The Data-Driven Homogenization of Mohr–Coulomb Parameters Based on a Bayesian Optimized Back Propagation Artificial Neural Network (BP-ANN)
Source abstract
Abstract
Homogenization methods can characterize the mechanical properties of these materials based on appropriate constitutive models and data. They are also applied to the characterization of mechanical parameters under complex geotechnical conditions in geotechnical engineering because of the complexity and heterogeneous nature of geotechnical materials. Unfortunately, existing homogenization methods for geotechnical mechanical parameters often incur immense computational costs. Hence, a framework that utilizes finite element analysis for generating a dataset which is then trained using a Bayesian Optimized Back Propagation Artificial Neural Network (BP-ANN) to obtain the homogenized Mohr–Coulomb parameters of the soils is proposed. This is the first time that Bayesian optimization and a BP-ANN have been used in conjunction to predict the homogenized mechanical parameters of soils. The dataset used for training the data is generated using the commercial FEM software ABAQUS (6.10). The maximum difference between the top and bottom part of the tunnel of the heterogeneous model and homogeneous model of our test cases only varies by 5.3%, thereby verifying the excellence of the Bayesian Optimized BP-ANN.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Drilling and Well Engineering · Rock Mechanics and Modeling · Non-Destructive Testing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
MOE Key Laboratory of Deep Earth Science and Engineering, College of Architecture and Environment, Sichuan University, Chengdu 610065, China
Funding
National Natural Science Foundation of China · Major research and development project of Metallurgical Corporation of China LTD. in the non-steel field
References (29)
Show source-provided references
1. A meso-macroscopic constitutive model of frozen saline sandy soil based on homogenization theory
2. Numerical homogenization of jointed rock masses using wave propagation simulation10.1007/s00603-013-0458-8 ↗
3. Modeling of dilatancy effect in layered rock with rough interfaces using micropolar continuum
4. Deep learning in neural networks: An overview10.1016/j.neunet.2014.09.003 ↗
5. Smart constitutive laws: Inelastic homogenization through machine learning10.1016/j.cma.2020.113482 ↗
6. Rodríguez, C.A., Rodríguez-Pérez, A.M., López, R., Hernández-Torres, J.A., and Caparrós-Mancera, J.J. (2023). A Finite Element Method Integrated with Terzaghi’s Principle to Estimate Settlement of a Building Due to Tunnel Construction. Buildings, 13.10.3390/buildings13051343 ↗
7. An ABAQUS (R) plug-in for generating virtual data required for inverse analysis of unidirectional composites using artificial neural networks10.1007/s00366-021-01525-1 ↗
8. Multiscale Modeling Meets Machine Learning: What Can We Learn?10.1007/s11831-020-09405-5 ↗
9. Data-driven estimation models of asphalt mixtures dynamic modulus using ANN, GP and combinatorial GMDH approaches10.1007/s00521-022-07382-3 ↗
10. Predicting the mechanical response of oligocrystals with deep learning10.1016/j.commatsci.2019.109099 ↗
11. Application of deep learning algorithms in geotechnical engineering: A short critical review10.1007/s10462-021-09967-1 ↗
12. Machine learning-based intelligent modeling of hydraulic conductivity of sandy soils considering a wide range of grain sizes10.1016/j.enggeo.2022.106899 ↗
13. 3D response surface modeling based in-situ assessment of physico-mechanical characteristics of alluvial soils using dynamic cone penetrometer10.1016/j.trgeo.2022.100781 ↗
14. Selected AI optimization techniques and applications in geotechnical engineering10.1080/23311916.2022.2153419 ↗
15. Mohr-Coulomb Failure Criterion10.1007/s00603-012-0281-7 ↗
16. Contrastive application of neural network and fuzzy comprehensive evaluation to slope stability analysis
17. Research on prediction of ultimate moment capacity of beam-to-column flush end-plate connection joint via BP-ANN model
18. Dropout: A Simple Way to Prevent Neural Networks from Overfitting
19. Activation functions in deep learning: A comprehensive survey and benchmark10.1016/j.neucom.2022.06.111 ↗
20. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
21. Using geologic structures to constrain constitutive laws not accessible in the laboratory10.1016/j.jsg.2018.06.006 ↗
22. Large-Scale Test Study on the Three-Dimensional Behavior of the Gravel-Concrete Interface of a CFR Dam10.1061/(ASCE)GM.1943-5622.0001701 ↗
23. Three-dimensional elasto-plastic damage model for gravelly soil-structure interface considering the shear coupling effect10.1016/j.compgeo.2020.103868 ↗
24. Application of the Mohr-Coulomb model for simulating the biomass compaction process10.1088/1757-899X/776/1/012066 ↗
25. Application of the Modified Mohr-Coulomb Yield Criterion in Seismic Numerical Simulation of Tunnels10.1155/2021/9968935 ↗
26. Wang, Y.W., Li, S.Y., Ma, Q., and Li, W. (2013, January 9–10). A Comparative Study of Artificial Boundary Conditions in ABAQUS. Proceedings of the International Conference on Structures and Building Materials (ICSBM 2013), Guizhou, China.
27. Infinite element boundary conditions for dynamic models under seismic loading10.1007/s12648-019-01533-4 ↗
28. Witten, I.H., Frank, E., and Hall, M.A. (2005). Data Mining: Practical Machine Learning Tools and Techniques, Elsevier. [3rd ed.].
29. Prediction of the shale gas permeability: A data mining approach10.1016/j.gete.2023.100435 ↗