Optimization framework for calibration of constitutive models enhanced by neural networks. (English) Zbl 1272.74463
Summary: A two-level procedure designed for the estimation of constitutive model parameters is presented in this paper. The neural network (NN) approach at the first level is applied to achieve the first approximation of parameters. This technique is used to avoid potential pitfalls related to the conventional gradient-based optimization techniques, considered here as a corrector that improves predicted parameters. The feed-forward NN (FFNN) and the modified Gauss-Newton algorithms are briefly presented. The proposed framework is verified for the elasto-plastic modified Cam Clay model that can be calibrated based on standard triaxial laboratory tests, i.e. the isotropic consolidation test and the drained compression test. Two different formulations of the input data to the NN, enhanced by a dimensional reduction of experimental data using principal component analysis, are presented. The determination of model characteristics is demonstrated, first on numerical pseudo-experiments and then on the experimental data. The efficiency of the proposed approach by means of accuracy and computational effort is also discussed.
MSC:
| 74L10 | Soil and rock mechanics |
| 74C05 | Small-strain, rate-independent theories of plasticity (including rigid-plastic and elasto-plastic materials) |
| 74P10 | Optimization of other properties in solid mechanics |
| 74G75 | Inverse problems in equilibrium solid mechanics |
| 92B20 | Neural networks for/in biological studies, artificial life and related topics |
Keywords:
back analysis; parameter identification; elasto-plastic model calibration; neural networks; principal component analysis; optimizationSoftware:
UCODEReferences:
| [1] | Graham, The 2003 R.M. Hardy Lecture: soil parameters for numerical analysis in clay, Canadian Geotechnical Journal 43 pp 187– (2006) |
| [2] | Anandarajah, Computer-aided calibration of soil plasticity model, International Journal for Numerical and Analytical Methods in Geomechanics 15 pp 835– (1991) · Zbl 0850.73366 |
| [3] | Ghaboussi, Knowledge-based modeling of material behavior with neural networks, Journal of Engineering Mechanics 117 pp 132– (1991) |
| [4] | Ghaboussi, New nested adaptive neural networks (NANN) for constitutive modeling, Computers and Geotechnics 22 (1) pp 29– (1998) |
| [5] | Sidarta, Constitutive modeling of geomaterials from non-uniform material tests, Computers and Geotechnics 22 (1) pp 53– (1998) |
| [6] | Ghaboussi, Autoprogressive training of neural network constitutive models, International Journal for Numerical Methods in Engineering 42 pp 105– (1998) · Zbl 0915.73075 |
| [7] | Shin, On self-learning finite element codes based on monitored response of structures, Computers and Geotechnics 27 pp 161– (2000) |
| [8] | Hashash, Numerical implementation of a neural network based material model in finite element analysis, International Journal for Numerical Methods in Engineering 59 pp 989– (2004) · Zbl 1065.74609 |
| [9] | Mayoraz, Neural networks for slope movement prediction, International Journal of Geomechanics 2 (2) pp 153– (2002) |
| [10] | Jan, Neural network forecast model in deep excavation, Journal of Computing in Civil Engineering 16 (1) pp 59– (2002) |
| [11] | Ding, ISC-2 on Geotechnical and Geophysical Site Characterization pp 889– (2004) |
| [12] | Goh, Reliability assessment of serviceability performance of braced retaining walls using a neural network approach, International Journal for Numerical and Analytical Methods in Geomechanics 29 pp 627– (2005) · Zbl 1104.74041 |
| [13] | Waszczyszyn, Advances in Engineering Computational Technology pp 173– (1998) |
| [14] | Shin, Identification of elastic constants for orthotropic materials from structural test, Computers and Geotechnics 30 pp 571– (2003) |
| [15] | Pichler, Back analysis of model parameters in geotechnical engineering by means of soft computing, International Journal for Numerical Methods in Engineering 57 pp 1943– (2003) · Zbl 1062.74567 |
