A hybrid machine learning model for in-process estimation of printing distance in laser Directed Energy Deposition

Autor(es)

Ribeiro, Kandice S. B. ; Nunez, Henrique H. L. ; Venter, Giuliana S. ; Doude, Haley R. ; Coelho, Reginaldo T.

• Tipo de documento: Artigo Científico
• Fonte: INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY; v. 127, n. 7-8, p. 12-pg., 2023-06-10.

Resumo

There are several parameters that highly influence material quality and printed shape in laser Directed Energy Deposition (L-DED) operations. These parameters are usually defined for an optimal combination of energy input (laser power, scanning speed) and material feed rate, providing ideal bead geometry and layer height to the printing setup. However, during printing, layer height can vary. Such variation affects the upcoming layers by changing the printing distance, inducing printing to occur in a defocus zone then cumulatively increasing shape deviation. In order to address such issue, this paper proposes a novel intelligent hybrid method for in-process estimating the printing distance (Z(s)) from melt pool images acquired during L-DED. The proposed hybrid method uses transfer learning to combine pre-trained Convolutional Neural Network (CNN) and Support Vector Regression (SVR) for an accurate yet computationally fast methodology. A dataset with 2,700 melt pool images was generated from the deposition of lines, at 60 different values of Z(s) , and used for training. The best hybrid algorithm trained performed with a Mean Average Error (MAE) of 0.266 and a Mean Absolute Percentage Error (MAPE) of 6.7%. The deployment of this algorithm in an application dataset allowed the printing distance to be estimated and the final part geometry to be inferred from the data. (AU)

• Processo FAPESP: 16/11309-0 - Estudo, desenvolvimento e aplicação de processo híbrido: Manufatura Aditiva (Ma) + High Speed Machining/Grinding (HSM/G)
• Beneficiário: Reginaldo Teixeira Coelho
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 20/03119-2 - Estudo e desenvolvimento de estratégias para processo híbrido
• Beneficiário: Henrique Hiram Libutti Núñez
• Modalidade de apoio: Bolsas no Brasil - Iniciação Científica
• Processo FAPESP: 19/00343-1 - Controle do processo de directed energy deposition para fabricação de componentes de Geometria complexa por Manufatura Aditiva (MA)
• Beneficiário: Kandice Suane Barros Ribeiro
• Modalidade de apoio: Bolsas no Brasil - Doutorado