Novel Wiener models with a time-delayed nonlinear block and their identification

Popular Wiener models are a combination of dominant linear behavior and static nonlinear characteristics. However, they are less accurate in dealing with problems with strong nonlinear time-delayed effects. Hence, a group of novel nonlinear models based on Wiener models are proposed in this study. The static nonlinear part of general Wiener models is replaced by a time-delayed nonlinear block. Thus, two novel Wiener models with a quasi-dynamic nonlinear block are constructed, called the Wiener-QDN models. The autoregressive with exogenous input (ARX) model is utilized to identify the dynamic linear block, and the radial basis function neural network is used to build the nonlinear part of Wiener and the Wiener-QDN models. Results reveal the effectiveness of these models in nonlinear system identification. The first test cases are systems governed by simple equations. The Wiener-QDN models can identify these systems with or without measurement noise. These models are further applied in unsteady aerodynamic modeling cases. Test cases of a NACA 0012 airfoil pitching in transonic flow indicate that both linearity and nonlinearity are well captured by the proposed Wiener-QDN models.

[1]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[2]  Yinggan Tang,et al.  Identification of wiener model with discontinuous nonlinearities using differential evolution , 2013 .

[3]  Matthias Haupt,et al.  Efficient Surrogate Modelling of Nonlinear Aerodynamics in Aerostructural Coupling Schemes , 2014 .

[4]  Jeffrey P. Thomas,et al.  Proper Orthogonal Decomposition Technique for Transonic Unsteady Aerodynamic Flows , 2000 .

[5]  Stephen A. Billings,et al.  Radial basis function network configuration using genetic algorithms , 1995, Neural Networks.

[6]  Jeen-Shing Wang,et al.  A Wiener-type recurrent neural network and its control strategy for nonlinear dynamic applications , 2009 .

[7]  Eduardo F. Camacho,et al.  Model predictive control techniques for hybrid systems , 2010, Annu. Rev. Control..

[8]  Dan Fan,et al.  Identification for disturbed MIMO Wiener systems , 2009 .

[9]  Ken Badcock,et al.  On the generation of flight dynamics aerodynamic tables by computational fluid dynamics , 2011 .

[10]  A. Mannarino,et al.  Nonlinear aeroelastic reduced order modeling by recurrent neural networks , 2014 .

[11]  Weiwei Zhang,et al.  Numerical study on the correlation of transonic single-degree-of-freedom flutter and buffet , 2015 .

[12]  L. Ljung.  Approaches to identification of nonlinear systems , 2010, Proceedings of the 29th Chinese Control Conference.

[13]  P. Spalart.  A One-Equation Turbulence Model for Aerodynamic Flows , 1992 .

[14]  Yves Rolain,et al.  Fast approximate identification of nonlinear systems , 2003, Autom..

[15]  P. Schmid,et al.  Dynamic mode decomposition of numerical and experimental data , 2008, Journal of Fluid Mechanics.

[16]  Lennart Ljung,et al.  Identification of nonlinear systems , 2019, 2019 Proceedings of the Conference on Control and its Applications.

[17]  Haiyan Hu,et al.  Nonlinear Reduced-Order Modeling for Multiple-Input/Multiple-Output Aerodynamic Systems , 2014 .

[18]  Dale Schuurmans,et al.  Automatic basis selection techniques for RBF networks , 2003, Neural Networks.

[19]  O. Agamennoni,et al.  A nonlinear model predictive control system based on Wiener piecewise linear models , 2003 .

[20]  Weiwei Zhang,et al.  Efficient Method for Limit Cycle Flutter Analysis Based on Nonlinear Aerodynamic Reduced-Order Models , 2012 .

[21]  M. Winter,et al.  Reduced-Order Modeling of Unsteady Aerodynamic Loads using Radial Basis Function Neural Networks , 2014 .

[22]  Zhang Weiwei.  ON UNSTEADY AERODYNAMIC MODELING BASED ON CFD TECHNIQUE AND ITS APPLICATIONS ON AEROELASTIC ANALYSIS , 2008 .

[23]  Javad Poshtan,et al.  Wiener-neural identification and predictive control of a more realistic plug-flow tubular reactor , 2008 .

[24]  Dingli Yu,et al.  Selecting radial basis function network centers with recursive orthogonal least squares training , 2000, IEEE Trans. Neural Networks Learn. Syst..

