aser 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

An artificial neural network approach for the control of the laser milling process / Campanelli, S.; Casalino, G.; Ludovico, A. D.; Bonserio, C.. - In: INTERNATIONAL JOURNAL, ADVANCED MANUFACTURING TECHNOLOGY. - ISSN 0268-3768. - STAMPA. - 66:9-12(2013), pp. 1777-1784. [10.1007/s00170-012-4457-9]

An artificial neural network approach for the control of the laser milling process

Campanelli, S.;Casalino, G.;Ludovico, A. D.;
2013-01-01

Abstract

aser 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
2013
An artificial neural network approach for the control of the laser milling process / Campanelli, S.; Casalino, G.; Ludovico, A. D.; Bonserio, C.. - In: INTERNATIONAL JOURNAL, ADVANCED MANUFACTURING TECHNOLOGY. - ISSN 0268-3768. - STAMPA. - 66:9-12(2013), pp. 1777-1784. [10.1007/s00170-012-4457-9]
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11589/3648
Citazioni
  • Scopus 57
  • ???jsp.display-item.citation.isi??? 42
social impact