Abstract:The secondary circuit of the substation is the basis of the secondary advanced integrated business. The automatic feature recognition and information extraction of the secondary circuit by image recognition technology can realize the secondary circuits intelligent operation and maintenance business. However, the images collected by the substation have messy backgrounds, low resolution, and distortion, making it very challenging to identify irregular text using image recognition technology. Therefore, a text detection and recognition method of a secondary loop terminal based on an attention mechanism is proposed. This method mainly includes preprocessing, text detection, and text recognition. In the text recognition part, a spatiotemporal embedding encoding method is proposed, which can better use the pictures location information. Compared with the unimproved method, only the sequence?level annotation information is needed in the training process, and no additional fine?grained character level box or segmentation mask is needed. Finally, it is proved that the proposed method is not only easy to use and has good performance but is also better than other methods in recognition accuracy.

Abstract:The field inspection of the secondary circuit is an important step in the field inspection of the gateway electrical energy metering device. However, the method of finding a secondary circuit terminal to be tested was rather complicated in the past. In order to optimize the process of finding terminals to be tested, this paper proposes a terminal number detection method based on EAST. In this method, the training dataset is first established, and the EAST model is trained. The trained model is used to detect the text in the terminal block image and outputs the size and position information of the terminal number region. Then, the region coordinates were clustered by DBSCAN clustering to distinguish possible multi-column terminals, and the tilt angle of each column terminal was calculated by linear regression. Finally, combined with the tilt angle and the average width and height of the region, the corrected detection results of the terminal number region are obtained. Examples show that this method can accurately detect the terminal number in the image and effectively improve the efficiency of terminal detection, which lays a foundation for the subsequent secondary circuit inspection work.