Model order reduction using artificial neural networks

In this paper, we present a new technique for model order reduction (MOR) that is based on an artificial neural network (ANN) prediction. The ANN-based MOR can be applied for different scale systems with substructure preservation. In the proposed technique, the ANN is implemented for predicting the unknown elements of the reduced order model. Prediction of the ANN architecture is based on minimizing the cost function obtained by the difference between the actual and desired system behavior. The ANN prediction process is pursued while maintaining the full order substructure in the reduced model. The proposed ANN-based model order reduction method is compared to recently published work on MOR techniques. Simulation results verify the validity of the new MOR technique.

[1]  C. Vishwakarma,et al.  Clustering Method for Reducing Order of Linear System using Pade Approximation , 2008 .

[2]  H. V. D. Vorst,et al.  Model Order Reduction: Theory, Research Aspects and Applications , 2008 .

[3]  Y. Shamash.  Stable reduced-order models using Padé-type approximations , 1974 .

[4]  G. Parmar,et al.  System reduction using factor division algorithm and eigen spectrum analysis , 2007 .

[5]  Timo Reis,et al.  Balanced truncation model reduction of second-order systems , 2008 .

[6]  Athanasios C. Antoulas,et al.  Approximation of Large-Scale Dynamical Systems , 2005, Advances in Design and Control.

[7]  J. Hickin,et al.  Approximate aggregation for linear multivariable systems , 1980 .

[8]  M. K. Pandey,et al.  System order reduction using GA for unit impulse input and a comparative study using ISE & IRE , 2009, ICAC3 '09.

[9]  K. Han,et al.  Model reduction using the stability-equation method and the Padé approximation method , 1980 .

[10]  B. Friedland,et al.  Routh approximations for reducing order of linear, time-invariant systems , 1975 .

[11]  N. Selvaganesan,et al.  Mixed Method of Model Reduction for Uncertain Systems , 2007 .

[12]  Rein Luus,et al.  Model reduction by minimization of integral square error performance indices , 1990 .

[13]  Suvranu De,et al.  A comparison of some model order reduction methods for fast simulation of soft tissue response using the point collocation-based method of finite spheres , 2009, Engineering with Computers.