Neural network approach for cutting parameter selection in milling

M. Sekar, J. Srinivas, Seung-Han Yang

Abstract

This paper proposes a predictive open-loop control approach to maintain effective speed regulation during end-milling operation. The process is analyzed analytically using two-degree of freedom model and the time domain and frequency domain data are used to construct a chatter prediction neural network model. Sixty training sets are prepared with and without chatter conditions. A neural network controller is proposed for tracking the overall response within chatter limits. The effectiveness of prediction network and controller is illustrated with an example.

Keywords

End-milling; Analytical Modeling; Neural network; Feedback control; Chatter stability

Download

IMEKO-TC14-2007-47.pdf

DOI

-

IMEKO TC

TC14 - Measurement of Geometrical Quantities

Back to the proceedings