Neural surrogate-driven modelling, optimisation, and generation of engineering designs: A concise review

–

Neural surrogate-driven modelling, optimisation, and generation of engineering designs: A concise review

CHEN Siyi, DING Jiangfeng, SHAO Zhutao, SHI Zhusheng, LIN Jianguo

Abstract. Synergies between neural networks and traditional surrogate modelling techniques have emerged as the forefront of data-driven engineering. Neural network-based surrogate models, trained on carefully selected experimental data or high-fidelity simulations, can predict behaviours of complex systems with remarkable speed and accuracy. This review examines the current state and recent developments in neural surrogate technologies, highlighting their expanding roles in engineering design optimisation and generation. It also covers various feature engineering methods for representing 3D geometries, the principles of neural surrogate modelling, and the potential of emerging AI-driven design tools. While feature engineering remains a challenge, especially in parameterising complex designs for machine learning, recent advancements in code/language-based representations offer promising solutions for digitalising various design scenarios. Moreover, the emergence of AI-driven design tools, including text-to-CAD models powered by large language models, enables engineers to rapidly generate and evaluate innovative design concepts. Neural surrogate modelling has the potential to transform engineering workflows. Continued research into geometric feature engineering, along with the integration of AI-driven design tools, will speed up the use of neural surrogate models in engineering designs.

Keywords
AI-Driven Design, Feature Engineering, Neural Surrogate Modelling, Surrogate-Driven Design Optimisation, Generative Design, Text-to-CAD, Digital Twin

Published online 9/15/2024, 10 pages
Copyright © 2024 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA

Citation: CHEN Siyi, DING Jiangfeng, SHAO Zhutao, SHI Zhusheng, LIN Jianguo, Neural surrogate-driven modelling, optimisation, and generation of engineering designs: A concise review, Materials Research Proceedings, Vol. 44, pp 493-502, 2024

DOI: https://doi.org/10.21741/9781644903254-53

The article was published as article 53 of the book Metal Forming 2024

Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.