| [16] | Sakurai, Back analysis of measured displacements of tunnels, Rock Mechanics and Rock Engineering 16 pp 173– (1983) |
| [17] | Gioda, Back analysis procedure for the interpretation of field measurements in geomechanics, International Journal for Numerical and Analytical Methods in Geomechanics 11 pp 555– (1987) · Zbl 0623.73116 |
| [18] | Ou, Soil parameter determination for deep excavation analysis by optimization, Journal of Chinese Institute of Engineers 17 (5) pp 671– (1994) · doi:10.1080/02533839.1994.9677634 |
| [19] | Zentar, Identification of soil parameters by inverse analysis, Computers and Geotechnics 28 pp 129– (1994) |
| [20] | Finno, Supported excavations: the observational method and inverse modeling, Journal of Geotechnical and Geoenvironmental Engineering 131 (7) pp 826– (2005) |
| [21] | Cailletaud, Inverse Problems in Engineering Mechanics pp 79– (1994) |
| [22] | Ledesma, Estimation of parameters in geotechnical backanalysis-I. Maximum likelihood approach, Computers and Geotechnics 18 (1) pp 1– (1996) |
| [23] | Poeter EP, Hill MC. Documentation of UCODE, a computer code for universal inverse modeling. US Geological Survey Water-Resources Investigations Report 98-4080, 1998. |
| [24] | Cividini, Parameter estimation of a static geotechnical model using a Bayes’ approach, International Journal of Rock Mechanics and Mining Sciences and Geomechanics Abstract 20 (5) pp 215– (1983) |
| [25] | Cekerevac, Calibration of an elasto-plastic constitutive model by a constrained optimisation procedure, Computers and Geotechnics 33 pp 432– (2006) |
| [26] | Pal, Calibration of a constitutive model using genetic algorithms, Computers and Geotechnics 19 (4) pp 325– (1996) |
| [27] | Samarajiva, Genetic algorithms for the calibration of constitutive models for soils, International Journal of Geomechanics 5 (3) pp 206– (2005) |
| [28] | Levasseur, Soil parameter identification using a genetic algorithm, International Journal for Numerical and Analytical Methods in Geomechanics 32 (2) pp 189– (2008) · Zbl 1273.74265 |
| [29] | Roscoe, Engineering Plasticity pp 535– (1968) |
| [30] | Kaczmarczyk, Identification of characteristic length of microstructure for second order continuum multiscale model by Bayesian neural networks, Computer Assisted Mechanics and Engineering Sciences 14 pp 183– (2007) · Zbl 1201.74241 |
| [31] | Haykin, Neural Networks. A Comprehensive Foundation (1999) |
| [32] | Rumelhart, Parallel Distributed Processing pp 287– (1986) |
| [33] | Flood, Neural networks in civil engineering. I: principles and understanding, Journal of Computing in Civil Engineering 8 (2) pp 131– (1994) |
| [34] | Diamantaras, Principal Component Neural Networks: Theory and Applications (1996) · Zbl 0911.68157 |
| [35] | Hujeux, Genie Parasismique pp 287– (1985) |
| [36] | Z_Soil.PC 2003. User Manual: Soil, Rock and Structural Mechanics in Dry or Partially Saturated Media. ZACE Services Ltd, Software Engineering: Lausanne, 2003. |
| [37] | Dascal, Caractéristique de copressibilité des argiles du complex Nottaway-Broadback-Rupert (Baie James), Canadian Geotechnical Journal 10 (1) pp 41– (1973) · doi:10.1139/t73-004 |
| [38] | Dzwilewski, Consolidation properties of Wilkinson basin soils, Journal of Geotechnical Engineering 100 (GT10) pp 1175– (1974) |
| [39] | Rendon-Herrero, Universal compression index equation, Journal of Geotechnical Engineering 106 (GT11) pp 1179– (1980) |
| [40] | Krizek, Probabilistic analysis of predicted and measured settlements, Canadian Geotechnical Journal 14 (1) pp 17– (1977) · doi:10.1139/t77-002 |
| [41] | Leroueil, Propriétés caractéristiques des argiles de l’est du Canada, Canadian Geotechnical Journal 20 (4) pp 681– (1983) |
| [42] | Mayne, Cam-Clay predictions of undrained strength, Journal of Geotechnical Engineering 106 (GT11) pp 1219– (1980) |
| [43] | Chang, Selection of training samples for model updating using neural networks, Journal of Sound and Vibration 249 (5) pp 867– (2002) |
| [44] | Calvello, 8th International Symposium on Numerical Models in Geomechanics-NUMOG VIII pp 107– (2002) · doi:10.1201/9781439833797-c16 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
