Bayesian optimization with Gaussian-process-based active machine learning for improvement of geometric accuracy in projection multi-photon 3D printing

Jason E. Johnson; Ishat Raihan Jamil; Liang Pan; Guang Lin; Xianfan Xu

doi:10.1038/s41377-024-01707-8

Go to Nature Website

Your Location：

Home >

Browse articles >

Bayesian optimization with Gaussian-process-based active machine learning for improvement of geometric accuracy in projection multi-photon 3D printing

Original Articles

- Bayesian optimization with Gaussian-process-based active machine learning for improvement of geometric accuracy in projection multi-photon 3D printing
- Light: Science & Applications Vol. 14, Issue 2, Pages: 509-520(2025)
- Affiliations：
  
  1.School of Mechanical Engineering, Purdue University, 585 Purdue Mall, West Lafayette, IN 47907, USA
  2.Birck Nanotechnology Center, Purdue University, 1205 Mitch Daniels Blvd., West Lafayette, IN 47907, USA
  3.Department of Mathematics, Purdue University, Mathematical Sciences Bldg, 150 N University St, West Lafayette, IN 47907, USA
- Author bio：
  
  Xianfan Xu (xxu@purdue.edu)
- Funds：
- DOI：10.1038/s41377-024-01707-8
  CLC：
- Received：06 June 2024，
  
  Revised：27 November 2024，
  
  Accepted：2024-11-29，
  
  Published Online：20 January 2025，
  
  Published：28 February 2025
- Accepted：
Scan QR Code
Johnson, J. E. et al. Bayesian optimization with Gaussian-process-based active machine learning for improvement of geometric accuracy in projection multi-photon 3D printing. Light: Science & Applications, 14, 509-520 (2025).
DOI：

Johnson, J. E. et al. Bayesian optimization with Gaussian-process-based active machine learning for improvement of geometric accuracy in projection multi-photon 3D printing. Light: Science & Applications, 14, 509-520 (2025). DOI： 10.1038/s41377-024-01707-8.

摘要

Abstract

Multi-photon polymerization is a well-established

yet actively developing

additive manufacturing technique for 3D printing on the micro/nanoscale. Like all additive manufacturing techniques

determining the process parameters necessary to achieve dimensional accuracy for a structure 3D printed using this method is not always straightforward and can require time-consuming experimentation. In this work

an active machine learning based framework is presented for determining optimal process parameters for the recently developed

high-speed

layer-by-layer continuous projection 3D printing process. The proposed active learning framework uses Bayesian optimization to inform optimal experimentation in order to adaptively collect the most informative data for effective training of a Gaussian-process-regression-based machine learning model. This model then serves as a surrogate for the manufacturing process: predicting optimal process parameters for achieving a target geometry

e.g.

the 2D geometry of each printed layer. Three representative 2D shapes at three different scales are used as test cases. In each case

the active learning framework improves the geometric accuracy

with drastic reductions of the errors to within the measurement accuracy in just four iterations of the Bayesian optimization using only a few hundred of total training data. The case studies indicate that the active learning framework developed in this work can be broadly applied to other additive manufacturing processes to increase accuracy with significantly reduced experimental data collection effort for optimization.

关键词

Keywords

references

Ngo, T. D. et al. Additive manufacturing (3D printing): a review of materials, methods, applications and challenges. Compos. Part B Eng. 143 , 172–196 (2018)..

Ng, W. L. et al. Progress and opportunities for machine learning in materials and processes of additive manufacturing. Adv. Mater. 36 , 2310006 (2024)..

Somers, P. et al. The physics of 3D printing with light. Nat. Rev. Phys. 6 , 99–113 (2024)..

Kawata, S. et al. Finer features for functional microdevices. Nature 412 , 697–698 (2001)..

Zhou, X. Q., Hou, Y. H. & Lin, J. Q. A review on the processing accuracy of two-photon polymerization. AIP Adv. 5 , 030701 (2015)..

Tumbleston, J. R. et al. Continuous liquid interface production of 3D objects. Science 347 , 1349–1352 (2015)..

Ge, Q. et al. Projection micro stereolithography based 3D printing and its applications. Int. J. Extrem. Manuf. 2 , 022004 (2020)..

Kiefer, P. et al. A multi-photon (7 × 7)-focus 3D laser printer based on a 3D-printed diffractive optical element and a 3D-printed multi-lens array. Light Adv. Manuf. 4 , 28–41 (2024)..

Saha, S. K. et al. Scalable submicrometer additive manufacturing. Science 366 , 105–109 (2019)..

Somers, P. et al. Rapid, continuous projection multi-photon 3D printing enabled by spatiotemporal focusing of femtosecond pulses. Light Sci. Appl. 10 , 199 (2021)..

He, H. Y., Yang, Y. & Pan, Y. Y. Machine learning for continuous liquid interface production: printing speed modelling. J. Manuf. Syst. 50 , 236–246 (2019)..

You, S. T. et al. Mitigating scattering effects in light-based three-dimensional printing using machine learning. J. Manuf. Sci. Eng. 142 , 081002 (2020)..

De Souza Borges Ferreira, R., Sabbaghi, A. & Huang, Q. Automated geometric shape deviation modeling for additive manufacturing systems via Bayesian neural networks. IEEE Trans. Autom. Sci. Eng. 17 , 584–598 (2020)..

Deneault, J. R. et al. Toward autonomous additive manufacturing: Bayesian optimization on a 3D printer. MRS Bull. 46 , 566–575 (2021)..

Brion, D. A. J. & Pattinson, S. W. Generalisable 3D printing error detection and correction via multi-head neural networks. Nat. Commun. 13 , 4654 (2022)..

