{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T12:39:30Z","timestamp":1770813570278,"version":"3.50.1"},"reference-count":13,"publisher":"ASME International","issue":"1","license":[{"start":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T00:00:00Z","timestamp":1664236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The nonparametric probabilistic method (NPM) for modeling and quantifying model-form uncertainties is a physics-based, computationally tractable, machine learning method for performing uncertainty quantification and model updating. It extracts from data information not captured by a deterministic, high-dimensional model (HDM) of dimension N and infuses it into a counterpart stochastic, hyperreduced, projection-based reduced-order model (SHPROM) of dimension n \u226a N. Here, the robustness and performance of NPM are improved using a two-pronged approach. First, the sensitivities of its stochastic loss function with respect to the hyperparameters are computed analytically, by tracking the complex web of operations underlying the construction of that function. Next, the theoretical number of hyperparameters is reduced from O(n2) to O(n), by developing a network of autoencoders that provides a nonlinear approximation of the dependence of the SHPROM on the hyperparameters. The robustness and performance of the enhanced NPM are demonstrated using two nonlinear, realistic, structural dynamics applications.<\/jats:p>","DOI":"10.1115\/1.4055546","type":"journal-article","created":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T08:01:14Z","timestamp":1662624074000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":13,"title":["Acceleration of a Physics-Based Machine Learning Approach for Modeling and Quantifying Model-Form Uncertainties and Performing Model Updating"],"prefix":"10.1115","volume":"23","author":[{"given":"Marie-Jo","family":"Azzi","sequence":"first","affiliation":[{"name":"Stanford University Department of Mechanical Engineering, , 440 Escondido Mall, Stanford, CA 94305"}]},{"given":"Chady","family":"Ghnatios","sequence":"additional","affiliation":[{"name":"Notre Dame University-Louaize Department of Mechanical Engineering, , P. O. Box 72, Zouk Mosbeh , Lebanon"}]},{"given":"Philip","family":"Avery","sequence":"additional","affiliation":[{"name":"Stanford University Department of Aeronautics and Astronautics, , 496 Lomita Mall, Stanford, CA 94305"}]},{"given":"Charbel","family":"Farhat","sequence":"additional","affiliation":[{"name":"Institute for Computational and Mathematical Engineering, Stanford University Department of Aeronautics and Astronautics; Department of Mechanical Engineering, , 496 Lomita Mall, Stanford, CA 94305"}]}],"member":"33","published-online":{"date-parts":[[2022,9,27]]},"reference":[{"issue":"6","key":"2022092713191895200_CIT0001","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1002\/nme.5312","article-title":"A Nonparametric Probabilistic Approach for Quantifying Uncertainties in Low-Dimensional and High-Dimensional Nonlinear Models","volume":"109","author":"Soize","year":"2017","journal-title":"Int. J. Numer. Methods Eng."},{"issue":"3","key":"2022092713191895200_CIT0002","doi-asserted-by":"publisher","first-page":"1198","DOI":"10.2514\/1.J056314","article-title":"Modeling and Quantification of Model-Form Uncertainties in Eigenvalue Computations Using a Stochastic Reduced Model","volume":"56","author":"Farhat","year":"2018","journal-title":"AIAA J."},{"issue":"11","key":"2022092713191895200_CIT0003","doi-asserted-by":"publisher","first-page":"4978","DOI":"10.2514\/1.J057797","article-title":"Feasible Probabilistic Learning Method for Model-Form Uncertainty Quantification in Vibration Analysis","volume":"57","author":"Farhat","year":"2019","journal-title":"AIAA J."},{"issue":"7","key":"2022092713191895200_CIT0004","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1002\/nme.5980","article-title":"Probabilistic Learning for Modeling and Quantifying Model-Form Uncertainties in Nonlinear Computational Mechanics","volume":"117","author":"Soize","year":"2019","journal-title":"Int. J. Numer. Methods Eng."},{"issue":"Part A","key":"2022092713191895200_CIT0005","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.cirpj.2020.02.002","article-title":"Characterising the Digital Twin: A Systematic Literature Review","volume":"29","author":"Jones","year":"2020","journal-title":"CIRP J. Manuf. Sci. Technol."},{"issue":"4","key":"2022092713191895200_CIT0006","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1137\/130932715","article-title":"A Survey of Projection-Based Model Reduction Methods for Parametric Dynamical Systems","volume":"57","author":"Benner","year":"2015","journal-title":"SIAM Rev."},{"key":"2022092713191895200_CIT0007","first-page":"181","article-title":"Computational Bottlenecks for Proms: Pre-Computation and Hyperreduction","volume":"2","author":"Farhat","year":"2021","journal-title":"Model Order Reduct."},{"issue":"9","key":"2022092713191895200_CIT0008","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1002\/nme.4668","article-title":"Dimensional Reduction of Nonlinear Finite Element Dynamic Models With Finite Rotations and Energy-Based Mesh Sampling and Weighting for Computational Efficiency","volume":"98","author":"Farhat","year":"2014","journal-title":"Int. J. Numer. Methods Eng."},{"issue":"5","key":"2022092713191895200_CIT0009","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1002\/nme.4820","article-title":"Structure-Preserving, Stability, and Accuracy Properties of the Energy-Conserving Sampling and Weighting Method for the Hyper Reduction of Nonlinear Finite Element Dynamic Models","volume":"102","author":"Farhat","year":"2015","journal-title":"Int. J. Numer. Methods Eng."},{"key":"2022092713191895200_CIT0010","first-page":"1671","article-title":"Adjoint-Based Derivative Evaluation Methods for Flexible Multibody Systems With Rotorcraft Applications","author":"Boopathy","year":"2017"},{"issue":"3","key":"2022092713191895200_CIT0011","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1061\/JMCEA3.0000098","article-title":"A Method of Computation for Structural Dynamics","volume":"85","author":"Newmark","year":"1959","journal-title":"J. Eng. Mech. Div."},{"key":"2022092713191895200_CIT0012","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.neucom.2015.08.104","article-title":"Auto-Encoder Based Dimensionality Reduction","volume":"184","author":"Wang","year":"2016","journal-title":"Neurocomputing"},{"key":"2022092713191895200_CIT0013","first-page":"4","article-title":"Anomaly Detection Using Autoencoders With Nonlinear Dimensionality Reduction","author":"Sakurada","year":"2014"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/23\/1\/011009\/6920723\/jcise_23_1_011009.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/23\/1\/011009\/6920723\/jcise_23_1_011009.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T13:19:49Z","timestamp":1664284789000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/23\/1\/011009\/1146065\/Acceleration-of-a-Physics-Based-Machine-Learning"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,27]]},"references-count":13,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,2,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4055546","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,27]]},"article-number":"011009"}}