Study On Surface Defect Detection Of Drum Roller Based On Line Stripe Structured Light

In recent years,China has been vigorously developing the equipment manufacturing industry,and the demand for bearing products has been increasing.Bearing roller as a key component of the bearing,its quality directly affects the working performance,accuracy and service life of the bearing.Therefore,how to quickly and accurately detect the surface defects of the bearing roller is a difficult problem for all manufacturers.Due to the low efficiency and poor stability of the manual visual measurement method,which cannot meet the production requirements of enterprises,machine vision nondestructive inspection technology is gradually applied to industrial inspection.This paper discusses the advantages and disadvantages of bearing roller surface defect detection technology based on machine vision,and proposes a visual inspection solution for bearing rollers based on line stripe structured light in combination with the application of structured light technology in the defect detection field.From the point light source to the line stripe structured light source,it makes up for the problem that the traditional light source visual imaging system does not reflect enough defect features to realize the surface defect detection of bearing rollers.The main research work is as follows:Firstly,this paper analyzes the problems of narrow imaging surface and easy overexposure of images when shooting the surface of highly reflective curved objects.Combined with the factory detection requirements and defect detection principle,We put forward the bearing roller visual detection scheme based on line stripe structured light,and determines the relevant detection requirements and indicators.Secondly,this paper designs a horizontal turntable-based rolling surface unfolding device for bearing rollers to ensure stable imaging of bearing rollers at high speed in the process of image acquisition due to jitter or offset.By analyzing the main parameters of camera,lens,light source and other hardware and combining the actual application scenarios,device cost and detection efficiency,the cost is controlled minimized under the condition of meeting the detection requirements.Then,all the hardware models of the experimental device are determined.Thirdly,by studying the adaptation of laser modulation signal,MEMS drive signal and motor control signal,this paper realizes line stripe structured light imaging in combination with a line camera,which makes up for the problem that the traditional LED line light source or line laser with a line camera does not reflect enough defect characteristics.The morphological characteristics of different defects under the three light sources of line stripe structured light,line laser and traditional LED line light source,are compared and analyzed.Experiments show that the line stripe structured light designed in this paper has great advantages in improving the contrast of the defect features,which can improve the image quality and ensure the accuracy of the defect detection system.Finally,aiming at the problems such as image skew,noise interference and how defects are correctly extracted.,this paper designs a step by step stripe defect detection algorithm based on Blob analysis according to the characteristic of stripe image.Through image correction,image filtering,image segmentation,morphological processing and Blob analysis,four defects of scratches,abrasions,rust and pits are effectively detected with an average accuracy of more than 95%.The visual graph GUI interface is designed for the statistics and display of detection results.The experimental results show that the defect detection system has some advantages in hardware device and software algorithm,which can provide practical reference value for the current bearing roller defect detection.