DISPLACEMENT AND THERMAL ERROR COMPENSATION USING RBF NETWORKS

With rapid development in the technologies of high precision machining and the ever increasing demand for high accuracy in the automation industry, addressing accuracy problems due to geometric and thermal errors are becoming more critical in recent years, especially thermal errors which may contribute up to 75% of the overall errors in the system. Retrofitting the mechanical design or maintaining the operational temperature may not be feasible and can significantly increase cost. An error compensation method is more efficient and cost effective. In this paper, a displacement and thermal error compensation approach is proposed and developed based on radial basis functions (RBFs). Feedback control is designed in both position control subsystem and temperature control subsystem. Raw position data are measured using the laser interferometer and the raw temperature data are measured using a thermistor. The overall geometric errors are related to both movement positions and the machine operating temperatures, so a 2-D RBF network is designed and trained to model and estimate the geometric errors. The RBFs are then used to compensate the error. The experimental results showed that the proposed approach can help improve the system performance and accuracy effectively.