{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T07:59:24Z","timestamp":1722067164958},"reference-count":24,"publisher":"Cambridge University Press (CUP)","issue":"1","license":[{"start":{"date-parts":[[2007,1,22]],"date-time":"2007-01-22T00:00:00Z","timestamp":1169424000000},"content-version":"unspecified","delay-in-days":21,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIEDAM"],"published-print":{"date-parts":[[2007,1]]},"abstract":"<jats:p>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\u2013strain 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\u2013strain 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\u2013strain data extracted from a simulated laboratory triaxial compression test with frictional ends.<\/jats:p>","DOI":"10.1017\/s089006040707014x","type":"journal-article","created":{"date-parts":[[2007,1,22]],"date-time":"2007-01-22T23:24:27Z","timestamp":1169508267000},"page":"61-72","source":"Crossref","is-referenced-by-count":0,"title":["Neural network material model enhancement: Optimization through selective data removal"],"prefix":"10.1017","volume":"21","author":[{"given":"JEREMY N.","family":"BUTKOVICH","sequence":"first","affiliation":[]},{"given":"YOUSSEF M.A.","family":"HASHASH","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2007,1,22]]},"reference":[{"key":"S089006040707014X_ref017","unstructured":"Marulanda, C. (2005).Integration of numerical modeling and field observations of deepexcavations.PhD Thesis.University of Illinois at Urbana\u2013Champaign."},{"key":"S089006040707014X_ref024","doi-asserted-by":"crossref","unstructured":"Whittle, A.J. , & Kavvadas, M.J. (1994).Formulation of MIT-E3 constitutive model for overconsolidatedclays.Journal of Geotechnical Engineering 120(1),173\u2013198.","DOI":"10.1061\/(ASCE)0733-9410(1994)120:1(173)"},{"key":"S089006040707014X_ref007","doi-asserted-by":"crossref","unstructured":"Hashash, Y.M.A. , Jung, S. , & Ghaboussi, J. (2004).Numerical implementation of a neural network based material model infinite element analysis.International Journal for Numerical Methods in Engineering 59(7),989\u20131005.","DOI":"10.1002\/nme.905"},{"key":"S089006040707014X_ref010","doi-asserted-by":"crossref","unstructured":"Hashash, Y.M.A. , Marulanda, C. , Ghaboussi, J. , & Jung, S. (2006).A novel approach to integration of numerical modeling and fieldobservations for deep excavations.Journal of Geotechnical and Geoenvironmental Engineering 123(8),1019\u20131031.","DOI":"10.1061\/(ASCE)1090-0241(2006)132:8(1019)"},{"key":"S089006040707014X_ref003","unstructured":"Dafalias, Y.F. (1980).The concept and application of the bounding surface in plasticitytheory.IUTAM Symp. Physical Non-Linearities in Structural Analysis,pp.56\u201363."},{"key":"S089006040707014X_ref001","doi-asserted-by":"crossref","unstructured":"Bland, J.M. , & Altman, D.G. (1986).Statistical methods for assessing agreement between two methods ofclinical measurements.Lancet 1(8476),307\u2013310.","DOI":"10.1016\/S0140-6736(86)90837-8"},{"key":"S089006040707014X_ref018","unstructured":"Prevost, J.H. , & Popescu, R. (1996).Constitutive relations for soil materials.Electronic Journal for Geotechnical Engineering 1. Accessed atwww.ejge.com\/1996\/Ppr9609\/Ppr9609.htm"},{"key":"S089006040707014X_ref015","doi-asserted-by":"crossref","unstructured":"Lin, L. (1989).A concordance correlation coefficient to evaluatereproducibility.Biometrics 45,255\u2013268.","DOI":"10.2307\/2532051"},{"key":"S089006040707014X_ref008","doi-asserted-by":"crossref","unstructured":"Hashash, Y.M.A. , Marulanda, C. , Ghaboussi, J. , & Jung, S. (2003a).Systematic update of a deep excavation model using field performancedata.Computers and Geotechnics 30(6),477\u2013488.","DOI":"10.1016\/S0266-352X(03)00056-9"},{"key":"S089006040707014X_ref006","doi-asserted-by":"crossref","unstructured":"Ghaboussi, J. , & Sidarta, D. (1998).A new nested adaptive neural network for modeling of constitutivebehaviour of materials.Computer and Geotechnics 22(1),29\u201352.","DOI":"10.1016\/S0266-352X(97)00034-7"},{"key":"S089006040707014X_ref014","unstructured":"Hill, T. , & Lewicki, P. (2006).STATISTICS: Methods and Applications.Tulsa, OK:StatSoft."