Study on Support Vector Machine Based on Nonlinear Correction of Double Parallel Beam Weighing Transducer

Abstract:

According to the non-linear problem caused by temperature and circuit interference during the detection process of the double parallel beam weighing transducer, a nonlinear compensation method is proposed based on the support vector machine theory. The nonlinear characteristics of measured values of sensor are analyzed, and the support vector machine (SVM) inverse model is established while the displacement parameters as the output and voltage parameter as input. The effectiveness of SVM inverse model is verified by the simulation. Compared with the RBF neural network model, the SVM model is efficiency. The average error of the model prediction is 0.027g mm, so it has good linearity, and nonlinear compensation of the double Parallel beam weighing transducer is realized.

• Periodical: Applied Mechanics and Materials (Volumes 121-126)
• Pages: 2299-2303
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.121-126.2299
• Online since: October 2011
• Authors: Li Hua Zhao, Ke Qi Wang, Yong Hua Xie
• Keywords: Adaptive, Fuzzy Reasoning, Nonlinear Compensation, Non-Linearity Correction, Support Vector Machine (SVM), Weighing Sensor

References

[1] Liu liqiu. Electric current sensor based on thickness measurement and material identification studies, Shenyang Institute of Aeronautical University, vol. 23, pp.84-86, (2006).

[2] Tian yurong, Zou hairong. Based on artificial neural network identification of nonlinear eddy current sensors, Instrumentation Journal, vol. 27, pp.836-838, (2006).

[3] Fan wenxia, Wang an, Wang junping. Study of the method of enlarging linear range of eddy current sensor using BP network, Journal of Xi an Institute of Technology, vol. 24, pp.137-140, (2004).

[4] Yu yating, Du pingan, Liao yaqin, Dong wenxuan. BP network based on the eddy current sensor nonlinear compensation, Sensors and Microsystems, vol. 26, pp.54-55, (2007).

[5] Yu along. Based on RBF Neural million passing through the thermistor temperature sensor non-linear compensation, Instrumentation Journal, vol. 28, pp.899-902, (2007).

[6] Wang dingcheng, Fang tingjian, Gao lifu, Ma yongjun. Support vector machine regression line modeling and applications, Control and decision-making, vol. 18, pp.89-91, (2003).

[7] Yan weiwu, Zhu hongdong, Shao huihe. Based on least squares support vector machine soft sensor modeling, Journal of System Simulation, vol. 15, pp.25-28, (2003).

DOI: 10.1109/icnnsp.2003.1279217