Catenary insulator detection method based on reconstruction and classification convolutional autoencoder network

Abstract

The invention discloses a catenary insulator detection method based on reconstruction and classification convolutional self-encoding network, specifically: 1. Imaging the support and suspension device of the high-speed railway catenary; 2. Establishing a sample data set of the insulator, and performing Insulator target detection and segmentation; 3. Use coordinate transformation to adjust the insulator to the level, use outlier detection to remove noise, perform edge detection on the insulator and perform quadratic function fitting, and cut the collected insulator images piece by piece, finally Establish an insulator sheet data set; 4. Build a reconstruction and classification convolutional automatic coding network to judge whether there is an insulator misclassification, and extract the insulator fault area; 5. Cluster the separated foreground images, and establish Fault judgment criteria; judge whether the insulator is faulty by setting a threshold, and further evaluate the fault level. The detection result of the invention is objective, true and accurate, and overcomes the defects of the traditional detection method.

Description

technical field [0001] The invention belongs to the technical field of high-speed railway image intelligent detection, and in particular relates to a catenary insulator detection method based on a reconstruction and classification convolutional self-encoding network. Background technique [0002] The catenary is one of the key components in the high-speed railway system, which plays a vital role in the stability and safe operation of the railway. However, due to the complex and harsh operating environment, the components of the catenary are easily damaged, which may cause interruption of train operation and endanger the safety of passengers. In the electrified railway power supply system, the arm support device mainly includes inclined arm, horizontal arm (tie rod), rod insulator and related parts. The rod insulator is used to suspend and support the inclined arm and the horizontal arm and keep the contact wire electrically insulated from the grounding body. The oblique ar...

AI Technical Summary

Problems solved by technology

The above methods have their own disadvantages. For example, GAN can only judge whether there is a fault, but not the distribution of the fault, and is easily affected by background interference. The AE network has functional redundancy, etc.

Since the images of catenary support and suspension devices collected on site are generally complex, and the image processing technology adopted is relatively complex, there is an urgent need for a simple and rapid image detection algorithm to quickly locate and detect the fault status of insulators

Images