{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T01:20:40Z","timestamp":1778808040589,"version":"3.51.4"},"reference-count":36,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2020,10,23]],"date-time":"2020-10-23T00:00:00Z","timestamp":1603411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Hybrid simulation (HS) is an advanced simulation method that couples experimental testing and analytical modeling to better understand structural systems and individual components\u2019 behavior under extreme events such as earthquakes. Conducting HS and real-time HS (RTHS) can be challenging with complex analytical substructures due to the nature of direct integration algorithms when the finite element method is employed. Thus, alternative methods such as machine learning (ML) models could help tackle these difficulties. This study aims to investigate the quality of the RTHS tests when a deep learning algorithm is used as a metamodel to represent the dynamic behavior of a nonlinear analytical substructure. The compact HS laboratory at the University of Nevada, Reno was utilized to conduct exclusive RTHS tests. Simulating a braced frame structure, the RTHS tests combined, for the first time, linear brace model specimens (physical substructure) along with nonlinear ML models for the frame (analytical substructure). Deep long short-term memory (Deep-LSTM) networks were employed and trained to develop the metamodels of the analytical substructure using the Python environment. The training dataset was obtained from pure analytical finite element simulations for the complete structure under earthquake excitation. The RTHS evaluations were first conducted for virtual RTHS tests, where substructuring was sought between the LSTM metamodel and virtual experimental substructure. To validate the proposed RTHS testing methodology and full system, several actual RTHS tests were conducted. The results from ML-based RTHS were evaluated for different ML models and compared against results from conventional RTHS with finite element models. The paper demonstrates the potential of conducting successful experimental RTHS using Deep-LSTM models, which could open the door for unparalleled new opportunities in structural systems design and assessment.<\/jats:p>","DOI":"10.3390\/make2040026","type":"journal-article","created":{"date-parts":[[2020,10,23]],"date-time":"2020-10-23T08:59:28Z","timestamp":1603443568000},"page":"469-489","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Real-Time Hybrid Simulation with Deep Learning Computational Substructures: System Validation Using Linear Specimens"],"prefix":"10.3390","volume":"2","author":[{"given":"Elif Ecem","family":"Bas","sequence":"first","affiliation":[{"name":"Department of Civil and Environmental Engineering, University of Nevada, 1664 N. Virginia Street, Reno, NV 89557, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1006-7685","authenticated-orcid":false,"given":"Mohamed A.","family":"Moustafa","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, University of Nevada, 1664 N. Virginia Street, Reno, NV 89557, USA"}]}],"member":"1968","published-online":{"date-parts":[[2020,10,23]]},"reference":[{"key":"ref_1","first-page":"1","article-title":"Non-Linear Earthquake Response Analaysis of Structures by a Computer-Actuator On-Line System","volume":"8","author":"Takanashi","year":"1975","journal-title":"Bull. Earthq. Resist. Struct. Res. Cent."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1002\/nme.4720","article-title":"A family of noniterative integration methods with desired numerical dissipation","volume":"100","author":"Chang","year":"2014","journal-title":"Int. J. Numer. Methods Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1002\/eqe.838","article-title":"Real-time hybrid testing using the unconditionally stable explicit CR integration algorithm","volume":"38","author":"Chen","year":"2009","journal-title":"Earthq. Eng. Struct. Dyn."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1108\/02644400510619530","article-title":"Predictor-corrector procedures for pseudo-dynamic tests","volume":"22","author":"Bonelli","year":"2005","journal-title":"Eng. Comput."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1002\/eqe.2484","article-title":"Implementation and application of the unconditionally stable explicit parametrically dissipative KR-alpha method for real-time hybrid simulation","volume":"44","author":"Kolay","year":"2015","journal-title":"Earthq. Eng. Struct. Dyn."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1007\/s11803-017-0411-z","article-title":"Evaluation of integration methods for hybrid simulation of complex structural systems through collapse","volume":"16","author":"Hashemi","year":"2017","journal-title":"Earthq. Eng. Eng. Vib."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Bas, E.E., and Moustafa, M.A. (2020). Performance and Limitations of Real-Time Hybrid Simulation with Nonlinear Computational Substructures. Exp. Tech.","DOI":"10.1007\/s40799-020-00385-6"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1697","DOI":"10.1002\/eqe.2294","article-title":"Adaptive time series compansator for delay compensation of servo-hydraulic actuator systems for real-time hybrid simulation","volume":"42","author":"Chae","year":"2013","journal-title":"Earthq. Eng. Struct. Dyn."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1773","DOI":"10.1002\/eqe.301","article-title":"Considerations for the development of real-time dynamic testing using servo-hydraulic actuation","volume":"32","author":"Zhao","year":"2003","journal-title":"Earthq. Eng. Struct. Dyn."},{"key":"ref_10","unstructured":"Carrion, J.E., and Spencer, B.F. (2007). Model-based Strategies for Real-time Hybrid Testing. NSEL Report Series Report No. NSEL-006, University of Illinois at Urbana-Champaign."},{"key":"ref_11","first-page":"3807","article-title":"An adaptive polynomial based forward prediction algorithm for multi-actuator Real-time dynamic substructuring","volume":"461","author":"Wallace","year":"2005","journal-title":"Proc. R. Soc. A Math. Phys. Eng. