ICA based thermal source extraction and thermal distortion compensation method for a machine tool

Thermal distortion in machine tools is one of the most significant causes of machining errors. One of the difficult issues in developing a system to compensate for thermal distortion is to select the appropriate temperature variables and to obtain an accurate thermal distortion model. This paper presents a new thermal distortion compensation method based on the Independent Component Analysis (ICA) method. The ICA method was used to extract the thermal sources from the temperature variables. The Optimal Brain Surgeon (OBS) algorithm was used to reduce the temperature variables with insignificant information. Using the extracted sources, a new thermal distortion model and a compensation method is proposed and is implemented in real-time hardware. In these experiments, the proposed method was shown to be capable of compensating for thermal distortions to a few micrometers.