Predicting the Non-Deterministic Response of a Micro-Scale Mechanical Model Using Generative Adversarial Networks
Abstract
:1. Introduction
2. Problem Description
2.1. Micro-Scale Problem
2.2. Crack Network Damage
2.3. Numerical Model
2.4. Failure Criterion
2.5. Loss of Uniqueness
2.6. Failure Sampling
3. Failure Modelling
3.1. Gaussian Process Regression
3.2. Neural Net Clustering
3.3. Generative Adversarial Networks
4. Application to a Material Point Loading
5. Discussion
or translated into machine learning “models should be no more complex than is sufficient to explain the data”. The principle very much applies to the present work since excessive network complexity in either depth or number of neurons resulted in the “Helvetica scenario” a kind of mode collapse.“Pluralitas non est ponenda sine neccesitate”
6. Conclusions
- Non-determinism is an inherent property of the material mechanical response. It plays a paramount role in the onset end evolution of strain localisation, thus the importance of its reproduction in numerical models.
- Gaussian Process Regression cannot reproduce the micro-scale response because of the presence of multiple distributions rather than a unique random distribution. This is due to the existence of different mechanisms leading to failure.
- Neural net clustering using Self-Organizing Maps can distinguish several of the micro-scale failure modes but does not succeed at identifying a small group of data points that are an important feature of the response.
- With the adequate network architecture, Generative Adversarial Networks can properly reproduce the micro-scale data including its non-deterministic characteristics. As the learning is totally unsupervised, no assumptions about data distribution are needed.
- The Generator trained in the Generative Adversarial Networks is ready to be deployed in multiscale numerical approaches allowing to, at list partially, avoid the costly numerical micro-computations. The computational economy must allow those multiscale models to compete with classical phenomenological models in terms of cost.
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
AI | Artificial Intelligence |
ML | Machine Learning |
PSO | Particle Swarm Optimizer |
PDE | Partial Differential Equation |
DoF | Degree of Freedom |
GPR | Gaussian Process Regression |
SOM | Self-Organizing Map |
GANs | Generative Adversarial Networks |
LSGANs | Least Squares Generative Adversarial Networks |
DCGANs | Deep Convolutional Generative Adversarial Networks |
WGANs | Wasserstein Generative Adversarial Networks |
TANN | Thermodynamics-based Artificial Neural Networks |
References
- Auriault, J.L. Heterogeneous medium. Is an equivalent macroscopic description possible? Int. J. Eng. Sci. 1991, 29, 785–795. [Google Scholar] [CrossRef]
- Argilaga, A.; Papachristos, E. Bounding the Multi-Scale Domain in Numerical Modelling and Meta-Heuristics Optimization: Application to Poroelastic Media with Damageable Cracks. Materials 2021, 14, 3974. [Google Scholar] [CrossRef] [PubMed]
- Stefanou, I.; Sulem, J.; Vardoulakis, I. Three-dimensional Cosserat homogenization of masonry structures: Elasticity. Acta Geotech. 2008, 3, 71–83. [Google Scholar] [CrossRef] [Green Version]
- Godio, M.; Stefanou, I.; Sab, K.; Sulem, J.; Sakji, S. A limit analysis approach based on Cosserat continuum for the evaluation of the in-plane strength of discrete media: Application to masonry. Eur. J.-Mech.-A/Solids 2017, 66, 168–192. [Google Scholar] [CrossRef] [Green Version]
