Font Size: a A A

Research On Ceramic Dispensing System Based On Vision

Posted on:2019-06-29Degree:MasterType:Thesis
Country:ChinaCandidate:K ZhangFull Text:PDF
GTID:2371330566983289Subject:Mechanical engineering
Abstract/Summary:PDF Full Text Request
The dispensing system is a kind of automatic equipment that applies the glue dripping or coating to the designated position of the product,and it is widely used in industrial production,such as IC packaging,lens bonding and automobile manufacturing.With the continuous advancement of ours industrialization,the traditional dispensing system is difficult to meet the requirements of modern production,and the demand for the intelligent dispensing system is increasing day by day.As a non-contact measurement method,the visual detection technology can quickly locate the workpiece and extract the information required by the dispensing,which is one of the key technologies of the intelligent dispensing system.In this paper,based on the application of ceramic ware dispensing,based on the coordinate mechanical body,the visual dispensing system was developed to realize the automatic positioning of the workpiece,the extraction of the dispensing contour and the automatic dispensing function of the robot.The main research contents of this paper are as follows:(1)Analyze the overall demand of the dispensing system and determine the structure ontology as the coordinate manipulator.The design of visual system and control system is carried out,and select the upper and lower computer secondary distributed control structure.Among them,the industrial computer is the upper computer,responsible for managing the system and processing images,etc.The motion control card and the image acquisition card are the lower computers,which are responsible for controlling the motion system and the image acquisition function.According to specific tasks in different parts of the software,the modular software system is designed.(2)Filter algorithms are used for image preprocessing to reduce noise effects and obtain high quality workpiece images.The contour region is obtained by the threshold segmentation method.According to the different types of workpieces,the morphological method and the thinning algorithm are respectively used to determine the position of the workpiece's dispensing contour.The contour tracking method is used to obtain the coordinates of the contour points arranged in an orderly manner,and the dispensing contours are screened by information such as the perimeter of the contour and the area.An improved contour polygon approximation algorithm is proposed,which used the feature point to divide the original contour,and the contour approximate points are extracted in segments to make the distribution of the contour approximation points more uniform.(3)Analyze the camera model and calibrate the camera using Zhang's method to obtain camera internal parameters and distortion parameters.The transformation relation between the image coordinate system and the world coordinate system is established,and the needle offset calibration is carried out by the method of glue coordinate comparison.(4)Explain the dispensing process,and specifically analyze the problems and solutions that may occur at the start point,process and end point.The effect of dispensing height on the quality of dispensing was explored through experiments.The dispensing height control scheme based on laser ranging sensor was proposed and the effectiveness of the scheme was improved.The experiment system was used to carry out a comprehensive dispensing experiment.The repeated positioning accuracy of the dispensing system meets the actual requirements.The droplet diameter was measured by image measuring instrument to verify the consistency and stability of the dispensing system.The six types of workpieces were dispensed.Analysis of the results showed that the dispensing system meets the demand of the workpiece in dispensing effect.
Keywords/Search Tags:ceramic ware, dispensing system, machine vision, image processing, system calibration
PDF Full Text Request
Related items