Two Dimensional Feedrate Control for High Performance CNC Machine Tools
| Authors: | Lee Seung Soo, Kyungpook National University, Korea, Republic of
Cho Jung Hwan, Kyungpook National University, Korea, Republic of
Jeon Gi Joon, Kyungpook National University, Korea, Republic of |
|---|
| Topic: | 4.2 Mechatronic Systems |
|---|
| Session: | Mechatronic Applications |
|---|
| Keywords: | CNC, neural network, learning algorithm, performance index, geometry |
|---|
Abstract
This paper proposes a new feedrate control technique of CNC that can achieve high machining accuracy and high productivity. The proposed adaptive neuro-controller adjusts both components of the feedrate and makes an improved command of contour geometry. This control architecture consists of a neural network identifier (NNI) and an iterative learning algorithm with inversion of the NNI. The NNI is an identifier for the non-linear characteristics of CNC and composed of two outputs that are identified with individual axis dynamics of the contour error. The iterative learning algorithm is exploited to derive an optimal feedrate control law by minimizing a performance index that is a measurement of the contour error and the machining time.
