Creating Sparse Rational Approximations for Linear Fractional Representations Using Surrogate Modeling

Abstract The objective of this paper is to stress that the size of a Linear Fractional Representation (LFR) significantly depends on the way tabulated or irrational data are approximated during the modeling process. It is notably shown that rational approximants can result in much smaller LFR than polynomial ones. In this context, a new method is introduced to generate sparse rational models, which avoid data overfitting and lead to simple yet accurate LFR. This method builds a parsimonious model based on neural networks, and then translates the result into a fractional form. A stepwise selection algorithm is used, combining the benefits of forward orthogonal least squares to estimate the regression parameters with a new powerful global optimization to determine the best location of the regressors. The proposed method is evaluated on an aeronautical example and successfully compared to more classical approaches.

[1]  Andries Petrus Engelbrecht,et al.  Measuring exploration/exploitation in particle swarms using swarm diversity , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[2]  G. Hardier.  Recurrent RBF networks for suspension system modeling and wear diagnosis of a damper , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[3]  Jean-Marc Biannic,et al.  LFT modelling of the 2-DOF longitudinal nonlinear aircraft behaviour , 2008, 2008 IEEE International Conference on Computer-Aided Control Systems.

[4]  Peter J. Bentley,et al.  Dynamic Search With Charged Swarms , 2002, GECCO.

[5]  G. Hardier,et al.  An Overview of Relevant Issues for Aircraft Model Identification. , 2012 .

[6]  Cédric Seren,et al.  On-line Estimation of Longitudinal Flight Parameters , 2011 .

[7]  Eugene A. Morelli,et al.  Wind Tunnel Database Development using Modern Experiment Design and Multivariate Orthogonal Functions , 2002 .

[8]  Kai Hormann,et al.  Barycentric rational interpolation with no poles and high rates of approximation , 2007, Numerische Mathematik.

[9]  Sheng Chen,et al.  Sparse modeling using orthogonal forward regression with PRESS statistic and regularization , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[10]  Annie A. M. Cuyt,et al.  Rational approximation of vertical segments , 2007, Numerical Algorithms.

[11]  K. Trojanowski.  Multi-Swarm That Learns , 2010 .

[12]  Bing Lam Luk,et al.  Non-linear system identification using particle swarm optimisation tuned radial basis function models , 2009, Int. J. Bio Inspired Comput..

[13]  P. Petrushev,et al.  Rational Approximation of Real Functions , 1988 .

[14]  O. Nelles,et al.  Basis function networks for interpolation of local linear models , 1996, Proceedings of 35th IEEE Conference on Decision and Control.

[15]  Andries Petrus Engelbrecht,et al.  Particle swarm optimization with spatially meaningful neighbours , 2008, 2008 IEEE Swarm Intelligence Symposium.

[16]  José Neves,et al.  The fully informed particle swarm: simpler, maybe better , 2004, IEEE Transactions on Evolutionary Computation.

[17]  Svetoslav Markov,et al.  On linear interpolation under interval data , 1996 .