Abstract
The availability of significant computational resources has played an essential role in developing advanced numerical models for the design and safety evaluation of complex structures such as rockfill dams. Determining the geomechanical parameters is deemed a crucial but challenging task for effective modelling. The general approach involves using in situ or laboratory tests or experimental relationships from the literature to assess these parameters. These measures, however, do not accurately reflect the actual situation. This paper proposes a data driven approach using deep neural networks and non-deterministic optimization algorithms to identify the soil parameters that will lead to displacements that best approximate the measured data. The methodology is applied to a rockfill dam recently built in Quebec, for which some measurements of inclinometer displacements are available. A finite element model (FEM) of two dimensions generates numerical solutions. A comparative study is performed to account for the heterogeneity of the materials by decomposing the computational domain into subdomains. Subsequently, the inverse analysis uses the surrogate model instead of the full FEM model for rapid computations. A suitable objective function is defined to account for large oscillations in the measurement data. Non-intrusive stochastic optimization algorithms such as Genetic algorithm (GA), Particle Swarm Optimization (PSO), and Differential evolution (DE) are evaluated for the minimization problem. Finally, the case study confirms the capability of the proposed methodology to identify the relevant dam parameters, provide some insights into the performance, and compare three optimization algorithms.
Similar content being viewed by others
References
Akbari Hamed A (2017) Predictive numerical modeling of the behavior of rockfill dams. MS Thesis, École de Technologie Supérieure, Canada
An J-S, Kang K-N, Kim S-H, Song K-I (2019) Analysis for applicability of differential evolution algorithm to geotechnical engineering field. Journal of the Korean Geotechnical Society 35(4):27–35, DOI: https://doi.org/10.7843/kgs.2019.35.4.27
Arora RK (2015) Optimization: Algorithms and applications. CRC Press
Asteris PG, Rizal FIM, Koopialipoor M, Roussis PC, Ferentinou M, Armaghani DJ, Gordan B (2022) Slope stability classification under seismic conditions using several tree-based intelligent techniques. Applied Sciences 12(3):1753, DOI: https://doi.org/10.3390/app12031753
Asthana B, Khare D (2022) Recent advances in dam engineering. Springer Nature, SN
Bao T, Li J, Lu Y, Gu C (2020) IDE-MLSSVR-based back analysis method for multiple mechanical parameters of concrete dams. Journal of Structural Engineering 146(8):04020155, DOI: https://doi.org/10.1061/(ASCE)ST.1943-541X.0002602
Beale M, Hagan M, Demuth H (2019) MATLAB Deep learning toolbox users guide: PDF documentation for release R2019a. The MathWorks, Inc
Bishop CM (2006) Pattern recognition and machine learning. Springer
Bolzon G, Buljak V (2011) An effective computational tool for parametric studies and identification problems in materials mechanics. Computational Mechanics 48(6):675–687, DOI: https://doi.org/10.1007/s00466-011-0611-8
Boumezerane D (2022) Recent tendencies in the use of optimization techniques in geotechnics: A review. Geotechnics 2(1):114–132
Carbonari S, Dezi F, Arezzo D, Gara F (2022) A methodology for the identification of physical parameters of soil-foundation-bridge pier systems from identified state-space models. Engineering Structures 255:113944
Coello CAC, Lamont GB, Van Veldhuizen DA, Others (2007) Evolutionary algorithms for solving multi-objective problems. Springer
Darwin C (2007) Theory of evolution. C. King & S. Scott, Trans. Encarta-Microsoft Student
