Transformer area fault detection method and device based on visual identification technology

Abstract

The invention relates to a transformer area fault detection method and device based on a visual identification technology. The method comprises the following steps : acquiring image information of a target area; detecting the image information according to a preset learning model to obtain position information and state information of target equipment; judging the position information and the state information to judge whether the position information and the state information meet preset early warning conditions or not so as to obtain alarm information; and in response to the obtained alarm information, sending the alarm information to a terminal. According to the transformer area fault detection method, the state of the target equipment is detected in real time based on deep learning, and the alarm information is actively sent to the terminal after the fault is found, so that the intelligent detection capability of the transformer area fault is realized, and the power distribution network equipment state detection efficiency and the fault position identification accuracy are improved.

Description

technical field [0001] The invention belongs to the technical field of power grid fault management, and in particular relates to a fault detection method and device for a station area based on visual recognition technology. Background technique [0002] The power network mainly includes the main network and the distribution network. Compared with the main network, the structure of the distribution network is more complicated, and the number of equipment is larger. With the increase of user load, the scale of distribution network grows rapidly, and the reliability requirements of power supply continue to increase. The importance of fault diagnosis and location of distribution network is increasing day by day. According to statistics, in all power outages that occur to users, more than 80% are caused by power distribution system failures. Timely and accurate judgment of equipment failure locations and fault-affected areas can quickly and accurately isolate equipment failure lo...

AI Technical Summary

Problems solved by technology

[0003] In order to detect the fault discharge of distribution network equipment, most of the current distribution transformer areas are equipped with drop-out fuses. When the fuse equipment fails, the fuse will drop, but after the fuse is dropped, manual inspection is required Locating the fault location seriously restricts the efficiency of distribution network equipment status detection and the accuracy of fault location identification

Images