Multivariate function approximations using the D-MORPH algorithm

Abstract Most real-life problems are computationally burdensome and time consuming, so we have to rely on approximate functions to represent the original functions with a specific level of accuracy. In this study, we propose a new method for approximating multivariate functions based on the diffeomorphic modulation under observable response preserving homotopy (D-MORPH) algorithm. D-MORPH is a regression technique that was originally developed for solving differential equation. Two distinct approaches using the proposed method are described, where one operates over the whole domain and the other operates by sub-dividing the domain into a finite number of sub-domains. This technique is based on a cost/objective function, which depends on a weight matrix. We also introduce a new weight matrix, which dramatically reduces the prediction error and improves the prediction accuracy. The potential of the proposed approach for approximating multivariate functions is illustrated using eight mathematical functions and two practical problems. Furthermore, a comparative assessment with other methods is provided to demonstrate the elegance of the proposed method.

[1]  Ilya M. Sobol,et al.  Theorems and examples on high dimensional model representation , 2003, Reliab. Eng. Syst. Saf..

[2]  Mohsen Khatibinia,et al.  Reliability-based design optimization of reinforced concrete structures including soil–structure interaction using a discrete gravitational search algorithm and a proposed metamodel , 2013 .

[3]  Ali Ajdari,et al.  An Adaptive Exploration-Exploitation Algorithm for Constructing Metamodels in Random Simulation Using a Novel Sequential Experimental Design , 2014, Commun. Stat. Simul. Comput..

[4]  P. Ramachandran,et al.  Multidimensional interpolation using osculatory radial basis functions , 1998 .

[5]  YUEYuncan,et al.  Modified Recursive Least Squares Algorithm with Variable Parameters and Resetting for Time—Varying System , 2002 .

[6]  Kai Meng Mok,et al.  Improvement of the multilayer perceptron for air quality modelling through an adaptive learning scheme , 2013, Comput. Geosci..

[7]  Arta A. Jamshidi,et al.  Skew-Radial Basis Function Expansions for Empirical Modeling , 2009, SIAM J. Sci. Comput..

[8]  Csaba Szepesvari,et al.  Regularized least-squares regression: Learning from a β-mixing sequence , 2012 .

[9]  Herschel Rabitz,et al.  Sixth International Conference on Sensitivity Analysis of Model Output Global Sensitivity Analysis for Systems with Independent and / or Correlated Inputs , 2013 .

[10]  Sondipon Adhikari,et al.  A spectral approach for fuzzy uncertainty propagation in finite element analysis , 2014, Fuzzy Sets Syst..

[11]  Bruno Sudret,et al.  Analytical derivation of the outcrossing rate in time-variant reliability problems , 2008 .

[12]  Sondipon Adhikari,et al.  Fuzzy parametric uncertainty analysis of linear dynamical systems: A surrogate modeling approach , 2012 .

[13]  Michel Salaün,et al.  A new adaptive response surface method for reliability analysis , 2013 .

[14]  Huajiang Ouyang,et al.  Crack Identification of Cantilever Plates Based on a Kriging Surrogate Model. , 2013, Journal of vibration and acoustics.

[15]  A. Meher Prasad,et al.  High dimensional model representation for piece‐wise continuous function approximation , 2007 .

[16]  Fionn Murtagh,et al.  Multilayer perceptrons for classification and regression , 1991, Neurocomputing.

[17]  H. Rabitz,et al.  D-MORPH regression: application to modeling with unknown parameters more than observation data , 2010 .

[18]  Giovanni Belingardi,et al.  Uncertainty in fatigue loading: Consequences on statistical evaluation of reliability in service , 2013 .

[19]  Juan Galvis,et al.  Approximating Infinity-Dimensional Stochastic Darcy's Equations without Uniform Ellipticity , 2009, SIAM J. Numer. Anal..

[20]  Sondipon Adhikari,et al.  Gaussian process emulators for the stochastic finite element method , 2011 .

[21]  Seymour M.J. Spence,et al.  Large scale reliability-based design optimization of wind excited tall buildings , 2012 .

[22]  John W. Tukey,et al.  A Projection Pursuit Algorithm for Exploratory Data Analysis , 1974, IEEE Transactions on Computers.

[23]  J. Friedman,et al.  Projection Pursuit Regression , 1981 .