- Scholtès, L.; Donzé, F.V.; Khanal, M. Scale effects on strength of geomaterials, case study: Coal. J. Mech. Phys. Solids 2011, 59, 1131–1146. [Google Scholar] [CrossRef]
- Bertrand, F.; Cerfontaine, B.; Collin, F. A fully coupled hydro-mechanical model for the modeling of coalbed methane recovery. J. Nat. Gas Sci. Eng. 2017, 46, 307–325. [Google Scholar] [CrossRef] [Green Version]
- Godyń, K.; Dutka, B. Sorption and Micro-Scale Strength Properties of Coals Susceptible to Outburst Caused by Changes in Degree of Coalification. Materials 2021, 14, 5807. [Google Scholar] [CrossRef]
- Valle, V.; Hedan, S.; Cosenza, P.; Fauchille, A.L.; Berdjane, M. Digital image correlation development for the study of materials including multiple crossing cracks. Exp. Mech. 2015, 55, 379–391. [Google Scholar] [CrossRef]
- Ougier-Simonin, A.; Renard, F.; Boehm, C.; Vidal-Gilbert, S. Microfracturing and microporosity in shales. Earth-Sci. Rev. 2016, 162, 198–226. [Google Scholar] [CrossRef] [Green Version]
- Arson, C. Micro-macro mechanics of damage and healing in rocks. Open Geomech. 2020, 2, 1–41. [Google Scholar] [CrossRef] [Green Version]
- Cartwright-Taylor, A.; Mangriotis, M.D.; Main, I.; Butler, I.; Fusseis, F.; Ling, M.; Andò, E.; Curtis, A.; Bell, A.; Crippen, A.; et al. Seismic events miss important grain-scale mechanisms governed by kinematics during shear failure of porous rock. Nat. Portf. 2022, 2693–5015. [Google Scholar] [CrossRef]
- Meier, H.; Steinmann, P.; Kuhl, E. Towards multiscale computation of confined granular media–Contact forces, stresses and tangent operators. Tech. Mech. 1996, 1, 77–88. [Google Scholar]
- Nitka, M.; Combe, G.; Dascalu, C.; Desrues, J. Two-scale modeling of granular materials: A DEM-FEM approach. Granul. Matter 2011, 13, 277–281. [Google Scholar] [CrossRef]
- de Souza Neto, E.; Blanco, P.; Sánchez, P.; Feijóo, R. An RVE-based multiscale theory of solids with micro-scale inertia and body force effects. Mech. Mater. 2015, 80, 136–144. [Google Scholar] [CrossRef] [Green Version]
- van den Eijnden, B.; Bésuelle, P.; Chambon, R.; Collin, F. A FE2 modelling approach to hydromechanical coupling in cracking-induced localization problems. Int. J. Solids Struct. 2016, 97–98, 475–488. [Google Scholar] [CrossRef]
- Desrues, J.; Argilaga, A.; Caillerie, D.; Combe, G.; Nguyen, T.; Richefeu, V.; Dal Pont, S. From discrete to continuum modelling of boundary value problems in geomechanics: An integrated FEM-DEM approach. Int. J. Numer. Anal. Methods Geomech. 2019, 43, 919–955. [Google Scholar] [CrossRef]
- Pardoen, B.; Bésuelle, P.; Dal Pont, S.; Cosenza, P.; Desrues, J. Accounting for Small-Scale Heterogeneity and Variability of Clay Rock in Homogenised Numerical Micromechanical Response and Microcracking. Rock Mech. Rock Eng. 2020, 53, 2727–2746. [Google Scholar] [CrossRef]
- Guo, N.; Yang, Z.; Yuan, W.H.; Zhao, J. A coupled SPFEM/DEM approach for multiscale modeling of large-deformation geomechanical problems. Int. J. Numer. Anal. Methods Geomech. 2020, 45, 648–667. [Google Scholar] [CrossRef]
- Papanicolau, G.; Bensoussan, A.; Lions, J.L. Asymptotic Analysis for Periodic Structures; Elsevier: Amsterdam, The Netherlands, 1978. [Google Scholar]
- Sánchez-Palencia, E. Non-Homogeneous Media and Vibration Theory; Springer: Berlin, Germany, 1980; Volume 127. [Google Scholar]
