Adaptive artificial neural networks for seismic fragility analysis

In seismic probabilistic risk assessment, fragility curves are used to estimate the probability of failure of a structure or its critical components at given values of seismic intensity measures, e.g. the peak ground acceleration. However, the computation of the fragility curves requires a large number of time-consuming mechanical simulations with the finite element method (FEM). To reduce the computational cost, in this paper a statistical metamodel based on artificial neural networks (ANNs) is constructed to replace the FEM model. An adaptive ANNs learning strategy, aimed at prioritizing the data close to the limit state of the structures, is proposed in order to improve the design of experiments for the fragility analysis. The adaptive learning strategy is developed and tested on a nonlinear Takeda oscillator.

[1]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[2]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[3]  R. P. Kennedy,et al.  Probabilistic seismic safety study of an existing nuclear power plant , 1980 .

[4]  E. Zio,et al.  A study of the bootstrap method for estimating the accuracy of artificial neural networks in predicting nuclear transient processes , 2006, IEEE Transactions on Nuclear Science.

[5]  B. Sudret,et al.  Metamodel-based importance sampling for structural reliability analysis , 2011, 1105.0562.

[6]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[7]  Léon Personnaz,et al.  Construction of confidence intervals for neural networks based on least squares estimation , 2000, Neural Networks.

[8]  E. Borgonovo,et al.  Construction of variance-based metamodels for probabilistic seismic analysis and fragility assessment , 2014 .

[9]  Alexandros A. Taflanidis,et al.  Kriging metamodeling in seismic risk assessment based on stochastic ground motion models , 2015 .

[10]  John B. Shoven,et al.  I , Edinburgh Medical and Surgical Journal.

[11]  Nicolas Gayton,et al.  AK-MCS: An active learning reliability method combining Kriging and Monte Carlo Simulation , 2011 .

[12]  Bruno Sudret,et al.  Adaptive sparse polynomial chaos expansion based on least angle regression , 2011, J. Comput. Phys..

[13]  Nicola Pedroni,et al.  Bootstrapped Artificial Neural Networks for the seismic analysis of structural systems , 2017 .

[14]  K. Campbell,et al.  NGA Ground Motion Model for the Geometric Mean Horizontal Component of PGA, PGV, PGD and 5% Damped Linear Elastic Response Spectra for Periods Ranging from 0.01 to 10 s , 2008 .

[15]  Irfan Kaymaz,et al.  Application Of Kriging Method To Structural Reliability Problems , 2005 .

[16]  Maurice Lemaire,et al.  Assessing small failure probabilities by combined subset simulation and Support Vector Machines , 2011 .

[17]  Enrico Zio,et al.  An improved adaptive kriging-based importance technique for sampling multiple failure regions of low probability , 2014, Reliab. Eng. Syst. Saf..

[18]  Zio Enrico,et al.  Computation of Seismic Fragility Curves Using Artificial Neural Network Metamodels , 2017 .

[19]  T. Takeda,et al.  Reinforced Concrete response to simulated earthquakes , 1970 .

[20]  H Y Kim,et al.  STATISTICAL ANALYSIS OF FRAGILITY CURVES , 2000 .

[21]  Leonardo Dueñas-Osorio,et al.  Surrogate modeling and failure surface visualization for efficient seismic vulnerability assessment of highway bridges , 2013 .

[22]  Enrico Zio,et al.  Application of metamodel-based techniques for the efficient seismic analysis of structural systems , 2015 .

[23]  S. Roberts,et al.  Confidence Intervals and Prediction Intervals for Feed-Forward Neural Networks , 2001 .