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Abbiati, G., Lanese, I., Cazzador, E., Bursi, O.S., and Pavase, A. (2019). A Computational framework for fast-time hybrid simulation based on partitioned time integration and state space modeling. Strc. Cont. and Health Mon., 1\u201328.","DOI":"10.1002\/stc.2419"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Miraglia, G., Petrovic, M., Abbiati, G., Mojsilovic, N., and Stojadinovic, B. (2020). A model-order reduction framework for hybrid simulation based on component-mode synthesis. Earthq. Eng. Struct. Dyn., 737\u2013753.","DOI":"10.1002\/eqe.3262"},{"key":"ref_14","first-page":"1271","article-title":"Real-time dynamic substructuring in a coupled oscillator\u2013pendulum system","volume":"462","author":"Kyrychko","year":"2006","journal-title":"Proc. R. Soc. A Math. Phys. Eng. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Bas, E.E., Moustafa, M.A., Feil-Seifer, D., and Blankenburg, J. (2020). Using a Machine Learning Approach for Computational Substructure in Real-Time Hybrid Simulation. Conf. Proc. Soc. Exp. Mech. Ser., 4.","DOI":"10.1007\/978-3-030-47630-4_16"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Xie, Y., Sichani, M.E., Padgett, J.E., and DesRoches, R. (2020). The promise of implementing machine learning in earthquake engineering: A state-of-the-art review. Earth. Spec., 1\u201333.","DOI":"10.1177\/8755293020919419"},{"key":"ref_17","first-page":"997","article-title":"Identification of Nonlinear Dynamic Systems Using Neural Networks","volume":"2","author":"Tian","year":"2003","journal-title":"Proc. Int. Symp. Test Meas."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1111\/0885-9507.00211","article-title":"Nonlinear identification of dynamic systems using neural networks","volume":"16","author":"Huang","year":"2001","journal-title":"Comp. Aided Civil Infr. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1007\/s11012-014-0085-9","article-title":"Damage detection on a three-storey steel frame using artificial neural networks and genetic algorithms","volume":"50","author":"Betti","year":"2015","journal-title":"Meccanica."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2176","DOI":"10.1016\/j.compstruc.2011.08.019","article-title":"Prediction of principal ground-motion parameters using a hybrid method coupling artificial neural networks and simulated annealing","volume":"89","author":"Alavi","year":"2011","journal-title":"Comput. Struct."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.asoc.2019.03.029","article-title":"Predicting the principal strong ground motion parameters: A deep learning approach","volume":"80","author":"Derakhshani","year":"2019","journal-title":"Appl. Soft Comput. J."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"915","DOI":"10.12989\/eas.2015.8.4.915","article-title":"Metamodeling of nonlinear structural systems with parametric uncertainty subject to stochastic dynamic excitation","volume":"8","author":"Spiridonakos","year":"2015","journal-title":"Earthq. Struct."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, R., Liu, Y., and Sun, H. (2020). Physics-guided convolutional neural network (PhyCNN) for data-driven seismic response modeling. Eng. Struct., 215.","DOI":"10.1016\/j.engstruct.2020.110704"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.compstruc.2019.05.006","article-title":"Deep long short-term memory networks for nonlinear structural seismic response prediction","volume":"220","author":"Zhang","year":"2019","journal-title":"Comput. Struct."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1007\/s00466-019-01731-1","article-title":"Model-free data-driven methods in mechanics: Material data identification and solvers","volume":"64","author":"Stainier","year":"2019","journal-title":"Comput. Mech."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Bas, E.E., Aslangil, D., and Moustafa, M.A. (2020). Predicting Nonlinear Seismic Response of Structural Braces Using Machine Learning. arXiv.","DOI":"10.1115\/IMECE2020-24014"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.advengsoft.2011.05.033","article-title":"Neural network based prediction schemes of the non-linear seismic response of 3D buildings","volume":"44","author":"Lagaros","year":"2012","journal-title":"Adv. Eng. Softw."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Mucha, W. (2019). Application of artificial neural networks in hybrid simulation. Appl. Sci., 9.","DOI":"10.3390\/app9214495"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Bas, E.E., and Moustafa, M.A. (2020). Communication Development and Verification for Python-Based Machine Learning Models for Real-Time Hybrid Simulation. Front. Built Environ. Earthq. Eng.","DOI":"10.3389\/fbuil.2020.574965"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Bas, E.E., Moustafa, M.A., and Pekcan, G. (2020). Compact Hybrid Simulation System: Validation and Applications for Braced Frames Seismic Testing. J. Earthq. Eng., 1\u201330.","DOI":"10.1080\/13632469.2020.1733138"},{"key":"ref_31","unstructured":"McKenna, F., Fenves, G.L., and Scott, M.H. (2000). Open System for Earthquake Engineering Simulation, Pacific Earthquake Engineering Research (PEER) Center, University of California."},{"key":"ref_32","unstructured":"Schellenberg, A., Kim, H.K., Fenves, G.L., and Mahin, S.A. (2009). OpenFresco Framework for Hybrid Simulation: Simulation Finite Element Adapter Experimental Control Example, University of California."},{"key":"ref_33","unstructured":"Filippou, F.C., Popov, E.P., and Bertero, V.V. (1983). Effects of Bond Deteroriation on Hysteretic Behavior of Reinforced Concrete Joints, University of California."},{"key":"ref_34","unstructured":"G\u00e9ron, A. (2017). Hands-on Machine Learning with Scikit-Learn and TensorFlow, O\u2019Reilly."},{"key":"ref_35","unstructured":"Abadi, M. (2016). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. arXiv."},{"key":"ref_36","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume":"1412","author":"Kingma","year":"2015","journal-title":"3rd Int. Conf. Learn. Represent. ICLR"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/2\/4\/26\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:26:54Z","timestamp":1760178414000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/2\/4\/26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,23]]},"references-count":36,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["make2040026"],"URL":"https:\/\/doi.org\/10.3390\/make2040026","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,23]]}}}