A deep learning-based infrared image processing method for power equipment

Abstract

The invention discloses a method for processing infrared images of power equipment based on deep learning. This method uses deep learning to process infrared images of power equipment, and uses a processing model established by a deep convolutional neural network to process infrared images of power equipment. Impact. At the same time, recursive calls and dilated convolutions are applied to the proposed deep convolutional neural network, which achieves better processing results under the same parameter amount. The invention is characterized by strong innovation and strong practicability, and can realize the requirements of good infrared image processing effect and fast speed of power equipment.

Description

technical field [0001] The present invention relates to the technical field of power equipment monitoring, and more specifically refers to a method for processing infrared images of power equipment based on deep learning. Background technique [0002] With the rapid development of my country's economy, the country proposes to build a strong and reliable smart grid. Electrical equipment is in the running state for a long time and is easily affected by the external environment, and various failures often occur. Therefore, effective monitoring of different types of electrical equipment has become a hot research topic at present. Infrared thermal imaging technology is a powerful tool in online real-time monitoring of power systems. Through thermal images, it is possible to find out the abnormal temperature of power equipment due to faults or hidden dangers, prevent potential risks, and improve the stability and reliability of power grid operation. However, due to the influence ...

AI Technical Summary

Problems solved by technology

However, due to the influence of external environment and interference factors such as electronic devices in the equipment, infrared images will inevitably be disturbed by various noises during the process of acquisition, transmission and storage, such as Gaussian noise, impulse noise, etc., which will not only cause image Quality decline, but also affect the infrared image analysis and recognition operations, thereby reducing the reliability of the detection system

In addition, electrical equipment usually produces mechanical vibrations when it is working. Some electrical equipment is installed outdoors, and foggy days will also lead to a decline in image quality. Therefore, it is very important to process the acquired infrared images.

In addition, the traditional infrared image processing method of electrical equipment only denoises the influence of various noises on the image, and does not deal with the influence of mechanical vibration and fog on the image.

Images