Detection of Foreign Objects Intrusion Into Transmission Lines Using Diverse Generation Model

Abstract

Foreign objects intrusion into transmission lines can lead to serious troubles, using deep learning technology for foreign object detection has good performance and can reduce losses. Due to the complexity and diversity of the surrounding environment of the transmission lines, and the limitations of data acquisition methods, the image data of foreign objects invading transmission lines used in current research are extremely rare, and the types of foreign objects and background features are single. Deep learning requires large image data as a research driving force, Rare number of images leads to insufficient model fitting and affects the detection accuracy. We propose a Diverse Generation model, which can generate many images of foreign objects invading the transmission lines to provide support for deep learning, thereby solving the shortcomings of existing models. The results show that the dataset generated by our model has high quality and diversity, and can cover different scenes including those that are not convenient for data acquisition in reality. Thus, the accuracy of foreign objects detection can be effectively improved. This achievement provides a preliminary guarantee for abnormal detection of transmission lines, and helps to promote the integration of artificial intelligence technology in the power system.