Das R, Soulaimani A (2021) Non-deterministic methods and surrogates in the design of rockfill dams. Applied Sciences 11(8):3699, DOI: https://doi.org/10.3390/app11083699
Deng-gang W, Ying-xi L, Shou-ju L (2000) Genetic algorithms for inverse analysis of displacements in geotechnical engineering. Chinese Journal of Rock Mechanics and Engineering 19(2):979–982
Dige N, Diwekar U (2018) Efficient sampling algorithm for large-scale optimization under uncertainty problems. Computers & Chemical Engineering 115:431–454, DOI: https://doi.org/10.1016/j.compchemeng.2018.05.007
Dou S, Li J, Kang F (2017) Parameter identification of concrete dams using swarm intelligence algorithm. Engineering Computations 34(7):2358–2378, DOI: https://doi.org/10.1108/EC-03-2017-0110
Dou S, Li J, Kang F (2019) Health diagnosis of concrete dams using hybrid FWA with RBF-based surrogate model. Water Science and Engineering 12(3):188–195
Eltaeib T, Mahmood A (2018) Differential evolution: A survey and analysis. Applied Sciences 8(10):1945, DOI: https://doi.org/10.3390/app8101945
Eykhoff P (1974) System identification. Parameter and state estimation, John Wiley and sons, Chichester, United Kingdom
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press
Gunantara N (2018) A review of multi-objective optimization: Methods and its applications. Cogent Engineering 5(1):1502242, DOI: https://doi.org/10.1080/23311916.2018.1502242
Hashash YM, Levasseur S, Osouli A, Finno R, Malecot Y (2010) Comparison of two inverse analysis techniques for learning deep excavation response. Computers and Geotechnics 37(3):323–333, DOI: https://doi.org/10.1016/j.compgeo.2009.11.005
He X, Wang F, Li W, Sheng D (2022) Deep learning for efficient stochastic analysis with spatial variability. Acta Geotechnica 17(4):1031–1051
He B, Armaghani DJ, Lai SH (2023) Assessment of tunnel blasting-induced overbreak: A novel metaheuristic-based random forest approach. Tunnelling and Underground Space Technology 133:104979, DOI: https://doi.org/10.1016/j.tust.2022.104979
Hokes F, Kral P, Krnavek O, Husek M (2017) Improved sensitivity analysis in the inverse identification of the parameters of a nonlinear material model. Procedia Engineering 172:347–354, DOI: https://doi.org/10.1016/j.proeng.2017.02.039
Holland JH (1992) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT press
Hsieh WW (2009) Machine learning methods in the environmental sciences: Neural networks and kernels. Cambridge University Press, Cambridge
Jacquier P, Abdedou A, Delmas V, Soulaimani A (2020) Non-intrusive reduced-order modeling using uncertainty-aware deep neural networks and proper orthogonal decomposition. Application to Flood Modeling: arXiv:2005.13506 [physics]
Jia Y, Chi S (2015) Back-analysis of soil parameters of the Malutang II concrete face rockfill dam using parallel mutation particle swarm optimization. Computers and Geotechnics 65:87–96, DOI: https://doi.org/10.1016/j.compgeo.2014.11.013
Kang F, Liu X, Li J, Li H (2022) Multi-parameter inverse analysis of concrete dams using kernel extreme learning machines-based response surface model. Engineering Structures 256:113999, DOI: https://doi.org/10.1016/j.engstruct.2022.113999
Kang F, Wu Y, Li J, Li H (2021) Dynamic parameter inverse analysis of concrete dams based on Jaya algorithm with Gaussian processes surrogate model. Advanced Engineering Informatics 49:101348
Kennedy J, Eberhart R (1995) Particle swarm optimization. Proceedings of ICNN’95 - International Conference on Neural Networks 1942–1948, 4
Kim S, Finno RJ (2019) Inverse analysis of a supported excavation in Chicago. Journal of Geotechnical and Geoenvironmental Engineering 145(9):04019050, DOI: https://doi.org/10.1061/(ASCE)GT.1943-5606.0002120
