Machine learning-based approaches for seismic demand and collapse of ductile reinforced concrete building frames

Abstract Robust seismic vulnerability assessment for a building under expected earthquake ground motions necessitates explicit consideration of all-important sources of uncertainty in structural model idealization. This paper presents a machine learning-based methodology for reliably predicting the seismic response and structural collapse classification of ductile reinforced concrete frame buildings under future earthquake events by accounting for component- and system-level modeling uncertainties. The proposed methodology uses two different types of machine learning methods—regression-based and classification-based methods—to achieve the goal of this study. Machine learning techniques with boosting algorithms (i.e., adaptive boosting and extreme gradient boosting) are the best methods for both response prediction and collapse status classification of modern code-compliant reinforced concrete frame buildings. Finally, the effect of uncertain modeling parameters on the response and collapse identification is examined. The reinforced concrete beam modeling-related parameters (i.e., plastic deformation properties) of ductile, low-to mid-rise frame buildings are significant predictors of seismic response due to capacity design principles.

[1]  N. Null.  Seismic Evaluation and Retrofit of Existing Buildings , 2014 .

[2]  R. Medina,et al.  A practical method for proper modeling of structural damping in inelastic plane structural systems , 2010 .

[3]  Jong-Su Jeon,et al.  Stripe‐based fragility analysis of multispan concrete bridge classes using machine learning techniques , 2018, Earthquake Engineering & Structural Dynamics.

[4]  Reginald DesRoches,et al.  Critical uncertainty parameters influencing seismic performance of bridges using Lasso regression , 2018 .

[5]  Curt B. Haselton,et al.  Assessing seismic collapse safety of modern reinforced concrete moment frame buildings , 2006 .

[6]  Tae-Hyung Lee,et al.  Seismic demand sensitivity of reinforced concrete shear‐wall building using FOSM method , 2005 .

[7]  Dimitrios Vamvatsikos,et al.  Seismic performance of a steel moment-resisting frame subject to strength and ductility uncertainty , 2014 .

[8]  Jack W. Baker,et al.  Incorporating modeling uncertainties in the assessment of seismic collapse risk of buildings , 2009 .

[9]  Seong-Hoon Hwang,et al.  Rapid seismic damage evaluation of bridge portfolios using machine learning techniques , 2019 .

[10]  Reginald DesRoches,et al.  Framework of aftershock fragility assessment–case studies: older California reinforced concrete building frames , 2015 .

[11]  Abbie B. Liel,et al.  Collapse indicators for existing nonductile concrete frame buildings with varying column and frame characteristics , 2017 .

[12]  Anil K. Chopra,et al.  A framework for the evaluation of ground motion selection and modification procedures , 2015 .

[13]  James L. Beck,et al.  Sensitivity of Building Loss Estimates to Major Uncertain Variables , 2002 .

[14]  Dimitrios Vamvatsikos,et al.  Incremental dynamic analysis , 2002 .

[15]  Adolfo B. Matamoros.  Study of Drift Limits for High-Strength Concrete Columns , 1999 .

[16]  Reginald DesRoches,et al.  Analytical Seismic Fragility Curves for Typical Bridges in the Central and Southeastern United States , 2007 .

[17]  S. Tesfamariam,et al.  Impact of Earthquake Types and Aftershocks on Loss Assessment of Non-Code-Conforming Buildings: Case Study with Victoria, British Columbia , 2017 .

[18]  M. D. McKay,et al.  A comparison of three methods for selecting values of input variables in the analysis of output from a computer code , 2000 .

[19]  Dionisio Bernal,et al.  Viscous Damping in Inelastic Structural Response , 1994 .

[20]  Gerard J. O'Reilly,et al.  Quantification of modelling uncertainty in existing Italian RC frames , 2018 .

[21]  Yoav Freund,et al.  Boosting the margin: A new explanation for the effectiveness of voting methods , 1997, ICML.

[22]  Eduardo Miranda,et al.  Inelastic displacement ratios for evaluation of existing structures , 2003 .

[23]  Curt B. Haselton,et al.  Seismic Collapse Safety of Reinforced Concrete Buildings. I: Assessment of Ductile Moment Frames , 2011 .

[24]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[25]  Barry J. Goodno,et al.  Metamodel-based regional vulnerability estimate of irregular steel moment-frame structures subjected to earthquake events , 2012 .

[26]  Lawrence L. Kupper,et al.  Probability, statistics, and decision for civil engineers , 1970 .

[27]  Jong-Su Jeon,et al.  Artificial neural network based multi-dimensional fragility development of skewed concrete bridge classes , 2018 .

[28]  Luis Ibarra,et al.  Variance of collapse capacity of SDOF systems under earthquake excitations , 2011 .

[29]  F. Charney.  Unintended Consequences of Modeling Damping in Structures , 2008 .

[30]  Pradip Sarkar,et al.  Stochastic response of reinforced concrete buildings using high dimensional model representation , 2019, Engineering Structures.

[31]  Jong-Su Jeon,et al.  Classification of failure mode and prediction of shear strength for reinforced concrete beam-column joints using machine learning techniques , 2018 .

[32]  Honglan Huang,et al.  Classification of in-plane failure modes for reinforced concrete frames with infills using machine learning , 2019, Journal of Building Engineering.

[33]  Junwon Seo,et al.  Use of response surface metamodels to generate system level fragilities for existing curved steel bridges , 2013 .

[34]  Wael W. El-Dakhakhni,et al.  Machine learning algorithms for structural performance classifications and predictions: Application to reinforced masonry shear walls , 2019 .

[35]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[36]  Dimitrios G. Lignos,et al.  Nonmodel-based framework for rapid seismic risk and loss assessment of instrumented steel buildings , 2018 .

[37]  Jonathan P. Stewart,et al.  Evaluation of the seismic performance of a code‐conforming reinforced‐concrete frame building—from seismic hazard to collapse safety and economic losses , 2007 .

[38]  Michael H. Scott,et al.  Nonlinear Finite-Element Analysis Software Architecture Using Object Composition , 2010, J. Comput. Civ. Eng..

[39]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[40]  C. Allin Cornell,et al.  Probabilistic seismic demand analysis of nonlinear structures , 1999 .

[41]  P. Paultre,et al.  Behavior of High-Strength Concrete Columns under Cyclic Flexure and Constant Axial Load , 2000 .

[42]  Dimitrios Vamvatsikos,et al.  Seismic Performance Uncertainty Estimation via IDA with Progressive Accelerogram-Wise Latin Hypercube Sampling , 2014 .

[43]  Gregory G. Deierlein,et al.  Seismic Collapse Safety of Reinforced Concrete Buildings. II: Comparative Assessment of Nonductile and Ductile Moment Frames , 2011 .

[44]  Shahram Pezeshk,et al.  On the application of machine learning techniques to derive seismic fragility curves , 2019, Computers & Structures.

[45]  Deierlein Gg,et al.  Quantifying the impacts of modeling uncertainties on the seismic drift demands and collapse risk of buildings with implications on seismic design checks , 2016 .

[46]  Henry V. Burton,et al.  Classifying earthquake damage to buildings using machine learning , 2020 .

[47]  John F. Hall,et al.  Problems encountered from the use (or misuse) of Rayleigh damping , 2006 .

[48]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[49]  Luis Ibarra,et al.  Hysteretic models that incorporate strength and stiffness deterioration , 2005 .

[50]  Dimitrios G. Lignos,et al.  An efficient method for estimating the collapse risk of structures in seismic regions , 2013 .

[51]  N. Null.  Minimum Design Loads for Buildings and Other Structures , 2003 .