[25]  H. Bloemen,et al.  Wiener Model Identification and Predictive Control for Dual Composition Control of a Distillation Column , 2001 .

[26]  André da Motta Salles Barreto,et al.  GOLS - Genetic orthogonal least squares algorithm for training RBF networks , 2006, Neurocomputing.

[27]  Lennart Ljung,et al.  Nonlinear black-box modeling in system identification: a unified overview , 1995, Autom..

[28]  Sheng Chen,et al.  Modeling of Complex-Valued Wiener Systems Using B-Spline Neural Network , 2011, IEEE Transactions on Neural Networks.

[29]  Weiwei Zhang,et al.  An approach to enhance the generalization capability of nonlinear aerodynamic reduced-order models , 2016 .

[30]  Weiwei Zhang,et al.  Reduced-Order-Model-Based Flutter Analysis at High Angle of Attack , 2007 .

[31]  Jozef Vörös,et al.  Parameter identification of Wiener systems with multisegment piecewise-linear nonlinearities , 2007, Syst. Control. Lett..

[32]  Nicholas J. Higham,et al.  Matlab guide, Second Edition , 2005 .

[33]  James J. Carroll,et al.  Approximation of nonlinear systems with radial basis function neural networks , 2001, IEEE Trans. Neural Networks.

[34]  Mark Beale,et al.  Neural Network Toolbox™ User's Guide , 2015 .

[35]  In-Beum Lee,et al.  Nonlinear regression using RBFN with linear submodels , 2003 .

[36]  L. Ljung,et al.  Identification of composite local linear state-space models using a projected gradient search , 2002 .

[37]  Kwok Leung Lai,et al.  Identification of a Hammerstein model for wing flutter analysis using CFD data and correlation method , 2010, Proceedings of the 2010 American Control Conference.

[38]  Nam Mai-Duy,et al.  Numerical solution of differential equations using multiquadric radial basis function networks , 2001, Neural Networks.

[39]  Ahmet Palazoglu,et al.  Model predictive control based on Wiener models , 1998 .

[40]  Bryan Glaz,et al.  Reduced-Order Nonlinear Unsteady Aerodynamic Modeling Using a Surrogate-Based Recurrence Framework , 2010 .

[41]  Earl H. Dowell,et al.  Reduced-Order Models for Computational-Fluid-Dynamics-Based Nonlinear Aeroelastic Problems , 2015 .

[42]  Y. K. Wong,et al.  Nonlinear system identification using optimized dynamic neural network , 2009, Neurocomputing.

[43]  H. Bijl,et al.  Mesh deformation based on radial basis function interpolation , 2007 .

[44]  Jian Sun,et al.  Support-Vector-Machine-Based Reduced-Order Model for Limit Cycle Oscillation Prediction of Nonlinear Aeroelastic System , 2012 .

[45]  Sun Jian,et al.  Active flutter suppression control law design method based on balanced proper orthogonal decomposition reduced order model , 2012 .

[46]  L. Ljung,et al.  Maximum Likelihood Identification of Wiener Models , 2008 .

[47]  Weiwei Zhang,et al.  Aeroservoelastic Analysis for Transonic Missile Based on Computational Fluid Dynamics , 2009 .

[48]  Fouad Giri,et al.  Frequency identification of nonparametric Wiener systems containing backlash nonlinearities , 2013, Autom..

[49]  Dario H. Baldelli,et al.  Control-Oriented Flutter/Limit-Cycle-Oscillation Prediction Framework , 2008 .

[50]  Weiwei Zhang,et al.  ROM Based Aeroservoelastic Analysis in Transonic Flow , 2007 .

[51]  Jozef Vörös.  Parameter identification of Wiener systems with discontinuous nonlinearities , 2001, Syst. Control. Lett..

[52]  Lennart Ljung.  Perspectives on System Identification , 2008 .

[53]  Michael T. Manry,et al.  LMS learning algorithms: misconceptions and new results on converence , 2000, IEEE Trans. Neural Networks Learn. Syst..

[54]  Weiwei Zhang,et al.  The interaction between flutter and buffet in transonic flow , 2015 .

[55]  Jeffrey P. Thomas,et al.  Nonlinear Inviscid Aerodynamic Effects on Transonic Divergence, Flutter, and Limit-Cycle Oscillations , 2001 .