Abstract
The manufacturing precisions of machine tools are seriously affected by high-speed spindle thermal error, especially the axial thermal deformation. A thermal error prediction model is an effective and economical approach to enhance the accuracy of machine tools, which is based on various artificial intelligence algorithms. This paper puts forward a novel optimal effective composite model (OM) for spindle thermal error prediction, which integrates the advantages of both gray model (GM(1,n)) and least squares support vector machine (LS-SVM) in terms of the experiment sample data. In the first place, the GM(1,n) and the LS-SVM are borrowed to establish the spindle thermal error prediction model, respectively. Then, the OM model is built by optimizing and adjusting the weighting coefficient of GM(1,n) and LS-SVM model, which is predicted by practical thermal error sample data. Finally, the prediction accuracy of the OM model is better than GM(1,n) model and LS-SVM by comparing the above models. After compensation, the maximum spindle thermal error, dropping from 16.4 to 3.5 μm, is significantly reduced with a droop rate of 78.7%. Therefore, the results show that, comparing with traditional GM(1,n) and LS-SVM method, the OM presented in this paper is more accurate and robust for thermal error prediction and compensation under complex machining conditions, which has preliminarily industrial application prospect.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: The International Journal of Advanced Manufacturing Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.