Hybrid Neural Network Models of Six-Axis Force Sensor

Abstract:

A method of analyzing the Six-axis force measuring system by hybrid modeling is introduced in this paper. The mapping function of signal voltage output, which is input vectors of the Neural Network (NN) model, and measuring force signal, which is output vectors of the NN model, is represented as two parts. The determined linear part obtains the main principle and the the information of transfer matrix. The undetermined nonlinear part are estimated by neural network. The problems about nonlinear error and coupling are solved. The accuracy and feasibility of the method are displayed by the result of experiment data simulation.

• Periodical: Advanced Materials Research (Volumes 591-593)
• Pages: 1450-1456
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.591-593.1450
• Online since: November 2012
• Authors: Sheng Lai Chen, Jian Zhong Hong
• Keywords: Calibration, Decouple, Hybrid Modeling, Neural Network (NN), Nonlinear Error

References

[1] N.R. Draper and H. Smith: Applied Regression Analysis 3rd edn (New York: Wiley,1998)

[2] E.F.J. Coolen, M.J. West and P.R.S. White: Calibration of a novel airflow transducer for use in pneumotachography Sensors Actuators, 76 (1999), 127–32

DOI: 10.1016/s0924-4247(98)00369-0

[3] M. Cao and K.W. Wang: A hybrid neural network approach for the development of friction component dynamic model J. Dyn. Syst. Meas. Control, 126 (2004), 144–53

[4] M. Cao, K.W. Wang and W.E. Tobler: Advanced hybrid neural network and automotive friction component model for powertrain system dynamic analysis: part 1. Model development Proc. Inst. Mech. Eng. D, 218 (2004), 831–43

DOI: 10.1243/0954407041581147

[5] Y. Oussar and G. Dreyfus: How to be a gray box: dynamic semi-physical modeling Neural Netw, 14 (2001), 1161–72

DOI: 10.1016/s0893-6080(01)00096-x

[6] L.P. Chao and K.T. Chen: Shape optimal design and force sensitivity evaluation of six-axis force sensors Sensors Actuators, 63 (1997), 105–12

DOI: 10.1016/s0924-4247(97)01534-3

[7] S.L. Chen: A Study of Hybrid Modeling for Multi-axis Force Measuring System Based on Artificial Neural Network (MS., Xi'an Jiaotong University, Xi'an, China 2008, in Chinese)

[8] M. Dubious: Six-component Strain-gauge Balance for Large Wind Tunnels Exp. Mech, 11 (1981), 401–7

[9] E. Canbay, U. Ersoy and T. Tankut: A Three Component Force Transducer for Reinforced Concrete Structural Testing Eng. Struct, 26 (2004), 257–65

DOI: 10.1016/j.engstruct.2003.10.002

[10] Y.J. Li, J. Zhang, Z.Y. Jia, M. Qian and H.G. Li: Research on Force-sensing Element's Spatial Arrangement of Piezoelectric Six-component Force/torque Sensor Mech. Syst. Signal Process, 23 (2009), 2687–98

DOI: 10.1016/j.ymssp.2009.05.014

[11] S.A. Liu and H.L. Tzo: Novel Six-component Force Sensor of Good Measurement Isotropy and Sensitivities Sensors Actuators, 100 (2002), 223–30

DOI: 10.1016/s0924-4247(02)00135-8

[12] C.G. Zhou, X.N. Zhang, S.L. Xie, T. Zhou and C.C. Zhu: Hybrid Modeling of Wire Cable Vibration Isolation System Through Neural Network, Math. Comput. Simul, 79 (2009), 3160–73