- Arbogast, T.; Douglas, J., Jr.; Hornung, U. Derivation of the double porosity model of single phase flow via homogenization theory. SIAM J. Math. Anal. 1990, 21, 823–836. [Google Scholar] [CrossRef]
- Sridhar, A.; Kouznetsova, V.; Geers, M. A general multiscale framework for the emergent effective elastodynamics of metamaterials. J. Mech. Phys. Solids 2017, 111, 411–433. [Google Scholar] [CrossRef]
- Waseem, A.; Heuzé, T.; Stainier, L.; Geers, M.; Kouznetsova, V. Model reduction in computational homogenization for transient heat conduction. Comput. Mech. 2020, 65, 249–266. [Google Scholar] [CrossRef] [Green Version]
- Auriault, J.L. Heterogeneous periodic and random media. Are the equivalent macroscopic descriptions similar? Int. J. Eng. Sci. 2011, 49, 806–808. [Google Scholar] [CrossRef]
- Argilaga, A.; Papachristos, E.; Caillerie, D.; Dal Pont, S. Homogenization of a cracked saturated porous medium: Theoretical aspects and numerical implementation. Int. J. Solids Struct. 2016, 94–95, 222–237. [Google Scholar] [CrossRef]
- Chen, C.T.; Gu, G.X. Effect of Constituent Materials on Composite Performance: Exploring Design Strategies via Machine Learning. Adv. Theory Simul. 2019, 2, 1900056. [Google Scholar] [CrossRef]
- Liu, X.; Athanasiou, C.E.; Padture, N.P.; Sheldon, B.W.; Gao, H. A machine learning approach to fracture mechanics problems. Acta Mater. 2020, 190, 105–112. [Google Scholar] [CrossRef]
- Hanakata, P.Z.; Cubuk, E.D.; Campbell, D.K.; Park, H.S. Forward and inverse design of kirigami via supervised autoencoder. Phys. Rev. Res. 2020, 2, 042006. [Google Scholar] [CrossRef]
- Wang, K.; Sun, W. A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning. Comput. Methods Appl. Mech. Eng. 2018, 334, 337–380. [Google Scholar] [CrossRef]
- Liu, Z.; Wu, C. Exploring the 3D architectures of deep material network in data-driven multiscale mechanics. J. Mech. Phys. Solids 2019, 127, 20–46. [Google Scholar] [CrossRef] [Green Version]
- Logarzo, H.J.; Capuano, G.; Rimoli, J.J. Smart constitutive laws: Inelastic homogenization through machine learning. Comput. Methods Appl. Mech. Eng. 2021, 373, 113482. [Google Scholar] [CrossRef]
- Jang, D.P.; Fazily, P.; Yoon, J.W. Machine learning-based constitutive model for J2-plasticity. Int. J. Plast. 2021, 138, 102919. [Google Scholar] [CrossRef]
- Vlassis, N.N.; Sun, W. Sobolev training of thermodynamic-informed neural networks for interpretable elasto-plasticity models with level set hardening. Comput. Methods Appl. Mech. Eng. 2021, 377, 113695. [Google Scholar] [CrossRef]
- Masi, F.; Stefanou, I.; Vannucci, P.; Maffi-Berthier, V. Thermodynamics-based Artificial Neural Networks for constitutive modeling. J. Mech. Phys. Solids 2021, 147, 104277. [Google Scholar] [CrossRef]
- Kim, D.W.; Lim, J.H.; Lee, S. Prediction and validation of the transverse mechanical behavior of unidirectional composites considering interfacial debonding through convolutional neural networks. Compos. Part Eng. 2021, 225, 109314. [Google Scholar] [CrossRef]
- Kim, Y.; Kim, Y.; Yang, C.; Park, K.; Gu, G.; Ryu, S. Deep learning framework for material design space exploration using active transfer learning and data augmentation. NPJ Comput. Mater. 2021, 7, 140. [Google Scholar] [CrossRef]
- Ashank; Chakravarty, S.; Garg, P.; Kumar, A.; Agrawal, M.; Agnihotri, P.K. Deep Neural Networks Based Predictive-Generative Framework for Designing Composite Materials. 2021. Available online: http://www.lanl.gov/abs/2105.01384 (accessed on 1 November 2021).
