Pillow spring detection method based on machine vision

Abstract

A pillow spring detection method based on machine vision comprises the following steps that step 1,setting the qualified range of detection parameters of a pillow spring according to detection requirements; step 2, adjusting parameters of the 3D visual imaging device so as to obtain clear target area point cloud data; step 3, the data processing and control system starts to act after obtaining thepillow spring arrival signal, a control module of the data processing and control system controls a visual imaging device to collect target area point cloud data including the pillow spring, and thetarget area point cloud data are sent to the data processing and control system; step 4, the data processing module calculates the detection parameter value of the pillow spring; and step 5, the datadetection module judges whether the pillow spring is qualified or not. By adopting the method provided by the invention, detection of multiple parameters can be automatically realized at one time, thedetection efficiency is high, the rhythm is fast, the precision is high, and the detection result can be stored to facilitate subsequent tracing and statistical analysis of the pillow spring detection result.

Description

technical field [0001] The invention relates to the field of pillow spring detection, in particular to a machine vision-based pillow spring detection method. Background technique [0002] Train maintenance plants usually use the following methods to detect train sleeper springs: for example, measure the free height of the sleeper spring by a testing machine or a height gauge, and use an outer diameter caliper to detect the corrosion degree of the diameter of the round steel, etc. That is, many inspection items of pillow springs often need to rely on a variety of different types of machines or manual inspection one by one. The process is complex and inefficient, and the accuracy of detection is easily affected by human errors. Not very accurate. Contents of the invention [0003] In view of the above deficiencies, the present invention proposes a pillow spring detection method based on machine vision. [0004] The purpose of the present invention is achieved through the f...

AI Technical Summary

Problems solved by technology

That is, many inspection items of pillow springs often need to rely on a variety of different types of machines or manual inspection one by one. The process is complex and inefficient, and the accuracy of detection is easily affected by human errors. low precision

Images