Epistemic uncertainty assessment using Incremental Dynamic Analysis and Neural Networks

Incremental dynamic analysis (IDA) is a powerful method for the seismic performance assessment of structures. IDA is also very efficient for handling uncertainty due to the mechanical properties of the structure. In the latter case, IDA should be performed within a Monte Carlo framework requiring the execution of a vast number of nonlinear response history analyses. The increased computing effort renders the calculation of performance statistics time-consuming and hence the method is not always practical. We propose a scheme based on artificial neural networks (NN) in order to reduce the computational effort. Within a Monte Carlo approach, trained NN can rapidly generate a large sample of IDA curves and therefore allow us to easily calculate useful response statistics and fragility curves. The implementation of the proposed approach is quick, straightforward and quite accurate.

[1]  Fatemeh Jalayer,et al.  The probabilistic basis for the 2000 SAC/FEMA steel moment frame guidelines , 2002 .

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

[3]  Michalis Fragiadakis,et al.  Fragility Assessment of Steel Frames Using Neural Networks , 2007 .

[4]  Manolis Papadrakakis,et al.  Accelerated subset simulation with neural networks for reliability analysis , 2012 .

[5]  Dimitrios Vamvatsikos,et al.  Fast performance uncertainty estimation via pushover and approximate IDA , 2009 .

[6]  R. Iman,et al.  A distribution-free approach to inducing rank correlation among input variables , 1982 .

[7]  Bruce R. Ellingwood,et al.  Seismic fragilities for non-ductile reinforced concrete frames – Role of aleatoric and epistemic uncertainties , 2010 .

[8]  Matjaž Dolšek,et al.  The impact of modelling uncertainties on the seismic performance assessment of reinforced concrete frame buildings , 2013 .

[9]  Kiril Velkov,et al.  Aleatoric and epistemic uncertainties in sampling based nuclear data uncertainty and sensitivity analyses , 2012 .

[10]  Dimitrios Vamvatsikos,et al.  Applied Incremental Dynamic Analysis , 2004 .

[11]  Dimitrios Vamvatsikos,et al.  Incremental dynamic analysis for estimating seismic performance sensitivity and uncertainty , 2010 .

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

[13]  D. Mackay,et al.  A Practical Bayesian Framework for Backprop Networks , 1991 .

[14]  C. Allin Cornell,et al.  Probabilistic Basis for 2000 SAC Federal Emergency Management Agency Steel Moment Frame Guidelines , 2002 .

[15]  Paolo Franchin,et al.  Seismic Fragility Analysis of Structural Systems , 2006 .

[16]  Dimitris G. Giovanis,et al.  Spectral representation-based neural network assisted stochastic structural mechanics , 2015 .

[17]  Matjaz Dolsek,et al.  Incremental dynamic analysis with consideration of modeling uncertainties , 2009 .

[18]  João Cardoso,et al.  Review and application of Artificial Neural Networks models in reliability analysis of steel structures , 2015 .

[19]  Fatemeh Jalayer,et al.  Structural modeling uncertainties and their influence on seismic assessment of existing RC structures , 2010 .

[20]  Martin T. Hagan,et al.  Neural network design , 1995 .

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

[22]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.