PA-DETR: End-to-End Visually Indistinguishable Bolt Defects Detection Method Based on Transmission Line Knowledge Reasoning

A transmission line is the lifeline of a power system, while bolts play the role of connecting fittings and tightening conductors. However, bolts at different positions have different definitions of defects, which belongs to the problem of visually indistinguishable. Aiming at visually indistinguishable bolt defects in transmission lines, this article proposes an end-to-end visually indistinguishable bolt defects detection method that is based on transmission line knowledge reasoning. First, we use the end-to-end object detection with transformers (DETR) as the basic model and augment it with the dilated encoder module to obtain the multiscale features of the target. Then, we design a transmission line image relative position encoding (TL-iRPE) to infer the bolt position knowledge. Finally, this article designs a bolt attributes classifier and a bolt defects classifier. By combining the position knowledge and the attributes knowledge to assist bolt defect classifier in reasoning bolt defects, the accuracy of bolt defects detection is further improved. We have constructed the visually indistinguishable bolt defects dataset (VIBD dataset) and carried out experiments on the dataset. We call the bolt defects detection method combining position knowledge and attributes knowledge PA-DETR. Compared with other transmission line bolt defect detection methods, PA-DETR has more advantages in transmission line bolt defect detection.

I. Introduction

As an important facility of the power grid, the safe and stable function of transmission lines is necessary for the normal transmission of electric energy [1], [2], [3]. However, due to the large coverage area of the transmission line, the perennial impact of various environments, and the diversity of its components, timely checking whether the transmission line is abnormal is one of the most rigorous and laborious work in the operation of the power system [4].