21-01-2013, 09:48 AM
Automatic Inspection of Cylindrical Components through Machine Vision System
1Automatic Inspection.docx (Size: 656.25 KB / Downloads: 39)
Abstract
Appearance defects inspection plays a vital role in bearing sub parts quality control. Human inspection is a traditional way to remove defective bearings, which is instable and time consuming. In this paper, we develop a machine vision system for bearing defect inspection, which can inspect various types of defects on bearing parts, such as diameter and design attributes such as size, shape, circular profile matching, scratches and so on. The proposed system designs a novel image acquisition system to enhance the defects appearances and get controlled image acquisition environment. A series of image processing methods are proposed or utilized to inspect the defects. Especially, we find a common rule on the distribution of projection, and design a simple but effective inspection coding based on the mat lab. The proposed system is under the process of evaluated and compared with skilled human,. Experimental results by using mat lab coding have show that the proposed vision system has high accuracy and efficiency
Keywords— vision system, inspection conveyor, image processing.
INTRODUCTION
In the industry of machinery, bearings are important components that connect different machine parts to reduce frictions. They have been widely used in air conditioners, cars, and many other rotating machines. The quality of bearings can directly influence the performance of many machines, and may even cause serious disasters. Bearings are usually mass-produced with high demand of precision, and a lot of inspection measures have been adopted in the production process to ensure the quality of bearings. The inspection measures can be classified into three steps: material inspection, assembling inspection and final goods inspection.
Inspection conveyor
The purpose of the system is to decide whether a bearing has appearance defects. Bearing inspection results will be used to remove bearings with defects from good ones automatically. As shown in Fig. 6, for a bearing, the main procedure of the inspection conveyor consists of four parts: Electronic Control Unit, Camera Specifications, MAT Lab Coding and Conveyor Design.
Electronic Control Unit
Consist of Power supply, Micro controller, Relay driver and Serial communication. This electronic control unit is used to control and manipulate the entire system that is capturing images by the camera, accept and rejection of parts by pneumatic cylinder to the rejection bin
Conclusions
This study develops a machine vision system for the inspection of design attributes of cylindrical components .
In the system, a mat lab coding has developed to
Indentify the design attributes parameters of the
Components deformation defects. Experimental
Results show that the proposed system can detect
Different parameters cover with high efficiency
And accuracy. In conclusion, it is possible to apply
The machine vision system to the automatic production line,
Replacing the human workers.
However, there are still many other works need to be
done. That is integration of all inspection conveyor, the
material inspection and assembling inspection procedures
also need automation inspection systems. Finally, the bearings
might be made from other materials. All of these problems
are worthy of further study.