The power system is constantly exposed to outdoor environments, which makes it susceptible to invasion by foreign body such as tree branches and garbage bags. Currently, most deep learning-based detection methods assume the presence of foreign body in the image, and there is still room for improvement in detection accuracy. In this paper, a foreign body detection method for the power system is proposed based on Inception-V3 and Trans-former. The method first classifies inspection images according to whether foreign bodies are present, and then detects foreign body that have invaded the power system. This method does not use pre-defined datasets and converts object detection into a direct bounding box prediction problem, which greatly optimizes existing detection methods. Experimental results on actual datasets show that our research effectively improves the accuracy and efficiency of foreign body detection compared to detection algorithms based on Faster R-CNN and YOLOv3.
To address the issues of low efficiency, insufficient accuracy, and high miss rate in traditional inspection methods for surface defects on ceramic insulators of transmission towers, this paper introduces a UAV-based intelligent inspection solution based on the deformable U-Net network to effectively detect and recognize surface defects on ceramic insulators in transmission towers. By using the deformable convolution operator to optimize the U-net network's convolution layer, the perceptual range of the convolution kernel is extended to improve the integrity of defect detail information. Meanwhile, the full-scale skip connection model is used to integrate high-dimensional and low-dimensional feature information to further improve the accuracy of ceramic insulator surface defect feature recognition. The experimental results show that the UAV-based intelligent inspection solution based on the deformable U-Net network can achieve an identification accuracy of 97.5%, an average precision of 95.55%, and an average intersection over union (IOU) of 91.67% in ceramic insulator surface defect detection. Compared with the traditional U-net method, the proposed solution in this study has improved the ceramic insulator surface defect inspection accuracy by 7.6%.
Pin defects can seriously affect the safety of transmission lines. Because the pin is small, it is difficult to detect the pin defects. Most existing methods detect pin defects by increasing the number of feature layers or cascade mechanisms. However, since there is too much redundant information in the high-resolution feature map, it is difficult for existing methods to achieve a balance between high-resolution feature maps and inference speed. In this paper, we proposed Sparse RetinaNet to effectively relieve the contradiction between high-resolution feature layer and slow inference speed. Specifically, we introduce high-resolution features in the prediction, and proposed a sparse mechanism to sparse the features in the high-resolution feature layer so as to make use of high-resolution features without seriously affecting the inference speed. Extensive experiments on our own pin defect detection dataset show that our proposed method can significantly improve training efficiency and performance.
KEYWORDS: Feature extraction, Power grids, Design and modelling, Convolution, Target recognition, Inspection, Data transmission, Education and training, Dielectrics, Image processing
A large number of aerial images are generated in the inspection of transmission lines. Due to the different sizes of conductors, insulators, shock absorbers and other components, the problem of rejection is easy to occur in the detection of external damage hazards, which affects the overall identification effect of lines. In this paper, a method to identify the hidden danger of external damage of high voltage overhead transmission lines is designed. From the three aspects of color, texture and shape, multi feature extraction is carried out on the line image to represent the location information of external damage hazards. The line image to be recognized is divided into uniform grids, and the coordinates and confidence of sub image blocks are used. Calculate the prediction accuracy of each region, filter the sub region with the largest value as the candidate target region, and output the corresponding prediction box. The deep transfer learning model is used to identify the hidden danger of external damage of the line, and the difference measurement index is used to evaluate the input feature vector. The difference feature results are fed back to the convolution layer to strengthen the interpretation ability of the difference information. The test results show that the design method improves the ability of image feature extraction, has high recognition accuracy, and provides decision-making basis for intelligent line early warning.
KEYWORDS: Data transmission, Data fusion, Detection and tracking algorithms, Lightning, Data modeling, Deep learning, Dielectrics, Wave propagation, Signal detection, Meteorology
Key transmission line fault detection methods have the problem of large detection errors and design a key transmission line fault detection method based on multi-source data fusion algorithm. The component symmetry between the forward and inverse traveling waves is used to discriminate the traveling wave abnormal region, combine the time window, pinpoint the information of the time field to the daily shift data, construct a tripping warning model based on the multi-source data fusion algorithm, and optimize the critical transmission line fault detection mode. Experimental results show that the mean error values of the key transmission line fault detection method in the paper, compared with three other key transmission line fault detection methods, are: 0.059, 0.113, 0.120 and 0.115 respectively, proving that the use of the fault detection method is improved when combined with the multi-source data fusion algorithm.
KEYWORDS: Data modeling, Data transmission, Power grids, Failure analysis, Environmental monitoring, Data acquisition, Sensors, Vibration, Education and training, Databases
The existing transmission line fault early warning can’t automatically identify the abnormal area, resulting in poor early warning effect for the line crossing and line touching fault. Based on this, an early-warning method of power transmission line crossing and collision fault based on multi-source data is proposed. Combined with the feature extraction method of multi-source data fusion, based on the analysis of the characteristics of the stock index of power grid transmission line crossing and touching, the leakage current acquisition model is constructed. Based on the model, the abnormal data of power grid are collected, and the characteristics of power grid transmission line crossing and touching are mined and identified. Then the texture features are obtained by using the local binary pattern operator to simplify the early warning steps of power grid transmission line crossing and touching. The experimental results show that the multi-source data-based power grid transmission line crossing and collision fault early warning is more practical than the traditional methods. In the process of practical application, the effect of abnormal data prediction and collection is significantly better. It can carry out fault early warning more quickly and accurately, and fully meet the research requirements.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.