- Papachristos, E.; Stefanou, I. Controlling earthquake-like instabilities using artificial intelligence. arXiv 2021, arXiv:2104.13180. [Google Scholar]
- Maizir, H.; Gofar, N.; Kassim, K. Artificial Neural Network Model for Prediction of Bearing Capacity of Driven Pile. J. Tek. Sipil Inst. Teknol. Bdg. 2015, 22, 49–56. [Google Scholar]
- Benbouras, M.A.; Petrişor, A.I.; Zedira, H.; Ghelani, L.; Lefilef, L. Forecasting the Bearing Capacity of the Driven Piles Using Advanced Machine-Learning Techniques. Appl. Sci. 2021, 11, 908. [Google Scholar] [CrossRef]
- Jahed Armaghani, D.; Harandizadeh, H.; Momeni, E.; Maizir, H.; Zhou, J. An optimized system of GMDH-ANFIS predictive model by ICA for estimating pile bearing capacity. Artif. Intell. Rev. 2021, 54, 1–38. [Google Scholar] [CrossRef]
- Omar, M.; Che Mamat, R.; Abdul Rasam, A.R.; Ramli, A.; Samad, A. Artificial intelligence application for predicting slope stability on soft ground: A comparative study. Int. J. Adv. Technol. Eng. Explor. 2021, 8, 362–370. [Google Scholar] [CrossRef]
- Chambon, R.; Caillerie, D.; Viggiani, G. Loss of uniqueness and bifurcation vs instability: Some remarks. Rev. Fr. Génie Civ. 2004, 8, 517–535. [Google Scholar] [CrossRef]
- Hill, R. Acceleration waves in solids. J. Mech. Phys. Solids 1962, 10, 1–16. [Google Scholar] [CrossRef]
- Rice, J.R. The Localization of Plastic Deformation; Division of Engineering, Brown University: Providence, RI, USA, 1976. [Google Scholar]
- Pietruszczak, S.; Mroz, Z. Finite element analysis of deformation of strain-softening materials. Int. J. Numer. Methods Eng. 1981, 17, 327–334. [Google Scholar] [CrossRef]
- Sluys, L.; De Borst, R.; Mühlhaus, H.B. Wave propagation, localization and dispersion in a gradient-dependent medium. Int. J. Solids Struct. 1993, 30, 1153–1171. [Google Scholar] [CrossRef] [Green Version]
- Argilaga, A.; Desrues, J.; Dal Pont, S.; Combe, G.; Caillerie, D. FEM×DEM multiscale modeling: Model performance enhancement from Newton strategy to element loop parallelization. Int. J. Numer. Methods Eng. 2018, 114, 47–65. [Google Scholar] [CrossRef] [Green Version]
- Eringen, A.C. Nonlocal polar elastic continua. Int. J. Eng. Sci. 1972, 10, 1–16. [Google Scholar] [CrossRef]
- Mindlin, R.D. Second gradient of strain and surface-tension in linear elasticity. Int. J. Solids Struct. 1965, 1, 417–438. [Google Scholar] [CrossRef]
- Germain, P. La méthode des puissances virtuelles en mécanique des milieux continus. J. Mec. 1973, 12, 236–274. [Google Scholar]
- De Borst, R.; Mühlhaus, H.B. Gradient-dependent plasticity: Formulation and algorithmic aspects. Int. J. Numer. Methods Eng. 1992, 35, 521–539. [Google Scholar] [CrossRef] [Green Version]
- Pamin, J.K. Gradient-Dependent Plasticity in Numerical Simulation of Localization Phenomena; TU Delft, Delft University of Technology: Amsterdam, The Netherlands, 1994. [Google Scholar]
- Peerlings, R.H.; de Borst, R.; Brekelmans, W.M.; de Vree, J. Gradient enhanced damage for quasi-brittle materials. Int. J. Numer. Methods Eng. 1996, 39, 3391–3403. [Google Scholar] [CrossRef]
- Chambon, R.; Caillerie, D.; El Hassan, N. One-dimensional localisation studied with a second grade model. Eur. J.-Mech.-A/Solids 1998, 17, 637–656. [Google Scholar] [CrossRef]
