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:
-
Event details
IMEKO TC:
TC14
Event name:
TC14 ISMQC 2007
Title:

9th Symposium on Measurement and Quality Control in Manufacturing

Place:
Chennai/Madras, INDIA
Time:
21 November 2007 - 24 November 2007