Enhanced Detection of Electric Power Facilities Utilizing a Re-Parameterized Convolutional Network

In electrical grid management, the integration of deep learning and digital twin technology constitutes a pivotal component of contemporary power network systems. The foundation of the intelligent digital electrical grid rests upon the meticulous collection of edge facility information, necessitating rapid and precise identification of electric power facilities for both civilian and military utilization within digital grid systems. This study introduces a novel object detection methodology tailored for a diverse array of electric power facilities, leveraging a re -parameterized Mask Region -based Convolutional Neural Network (Mask RCNN) augmented by transfer learning techniques. A multi -scale dataset of electric facilities was developed, facilitating the training and testing of the proposed model on images featuring manually annotated electric power facilities. These facilities are categorized into two distinct groups based on target scale, encompassing utility poles, transformers, insulators, cross arms, and wire clips. To enhance the efficiency of bounding region localization, the Mean Shift (MS) algorithm was employed to adjust the size of anchors within the Region Proposal Network (RPN), thereby streamlining the detection process. Experimental outcomes reveal that, in comparison to the original model, the reparameterized Mask R -CNN (Rep -Mask R -CNN) demonstrates a 6.17% increase in mean Average Precision (AP) and a 33% reduction in inference time. Equipped with a geolocation module, Unmanned Aerial Vehicles (UAVs) deploying this model can achieve comprehensive digital base map management, encompassing geographic and equipment information, while also supporting visual display services within the digital electrical grid. This study underscores the potential of re -parameterized convolutional networks in enhancing the accuracy and efficiency of electric power facility detection, contributing significantly to the advancement of intelligent digital grid management systems.