[24]  Stefano De Marchi,et al.  A new stable basis for radial basis function interpolation , 2013, J. Comput. Appl. Math..

[25]  M. Valdebenito,et al.  Compromise design of stochastic dynamical systems: A reliability-based approach , 2012 .

[26]  Eun-Kyung Lee,et al.  Projection Pursuit for Exploratory Supervised Classification , 2005 .

[27]  A. M. Prasad,et al.  Cut-HDMR-based fully equivalent operational model for analysis of unreinforced masonry structures , 2012 .

[28]  Subrata Chakraborty,et al.  Reliability based optimum design of Tuned Mass Damper in seismic vibration control of structures with bounded uncertain parameters , 2011 .

[29]  A. Meher Prasad,et al.  High‐dimensional model representation for structural reliability analysis , 2009 .

[30]  A comparison of three metamodel-based methods for global sensitivity analysis: GP modelling, HDMR and LAR-gPC , 2010 .

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

[32]  T. Simpson,et al.  Comparative studies of metamodeling techniques under multiple modeling criteria , 2000 .

[33]  Sondipon Adhikari,et al.  Stochastic structural dynamic analysis using Bayesian emulators , 2013 .

[34]  Bert Jüttler,et al.  Least-Squares Fitting of Algebraic Spline Surfaces , 2002, Adv. Comput. Math..

[35]  Sondipon Adhikari,et al.  High dimensional model representation method for fuzzy structural dynamics , 2011 .

[36]  George E. Karniadakis,et al.  Adaptive Generalized Polynomial Chaos for Nonlinear Random Oscillators , 2005, SIAM J. Sci. Comput..

[37]  Lorena A. Barba,et al.  Fast radial basis function interpolation with Gaussians by localization and iteration , 2009, J. Comput. Phys..

[38]  T. Simpson,et al.  Comparative studies of metamodelling techniques under multiple modelling criteria , 2001 .

[39]  I. Sobola,et al.  Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates , 2001 .

[40]  B. Sudret,et al.  Reliability-based design optimization using kriging surrogates and subset simulation , 2011, 1104.3667.

[41]  A. S. Balu,et al.  Confidence Bounds on Design Variables Using High-Dimensional Model Representation–Based Inverse Reliability Analysis , 2013 .

[42]  Henri P. Gavin,et al.  High-order limit state functions in the response surface method for structural reliability analysis , 2008 .

[43]  Eugenio Oñate,et al.  An extended class of multilayer perceptron , 2008, Neurocomputing.

[44]  Xiang Ma,et al.  An adaptive high-dimensional stochastic model representation technique for the solution of stochastic partial differential equations , 2010, J. Comput. Phys..

[45]  Stefan Jakubek,et al.  Optimal experiment design based on local model networks and multilayer perceptron networks , 2013, Eng. Appl. Artif. Intell..

[46]  Herschel Rabitz,et al.  Estimation of molecular properties by high-dimensional model representation. , 2006, The journal of physical chemistry. A.

[47]  A. M. Prasad,et al.  Development of fragility curves using high‐dimensional model representation , 2013 .

[48]  Bruno Sudret,et al.  Stochastic evaluation of the damage length in RC beams submitted to corrosion of reinforcing steel , 2007 .

[49]  S. Adhikari,et al.  A reduced polynomial chaos expansion method for the stochastic finite element analysis , 2012 .

[50]  Guanyu Zhang,et al.  Global optimization of reliability design for large ball mill gear transmission based on the Kriging model and genetic algorithm , 2013 .

[51]  Herschel Rabitz,et al.  Regularized random-sampling high dimensional model representation (RS-HDMR) , 2008 .

[52]  Evan F. Bollig,et al.  Solution to PDEs using radial basis function finite-differences (RBF-FD) on multiple GPUs , 2012, J. Comput. Phys..

[53]  H. Rabitz,et al.  D-MORPH regression for modeling with fewer unknown parameters than observation data , 2012, Journal of Mathematical Chemistry.

[54]  Qiqi Wang,et al.  Forward and adjoint sensitivity computation of chaotic dynamical systems , 2012, J. Comput. Phys..

[55]  Byeongdo Kim,et al.  Comparison study on the accuracy of metamodeling technique for non-convex functions , 2009 .

[56]  Herschel Rabitz,et al.  General formulation of HDMR component functions with independent and correlated variables , 2011, Journal of Mathematical Chemistry.