To avoid the interference of blur and noise in substation inspection images, which can impact the recognition of foreign objects hanging within these images, and to swiftly generate precise candidate areas for the acc...
详细信息
To avoid the interference of blur and noise in substation inspection images, which can impact the recognition of foreign objects hanging within these images, and to swiftly generate precise candidate areas for the accurate identification and localization of such foreign objects, a substation inspection method based on the edge-optimized faster r-cnn algorithm is proposed. This method represents a remote, intelligent identification approach for foreign objects suspended in inspection images. Using drones equipped with cameras, the method performs substation inspection tasks. After collecting substation inspection images, bilateral filters and adaptive edge compensation techniques are applied to enhance the images, thereby removing interference and noise. This enhancement improves the image contrast, and the refined substation inspection image is then fed into the faster r-cnn algorithm. The model performs convolution, feature extraction, classification, and otherrelevant operations on the image, ultimately outputting the substation inspection image along with remote intelligent identification of the suspended foreign object. Consequently, to enhance the accuracy of candidate areas during the remote intelligent identification of foreign objects hanging in substation inspection images, the faster r-cnn algorithm is optimized using an edge algorithm. The experimental results demonstrate that this method possesses a robust capability to enhance substation inspection images, can effectively remotely identify various types of foreign objects hanging in these images, provides valuable data on foreign object hangings for substation operations and arcs, and exhibits strong applicability.
The technology of relay protection in China's power system has gradually changed from the traditional operation mode to the development direction of informatization, intelligence, and automation. As a result, the ...
详细信息
The technology of relay protection in China's power system has gradually changed from the traditional operation mode to the development direction of informatization, intelligence, and automation. As a result, the role of relay protection in the power system has become more and more important. It brings higherrequirements to the reliability of relay protection;effective reliability assessment of the relay protection system and the corresponding condition operation, minimize or avoid accidents, and ensure the safety of power grids. Starting from the operating characteristics of relay protection, it is suitable for practical engineering applications. Aiming at the problems of low work efficiency and low inspection quality in manual inspection of relay protection pressure plate switching state, The fasterr-cnn image processing algorithm will be come up with. This method uses grayscale, binarization and filtering techniques to preprocess the platen photos, and uses rPN.
China's operational roadbed diseases show a growing trend in terms of both diversity and quantity, leading to an increasing frequency of road safety accidents caused by these diseases. It is of significant importa...
详细信息
China's operational roadbed diseases show a growing trend in terms of both diversity and quantity, leading to an increasing frequency of road safety accidents caused by these diseases. It is of significant importance to identify the location, morphology, and developmental degree of hidden roadbed diseases and address them accordingly for the safe operation and maintenance of highways during their operational period. Current non-destructive testing methods such as ground-penetrating radar heavily rely on subjective experience for data processing and interpretation, which no longer meet the growing demand for precise and rapid identification of disasters in roadbed engineering. In this study, we established a training set and a test set using images of common roadbed diseases, specifically roadbed looseness and roadbed voids, in a 1:4 ratio, and labeled the disease types in each image. We improved the faster r-cnn algorithm and obtained two enhanced versions, namely faster_rcnn_inception_v2 and faster_rcnn_resnet50. Both algorithms were trained and indicators such as loss value, test recognition area, and accuracy were analyzed. The results showed that the faster_rcnn_inception_v2 algorithm outperformed the faster_rcnn_resnet50 algorithm with a total loss value of 0.0235, a total of 425 recognized regions, and an accuracy of 91.1% forregion recognition. Therefore, the faster_rcnn_inception_v2 algorithm is chosen for the image detection and recognition of roadbed diseases in urban roads.
暂无评论