Intelligent detection method and device for pin missing of transformer substation

• Main Authors: WANG LEI, ZHOU DAZHOU, ZHANG BIN, WANG ZHENLI, GUO XIUXIAO, SUN ZHIZHOU, WANG WANGUO, JIA ZHAOXIN
• Format: Patent
• Language: Chinese; English
• Published: 05.03.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention provides an intelligent detection method and device for pin missing of a transformer substation. The method comprises the following steps: acquiring multi-time-point, multi-angle and multi-shooting-distance image data of a pin; preprocessing the image data; marking the positions of the pins in all the preprocessed images to serve as a training sample data set for pin detection; training a constructed pin detection network model by using the training sample data set, acquiring feature maps of different receptive fields of a training sample image by the pin detection network model by using multiple down-sampling operations with different multiples, performing feature map fusion, retaining features of a pin in different receptive fields, and optimizing model parameters; and processing a target pin image by using the trained pin detection network model, judging whether a pin exists in the image, and if the pin is not detected, sending out an alarm signal. According to the invention, the intelligence