Research On Automatic Feeding System Based On Android Machine Vision

Since Google Corporation released the Android system,Android has achieved unprecedented success and development.However,in the industrial field,the development of Android is not as fast as in the field of commodities.Combined with the current situation of our factories,regions and automobile manufacturing industry,automated production is the trend of the future,and it is also forced by the situation.At present,one factor that restricts the automation of our factory is the high price of equipment and the greater cost of investment;the other factor is the distribution of parts from the material box to the equipment.Because the parts of each product are different,the technology is difficult and the cost is high if the different parts are developed for different parts.If we can develop a kind of automatic and low cost automatic feeding system,it will greatly reduce the cost of automatic production equipment at the same time,and can greatly promote the advancement of automation production in our factory.In view of the above needs,the following research works are carried out in this paper.1)according to the conceptual model of the feeding machine proposed by ABB company R & D center,a feeding machine suitable for our factory is designed,which is versatile and adaptable to different kinds of parts.The design of machinery,circuit,gas circuit and logic control is completed.The electric cylinder is used as the grabbing mechanism,and the design of the mechanical,electrical and logical control is completed,and the communication is carried out with the visual recognition software to realize the capture of the object.2)based on the OpenCV library,the visual recognition software that can run on the Android is developed,and the coordinates and angles of the object are identified,and the coordinates and angles are transferred to the grasping system of the manipulator.3)finally,this paper completed the development of a complete set of machine visual flexible feeding system,including the improvement of the feeder,the writing of machine vision software,the design of the grasping mechanism and the debugging of the whole system,so as to realize the automatic recognition and grasping of the object.