BACKPROPAGATION APPROXIMATION APPROACH FOR THE GENERATION OF MACROMODELS

In this paper, the authors propose a backpropagation approximation approach macromodeling technique for the automatic generation of dynamic reduced-order analytical model for a lateral folded-beam comb-drive micro resonator. The approximation approach is a novel method that represents a potentially valuable generic modeling technique for rapid and accurate non-linear model formulation. When compared to the 3-D finite element analysis results, the results show that the proposed macromodel speeds up simulations by a maximum factor of 464 over the finite element approach with less than 1.7 % error for small displacements up to 2 mm. The simulation results also show good agreement with the experimental results.

[1]  Yao-Joe Yang,et al.  Low-order models for fast dynamical simulation of MEMS microstructures , 1997, Proceedings of International Solid State Sensors and Actuators Conference (Transducers '97).

[2]  F. Frost,et al.  Optimum back propagation network conditions with respect to computation time and output accuracy , 1999, Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300).

[3]  Linda Jankauskas,et al.  BestFit, distribution fitting software by Palisade Corporation , 1995, WSC '95.

[4]  James T. Luxhoj,et al.  Integrated decision support for aviation safety inspectors , 1996 .

[5]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[6]  S. F. Bart,et al.  AutoMM: automatic generation of dynamic macromodels for MEMS devices , 1998, Proceedings MEMS 98. IEEE. Eleventh Annual International Workshop on Micro Electro Mechanical Systems. An Investigation of Micro Structures, Sensors, Actuators, Machines and Systems (Cat. No.98CH36176.

[7]  James P. Ignizio,et al.  A practical overview of neural networks , 1997, J. Intell. Manuf..

[8]  S. D. Senturia,et al.  Generating efficient dynamical models for microelectromechanical systems from a few finite-element simulation runs , 1999 .

[9]  M. Vidyasagar.  Can neural networks really generalize? , 1999, Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300).

[10]  Stephen D. Senturia,et al.  Simulation and design of microsystems: a 10-year perspective , 1998 .

[11]  Stephen D. Senturia,et al.  Computer aided macromodeling for mems , 1998 .

[12]  H. Tilmans.  Equivalent circuit representation of electromechanical transducers: I. Lumped-parameter systems , 1996 .

[13]  William J. Kaiser,et al.  Microelectromechanical gyroscope: analysis and simulation using SPICE electronic simulator , 1995, MOEMS-MEMS.

[14]  S. F. Bart,et al.  An Environment for MEMS Design and Verification , 1998 .

[15]  Linda Salchenberger,et al.  Using neural networks to aid the diagnosis of breast implant rupture , 1997, Comput. Oper. Res..

[16]  Stephen A. Billings,et al.  Please Scroll down for Article , 1992 .