An artificial neural network approach for the control of the laser milling process
- 426 Downloads
Laser milling (LM) can be classified as a layer manufacturing process in which the material is removed by a laser beam by means of the ablation mechanism. It is a laser machining process which uses a laser beam to produce 3D shapes into a wide variety of materials. It is also known as laser ablation. It shows clear advantages versus the traditional milling such as the unlimited choice of materials, the direct use of computer-aided design structure data, the high geometric flexibility, and the touchless tool. LM requires the selection of optimal machining parameters for the job. Unlike the mechanical milling and the mechanical incision, the depth of the single removed layer is chosen at the beginning as input parameter of the process. In LM, the ablated depth depends from the process parameters such as laser power, scan speed, pulse duration, and pulse frequency. This work aims to develop an algorithm that can predict the parameters necessary to execute the material removal with a preset ablation depth. Using the results of an experimental campaign, the laser milling process was modeled by means of a back-propagation artificial neural network. Then, an iterative algorithm, based on the previous trained neural network, permitted to calculate the scanning velocity and pulse frequency that approached for the best the preset ablation depth. The developed approach represents a mean for the rational selection of laser ablation process parameters. It can be performed in an intuitive manner since it uses simple artificial intelligence like the artificial neural network.
KeywordsLaser milling ANN modeling Ablation depth Velocity and pulse frequency optimization
Unable to display preview. Download preview PDF.
- 1.Pham DT, Dimov SS, Petkov PV, Dobrev T (2005) Laser milling for micro-tooling. CU IMRC Working Paper Series, Cardiff University, UKGoogle Scholar
- 6.Kovalenko V, Anyakin M, Uno Y (2000) Modelling and optimisation of laser semiconductor cutting. Proc ICALEO Laser Micro-Fabr 90:D82–D92Google Scholar
- 7.Karnakis D, Rutterford G, Knowles M, Dobrev T, Petkov P, Dimov S (2006) High quality laser milling of ceramics, dielectrics and metals using nanosecond and picosecond lasers. SPIE Photonics West LASE 2006, San Jose CA, USA, 6106Google Scholar
- 10.Campanelli SL, Ludovico AD, Deramo C (2007) Dimensional accuracy optimisation of the laser milling process. Proceedings of the 26 International Congress on Applications of Lasers and Electro–Optics (ICALEO), Orlando, FloridaGoogle Scholar
- 12.Ganesan T, Vasant P, Irraivan E (2011) Solving engineering optimization problems with KKT Hopfield neural networks. Int Rev Mech Eng 7(7):1333–1339Google Scholar
- 20.Kuhl M (2002) From macro to micro—the development of laser ablation. Proceedings of ICALEO 2002Google Scholar