Prediction of Density and Surface Roughness in LPBF-Printed Parts from Recycled SS316L Powder Using Random Forest Regression Model

Yusuf  Busari; Muhammad Asmadi  Abdunkarim Yakoh; Mansir  Abubakar; Adel Mohammed  Al-Dhahebi; Ajibike Joan  Farounbi

doi:10.24191/jaeds.v6i1.167

Authors

Yusuf Busari Faculty of Mechanical Engineering & Smart Manufacturing Research Institute (SMRI), Universiti Teknologi MARA, Shah Alam, Malaysia.
Muhammad Asmadi Abdunkarim Yakoh Faculty of Mechanical Engineering & Smart Manufacturing Research Institute (SMRI), Universiti Teknologi MARA, Shah Alam, Malaysia.
Mansir Abubakar Faculty of Computer Science and Mathematics, Universiti Teknologi MARA, Shah Alam, Malaysia.
Adel Mohammed Al-Dhahebi Faculty of Mechanical Engineering & Smart Manufacturing Research Institute (SMRI), Universiti Teknologi MARA, Shah Alam, Malaysia.
Ajibike Joan Farounbi Applied Physics and Material Science Department, Alabama Agricultural and Mechanical Engineering University, Huntsville, USA.

DOI:

https://doi.org/10.24191/jaeds.v6i1.167

Keywords:

Density, Laser Powder Bed Fusion, Random Forest Regression (RFR), Surface roughness

Abstract

This paper use of machine learning algorithm to predict the density and surface roughness of 316L stainless steel parts manufactured using recycled powder based on the process parameter and powder characteristics. The advancement in Laser Powder Bed Fusion (LPBF), has enabled the production of complex and high-performance metallic components. However, the high cost of virgin powders and the substantial material waste generated during the AM process present economic and environmental challenges. The developed models with dedicated system interface built on the understanding of the effect of powder characteristics on the part properties included layer thickness, hatch spacing, laser power, and scanning speed. Feature relationships were analyzed using a correlation heatmap, highlighting strong interdependencies such as the inverse correlation between density and surface roughness (R = 0.98), and the alignment between laser power and scanning speed (R = 0.74). The RFR model was trained on datasets of varying sizes, and its performance was evaluated using standard error metrics (MAE, MSE, RMSE) and the coefficient of determination (R²). The model achieved high predictive accuracy, with an R² of 0.821 for density and 0.795 for surface roughness on a benchmark dataset. Error metrics were significantly lower than previous studies: MAE of 0.218 for density and 0.256 for surface roughness. Performance improved with larger datasets, reaching an R² of 0.973 for density and 0.942 for roughness at 250 samples, though a slight drop in accuracy was observed beyond this point due to potential data noise. The Random Forest model demonstrated strong capability in predicting quality outcomes in LPBF processes, outperforming earlier works in both accuracy and consistency. The developed system provides a model tool to inform AM optimization effectively, especially when supported by carefully selected features and appropriate dataset sizes.

Downloads

Download data is not yet available.

References

C. Guo et al., ‘Additive manufacturing of Ni-based superalloys: Residual stress, mechanisms of crack formation and strategies for crack inhibition’, Nano Materials Science, no. June, 2022.

L. A. Tochiro et al., ‘Powder bed fusion of high-Mn-N Ni-free austenitic stainless steel: achieving low porosity and high mechanical strength through process parameter selection’, International Journal of Advanced Manufacturing Technology, vol. 131, no. 3–4, pp. 1377–1396, 2024.

Y. O. Busari et al., ‘Evaluation of recycling strategies for SS316L powder in laser powder bed fusion: impacts on mechanical properties and fatigue performance’, International Journal of Advanced Manufacturing Technology, vol. 139, no. 3, pp. 1123–1144, 2025.

A. Lanzutti et al., ‘Effect of powder recycling on inclusion content and distribution in AISI 316L produced by L-PBF technique’, Journal of Materials Research and Technology, vol. 23, pp. 3638–3650, 2023.

S. Li, B. Chen, C. Tan, and X. Song, ‘Study on Recyclability of 316L Stainless Steel Powder by Using Laser Directed Energy Deposition’, Journal of Materials Engineering and Performance, vol. 31, no. 1, pp. 400–409, 2022.

