Vol. 29 No. 3 (2026) Cover Image
Vol. 29 No. 3 (2026)

Published: September 20, 2026

Pages: 552-565

Articles

Calibrated Uncertainty Quantification of LPBF/DMLS SS316L Surface Roughness Using Leave-One-Setting-Out Benchmarking and Reliability Decisions

Venkata Phani Babu Vemuri 1 Sivaramakrishna Valiveti 2 Subbarao C.V 3 Sushma Pappula 3 Ravikiran Chintalapudi 4 Sunanda A 5
1 Department of Civil Engineering, Dadi Institute of Engineering & Technology, Anakapalle, Andhra Pradesh- 531002, India
2 Department of Mechanical Engineering, VNR Vignana Jyothi Institute of Engineering and Technology, Hyderabad - 500090, Telangana, India
3 Department of Mechanical Engineering, PACE Institute of Technology & Sciences, Ongole-523272, Andhra Pradesh, India.
4 Department of Mechanical Engineering, MLR Institute of Technology, Hyderabad- 500043, India.
5 Department of Mechanical Engineering, Sreenidhi Institute of Science and Technology, Yamnampet, Hyderabad, India
History
  • Received: February 23, 2026
  • Revised: April 24, 2026
  • Accepted: May 29, 2026
  • Available Online: September 20, 2026
DOI

https://doi.org/10.29194/NJES.29030552

Abstract

This study develops a decision-oriented uncertainty quantification methodology for analyzing as-built surface roughness in laser powder bed fusion/direct metal laser sintering (LPBF/DMLS) SS316L. A Taguchi L9 design was used to vary laser power (300-360 W), scan speed (800-1000 mm·s-1), and layer thickness (20-80 μm), producing nine process settings with three independently fabricated specimens per setting, resulting in 27 total specimens. Surface roughness was measured by contact stylus profilometry using arithmetic mean roughness (Ra), root mean square roughness (Rq), and maximum profile height (Rz). The mean roughness varied within narrow ranges, Ra as 5.748-5.952 μm, Rq as 6.673-6.811 μm, and Rz as 28.828-28.892 μm, while within-setting scatter remained non-negligible, particularly for Rz. Probabilistic regression models were evaluated using leave-one-setting-out validation, negative log predictive density, interval coverage, calibration diagnostics, and reliability-driven accept/reject analysis. For Ra and Rq, a low-capacity linear mean model with pooled variance achieved the best predictive density, indicating limited transportable heteroscedastic structure under setting-wise extrapolation. For Rz, a nonlinear mean model with pooled variance performed best. Unregularized two-stage variance learning produced unstable uncertainty estimates, whereas shrinkage regularization improved calibration and reduced spurious setting-dependent variance effects. The decision analysis showed that calibration strongly influences process acceptance, reliability thresholds sharply reduced the number of accepted settings, and shrinkage-stabilized uncertainty produced a conservative and consistent decision frontier. The main contribution of this work is the integration of grouped validation, probabilistic calibration, variance-shrinkage modelling, and reliability-aware decision analysis for surface roughness qualification in LPBF/DMLS SS316L.