- Matsushima, T.; Chambon, R.; Caillerie, D. Second gradient models as a particular case of microstructured models: A large strain finite elements analysis. C. R. l’Académie Sci. IIB-Mech. 2000, 328, 179–186. [Google Scholar] [CrossRef]
- Chambon, R.; Caillerie, D.; Matsuchima, T. Plastic continuum with microstructure, local second gradient theories for geomaterials: Localization studies. Int. J. Solids Struct. 2001, 38, 8503–8527. [Google Scholar] [CrossRef]
- Yang, Y.; Misra, A. Micromechanics based second gradient continuum theory for shear band modeling in cohesive granular materials following damage elasticity. Int. J. Solids Struct. 2012, 49, 2500–2514. [Google Scholar] [CrossRef] [Green Version]
- Collin, F.; Chambon, R.; Charlier, R. A finite element method for poro mechanical modelling of geotechnical problems using local second gradient models. Int. J. Numer. Methods Eng. 2006, 65, 1749–1772. [Google Scholar] [CrossRef]
- Marinelli, F. Comportement Couplé des Géomatériaux: Deus Approches de Módelisation Numérique. Ph.D. Thesis, Communauté Université Grenoble Alpes, Saint-Martin-d’Hères, France, 2013. [Google Scholar]
- Jouan, G.; Kotronis, P.; Collin, F. Using a second gradient model to simulate the behaviour of concrete structural elements. Finite Elem. Anal. Des. 2014, 90, 50–60. [Google Scholar] [CrossRef] [Green Version]
- Salehnia, F.; Collin, F.; Li, X.L.; Dizier, A.; Sillen, X.; Charlier, R. Coupled modeling of Excavation Damaged Zone in Boom clay: Strain localization in rock and distribution of contact pressure on the gallery’s lining. Comput. Geotech. 2015, 69, 396–410. [Google Scholar] [CrossRef]
- Sieffert, Y.; Al Holo, S.; Chambon, R. Loss of uniqueness of numerical solutions of the borehole problem modelled with enhanced media. Int. J. Solids Struct. 2009, 46, 3173–3197. [Google Scholar] [CrossRef] [Green Version]
- Desrues, J.; Argilaga, A.; Pont, S.D.; Combe, G.; Caillerie, D.; Nguyen, T.K. Restoring Mesh Independency in FEM-DEM Multi-Scale Modelling of Strain Localization Using Second Gradient Regularization; Springer Series in Geomechanics and Geoengineering; Springer International Publishing: Cham, Switzerland, 2017; pp. 453–457. [Google Scholar]
- Guo, S.; Qi, S.; Zou, Y.; Zheng, B. Numerical Studies on the Failure Process of Heterogeneous Brittle Rocks or Rock-Like Materials under Uniaxial Compression. Materials 2017, 10, 378. [Google Scholar] [CrossRef] [Green Version]
- Shahin, G.; Cil, M.; Buscarnera, G. Assessment of statistical homogeneity in chemically treated granular materials. Geotech. Lett. 2018, 8, 32–39. [Google Scholar] [CrossRef]
- Pardoen, B.; Dal Pont, S.; Desrues, J.; Bésuelle, P.; Prêt, D.; Cosenza, P. Heterogeneity and Variability of Clay Rock Microstructure in a Hydro-Mechanical Double Scale FEM × FEM Analysis. In Micro to MACRO Mathematical Modelling in Soil Mechanics; Giovine, P., Mariano, P.M., Mortara, G., Eds.; Springer International Publishing: Cham, Switzerland, 2018; pp. 247–256. [Google Scholar] [CrossRef]
- Pardoen, B.; Collin, F. Modelling the influence of strain localisation and viscosity on the behaviour of underground drifts drilled in claystone. Comput. Geotech. 2016, 85, 351–367. [Google Scholar] [CrossRef] [Green Version]