DebRoy, T. et al. Metallurgy, mechanistic models and machine learning in metal printing. Nat. Rev. Mater. 6 , 48–68 (2021)..

Wang, H. et al. Two-photon polymerization lithography for optics and photonics: fundamentals, materials, technologies, and applications. Adv. Funct. Mater. 33 , 2214211 (2023)..

Johnson, J. E., Chen, Y. & Xu, X. Model for polymerization and self-deactivation in two-photon nanolithography. Opt. Express 30 , 26824–26840 (2022)..

Mueller, J. B. et al. Polymerization kinetics in three-dimensional direct laser writing. Adv. Mater. 26 , 6566–6571 (2014)..

Wang, H. et al. Toward near-perfect diffractive optical elements via nanoscale 3D printing. ACS Nano 14 , 10452–10461 (2020)..

Aderneuer, T., Fernández, O. & Ferrini, R. Two-photon grayscale lithography for free-form micro-optical arrays. Opt. Express 29 , 39511–39520 (2021)..

Yang, Y. H. et al. Machine-learning-enabled geometric compliance improvement in two-photon lithography without hardware modifications. J. Manuf. Process. 76 , 841–849 (2022)..

Pingali, R. & Saha, S. K. Printability prediction in projection two-photon lithography via machine learning based surrogate modeling of photopolymerization. J. Micro Nano-Manuf. 10 , 031005 (2022)..

Lee, X. Y. et al. Automated detection of part quality during two-photon lithography via deep learning. Addit. Manuf. 36 , 101444 (2020)..

Ovsianikov, A. et al. Shrinkage of microstructures produced by two-photon polymerization of Zr-based hybrid photosensitive materials. Opt. Express 17 , 2143–2148 (2009)..

Jariwala, A. S. et al. Modeling effects of oxygen inhibition in mask‐based stereolithography. Rapid Prototyp. J. 17 , 168–175 (2011)..

Rasmussen, C. E. & Williams, C. K. I. Gaussian Processes for Machine Learning (The MIT Press, 2005).

Garnett, R. Bayesian Optimization (Cambridge University Press, 2023).

Hu, B. et al. Multi-objective Bayesian optimization accelerated design of TPMS structures. Int. J. Mech. Sci. 244 , 108085 (2023)..

Snapp, K. L. et al. Superlative mechanical energy absorbing efficiency discovered through self-driving lab-human partnership. Nat. Commun. 15 , 4290 (2024)..

Sheikh, H. M. et al. Systematic design of Cauchy symmetric structures through Bayesian optimization. Int. J. Mech. Sci. 236 , 107741 (2022)..

Huang, Q. An impulse response formulation for small-sample learning and control of additive manufacturing quality. IISE Trans. 55 , 926–939 (2023)..

Sobol', I. M. On the distribution of points in a cube and the approximate evaluation of integrals. USSR Comput. Math. Math. Phys. 7 , 86–112 (1967)..

Zhou, C., Xu, H. & Chen, Y. Spatiotemporal projection-based additive manufacturing: a data-driven image planning method for subpixel shifting in a split second. Adv. Intell. Syst. 3 , 2100079 (2021)..

Zhou, C., Chen, Y. & Waltz, R. A. Optimized mask image projection for solid freeform fabrication. Proceedings of the ASME 2009 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference 543–557 (ASME, 2009).

Otto, O. W. et al. Automated optical proximity correction: a rules-based approach. Proceedings of SPIE 2197, Optical/Laser Microlithography VII 278–293 (SPIE, 1994).

Zhang, H. et al. Fast optimization of defect compensation and optical proximity correction for extreme ultraviolet lithography mask. Opt. Commun. 452 , 169–180 (2019)..

Bradski, G. The OpenCV library. Dr. Dobb's J. Softw. Tools 120 , 122–125 (2000)..

Otsu, N. A threshold selection method from gray-level histograms. IEEE Trans. Syst., Man, Cybern. 9 , 62–66 (1979)..

Huttenlocher, D. P., Klanderman, G. A. & Rucklidge, W. J. Comparing images using the Hausdorff distance. IEEE Trans. Pattern Anal. Mach. Intell. 15 , 850–863 (1993)..

Bonilla, E. V., Chai, K. M. A. & Williams, C. K. I. Multi-task Gaussian process prediction. Proceedings of the 20th International Conference on Neural Information Processing Systems 153–160 (Curran Associates Inc., 2007).

Gardner, J. R. et al. GPyTorch: blackbox matrix-matrix Gaussian process inference with GPU acceleration. Proceedings of the 32nd International Conference on Neural Information Processing Systems 7587–7597 (Curran Associates Inc., 2018).

Ansel, J. et al. PyTorch 2: faster machine learning through dynamic Python bytecode transformation and graph compilation. Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems 929–947 (ACM, 2024).

Zvagelsky, R. et al. In-situ quantitative phase imaging during multi-photon laser printing. ACS Photonics 10 , 2901–2908 (2023)..

Zvagelsky, R. et al. Towards in-situ diagnostics of multi-photon 3D laser printing using optical coherence tomography. Light Adv. Manuf. 3 , 466–480 (2022)..

Zyla, G. & Farsari, M. Frontiers of laser-based 3D printing: a perspective on multi-photo n lithography. Laser Photonics Rev. 18 , 2301312. https://doi.org/10.1002/lpor.202301312 (2024)..

Kiefer, P. et al. Sensitive photoresists for rapid multiphoton 3D laser micro- and nanoprinting. Adv. Opt. Mater. 8 , 2000895 (2020)..

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