Research And Application On An Automatic Counting Detect System For Steel Rods

Automatic count of the steel rods in assembly lines is a tough problem which has been puzzling producers for long. At present, the count of the steel rods online is implemented by manual, This method, however, is labor-consuming, inefficient and limited in systematic producing capability while it is difficult to ensure the counting accuracy. Thus, developing a automatic counting system, which is able to automatically detect the number of the steel rods, will enhance productivity effectively, improve the traditional machining pattern that relies on manual calculating, free workers from heavy physical labor and horrible working environment, as well as make the stage of count achieve mechanization and automation in operation.In order to realize automatically count the steel rods in assembly lines, an automatic detect system is developed in this thesis, based on computer vision, image processing, and pattern recognition, including both software and hardware designing. The following are the major research work:First, both the manual and photoelectric cell counting methods are analyzed, research work related to detect technology based on the computer vision is briefly introduced, and the applications of this technology to automatic count the steel rods are summarized.Second, an automatic detect system's general structure is designed, specific solutions for the hardware part are put forward, including lighting system, camera system, image acquisition card and anti-interference.Third, an image processing software platform for the automatic detect system is developed, which involves four modules: image controlling, pre-processing, analyzing and recognizing, area shielding. A new method of image processing is proposed: as pretreatment, noise is eliminated to some extent and edge information is highlighted for real-time collected the steel rods section; three types of information -edge search, gray average value and gray average grads - are synthesized; patternrecognition is carried out; fusion algorithm based on Dempster-shafer evidence theory is applied to achieve the final result.Through researching and debugging in the lab, the developed detect system has been applied to count the steel rods online in the assembly lines in Nan Chang steel Co..Ltd for two years. The applied result shows that the counting accuracy of the developed system achieves 99.7%. So its accuracy, stability and reliability could meet the need of the steel industry to detect the count of the steel rods online. That means that it has already reached the standard for the industry manufacture.