- Shahin, G.; Desrues, J.; Pont, S.D.; Combe, G.; Argilaga, A. A study of the influence of REV variability in double-scale FEM ×DEM analysis. Int. J. Numer. Methods Eng. 2016, 107, 882–900. [Google Scholar] [CrossRef] [Green Version]
- Cheng, X.; Tang, C.; Zhuang, D. A finite-strain viscoelastic-damage numerical model for time-dependent failure and instability of rocks. Comput. Geotech. 2022, 143, 104596. [Google Scholar] [CrossRef]
- Andò, E.; Viggiani, G.; Hall, S.; Desrues, J. Experimental micro-mechanics of granular media studied by X-ray tomography: Recent results and challenges. Geotech. Lett. 2013, 3, 142–146. [Google Scholar] [CrossRef]
- Couture, C.; Bésuelle, P. Diffuse and localized deformation of a porous Vosges sandstone in true triaxial conditions. E3S Web Conf. 2019, 92, 06007. [Google Scholar] [CrossRef]
- Pardoen, B.; Bésuelle, P.; Dal Pont, S.; Cosenza, P.; Desrues, J. Effect of Claystone Small-Scale Characteristics on the Variability of Micromechanical Response and on Microcracking Modelling; Challenges and Innovations in Geomechanics; Barla, M., Di Donna, A., Sterpi, D., Eds.; Springer International Publishing: Cham, Switzerland, 2021; pp. 522–530. [Google Scholar]
- Tudisco, E.; Vitone, C.; Mondello, C.; Viggiani, G.; Athanasopoulos, S.; Hall, S.; Cotecchia, F. Localised strain in fissured clays: The combined effect of fissure orientation and confining pressure. Acta Geotech. 2021, 1–9. [Google Scholar] [CrossRef]
- Royer, P.; Cherblanc, F. Homogenisation of advective–diffusive transport in poroelastic media. Mech. Res. Commun. 2010, 37, 133–136. [Google Scholar] [CrossRef] [Green Version]
- Auriault, J.L. Transport in porous media: Upscaling by multiscale asymptotic expansions. In Applied Micromechanics of Porous Materials; Springer: Vienna, Austria, 2005; pp. 3–56. [Google Scholar]
- Caillerie, D. Thin and periodic plates. Math. Meth. Appl. Sci. 1984, 6, 159–191. [Google Scholar] [CrossRef]
- Dascalu, C.; Bilbie, G.; Agiasofitou, E. Damage and size effects in elastic solids: A homogenization approach. Int. J. Solids Struct. 2008, 45, 409–430. [Google Scholar] [CrossRef] [Green Version]
- Marinelli, F.; Sieffert, Y.; Chambon, R. Hydromechanical modeling of an initial boundary value problem: Studies of non-uniqueness with a second gradient continuum. Int. J. Solids Struct. 2015, 54, 238–257. [Google Scholar] [CrossRef]
- Nova, R. Controllability of the incremental response of soil specimens subjected to arbitrary loading programmes. J. Mech. Behav. Mater. 1994, 5, 193–202. [Google Scholar] [CrossRef]
- Rasmussen, C.E. Gaussian Processes in Machine Learning. In Advanced Lectures on Machine Learning: ML Summer Schools 2003, Canberra, Australia, 2–14 February 2003, Tübingen, Germany, 4–16 August 2003, Revised Lectures; Bousquet, O., von Luxburg, U., Rätsch, G., Eds.; Springer: Berlin/Heidelberg, Germany, 2004; pp. 63–71. [Google Scholar] [CrossRef] [Green Version]
- Qian, J.; Nguyen, N.P.; Oya, Y.; Kikugawa, G.; Okabe, T.; Huang, Y.; Ohuchi, F.S. Introducing self-organized maps (SOM) as a visualization tool for materials research and education. Results Mater. 2019, 4, 100020. [Google Scholar] [CrossRef]
- Goodfellow, I.J. NIPS 2016 Tutorial: Generative Adversarial Networks. In CoRR; 2017. Available online: http://www.lanl.gov/abs/1701.00160 (accessed on 5 November 2021).