References
[1] A. Keane, A. Forrester, A. Sobester, Engineering design via surrogate modelling: A practical guide, John Wiley & Sons, 2008. https://doi.org/10.2514/4.479557
[2] L. Regenwetter, A. Nobari, F. Ahmed, Deep generative models in engineering design: a review, J. Mech. Des. 144 (2022) 071704. https://doi.org/10.1115/1.4053859
[3] H. Attar, A. Foster, N. Li, Development of a deep learning platform for sheet stamping geometry optimisation under manufacturing constraints, Eng. Appl. Artif. Intell. 123 (2023) 106295. https://doi.org/10.1016/j.engappai.2023.106295
[4] H. Zhou, N. Li, Image-based Artificial Intelligence empowered surrogate model and shape morpher for real-time blank shape optimisation in the hot stamping process. https://doi.org/10.48550/arXiv.2212.05885
[5] Information on https://shorturl.at/efjSV
[6] S. Liu, Development of an Intelligent Flexible Sheet Metal Forming Technique, PhD Thesis, Imperial College London, 2022
[7] A. Géron, Hands-on machine learning with Scikit-Learn, Keras and TensorFlow: concepts, tools, and techniques to build intelligent systems, Oreilly, Newton, 2019. https://www.oreilly.com/library/view/hands-on-machine-learning/9781098125967/
[8] Information on https://domino.ai/data-science-dictionary/feature-engineering
[9] V. Jovanovic, M. Kuzlu, U. Cali, D.H. Utku, F.O. Catak, S. Sarp, N. Zohrabi, Digital Twin in Industry 4.0 and Beyond Applications, in: Digital Twin Driven Intelligent Systems and Emerging Metaverse, Springer, Singapore, 2023, pp. 155–174. https://doi.org/10.1007/978-981-99-0252-1_7
[10] Information on https://shorturl.at/bfF15
[11] Z. Han, K. Zhang, Surrogate-Based Optimization, in: Engineering Design Optimization, InTech, 2012, pp. 343–362. https://doi.org/10.5772/36125
[12] F. Viana, C. Gogu, T. Goel, Surrogate modeling: tricks that endured the test of time and some recent developments, Struct. Multidiscipl. Optim. 64 (2021) 2881–2908. https://doi.org/10.1007/S00158-021-03001-2
[13] G. Sun, S. Wang, A review of the artificial neural network surrogate modeling in aerodynamic design, Proc. Inst. Mech. Eng. G. J. Aerosp. Eng. 233 (2019) 5863–5872. https://doi.org/10.1177/0954410019864485
[14] H. Attar, H. Zhou, A. Foster, N. Li, Rapid feasibility assessment of components to be formed through hot stamping: A deep learning approach, J. Manuf. Process. 68 (2021) 1650–1671. https://doi.org/10.1016/j.jmapro.2021.06.011
[15] Information on https://www.neuralconcept.com/
[16] Information on https://www.monolithai.com/products
[17] Information on https://shorturl.at/twGPU
[18] Information on https://www.visendi.ai/
[19] Information on https://zoo.dev/text-to-cad
[20] C. Zhang, R. Pinquié, A. Polette, G. Carasi, H. De Charnace, J.P. Pernot, Automatic 3D CAD models reconstruction from 2D orthographic drawings, Comput. Graph. 114 (2023) 179–189. https://doi.org/10.1016/J.CAG.2023.05.021
[21] J. Yet, C. Lau, K. Thang, 2D Orthographic Drawings to 3D Conversion using Machine Learning, ICOSEC (2022) 1308–1312. https://doi.org/10.1109/ICOSEC54921.2022.9952009
[22] R. John, S. Peter, J. Alfred, R.J. Spick, S. Demediuk, J. Alfred Walker, Naive mesh-to-mesh coloured model generation using 3D GANs, Proc. ACSW (2020) 1–6. https://doi.org/10.1145/3373017.3373067
[23] K. Murdock, Advanced Materials, in: 3ds Max 2011 Bible, Wiley Publishing, Indianapolis, 2010: pp. 759–815. https://www.wiley.com/en-gb/3ds+Max+2011+Bible-p-9780470908372
[24] T. Mullen, Working with Textures and Materials, in: Mastering Blender, Second Edition, John Wiley & Sons, Inc., Indianapolis, 2013: pp. 33–84. https://www.wiley.com/en-cn/Mastering+Blender,+2nd+Edition-p-9781118275405
[25] H. Attar, A. Foster, N. Li, Implicit Neural Representations of Sheet Stamping Geometries with Small-Scale Features, Eng. Appl. Artif. Intell. 123 (2023) 106482. https://doi.org/10.1016/j.engappai.2023.106482
[26] R. Wu, C. Xiao, C. Zheng, DeepCAD: A deep generative network for computer-aided design models, Proc. IEEE Int. Conf. Comput. Vis. (2021) 6752-6762. https://doi.org/10.1109/ICCV48922.2021.00670
