Hybrid neural network models of transducers

A hybrid neural network (NN) approach is proposed and applied to modeling of transducers in the paper. The modeling procedures are also presented in detail. First, the simulated studies on the modeling of single input?single output and multi input?multi output transducers are conducted respectively by use of the developed hybrid NN scheme. Secondly, the hybrid NN modeling approach is utilized to characterize a six-axis force sensor prototype based on the measured data. The results show that the hybrid NN approach can significantly improve modeling precision in comparison with the conventional modeling method. In addition, the method is superior to NN black-box modeling because the former possesses smaller network scale, higher convergence speed, higher model precision and better generalization performance.

[1]  Zhou Tong,et al.  Hybrid modeling of wire cable vibration isolation system through neural network , 2009, Math. Comput. Simul..

[2]  M Cao,et al.  Advanced hybrid neural network automotive friction component model for powertrain system dynamic analysis. Part 1: Model development , 2004 .

[3]  Gong Hai-li,et al.  New Calibration Method of Six-Axis Force Sensor Based on Stewart Platform , 2006 .

[4]  Ian W. Hunter,et al.  Calibration of a horizontally acting force transducer with the use of a simple pendulum , 2006 .

[5]  N. Draper,et al.  Applied Regression Analysis: Draper/Applied Regression Analysis , 1998 .

[6]  Sheng A. Liu,et al.  A novel six-component force sensor of good measurement isotropy and sensitivities , 2002 .

[7]  Kon-Well Wang,et al.  A Hybrid Neural Network Approach for the Development of Friction Component Dynamic Model , 2004 .

[8]  Gérard Dreyfus,et al.  How to be a gray box: dynamic semi-physical modeling , 2001, Neural Networks.

[9]  van de Mjg René Molengraft,et al.  Hybrid Modeling for Mechanical Systems: Methodologies and Applications , 1999 .

[10]  Ugur Ersoy,et al.  A three component force transducer for reinforced concrete structural testing , 2004 .

[11]  Lu-Ping Chao,et al.  Shape optimal design and force sensitivity evaluation of six-axis force sensors , 1997 .

[12]  Sami F. Masri,et al.  A hybrid parametric/nonparametric approach for the identification of nonlinear systems , 1994 .

[13]  E.F.J. Coolen,et al.  Calibration of a novel airflow transducer for use in pneumotachography , 1999 .

[14]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[15]  Jun Zhang,et al.  Research on force-sensing element's spatial arrangement of piezoelectric six-component force/torque sensor , 2009 .

[16]  Joel L. Everhart,et al.  Development and Characterization of a Low-Pressure Calibration System for Hypersonic Wind Tunnels , 2004 .

[17]  Maurice Dubois.  Six-component strain-gage balances for large wind tunnels , 1981 .

[18]  R. L. Schultz,et al.  Dynamic neural network calibration of quartz transducers , 2002 .

[19]  N. Draper,et al.  Applied Regression Analysis , 1966 .

[20]  Wojtek J. Bock,et al.  Calibration of an electronically scanned white-light interferometric transducer for measurements of high pressure , 1995 .

[21]  Robert J. Rogers,et al.  Dynamic calibration of tri-axial piezoelectric force transducers , 2008 .

[22]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.