Efficient Substructure Preserving MOR Using Real-Time Temporal Supervised Neural Network
This paper addresses a novel model order reduction (MOR) technique with dominant substructure preservation. This process leads to cost minimization of the considered physical system which could be of any type from motors to circuitry packaging to software design. The new technique is formulated based on an artificial neural network (ANN) transformation along with the linear matrix inequality (LMI) optimization method. The proposed method is validated by comparing its performance with the following well-known reduction techniques Balanced Schur Decomposition (BSD) and state elimination via balanced realization.
KeywordsNeural networks model order reduction
Unable to display preview. Download preview PDF.
- 1.Rudnyi, E.B., Korvink, J.G.: Model Order Reduction of MEMS for Efficient Computer Aided Design and System Simulation. In: 16th International Symposium on Mathematical Theory of Networks and Systems, Leuven, Netherlands, pp. 1–6 (2004)Google Scholar
- 2.Ramesh, K., Ayyar, K., Nirmalkumar, A., Gurusamy, G.: Design of Current Controller for Two Quadrant DC Motor Drive by Using Model Order Reduction Technique. International Journal of Computer Science and Information Security 7(1), 17–23 (2010)Google Scholar
- 3.Antoulas, A.: Approximation of large-scale dynamical systems, advances in design and control. SIAM, Philadelphia (2005)Google Scholar
- 4.Freund, R.: SPRIM: Structure-preserving reduced-order interconnect macro-modeling. In: IEEE/ACM ICCAD (2004)Google Scholar
- 5.Fujimoto, K., Scherpen, J.M.A.: Balancing and Model Reduction for Discrete-Time Nonlinear Systems based on Hankel Singular Value Analysis. In: Proc. MTNS 2004, Leuven, Belgium, pp. 343–347 (2004)Google Scholar
- 7.Rabiei, P., Pedram, M.: Model-order reduction of large circuits using balanced truncation. In: Proc. IEEE ASP-DAC, pp. 237–240 (1999)Google Scholar
- 9.Varga, A., Anderson, B.D.O.: Accuracy enhancing method for the frequency-weighted balancing related method reduction. In: Proc. CDC 2001, Orlando, Florida, pp. 3659–3664 (2001)Google Scholar