faults Achieves a precision of 94% and a recall of 88% Faster R-CNN [21] Insulator detection e average precision value reaches 0.818 using VGG-16 Faster R-CNN [22] 8 defects in transmission lines e defects can be effectively and accurately identified Faster R-CNN [23] Insulator self-explosion defect e identification rate reaches 89.0% Faster R-CNN [24] Insulator e average precision at a level of 0.8 for 60 frames R-FCN [25] Cracked insulator detection e average accuracy rate of 90.5%…”

“…e representative algorithms of two-stage are faster regions with convolutional neural networks (faster R-CNN) [20][21][22][23][24], region-based fully convolutional networks (R-FCN) [25], mask R-CNN [26], and cascade R-CNN [27][28][29]. e application research of electrical equipment detection in transmission lines based on two-stage target detection algorithms is shown in Table 1.…”

Insulator Faults Detection in Aerial Images from High-Voltage Transmission Lines Based on Deep Learning Model

“…It can be seen from Figure 7 that the average IoU becomes more and more stable with the increase in k values; when k = 9, the average IoU is 89.13%, and the average IoU varies slowly when the number k is bigger than 9. Finally, the clustering center k was set as 9 for dataset 'InSF-detection', and the initial anchor boxes for insulator faults detection were obtained as follows: (17,13), (23,15), (20,17), (25,17), (21,21), (24,19), (26,23), (23,26), and (30, 28), respectively. Specifically, 1331 simulated insulator fault images were collected using the above method.…”

“…In recent years, with the rapid development of deep learning theory, image processing methods based on deep neural networks have been widely used in the field of object detection and classification, which have several advantages over traditional image processing methods [11][12][13][14][15]. Object detection methods based on deep neural networks are composed of convolutional neural networks (CNN), which are capable of extracting image features automatically and learning from different environmental conditions.…”

Detection of Insulator Faults in Catenary Systems with Deep Learning

“…Fan vd. [5] otomatik bir izolatör kusur tespit yöntemi önermişlerdir. Önerdikleri yöntemde ilk olarak Rastgele Orman sınıflandırma yöntemi ile izolatör görüntülerini bölütlemişlerdir.…”