Intelligent Machine Tool for Autonomic Process Optimization

点击翻译按钮获取中文摘要

Self-excited vibrations during machining are the main reason for limit cutting parameters. In general, an optimization of cutting parameters is performed by machine operators based on their know-how or by determining a stability lobe chart. Up to now, only the parameters cutting speed and axis feed are adapted automatically during the machining process. The potential of adapting depth and width of cut remains unexploited. Main goal of the project is to investigate an algorithm that adapts cutting parameters for an autonomic process optimization. The algorithm rates process parameters during machining by the means of sensor signals and a continuously expanding knowledge data-base. Machine integrated strain gauges and accelerometers serve to detect chatter and hence to determine the maximal material removal rate. Different chatter detection approaches are analyzed regarding the new measurement concept. Furthermore, the autonomous segmentation of tool path will be analyzed for a process parallel adaption of the depth and width of cut. Thus, the common approach will be extended and the process parameters (vc, vf, ae, ap) are used for optimization. Additionally, fundamental knowledge will be generated by creating decision rules required for the autonomic process optimization. Therefore, the project is a step forward towards autonomic machine tools.