Neural network approach to modeling the laser micro-machining process

Lasers are used for a variety of micro-machining applications because these tools provide a highly focused energy source that can be easily transmitted and manipulated to create geometric micro-features, often as small as the laser wavelength. Micro-machining with a laser beam is, however, a complex dynamic process with numerous nonlinear and stochastic parameters [1-3]. At present, the operator must use trial-and-error methods to set the process control parameters related to the laser beam, motion system, and work piece material. Furthermore, dynamic characteristics of the process that cannot be controlled by the operator such as power density fluctuations, intensity distribution within the laser beam, and thermal effects can greatly influence the machining process and the quality of part geometry.