Hostname: page-component-76fb5796d-25wd4 Total loading time: 0 Render date: 2024-04-26T08:57:56.763Z Has data issue: false hasContentIssue false
  • English
  • Français

Neural network material model enhancement: Optimization through selective data removal

Published online by Cambridge University Press:  22 January 2007

JEREMY N. BUTKOVICH  and
YOUSSEF M.A. HASHASH
JEREMY N. BUTKOVICH
Affiliation:
Shannon and Wilson, Seattle, Washington, USA
YOUSSEF M.A. HASHASH
Affiliation:
Department of Civil and Environmental Engineering, University of Illinois at Urbana–Champaign, Urbana, Illinois, USA
Get access Rights & Permissions [Opens in a new window]

Abstract

Neural network (NN)-based constitutive models have been used increasingly to capture soil constitutive response. When combined with the self-learning simulation (SelfSim) inverse analysis framework, NN models can be used to extract soil behavior when given field measurements of boundary deformations and loads. However, the data sets used to train and repeatedly retrain the NN models are large, and training times, especially when used in SelfSim, are long. A diverse set of stress–strain data is extracted from a simulated braced excavation problem to train a NN-based constitutive model. Several methods for reducing the data set size are proposed and evaluated. Each of these methods selectively removes training data so that the smallest amount of data is used to train the NN. The Gaussian point method removes data based on its position in each finite element in the model. The lattice method removes data so that all remaining points are evenly spaced in stress space. Finally, the loading path method compares the stress–strain history of each Gaussian point and removes points with similar loading histories. Each of these methods shows that a large amount of the training data (up to 94%) can be removed without adversely affecting the performance of the NN model, with the loading path method showing the best and most consistent performance. Model training times are reduced by a factor of 20. The performance of the loading path method is also demonstrated using stress–strain data extracted from a simulated laboratory triaxial compression test with frictional ends.

Keywords

Data ReductionFinite Element AnalysisMaterial ModelNeural NetworkNumerical Modeling
Type
Research Article
Information
AI EDAM , Volume 21 , Issue 1: 20th Anniversary Issue , January 2007 , pp. 61 - 72
Copyright
© 2007 Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

REFERENCES

Bland, J.M., & Altman, D.G. (1986). Statistical methods for assessing agreement between two methods of clinical measurements. Lancet 1(8476), 307–310.Google Scholar
Chen, B., Dash, M., Haas, P., Qiao, Y., & Scheuerman, P. (2004). Efficient data-reduction methods for on-line association rule discovery. Selected Papers From the NSF Workshop on Next-Generation Data Mining, pp. 190–208. Cambridge, MA: MIT Press.
Dafalias, Y.F. (1980). The concept and application of the bounding surface in plasticity theory. IUTAM Symp. Physical Non-Linearities in Structural Analysis, pp. 56–63.
Ghaboussi, J., Garrett, J.H., & Wu, X. (1991). Knowledge-based modeling of material behaviour with neural networks. Journal of the Engineering Mechanics Division, ASCE 117(1), 132–153.Google Scholar
Ghaboussi, J., & Sidarta, D.E. (1997). New method of material modeling using neural networks. 6th Int. Symp. Numerical Models in Geomechanics, pp. 393–400. Montreal, Canada.
Ghaboussi, J., & Sidarta, D. (1998). A new nested adaptive neural network for modeling of constitutive behaviour of materials. Computer and Geotechnics 22(1), 29–52.Google Scholar
Hashash, Y.M.A., Jung, S., & Ghaboussi, J. (2004). Numerical implementation of a neural network based material model in finite element analysis. International Journal for Numerical Methods in Engineering 59(7), 989–1005.Google Scholar
Hashash, Y.M.A., Marulanda, C., Ghaboussi, J., & Jung, S. (2003a). Systematic update of a deep excavation model using field performance data. Computers and Geotechnics 30(6), 477–488.Google Scholar
Hashash, Y.M.A., Marulanda, C., Ghaboussi, J., & Jung, S. (2003b). Update of a numerical model of a deep excavation using field measurements. Soil Rock America 2003, 12th Panamerican Conf. Soil Mechanics and Geotechnical Engineering, Boston.
Hashash, Y.M.A., Marulanda, C., Ghaboussi, J., & Jung, S. (2006). A novel approach to integration of numerical modeling and field observations for deep excavations. Journal of Geotechnical and Geoenvironmental Engineering 123(8), 1019–1031.Google Scholar
Hashash, Y.M.A., & Whittle, A.J. (2002). Mechanisms of load transfer and arching for braced excavations in clay. Journal of Geotechnical and Geoenvironmental Engineering 128(3), 187–197.Google Scholar
Hashash, Y.M.A., Wotring, D., Yao, J.I.-C., Lee, J.-S., & Fu, Q. (2002). Visual framework for development and use of constitutive models. International Journal for Numerical and Analytical Methods in Geomechanics 26(15), 1493–1513.Google Scholar
Hashash, Y.M.A., Yao, J.I.-C., and Wotring, D. (2003c). Glyph and hyperstreamline representation of stress and strain tensors and material constitutive response. International Journal for Numerical and Analytical Methods in Geomechanics 27(7), 603–626.Google Scholar
Hill, T., & Lewicki, P. (2006). STATISTICS: Methods and Applications. Tulsa, OK: StatSoft.
Lin, L. (1989). A concordance correlation coefficient to evaluate reproducibility. Biometrics 45, 255–268.
Lin, L. (1992). Assay validation using the concordance correlation coefficient. Biometrics 48(2), 599–604.Google Scholar
Marulanda, C. (2005). Integration of numerical modeling and field observations of deep excavations. PhD Thesis. University of Illinois at Urbana–Champaign.
Prevost, J.H., & Popescu, R. (1996). Constitutive relations for soil materials. Electronic Journal for Geotechnical Engineering 1. Accessed at www.ejge.com/1996/Ppr9609/Ppr9609.htm
Reed, R.D., & Marks, R.J. (1999). Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks. Cambridge, MA: MIT Press.
Roscoe, K.H., & Burland, J.B. (1968). On the generalized stress–strain behaviour of “wet” clay. In Engineering Plasticity (Heyman, J., Ed.), pp. 535–609. Cambridge: Cambridge University Press.
Shin, H.S., & Pande, G.N. (2000). On self-learning finite element codes based on monitored response of structures. Computers and Geotechnics 27(7), 161–178.Google Scholar
Shin, H.S., & Pande, G.N. (2002). Enhancement of data for training neural network based constitutive models for geomaterials. Eighth Int. Symp. Numerical Models in Geomechanics, NUMOG VIII, pp. 141–146.
Sidarta, D., & Ghaboussi, J. (1998). Modelling constitutive behavior of materials from non-uniform material tests. Computers and Geotechnics 22(1), 53–71.Google Scholar
Whittle, A.J., & Kavvadas, M.J. (1994). Formulation of MIT-E3 constitutive model for overconsolidated clays. Journal of Geotechnical Engineering 120(1), 173–198.Google Scholar