[27] J. Lambourne, K. Willis, P. Jayaraman, A. Sanghi, P. Meltzer, H. Shayani, BRepNet: A topological message passing system for solid models, IEEE/CVF CVPR (2021) 12768–12777. https://doi.org/10.1109/CVPR46437.2021.01258
[28] J. Pongetti, T. Kipouros, M. Emmanuelli, R. Ahlfeld, S. Shahpar, Using autoencoders and output consolidation to improve machine learning models for turbomachinery applications, Proc. ASME Turbo Expo. (2021) V02DT36A018. https://doi.org/10.1115/GT2021-60158
[29] T. Rios, B. Van Stein, T. Back, B. Sendhoff, S. Menzel, Multitask shape optimization using a 3-D point cloud autoencoder as unified representation, IEEE TEVC 26 (2022) 206–217. https://doi.org/10.1109/TEVC.2021.3086308
[30] K. Willis, Y. Pu, J. Luo, H. Chu, T. Du, J. Lambourne, A. Solar-Lezama, W. Matusik, Fusion 360 Gallery: A dataset and environment for programmatic CAD construction from human design sequences, ACM Trans. Graph. 40 (2021) 1–24. https://doi.org/10.1145/3450626.3459818
[31] S. Kucherenko, D. Albrecht, A. Saltelli, Exploring multi-dimensional spaces: a comparison of Latin hypercube and quasi monte carlo sampling techniques, (2015). https://doi.org/10.48550/arXiv.1505.02350
[32] F. Tejero, D. MacManus, F. Sanchez-Moreno, C. Sheaf, Neural network-based multi-point, multi-objective optimisation for transonic applications, Aerosp. Sci. Technol. 136 (2023) 108208. https://doi.org/10.1016/J.AST.2023.108208
[33] M. Norgaard, J. Ross, M. Ncrgaard, C. Jorgensen, Neural network prediction of new aircraft design coefficients, (1997). https://ntrs.nasa.gov/citations/19970023478
[34] H. Zhou, Q. Xu, N. Li, A study on using image based machine learning methods to develop the surrogate models of stamp forming simulations, J. Manuf. Sci. Eng. 144 (2022) 021012. https://doi.org/10.1115/1.4051604
[35] H. Zhou, H. Attar, Y. Pan, X. Li, P. Childs, N. Li, On the feasibility of small-data learning in simulation-driven engineering tasks with known mechanisms and effective data representations, in: NeurIPS-AI4Science Poster, 2021. https://openreview.net/forum?id=qvxJBCp7aji
[36] J. Petrik, S. Ali, M. Feistle, M. Bambach, CrystalMind: A surrogate model for predicting 3D models with recrystallization in open-die hot forging including an optimization framework, Mech. Mater. 189 (2024) 104875. https://doi.org/10.1016/J.MECHMAT.2023.104875
[37] B. Shahriari, K. Swersky, Z. Wang, R.P. Adams, N. De Freitas, Taking the human out of the loop: A review of Bayesian optimization, Proc. IEEE 104 (2016) 148–175. https://doi.org/10.1109/JPROC.2015.2494218
[38] N. Loka, I. Couckuyt, F. Garbuglia, D. Spina, I. Van Nieuwenhuyse, T. Dhaene, Bi-objective Bayesian optimization of engineering problems with cheap and expensive cost functions, Eng. Comput. 39 (2023) 1923–1933. https://doi.org/10.1007/s00366-021-01573-7
[39] E. Ruff, R. Russell, M. Stoeckle, P. Miotto, J.P. How, Surrogate neural networks for efficient simulation-based trajectory planning optimization (2023). https://doi.org/10.48550/arXiv.2303.17468
[40] Information on https://www.cadify.ai/
[41] Information on https://www.getleo.ai/cad
[42] F. Bie, Y. Yang, Z. Zhou, A. Ghanem, M. Zhang, Z. Yao, X. Wu, C. Holmes, P. Golnari, D.A. Clifton, Y. He, D. Tao, S.L. Song, RenAIssance: A survey into AI text-to-image generation in the era of large model, (2023). https://doi.org/10.48550/arXiv.2309.00810
[43] A. Nichol, H. Jun, P. Dhariwal, P. Mishkin, M. Chen, Point-E: A system for generating 3D point clouds from complex prompts, (2022). https://doi.org/10.48550/arXiv.2212.08751
[44] C. Lin, J. Gao, L. Tang, T. Takikawa, X. Zeng, X. Huang, K. Kreis, S. Fidler, M. Liu, T. Lin, Magic3D: High-resolution text-to-3D content creation, Proc. IEEE CVPR 2023-June (2023) 300–309. https://doi.org/10.1109/CVPR52729.2023.00037
[45] Information on https://www.solidworks.com/media/wild-imagination-artificial-intelligence