Impedance model force control using a neural network-based effective stiffness estimator for a desktop NC machine tool

In manufacturing industries of metallic molds, various NC machine tools are used. A desktop NC machine tool with compliance control capability has been already proposed to automatically cope with the finishing process of an LED lens mold. The NC machine tool can control the polishing force acting between an abrasive tool and a workpiece, where the force control method developed is an impedance model force control. The most important gain, which gives a large influence to the stability, is the desired damping of the impedance model. Ideally, the desired damping is calculated from the critical damping condition of the force control system in consideration of the effective stiffness. The effective stiffness means the total stiffness including the characteristics composed of the NC machine tool itself, force sensor, tool attachment, abrasive tool, workpiece, zig and floor. One of the serious problems is that the effective stiffness of the NC machine tool has undesirable nonlinearity, so that it may destroy the stability of the force control system. In this paper, a systematic tuning method of the desired damping in the control system is considered by using neural networks, where the neural networks acquire the nonlinearity of effective stiffness. It is confirmed that the impedance model force controller with the neural network-based (NN-based) stiffness estimator allows the NC machine tool to achieve a high quality finished surface of an LED lens mold with a diameter of 3.6 mm.