},{"key":"S089006040707014X_ref023","doi-asserted-by":"crossref","unstructured":"Sidarta, D. , & Ghaboussi, J. (1998).Modelling constitutive behavior of materials from non-uniformmaterial tests.Computers and Geotechnics 22(1),53\u201371.","DOI":"10.1016\/S0266-352X(97)00035-9"},{"key":"S089006040707014X_ref005","unstructured":"Ghaboussi, J. , & Sidarta, D.E. (1997).New method of material modeling using neural networks.6th Int. Symp. Numerical Models in Geomechanics, pp.393\u2013400.Montreal, Canada."},{"key":"S089006040707014X_ref020","unstructured":"Roscoe, K.H. , & Burland, J.B. (1968).On the generalized stress\u2013strain behaviour of\u201cwet\u201d clay. InEngineering Plasticity( Heyman, J. , Ed.), pp.535\u2013609.Cambridge:Cambridge University Press."},{"key":"S089006040707014X_ref009","unstructured":"Hashash, Y.M.A. , Marulanda, C. , Ghaboussi, J. , & Jung, S. (2003b).Update of a numerical model of a deep excavation using fieldmeasurements.Soil Rock America 2003, 12th Panamerican Conf. Soil Mechanics andGeotechnical Engineering,Boston."},{"key":"S089006040707014X_ref002","unstructured":"Chen, B. , Dash, M. , Haas, P. , Qiao, Y. , & Scheuerman, P. (2004).Efficient data-reduction methods for on-line association rulediscovery.Selected Papers From the NSF Workshop on Next-Generation DataMining, pp.190\u2013208.Cambridge, MA:MIT Press."},{"key":"S089006040707014X_ref022","doi-asserted-by":"crossref","unstructured":"Shin, H.S. , & Pande, G.N. (2002).Enhancement of data for training neural network based constitutivemodels for geomaterials.Eighth Int. Symp. Numerical Models in Geomechanics, NUMOGVIII, pp.141\u2013146.","DOI":"10.1201\/9781439833797-c21"},{"key":"S089006040707014X_ref004","doi-asserted-by":"crossref","unstructured":"Ghaboussi, J. , Garrett, J.H. , & Wu, X. (1991).Knowledge-based modeling of material behaviour with neuralnetworks.Journal of the Engineering Mechanics Division, ASCE 117(1),132\u2013153.","DOI":"10.1061\/(ASCE)0733-9399(1991)117:1(132)"},{"key":"S089006040707014X_ref016","doi-asserted-by":"crossref","unstructured":"Lin, L. (1992).Assay validation using the concordance correlationcoefficient.Biometrics 48(2),599\u2013604.","DOI":"10.2307\/2532314"},{"key":"S089006040707014X_ref011","doi-asserted-by":"crossref","unstructured":"Hashash, Y.M.A. , & Whittle, A.J. (2002).Mechanisms of load transfer and arching for braced excavations inclay.Journal of Geotechnical and Geoenvironmental Engineering 128(3),187\u2013197.","DOI":"10.1061\/(ASCE)1090-0241(2002)128:3(187)"},{"key":"S089006040707014X_ref013","doi-asserted-by":"crossref","unstructured":"Hashash, Y.M.A. , Yao, J.I.-C. , and Wotring, D. (2003c).Glyph and hyperstreamline representation of stress and straintensors and material constitutive response.International Journal for Numerical and Analytical Methods inGeomechanics 27(7),603\u2013626.","DOI":"10.1002\/nag.288"},{"key":"S089006040707014X_ref012","doi-asserted-by":"crossref","unstructured":"Hashash, Y.M.A. , Wotring, D. , Yao, J.I.-C. , Lee, J.-S. , & Fu, Q. (2002).Visual framework for development and use of constitutivemodels.International Journal for Numerical and Analytical Methods inGeomechanics 26(15),1493\u20131513.","DOI":"10.1002\/nag.255"},{"key":"S089006040707014X_ref019","doi-asserted-by":"crossref","unstructured":"Reed, R.D. , & Marks, R.J. (1999).Neural Smithing: Supervised Learning in Feedforward ArtificialNeural Networks.Cambridge, MA:MIT Press.","DOI":"10.7551\/mitpress\/4937.001.0001"},{"key":"S089006040707014X_ref021","doi-asserted-by":"crossref","unstructured":"Shin, H.S. , & Pande, G.N. (2000).On self-learning finite element codes based on monitored response ofstructures.Computers and Geotechnics 27(7),161\u2013178.","DOI":"10.1016\/S0266-352X(00)00016-1"}],"container-title":["Artificial Intelligence for Engineering Design, Analysis and Manufacturing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S089006040707014X","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,4,23]],"date-time":"2019-04-23T22:25:37Z","timestamp":1556058337000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S089006040707014X\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,1]]},"references-count":24,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2007,1]]}},"alternative-id":["S089006040707014X"],"URL":"https:\/\/doi.org\/10.1017\/s089006040707014x","relation":{},"ISSN":["0890-0604","1469-1760"],"issn-type":[{"value":"0890-0604","type":"print"},{"value":"1469-1760","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007,1]]}}}