Thermal Error Modeling of a Machine Tool using Data Mining Scheme

K.-C. Wang, T.-L. Yei, T.-C. Chang, and K.-L. Wen (Taiwan)


thermal error compensation, K-means method, rough set theory, ANFIS, machine tools.


Thermal effect on machine tools is a well-recognized problem in an environment of increasing demand for product quality. The performance of a thermal error compensation system significantly depends on the thermal error model used. How to efficiently, quickly and accurately build a thermal error model is always drawing much attention in regard of engineering application. This paper presents an integrated scheme which includes k-means (KM) theory, rough set (RS) theory and linear regression (LR) method that seek to address this issue. The experimental data is first classified by the KM method and then the RS scheme is used to select crucial factors combination that contributes to the thermal error linearly. Eventually a LR thermal error model is established via these processed data. To evaluate the performance of this integrated model, an adaptive network fuzzy inference system (ANFIS) model was included. The proposed integrated thermal error modeling scheme can be built quickly and applied accurately. Besides, the established simple linear regression relationship can be easily installed into a CNC controller.

Important Links:

Go Back