Data-driven uncertainty quantification of structural systems via B-spline expansion

Abstract A data-driven uncertainty quantification scheme relying on B-spline functions is investigated in this study. Instead of predefining basis functions according to the statistics of the uncertain input, as in conventional polynomial chaos expansion (PCE)-based implementations, the method introduced herein takes advantage of the increased flexibility of B-splines materializing a basis function parametrization, which is adaptable to a given input–output data set. Parameter estimation is effectively dealt through a Separable Non-linear Least Squares (SNLS) procedure that allows for simultaneous estimation of both the B-splines’ free knots and the corresponding coefficients of projection. The induced constrained non-quadratic optimization problem is treated through the implementation of a hybrid optimization algorithm that interrelates the advantages of evolutionary and deterministic schemes, exhibiting accelerated convergence and robustness in the search for global optimum. The efficiency of the method is examined through both numerical and experimental case studies, while comparisons with the standard PCE, which relies on the Wiener–Askey scheme, as well as alternative data-driven methods, such as the arbitrary PC, indicate superior performance.

[1]  Hans-Paul Schwefel,et al.  Evolution strategies – A comprehensive introduction , 2002, Natural Computing.

[2]  Data-driven polynomial chaos basis estimation , 2015 .

[3]  Stephen J. Wright,et al.  Numerical Optimization , 2018, Fundamental Statistical Inference.

[4]  Nicolas Monmarché,et al.  On how Pachycondyla apicalis ants suggest a new search algorithm , 2000, Future Gener. Comput. Syst..

[5]  Jorge Nocedal,et al.  An interior algorithm for nonlinear optimization that combines line search and trust region steps , 2006, Math. Program..

[6]  Axel Ruhe,et al.  Algorithms for separable nonlinear least squares problems , 1980 .

[7]  Bruno Sudret,et al.  Surrogate modeling for stochastic dynamical systems by combining nonlinear autoregressive with exogenous input models and polynomial chaos expansions , 2016 .

[8]  Bruno Sudret,et al.  Efficient computation of global sensitivity indices using sparse polynomial chaos expansions , 2010, Reliab. Eng. Syst. Saf..

[9]  B. Sudret,et al.  Surrogate modelling for stochastic dynamical systems by combining NARX models and polynomial chaos expansions , 2016, 1604.07627.

[10]  Nicolas Molinari,et al.  Bounded optimal knots for regression splines , 2004, Comput. Stat. Data Anal..

[11]  Thomas C. M. Lee,et al.  On algorithms for ordinary least squares regression spline fitting: A comparative study , 2002 .

[12]  Gene H. Golub,et al.  The differentiation of pseudo-inverses and non-linear least squares problems whose variables separate , 1972, Milestones in Matrix Computation.

[13]  B. Sudret,et al.  An adaptive algorithm to build up sparse polynomial chaos expansions for stochastic finite element analysis , 2010 .

[14]  Hubert Schwetlick,et al.  Least squares approximation by splines with free knots , 1995 .

[15]  George E. Karniadakis,et al.  Beyond Wiener–Askey Expansions: Handling Arbitrary PDFs , 2006, J. Sci. Comput..

[16]  Long Quan,et al.  Diversity enhanced and local search accelerated gravitational search algorithm for data fitting with B-splines , 2013, Engineering with Computers.

[17]  G. I. Schuëller,et al.  Benchmark Study on Reliability Estimation in Higher Dimensions of Structural Systems – An Overview , 2007 .

[18]  V. K. Jayaraman,et al.  Ant colony framework for optimal design and scheduling of batch plants , 2000 .

[19]  Mary J. Lindstrom,et al.  Penalized Estimation of Free-Knot Splines , 1999 .

[20]  Giovanni Righini,et al.  Heuristics from Nature for Hard Combinatorial Optimization Problems , 1996 .

[21]  Andrés Iglesias,et al.  Efficient particle swarm optimization approach for data fitting with free knot B-splines , 2011, Comput. Aided Des..

[22]  K. A. Cliffe,et al.  Multilevel Monte Carlo methods and applications to elliptic PDEs with random coefficients , 2011, Comput. Vis. Sci..

[23]  Jonathan E. Cooper,et al.  Modeling composite wing aeroelastic behavior with uncertain damage severity and material properties , 2012 .

[24]  Eleni Chatzi,et al.  Polynomial chaos expansion models for the monitoring of structures under operational variability , 2016 .

[25]  Vasilis K. Dertimanis,et al.  Hybrid evolutionary identification of output-errorstate-space models , 2014 .

[26]  Dongbin Xiu,et al.  The Wiener-Askey Polynomial Chaos for Stochastic Differential Equations , 2002, SIAM J. Sci. Comput..

[27]  Bruno Sudret,et al.  Sparse polynomial chaos expansions and adaptive stochastic finite elements using a regression approach , 2008 .

[28]  Philip Smith,et al.  Knot selection for least-squares and penalized splines , 2013 .

[29]  Vasilis K. Dertimanis,et al.  Design of a Novel Hybrid Optimization Algorithm , 2009, ICINCO-ICSO.

[30]  Franz S. Hover,et al.  Application of polynomial chaos in stability and control , 2006, Autom..

[31]  G. Golub,et al.  Separable nonlinear least squares: the variable projection method and its applications , 2003 .

[32]  Juan M. Caicedo,et al.  Practical guidelines for the natural excitation technique (NExT) and the eigensystem realization algorithm (ERA) for modal identification using ambient vibration , 2011 .

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

[34]  Eleni Chatzi,et al.  Metamodeling of uncertain structural systems based on wavelet transform decomposition , 2013, SOCO 2013.

[35]  Carl de Boor,et al.  A Practical Guide to Splines , 1978, Applied Mathematical Sciences.

[36]  D. Xiu,et al.  Stochastic Modeling of Flow-Structure Interactions Using Generalized Polynomial Chaos , 2002 .

[37]  Vasilis K. Dertimanis.  Output–error state–space identification of vibrating structures using evolution strategies: a benchmark study , 2014 .

[38]  Soroosh Sorooshian,et al.  Evolution of ensemble data assimilation for uncertainty quantification using the particle filter‐Markov chain Monte Carlo method , 2012 .

[39]  R. Ghanem,et al.  Uncertainty propagation using Wiener-Haar expansions , 2004 .

[40]  Sergey Oladyshkin,et al.  Data-driven uncertainty quantification using the arbitrary polynomial chaos expansion , 2012, Reliab. Eng. Syst. Saf..

[41]  Frances Y. Kuo,et al.  Multi-level quasi-Monte Carlo finite element methods for a class of elliptic partial differential equations with random coefficients , 2012, 1208.6349.

[42]  Linda H. Zhao,et al.  Free‐knot polynomial splines with confidence intervals , 2003 .

[43]  Stochastic Finite Element Analysis of Uncertain Nonlinear Trusses under Random Loadings , 1992 .

[44]  Jennifer Pittman,et al.  Adaptive Splines and Genetic Algorithms , 2000 .

[45]  Hubert Schwetlick,et al.  Constrained approximation by splines with free knots , 1997 .

[46]  Marco Dorigo,et al.  Ant algorithms and stigmergy , 2000, Future Gener. Comput. Syst..