关键词: 变电站, 二次接线图纸, YOLOv5, 智能识别

Abstract:

The secondary wiring drawings of the substation are an important basis for the operation and maintenance of the substation.Manual review of the drawings has problems of low efficiency and poor accuracy.Therefore, an intelligent recognition method for the connection relationship of secondary wiring drawings in substations, which combines YOLOv5 and the backtracking algorithm,is proposed to improve the efficiency and accuracy of processing secondary wiring drawings in substations.The YOLOv5 model and optical character recognition (OCR) technology are integrated to achieve automatic recognition and information extraction of secondary drawings.The backtracking algorithm is used to verify the extracted connection information and determine the connection relationship of secondary drawings.Through examples, it is verified that the proposed method can successfully identify the circuit connection relationship in the wiring drawings, with a minimum recognition accuracy of 96.50%, an average recognition accuracy of 97.22%, and a recognition efficiency approroximately 5 times higher than that of manual recgnition, which verifies the effectiveness of the proposed method.

Key words: substation, secondary wiring drawings, YOLOv5, intelligent recognition