K. Riener, S. Oswald, M. Winkler, and G. J. Leichtfried, ‘Influence of storage conditions and reconditioning of AlSi10Mg powder on the quality of parts produced by laser powder bed fusion (LPBF)’, Additive Manufacturing, vol. 39, no. February, p. 101896, 2021.

T. Delacroix, F. Lomello, F. Schuster, H. Maskrot, and J. P. Garandet, ‘Influence of powder recycling on 316L stainless steel feedstocks and printed parts in laser powder bed fusion’, Additive Manufacturing, vol. 50, no. September 2021, 2022.

A. B. Spierings, N. Herres, and G. Levy, ‘Influence of the particle size distribution on surface quality and mechanical properties in AM steel parts’, Rapid Prototyping Journal, vol. 17, no. 3, pp. 195–202, 2011.

R. Douglas, R. Lancaster, T. Jones, N. Barnard, and J. Adams, ‘The Influence of Powder Reuse on the Properties of Laser Powder Bed-Fused Stainless Steel 316L: A Review’, Advanced Engineering Materials, vol. 2200596, 2022.

Q. Wu et al., ‘Numerical investigation on the reuse of recycled powders in powder bed fusion additive manufacturing’, Additive Manufacturing, vol. 77, no. June, p. 103821, 2023.

I. A. Pelevin et al., ‘New Scanning Strategy Approach for Laser Powder Bed Fusion of Nd-Fe-B Hard Magnetic Material’, Metals, vol. 13, no. 6, 2023.

I. A. Pelevin et al., ‘Laser Powder Bed Fusion of Chromium Bronze Using Recycled Powder’, materials, vol. 14, no. 3644, pp. 1–11, 2021.

F. Jáñez-Martino, E. Fidalgo, S. Martínez-Pellitero, S. Giganto, and E. Alegre, ‘Estimation of arithmetical mean roughness using a regression approach and computer vision in stainless steel specimens manufactured by additive manufacturing’, International Journal of Computer Integrated Manufacturing, vol. 0, no. 0, pp. 1–12, 2025.

B. V. S. Reddy, A. M. Shaik, C. C. Sastry, J. Krishnaiah, S. Patil, and C. P. Nikhare, ‘Performance evaluation of machine learning techniques in surface roughness prediction for 3D printed micro-lattice structures’, Journal of Manufacturing Processes, vol. 137, no. November 2024, pp. 320–341, 2025.

M. A. Equbal, A. Equbal, Z. A. Khan, and I. A. Badruddin, ‘Machine learning in additive manufacturing: A comprehensive insight’, International Journal of Lightweight Materials and Manufacture, vol. 8, no. 2, pp. 264–284, 2025.

F. Ahmed, U. Ali, D. Sarker, E. Marzbanrad, K. Choi, and Y. Mahmoodkhani, ‘Study of powder recycling and its effect on printed parts during laser powder-bed fusion of 17-4 PH stainless steel’, Journal of Materials Processing Tech, vol. 278, p. 116522, 2020.

D. N. Aqilah, A. K. M. Sayuti, Y. Farazila, D. Y. Suleiman, M. A. N. Amirah, and W. B. W. N. Izzati, ‘Effects of Process Parameters on the Surface Roughness of Stainless Steel 316L Parts Produced by Selective Laser Melting’, Journal of Testing and Evaluation, vol. 46, no. 4, pp. 1673–1683, 2018.

E. Toyserkani, D. Sarker, O. O. Ibhadode, F. Liravi, P. Russo, and K. Taherkhani, ‘Monitoring and Quality Assurance for Metal Additive Manufacturing’, in Metal Additive Manufacturing, Wiley & Sons Ltd, 2021.

W. Abd-Elaziem, S. Elkatatny, T. A. Sebaey, M. A. Darwish, M. A. Abd El-Baky, and A. hamada, ‘Machine learning for advancing laser powder bed fusion of stainless steel’, Journal of Materials Research and Technology, vol. 30, no. April, pp. 4986–5016, 2024.