Kim T, Jung Y-H (2022) Optimizing material parameters to best capture deformation responses in supported bottom-up excavation: Field monitoring and inverse analysis. KSCE Journal of Civil Engineering 26(8):3384–3401, DOI: https://doi.org/10.1007/s12205-022-1582-3
Labuz JF, Zang A (2012) Mohr-Coulomb failure criterion. The ISRM Suggested Methods for Rock Characterization, Testing and Monitoring: 2007–2014, Springer, 227–231
Levasseur S, Malecot Y, Boulon M, Flavigny E (2010) Statistical inverse analysis based on genetic algorithm and principal component analysis: Applications to excavation problems and pressuremeter tests. International Journal for Numerical and Analytical Methods in Geomechanics 34(5):471–491
Li Y, Hariri-Ardebili MA, Deng T, Wei Q, Cao M (2023) A surrogate-assisted stochastic optimization inversion algorithm: Parameter identification of dams. Advanced Engineering Informatics 55:101853, DOI: https://doi.org/10.1016/j.aei.2022.101853
Lin C, Li T, Chen S, Lin C, Liu X, Gao L, Sheng T (2020) Structural identification in long-term deformation characteristic of dam foundation using meta-heuristic optimization techniques. Advances in Engineering Software 148:102870, DOI: https://doi.org/10.1016/j.advengsoft.2020.102870
Lin S, Zheng H, Han B, Li Y, Han C, Li W (2022) Comparative performance of eight ensemble learning approaches for the development of models of slope stability prediction. Acta Geotechnica 17(4): 1477–1502
Mathworks T (2007) MATLAB optimization toolbox user’s guide. Math Work
Murata T, Ishibuchi H (1995) MOGA: Multi-objective genetic algorithms. IEEE International Conference on Evolutionary Computation 289–294
Nocedal J, Wright S (2006) Numerical optimization. Springer Science
Phoon K-K, Zhang W (2022) Future of machine learning in geotechnics. Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards 1–16
Pietruszczak S (2010) Fundamentals of plasticity in geomechanics. Crc Press Boca Raton, FL
Plaxis B (2017) PLAXIS Reference manual. Delft University of Technology & Plaxis BV, The Netherlands
Salazar F, Hariri-Ardebili MA (2022) Coupling machine learning and stochastic finite element to evaluate heterogeneous concrete infrastructure. Engineering Structures 260:114190
Shahriari M, Pardo D, Moser B, Sobieczky F (2020) A deep neural network as surrogate model for forward simulation of borehole resistivity measurements. Procedia Manufacturing 42:235–238, DOI: https://doi.org/10.1016/j.promfg.2020.02.075
Shahzadi G, Soulaïmani A (2021) Deep neural network and polynomial chaos expansion-based surrogate models for sensitivity and uncertainty propagation: An application to a rockfill dam. Water 13(13):1830, DOI: https://doi.org/10.3390/w13131830
Shan F, He X, Jahed Armaghani D, Zhang P, Sheng D (2022) Success and challenges in predicting TBM penetration rate using recurrent neural networks. Tunnelling and Underground Space Technology 130:104728, DOI: https://doi.org/10.1016/j.tust.2022.104728
Shan F, He X, Xu H, Armaghani DJ, Sheng D (2023) Applications of machine learning in mechanised tunnel construction: A systematic Review. Eng 4(2):1516–1535, DOI: https://doi.org/10.3390/eng4020087
Shang L, Nguyen H, Bui X-N, Vu TH, Costache R, Hanh LTM (2022) Toward state-of-the-art techniques in predicting and controlling slope stability in open-pit mines based on limit equilibrium analysis, radial basis function neural network, and brainstorm optimization. Acta Geotechnica 17(4):1295–1314
Sharifzadeh M, Tarifard A, Moridi MA (2013) Time-dependent behavior of tunnel lining in weak rock mass based on displacement back analysis method. Tunnelling and Underground Space Technology 38:348–356
