Deep Learning; Temperature evolution; Directed Energy Deposition
Abstract :
[en] In this study, a data-driven deep learning model for fast and accurate prediction of temperature evolution and melting pool size of metallic additive manufacturing processes are developed. The study focuses on bulk experiments of the M4 high-speed steel material powder manufactured by Direct Energy Deposition. Under non-optimized process parameters, many deposited layers (above 30) generate large changes of microstructure through the sample depth caused by the high sensitivity of the cladding material on the thermal history. A 2D finite element analysis (FEA) of the bulk sample, validated in a previous study by experimental measurements, is able to achieve numerical data defining the temperature field evolution under different process settings. A Feed-forward neural networks (FFNN) approach is trained to reproduce the temperature fields generated from FEA. Hence, the trained FFNN is used to predict the history of the temperature fields for new process parameter sets not included in the initial dataset. Besides the input energy, nodal coordinates, and time, five additional features relating layer number, laser location, and distance from the laser to sampling point are considered to enhance prediction accuracy. The results indicate that the temperature evolution is predicted well by the FFNN with an accuracy of 99% within 12 seconds.
Disciplines :
Mechanical engineering
Author, co-author :
Pham Quy Duc, Thinh ; Université de Liège - ULiège > Aérospatiale et Mécanique (A&M)
Uriondo, A., Esperon-Miguez, M., & Perinpanayagam, S. (2015). The present and future of additive manufacturing in the aerospace sector: A review of important aspects. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 229(11), 2132-2147.
Culmone, C., Smit, G., & Breedveld, P. (2019). Additive manufacturing of medical instruments: A state-of-the-art review. Additive Manufacturing, 27, 461-473.
Mohamed, O. A., Masood, S. H., & Bhowmik, J. L. (2015). Optimization of fused deposition modeling process parameters: a review of current research and future prospects. Advances in Manufacturing, 3(1), 42-53.
Jardin, R. T., Tchuindjang, J. T., Duchêne, L., Tran, H. S., Hashemi, N., Carrus, R.,... & Habraken, A. M. (2019). Thermal histories and microstructures in Direct Energy Deposition of a High Speed Steel thick deposit. Materials Letters, 236, 42-45.
Meng, L., McWilliams, B., Jarosinski, W., Park, H. Y., Jung, Y. G., Lee, J., & Zhang, J. (2020). Machine Learning in Additive Manufacturing: A Review. JOM, 1-15.
Mozaffar, M., Paul, A., Al-Bahrani, R., Wolff, S., Choudhary, A., Agrawal, A.,... & Cao, J. (2018). Data-driven prediction of the high-dimensional thermal history in directed energy deposition processes via recurrent neural networks. Manufacturing letters, 18, 35-39.
Ren, K., Chew, Y., Zhang, Y. F., Fuh, J. Y. H., & Bi, G. J. (2020). Thermal field prediction for laser scanning paths in laser aided additive manufacturing by physics-based machine learning. Computer Methods in Applied Mechanics and Engineering, 362, 112734.
Roy, M., & Wodo, O. (2020). Data-driven modeling of thermal history in additive manufacturing. Additive Manufacturing, 32, 101017.
Hashemi, S. N. (2017). Study of High Speed Steel deposits produced by Laser cladding, Microstructure-Wear-Thermal model (Doctoral dissertation, University of Liège, Liège, Belgium).
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. ar Xiv preprint arXiv:1412.6980.
Fetni, S., Pham, Q., Tran, V., Duchêne, L., Tran, H. & Habraken, A. (2021) Thermal field prediction in DED manufacturing process using Artificial Neural Network. Paper presented at ESAFORM 2021. 24th International Conference on Material Forming, Liège.
