Dissertation
Dissertation > Industrial Technology > Metallurgy and Metal Craft > Metal cutting and machine tools > Program control machine tools, CNC machine tools and machining

Intelligent control method for a New Type Hybrid Machine Tool

Author DuYingKui
Tutor FanShouWen
School University of Electronic Science and Technology
Course Mechanical and Electronic Engineering
Keywords hybrid machine tool interpolation BP neural network PID fuzzy PID
CLC TG659
Type Master's thesis
Year 2006
Downloads 86
Quotes 0
Download Dissertation

With the development of parallel machine tool (PMT) technology, hybrid machine tool (HMT) is emergenced, which combines serial structure with parallel structure. The potential of the HMT in industrial production is revealed. The 1PT+3TPS HMT is a novel lower-mobility hybrid mechanism, which can perform one translational DOF and two rotational DOF. The novel HMT has such priories as simple structure, high stiffness, high dexterity, low inertia and large payload capacity. It can be widely used for different kinds of practical applications, such as motion simulator, micromanipulator and machine tools. Because of its serious nonlinear and coupling, most traditional control methods are failed to get a satisfying effect on the HMT, so the intelligent control strategy research of HMT is becoming one of the most principle problems.Some research works on virtual prototyping technology, kinematic analysis, interpolation, PID method and fuzzy PID method are presented for the 1PT+3TPS HMT in this dissertation.Firstly, the structure parameters and the degree of freedom (DOF) of the novel HMT are analyzed. The model and joints of 1PT+3TPS HMT are simplificated and built in Solidworks, then the model of HMT model will be revised in ADAMS. Under the giving trochoid of moving platform, the kinematics simulation is carried on in ADAMS. The motion of 1PT+3TPS HMT will be revelated clealy by the resulted simulation animation and analysis curves, then the analysis curves will be used as training samples for the following research on the ANN interpolator of HMT.Under combining the interpolation theory with non-linear capacity and parallel calculation structure of artificial neural network (ANN), a software implement technique for fine interpolation of the 1PT+3TPS HMT is researched. The roughing interpolation and fine interpolation algorithm of HMT are introduced in the first. The interpolation controller is constructed by BP neural network and the training with the LM algorithm to the controller is carried on. The simulation of ANN interpolation controller is implemented by the neural network toolbox of Matlab6.5 and the feasiblity

Related Dissertations
More Dissertations