The selection of key temperature measurement points for thermal error modeling of heavy-duty computer numerical control machine tools with density peaks clustering. (April 2019)

• Record Type: Journal Article
• Authors: Zhou, Zude; Hu, Jianmin; Liu, Quan; Lou, Ping; Yan, Junwei; Hu, Jiwei; Gui, Lin
• Is Part Of: Advances in mechanical engineering. Volume 11:Number 4(2019)
• Publication Date: 2019-04
• Subjects: Temperature field -- selection method -- temperature measurement points -- machine tools -- density peaks clustering; Mechanical engineering -- Periodicals; 621.05
• DOI: 10.1177/1687814019839513
• Languages: English
• ISSNs: 1687-8132

Abstract

Having great impacts on machining precision, thermal error is one of the main error sources for heavy-duty computer numerical control machine tools. Thermal error compensation using prediction models with temperature field is an effective way to improve machining precision of computer numerical control machine tools. The accuracy and robustness of thermal error prediction models depend considerably on the selection of temperature measurement points. Too many temperature measurement points will increase the complexity of thermal error prediction models and incur over-fitting problems. To improve the complexity and performances of prediction models, a selection method of key temperature measurement points based on density peaks clustering is presented in this article. This method is able to cluster massive temperature measurement points quickly and select the key temperature measurement point which characterizes the common feature of each cluster automatically. It is verified on the ZK5540A heavy-duty computer numerical control gantry drilling machine tool. Six key temperature measurement points are selected from the total 222 temperature measurement points with this method. Then, the back propagation neural network optimized by genetic algorithm thermal error model with the six key temperature measurement points is built and the accuracy and robustness of the model are analyzed. The results show that the model has high prediction accuracy and strong robustness.