- Mao, X.; Li, Q.; Xie, H.; Lau, R.Y.K.; Wang, Z.; Smolley, S.P. Least Squares Generative Adversarial Networks. 2017. Available online: http://www.lanl.gov/abs/1611.04076 (accessed on 5 November 2021).
- Radford, A.; Metz, L.; Chintala, S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. 2016. Available online: http://www.lanl.gov/abs/1511.06434 (accessed on 5 November 2021).
- Arjovsky, M.; Chintala, S.; Bottou, L. Wasserstein Generative Adversarial Networks. In Proceedings of the 34th International Conference on Machine Learning–Volume 70, Sydney, NSW, Australia, 6–11 August 2017; pp. 214–223. [Google Scholar]
- Metz, L.; Poole, B.; Pfau, D.; Sohl-Dickstein, J. Unrolled Generative Adversarial Networks. 2017. Available online: http://www.lanl.gov/abs/1611.02163 (accessed on 5 November 2021).
Configuration | Pa] | Pa] | Pa] | Tol. | n | ||
---|---|---|---|---|---|---|---|
-scale 1 | 0.0050 | 961 | 1442 | [0.001–0.0001] | [195–205] | 0.9 | |
-scale 2 | 0.0025 | 961 | 1442 | [0.001–0.0001] | [195–205] | 0.9 | |
-scale 3 | 0.0025 | [480–1442] | [721–2163] | 0.0001 | 200 | 0.9 | |
-scale 4 | 0.0050 | 961 | 1442 | 0.0001 | 200 | 0.8 | |
-scale 5 | 0.0050 | 961 | 1442 | 0.0001 | 200 | 0.8 | |
-scale 6 | 0.0050 | 961 | 1442 | 0.0001 | 200 | 0.8 |
Layer/Neurons | Generator | Discriminator |
---|---|---|
Input Layer | Latent dimension | Image size |
Hidden Layer 1 | 32 | 64 |
Hidden Layer 2 | 64 | 32 |
Output Layer | Image size | 1 |
Hyperparameter | Value |
---|---|
Latent dimension | 64 |
Batch size | 24 |
Image size | 128 × 128 |
Dis learning rate | 0.0003 |
Gen learning rate | 0.0003 |
Gen decay | 0.201 |
Gen squared decay | 0.799 |
Max epochs | 150 |
Algorithm | Learning | Depth | Typical Application |
---|---|---|---|
GPR | Supervised | Shallow | Curve fitting |
SOM | Unsupervised | Shallow | Maps, clustering |
GANs | Unsupervised | Deep | Fake image generation |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Argilaga, A.; Zhuang, D. Predicting the Non-Deterministic Response of a Micro-Scale Mechanical Model Using Generative Adversarial Networks. Materials 2022, 15, 965. https://doi.org/10.3390/ma15030965
Argilaga A, Zhuang D. Predicting the Non-Deterministic Response of a Micro-Scale Mechanical Model Using Generative Adversarial Networks. Materials. 2022; 15(3):965. https://doi.org/10.3390/ma15030965
Chicago/Turabian StyleArgilaga, Albert, and Duanyang Zhuang. 2022. "Predicting the Non-Deterministic Response of a Micro-Scale Mechanical Model Using Generative Adversarial Networks" Materials 15, no. 3: 965. https://doi.org/10.3390/ma15030965
APA StyleArgilaga, A., & Zhuang, D. (2022). Predicting the Non-Deterministic Response of a Micro-Scale Mechanical Model Using Generative Adversarial Networks. Materials, 15(3), 965. https://doi.org/10.3390/ma15030965