Skentou AD, Bardhan A, Mamou A, Lemonis ME, Kumar G, Samui P, Armaghani DJ, Asteris PG (2023) Closed-form equation for estimating unconfined compressive strength of granite from three non-destructive tests using soft computing models. Rock Mechanics and Rock Engineering 56(1):487–514, DOI: https://doi.org/10.1007/s00603-022-03046-9
Smith M (2015) Rockfill settlement measurement and modelling of the Romaine-2 dam during construction. International Commission on Large Dams; Proceedings of the 25th International Congress, Stavanger
Sobol IM (1993) Sensitivity analysis for non-linear mathematical models. Mathematical Modelling and Computational Experiment 1:407–414
Storn R, Price K (1997) Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization 11(4):341–359, DOI: https://doi.org/10.1023/A:1008202821328
Su H, Li J, Wu Z (2007) Feedback analysis for mechanical parameters of dam and its foundation with optimization algorithm. Journal of Hydraulic Engineering 38:129–134
Vahdati P (2014) Identification of soil parameters in an embankment dam by mathematical optimization. Luleå
Vahdati P, Levasseur S, Mattsson H, Knutsson S (2013) Inverse Mohr-Coulomb soil parameter identification of an earth and rockfill dam by genetic algorithm optimization. The Electronic Journal of Geotechnical Engineering 18(X):5419–5440
Vannobel P, Smith M, Lefebvre G, Karray M, Éthier Y (2013) Control of rockfill placement for the romaine-2 asphaltic core dam in northern Quebec. Canadian Geotechnical Journal, https://espace2.etsmtl.ca/id/eprint/8918
Yagiz S, Yazitova A, Karahan H (2020) Application of differential evolution algorithm and comparing its performance with literature to predict rock brittleness for excavatability. International Journal of Mining, Reclamation and Environment, 1–14
Yang L, Li Z (2019) Inverse analysis of rock creep model parameters based on improved simulated annealing differential evolution algorithm. Geotechnical and Geological Engineering 37(2):639–649, DOI: https://doi.org/10.1007/s10706-018-0634-4
Yin Z-Y, Jin Y-F, Shen JS, Hicher P-Y (2018) Optimization techniques for identifying soil parameters in geotechnical engineering: Comparative study and enhancement. International Journal for Numerical and Analytical Methods in Geomechanics 42(1):70–94
Zhang W, Gu X, Tang L, Yin Y, Liu D, Zhang Y (2022) Application of machine learning, deep learning and optimization algorithms in geoengineering and geoscience: Comprehensive review and future challenge. Gondwana Research
Zhang W, Li H, Li Y, Liu H, Chen Y, Ding X (2021) Application of deep learning algorithms in geotechnical engineering: A short critical review. Artificial Intelligence Review 54(8): 5633–5673
Zhang W, Liu Z (2022) Editorial for machine learning in geotechnics. Acta Geotechnica 1–1
Zhao H, Yin S (2016) Inverse analysis of geomechanical parameters by the artificial bee colony algorithm and multi-output support vector machine. Inverse Problems in Science and Engineering 24(7):1266–1281, DOI: https://doi.org/10.1080/17415977.2016.1178257
Zhou J, Li E, Wei H, Li C, Qiao Q, Armaghani DJ (2019) Random forests and cubist algorithms for predicting shear strengths of rockfill materials. Applied Sciences 9(8):1621, DOI: https://doi.org/10.3390/app9081621
Zhou W, Li S, Ma G, Chang X, Ma X, Zhang C (2016) Parameters inversion of high central core rockfill dams based on a novel genetic algorithm. Science China Technological Sciences 59(5):783–794, DOI: https://doi.org/10.1007/s11431-016-6017-2
Acknowledgments
Hydro Quebec and the Natural Sciences and Engineering Research Council of Canada supported research for this project.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Shahzadi, G., Soulaimani, A. Deep Neural Network-based Inverse Analysis with Application to a Rockfill Dam. KSCE J Civ Eng 28, 155–168 (2024). https://doi.org/10.1007/s12205-023-0355-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12205-023-0355-y