Fault identification method for cotter pin on spring supporting plate of railway wagon

Abstract

The invention discloses a fault identification method for a cotter pin on a spring supporting plate of a railway wagon, solves the problem that missing detection is easily caused when cotter pin lossfault detection is carried out by adopting a manual image observation mode, and belongs to the field of railway wagon fault identification. The method comprises the steps: collecting images on the twosides of a rail wagon, and constructing a sample set; inputting the images in the sample set into a U-Net segmentation network for training, and obtaining a segmentation model, wherein the U-Net segmentation network is used for reducing two convolution and down-sampling of a first layer and two convolution and up-sampling of a last layer on the basis of an existing U-Net network, and changing thenumber of feature maps of each layer into half of the original number; inputting a to-be-detected railway wagon image into the segmentation model, and obtaining a segmentation region of the cotter pin; carrying out fault analysis on the segmentation area, judging whether the cotter pin is lost or not, if yes, judging that the cotter pin is lost, and giving an alarm for the lost cotter pin.

Description

Technical field [0001] The invention relates to a fault identification method, in particular to a method for identifying the loss of a split pin on a spring pallet of a railway freight car, belonging to the field of railway freight car fault identification. Background technique [0002] If the loss of the split pin of the folded head bolt on the spring pallet of the truck is not discovered in time, it will bury the hidden danger of the loss of the nut and endanger the driving safety. In the existing cotter pin loss fault detection, the method of manually observing the image is used to detect the cotter pin loss fault. The target of the cotter pin is small and the color difference with other parts is small. It is easy to cause visual fatigue for the naked eye detection and affect the vision of the staff. And cause the occurrence of missed inspections, which affects driving safety. Summary of the invention [0003] Aiming at the problem that the existing method of manually observin...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the problem that the fault detection of cotter pin loss by manual image observation is easy to cause missing detection, the present invention provides a fault identification method for automatic identification of cotter pins on the spring pallet of railway wagons

Images