N. Emminghaus, C. Hoff, J. Hermsdorf, and S. Kaierle, ‘Residual oxygen content and powder recycling: Effects on surface roughness and porosity of additively manufactured Ti-6Al-4V’, Additive Manufacturing, vol. 46, 2021.

N. E. Gorji et al., ‘A new method for assessing the recyclability of powders within Powder Bed Fusion process’, Materials Characterization, vol. 161, no. October 2019, p. 110167, 2020.

G. Assunção, R. Izbicki, and M. Prates, ‘Is Augmentation Effective in Improving Prediction in Imbalanced Datasets?’, Journal of Data Science, pp. 1–16, Oct. 2024.

R. Douglas, N. Barnard, N. Lavery, J. Sullivan, T. Jones, and R. Lancaster, ‘The effect of powder recycling on the mechanical performance of laser powder bed fused stainless steel 316L’, Additive Manufacturing, vol. 88, no. June, p. 104245, 2024.

S. M. Yusuf, E. Choo, and N. Gao, ‘Comparison between virgin and recycled 316l ss and alsi10mg powders used for laser powder bed fusion additive manufacturing’, Metals, vol. 10, no. 12, pp. 1–18, 2020.

C. Lu et al., ‘A comprehensive characterization of virgin and recycled 316L powders during laser powder bed fusion’, Journal of Materials Research and Technology, vol. 18, pp. 2292--2309, 2022.

G. Jacob, S. Watson, C. Brown, and S. Watson, ‘Effects of powder recycling on stainless steel powder and built material properties in metal powder bed fusion processes NIST Advanced Manufacturing Series 100-6 Effects of powder recycling on stainless steel powder and built material properties in metal’, NIST Advanced Manufacturing Series 100-6, p. 59, 2017.

A. Gopaluni, C. Nayak, A. Piironen, T. Kantonen, and A. Salminen, ‘Effects of powder recycling on laser-based powder bed fusion produced SS316L parts’, in NOLAMP- Nordic Laser Materials Processing Conference (19TH-NOLAMP-2023), 2023, vol. 1296, no. 1, p. 012021.

N. D. Dejene, H. G. Lemu, and E. M. Gutema, ‘Effects of process parameters on the surface characteristics of laser powder bed fusion printed parts: machine learning predictions with random forest and support vector regression’, International Journal of Advanced Manufacturing Technology, vol. 133, no. 11, pp. 5611–5625, 2024.

G. O. Barrionuevo, J. A. Ramos-Grez, M. Walczak, and C. A. Betancourt, ‘Comparative evaluation of supervised machine learning algorithms in the prediction of the relative density of 316L stainless steel fabricated by selective laser melting’, International Journal of Advanced Manufacturing Technology, vol. 113, no. 1–2, pp. 419–433, 2021.

J. Gehrke, R. Ramakrishnan, and V. Ganti, ‘RainForest - A framework for fast decision tree construction of large datasets’, Data Mining and Knowledge Discovery, vol. 4, no. 2–3, pp. 127–162, 2000.

H. A. Salman, A. Kalakech, and A. Steiti, ‘Random Forest Algorithm Overview’, Babylonian Journal of Machine Learning, vol. 2024, pp. 69–79, 2024.

A. K. Kausik, A. Bin Rashid, R. F. Baki, and M. M. Jannat Maktum, ‘Machine learning algorithms for manufacturing quality assurance: A systematic review of performance metrics and applications’, Array, vol. 26, no. March, p. 100393, 2025.

E. Scornet, ‘Tuning parameters in random forests’, ESAIM: Proceedings and Surveys, vol. 60, pp. 144–162, Dec. 2017.

M. Gor et al., ‘Density Prediction in Powder Bed Fusion Additive Manufacturing: Machine Learning-Based Techniques’, Applied Sciences (Switzerland), vol. 12, no. 14, 2022.

D. Wu, Y. Wei, and J. Terpenny, ‘Surface Roughness Prediction in Additive Manufacturing Using Machine Learning’, in Proceedings of the ASME 2018 13th International Manufacturing Science and Engineering Conference. Volume 3: Manufacturing Equipment and Systems, 2018.