Keywords

References

  1. V. V. Phani Babu, V. K. GB, and P. Barmavatu, "An experimental investigation on surface quality of 3D metal printed SS316L by direct metal laser sintering technique," International Journal on Interactive Design and Manufacturing (IJIDeM), vol. 19, no. 1, pp. 393-403, 2025. https://doi.org/10.1007/s12008-024-01801-6
  2. B. Pappula, J. K. Jatavallabhula, V. P. B. Vemuri, R. Chintalapudi, G. N. Kannaiyan, and S. Makgato, "Machine Learning-Enhanced Reverse Engineering for Dimensional Accuracy Optimization in DMLS-Fabricated SS316L Components," Materials Today Communications, p. 114293, 2025. https://doi.org/10.1016/j.mtcomm.2025.114293
  3. A. Adin, E. T. Krainski, A. Lenzi, Z. Liu, J. Martínez-Minaya, and H. Rue, "Automatic cross-validation in structured models: Is it time to leave out leave-one-out?," Spatial Statistics, vol. 62, p. 100843, 2024. https://doi.org/10.1016/j.spasta.2024.100843
  4. Q. He, C. Hong, L. Xu, and L. Li, "Robust portfolio management: A novel multi-task learning model fusing predicted returns and residual data under the framework of Mean-VaR," Journal of the Operational Research Society, vol. 76, no. 7, pp. 1466-1480, 2025. https://doi.org/10.1080/01605682.2024.2438333
  5. Y. Kwon and Z. Zhao, "On F-modelling-based empirical Bayes estimation of variances," Biometrika, vol. 110, no. 1, pp. 69-81, 2023. https://doi.org/10.1093/biomet/asac019
  6. V. Dheur and S. B. Taieb, "A large-scale study of probabilistic calibration in neural network regression," in International Conference on Machine Learning, 2023: PMLR, pp. 7813-7836.
  7. N. I. Bosse, S. Abbott, A. Cori, E. Van Leeuwen, J. Bracher, and S. Funk, "Scoring epidemiological forecasts on transformed scales," PLoS computational biology, vol. 19, no. 8, p. e1011393, 2023. https://doi.org/10.1371/journal.pcbi.1011393
  8. P. Pernot, "Calibration in machine learning uncertainty quantification: beyond consistency to target adaptivity," APL Machine Learning, vol. 1, no. 4, 2023. https://doi.org/10.1063/5.0174943
  9. T. Yin, G. Panapitiya, E. D. Coda, and E. G. Saldanha, "Evaluating uncertainty-based active learning for accelerating the generalization of molecular property prediction," Journal of Cheminformatics, vol. 15, no. 1, p. 105, 2023. https://doi.org/10.1186/s13321-023-00753-5
  10. T. Löfström, H. Löfström, U. Johansson, C. Sönströd, and R. Matela, "Calibrated explanations for regression," Machine Learning, vol. 114, no. 4, pp. 1-34, 2025. https://doi.org/10.1007/s10994-024-06642-8
  11. M. B. Bjerregård, J. K. Møller, and H. Madsen, "An introduction to multivariate probabilistic forecast evaluation," Energy and AI, vol. 4, p. 100058, 2021. https://doi.org/10.1016/j.egyai.2021.100058
  12. S. Allen, J. Koh, J. Segers, and J. Ziegel, "Tail calibration of probabilistic forecasts," Journal of the American Statistical Association, no. just-accepted, pp. 1-20, 2025. https://doi.org/10.5194/egusphere-egu24-6281
  13. L. Hao, W. Wang, J. Zeng, M. Song, S. Chang, and C. Zhu, "Effect of scanning speed and laser power on formability, microstructure, and quality of 316L stainless steel prepared by selective laser melting," Journal of Materials Research and Technology, vol. 25, pp. 3189-3199, 2023. https://doi.org/10.1016/j.jmrt.2023.06.144
  14. T. Zhang and L. Yuan, "Understanding surface roughness on vertical surfaces of 316 L stainless steel in laser powder bed fusion additive manufacturing," Powder Technology, vol. 411, p. 117957, 2022. https://doi.org/10.1016/j.powtec.2022.117957
  15. S. Chowdhury et al., "Laser powder bed fusion: a state-of-the-art review of the technology, materials, properties & defects, and numerical modelling," Journal of Materials Research and Technology, vol. 20, pp. 2109-2172, 2022. https://doi.org/10.1016/j.jmrt.2022.07.121
  16. A. Leicht, M. Fischer, U. Klement, L. Nyborg, and E. Hryha, "Increasing the productivity of laser powder bed fusion for stainless steel 316L through increased layer thickness," Journal of Materials Engineering and Performance, vol. 30, no. 1, pp. 575-584, 2021. https://doi.org/10.1007/s11665-020-05334-3
  17. H. Lei and A. Bellotti, "Reliable prediction intervals with directly optimized inductive conformal regression for deep learning," Neural Networks, vol. 168, pp. 194-205, 2023. https://doi.org/10.1016/j.neunet.2023.09.008
  18. T. Gneiting and A. E. Raftery, "Strictly proper scoring rules, prediction, and estimation," Journal of the American statistical Association, vol. 102, no. 477, pp. 359-378, 2007. https://doi.org/10.1198/016214506000001437
  19. T. Gneiting and M. Katzfuss, "Probabilistic forecasting," Annual Review of Statistics and Its Application, vol. 1, no. 1, pp. 125-151, 2014. https://doi.org/10.1146/annurev-statistics-062713-085831
  20. B. S. Reddy et al., "From metrics to decisions: a robust evidential methodology for dimensional accuracy and manufacturability in DMLS SS316L," The International Journal of Advanced Manufacturing Technology, pp. 1-27, 2026. https://doi.org/10.1007/s00170-026-17524-9
  21. M. V. Wüthrich and J. Ziegel, "Isotonic recalibration under a low signal-to-noise ratio," Scandinavian Actuarial Journal, vol. 2024, no. 3, pp. 279-299, 2024. https://doi.org/10.1080/03461238.2023.2246743
  22. C.-L. Yang, T. Y. Meles, A. A. Yilma, and M. M. Teshome, "Uncertainty aware predictive maintenance using a hybrid Transformer with Monte Carlo Dropout and conformal prediction," Ain Shams Engineering Journal, vol. 17, no. 2, p. 103992, 2026. https://doi.org/10.1016/j.asej.2026.103992
  23. C. Qian, D. Ries, F. Liang, and J. Adams, "Regression Recalibration by Learning PIT Map Values," Technometrics, pp. 1-12, 2025. https://doi.org/10.1080/00401706.2025.2464004
  24. X. Wang and W. Xiong, "Uncertainty quantification and composition optimization for alloy additive manufacturing through a CALPHAD-based ICME framework," npj Computational Materials, vol. 6, no. 1, p. 188, 2020. https://doi.org/10.1038/s41524-020-00454-9
  25. S. Mahadevan, P. Nath, and Z. Hu, "Uncertainty quantification for additive manufacturing process improvement: Recent advances," ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering, vol. 8, no. 1, p. 010801, 2022. https://doi.org/10.1115/1.4053184