Please use this identifier to cite or link to this item:
標題: 可調式模糊理論在CNC工具機熱變位預測之應用
An Application of Neural-Fuzzy Theory in CNC Machine Thermal Error Prediction
作者: 陳宣任
Chen, Hsuan-Jen
關鍵字: thermal earror;熱變位;fuzzy;thermal prediction model;模糊理論;熱變位預測模型
出版社: 機械工程學系
本論文即針對熱變位補償效果,導入可調式模糊控制理論,以建立熱變位預測模型。以I.C.型溫度感測器量測熱源之溫度變化,以標準桿配合觸發式探頭進行切削中熱變位之量測。收集溫度與變位資料,以可調式模糊理論,建立熱變位預測模型。為了讓使用者能有更友善之操作介面,因此以Inprise C++ Builder建構視窗型使用者圖形介面之熱變位量測與補償系統。
經由模擬結果顯示,此熱變位預測模型可將主軸熱變位由80μm降至 3μm,其較以線性複迴歸法建立之預測模型所能達到之 10μm補償範圍有更佳之效果。

The geometric errors and structural thermal deformation are factors that influence the machining accuracy of Computer Numerical Control (CNC) machine tool. Therefore, researchers pay attention to thermal error compensation technology on a CNC machine tool. The real-time error compensation techniques have been successfully demonstrated in both laboratories and industrial sites. Still the result of compensation methodologies need to enhance.
In this paper, the neural-fuzzy theory has been conducted to derive a thermal prediction model. An IC-type thermometers have been used to detect the heat sources temperature variation. The thermal drifts are measure on-line by a touch-triggered probe with a standard instrument. An thermal prediction model is then derived, based on the temperature variation and the thermal drifts by neural-fuzzy theory. A Graphic User Interface (GUI) system is built to conduct the user friendly opration interface with Insprise C++ Builder.
The result shows that the thermal prediction model developed by neural-fuzzy theory methodology can improve machining accuracy from 80um to 3um. Comparing with the multi-variable regression analysis the compensation accuracy is increased from 10um to 3um.
Appears in Collections:機械工程學系所

Show full item record
TAIR Related Article

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.