Deep learning-based transformer patrol image intelligent identification and fault detection system

Abstract

The invention discloses a deep learning-based transformer patrol image intelligent identification and fault detection system. The system comprises an image storage and calibration module, a deep learning module and a fault detection module located in a storage layer, a modeling layer and an application layer in sequence; the image storage and calibration module obtains massive patrol images from apower grid information system, performs distributed storage, performs calibration on parts in the patrol images and parts in an image of a transformer in a normal / fault state, and forms a part feature set, a normal state feature set and a fault state feature set; a feature data set is transmitted into the deep learning module; the deep learning module constructs and trains a convolutional neuralnetwork to obtain a training result; and the fault detection module performs part identification, fault identification and conclusion pushing in sequence by utilizing the training result. Compared with a manual identification mode, the identification efficiency and accuracy of the transformer patrol images are greatly improved.

Description

technical field [0001] The invention relates to the technical field of digital image recognition, and more specifically, to a deep learning-based intelligent recognition and fault detection system for transformer inspection images. Background technique [0002] Inspection of substation equipment is an important system to ensure the safe operation of substations. In view of the problems of heavy workload, high operation risk, subjective factors such as the experience of inspectors, and difficulty in keeping manual records in traditional manual inspections, more and more intelligent inspection systems are actually applied in substations. It effectively improves the efficiency of equipment inspection work, reduces the labor intensity and risks of operation and maintenance personnel, and provides strong technical support for unattended substations. Inspection robots, inspection drones, and online video monitoring systems generate a large amount of visible light images, which pr...

AI Technical Summary

Problems solved by technology

[0004] (1) The imaging characteristics of pictures taken at different angles, heights, and distances are quite different, and the range of pictures that can be used by traditional image recognition methods is narrow;

[0005] (2) Bad weather conditions, lighting and shadows, interference from background facilities and scenery reduce the recognizability of images;

[0006] (3) The proportion of key components in the entire transformer image is small, and the extraction efficiency of fault information is low

Images