IWPDF2023

Simulations of the Directed Energy Deposition process to manufac ture parts in M4 High Speed Steel

A. M. Habraken 1 , 2 , ∗ , R. T. Jardin 1 , T. Q. D. Pham 1 , 3 , J. T. Tchuindjang 4 , R. Carrus 5 , V. Tuninetti 6 , L. Duchêne 1 , A. Mertens 4 , T.VHoang 7 , X.V. Tran 3

1 Department ArGEnCo, MSM Unit, University of Liège, Allée de la Découverte, 9 B52/3, B 4000 Liège, Belgium 2 Fonds de la Recherche Scientifique de Belgique (F.R.S-FNRS), 6, rue d’Egmont B 1000 Brux elles, Belgique 3 Institute of Strategy Development, Thu Dau Mot University, 75100 Binh Duong Province, Viet nam 4 Department A&M, MMS Unit, University of Liège, Allée de la Découverte, 9 B52/3, B 4000 Liège, Belgium 5 Sirris Research Centre (Liège), Rue Bois St-Jean,12, B-4102, Seraing, Belgium. 6 Department of Mechanical Engineering, Universidad de La Frontera, Avenida Francisco Salazar, 01145 Temuco, Chile. 7 Chair of Mathematics for Uncertainty Quantification, RWTH-Aachen University, 52056 Aachen, Germany This lecture presents all the steps required to reach a framework for the robust optimization under uncertainty in the directed energy deposition (DED) of M4 High-Speed Steel [1]. These developments were applied to identify optimal process parameters for robust manufacturing of printed parts with a stationary melt pool depth and low consumed energy under uncertainty within the multiple layers of a bulk sample. Based on 2D finite element simulations validated by experiments [2], a surrogate model using a feedforward neural network (FFNN) was developed for a fast and accurate prediction of the temperature evolutions and the melting pool sizes in a metal bulk sample (3D horizontal layers) manufactured by the DED process. The uncertainty characterization and propagation within the process were studied in [3] and prepared the possible use of robust optimization. References [1] Pham, T.Q.D., Hoang, T.V., Tran, X.V., Fetni, S., Duchêne, L., Tran, H.S., Habraken, A.M., (2023). A framework for the robust optimization under uncertainty in additive manufacturing Journal of Manufacturing Processes,103, 53-63 [2] Jardin, R.T. Tchoufang Tchuindjang, J. Duchêne, L.,Tran, H.S., Hashemi, N., Carrus, R., Mertens, A., Habraken, A.M.(2019).Thermal histories and microstructures in Direct Energy De position of a High Speed Steel thick deposit, Mater. Lett. 236. [3] Pham, T.Q.D., Hoang, T.V., Tran, X.V., Fetni, S., Duchêne, L., Tran, H.S., Habraken, A.M., (2022). Characterization, propagation, and sensitivity analysis of uncertainties in the directed ∗ anne.habraken@uliege.be Keywords: Deep Learning, High Speed Steel, Additive Manufacturing

13