| CNC technology relates to the level of a country's industrial and strategic position, it is one of the core of advanced manufacturing. Research shows that joint face has enormous impact on the dynamic characteristics of CNC machines, the research on joint face in our country has a big gap compare with foreign. It is mainly reflected when modeling and analyzing the CNC machine tool, it is lack of the support of database. Therefore, it is important to establish a database management system with joint face for designing and researching CNC machine tools.In this paper, it outlines and summarizes the definition, type and dynamic characteristics of joint face, and describes the research methods and status both in domestic and foreign country. Designing and analyzing the overall program of database system of CNC machine tools according to the demand, including architecture design, process analysis, data flow diagram analysis and modules of system functions classification, and describe the key technology in system development. The neural network technique is used in the study of dynamic characteristics of joint face, BP neural network model is established to predict dynamic characteristics of joint face. Traditional BP's convergence rate is slow and it is easy to fall into local minimum features, thinking that the genetic has characteristics of global optimization algorithms, this paper presents genetic algorithm and the LM-BP, these are two different model of characteristics of joint face. This paper verifies the accuracy of the two models by actual data. In the end, elaborate the realization method of visual database and develop the system by VB and MATLAB. Finally, this paper describes the operation instance of the system.Based on the above analysis, this paper developed a database management system of joint face using C/S mode, practice shows that the system can guide the machine design effectively and lay a solid foundation for CAD/CAM analysis of machine tools. |
PDF Full Text Request