Accessory quality detection method and device for rail train

Abstract

The invention provides an accessory quality detection method for a rail train, and the method comprises the steps: collecting the image information of a to-be-overhauled accessory on the rail train, and uploading the image information to a detection model; and performing content feature extraction and style feature extraction on the image information through the detection model, and judging whether the to-be-overhauled accessory is qualified or not through the identification points on the to-be-overhauled accessory to obtain a quality detection result. According to the invention, quality detection can be carried out on accessories on a rail train, and a detection model capable of detecting part image information in real time is constructed. The method provides machine assistance for key accessory detection work, automatically collects part characteristics, adds a guarantee for the detection work, reduces the detection workload, improves the detection accuracy, reduces the possibility of missing detection, and simplifies the shooting, storage, copying and other work flows.

Description

technical field [0001] The invention relates to the field of quality monitoring, in particular to a method and device for detecting the quality of rail train accessories. Background technique [0002] In the maintenance and operation of locomotives, the inspection of key accessories is very strict, and the workload of manual inspection is very large, but manual inspection always has the risk of false inspection and missed inspection caused by inertial thinking. The key components of the EMU play a vital role in the running process of the EMU, which is related to the safety of passengers' lives and property. [0003] At present, the detection technology of the key parts of the EMU relies on manual review, relying on multiple manual review processes, combined with taking photos to keep the bottom, to ensure the qualification of the parts installation, lack of intelligent detection links, in the existing technology, there is no perfect, An efficient and practically applicable ...

AI Technical Summary

Problems solved by technology

[0003] At present, the detection technology of the key parts of the EMU relies on manual review, relying on multiple manual review processes, combined with taking photos to keep the bottom, to ensure the qualification of the parts installation, lack of intelligent detection links, in the existing technology, there is no perfect, An Efficient and Practical Applicable Detection Method for EMU Parts

Images