Nonlinearity Compensation for Thermocouple Vacuum Gauge Using Particle Swarm Optimized Least Squares Support Vector Machine

Abstract:

A method for compensating nonlinear characteristic of thermocouple vacuum gauge is proposed. Least squares support vector machine (LS-SVM) is adopt as compensation model, of which parameters are optimized using particle swarm optimization (PSO) algorithm. Experimental results using data obtained on-site show that the proposed approach effectively compensates the nonlinearity characteristic, and the accuracy of this method is higher than those obtained by SVM model.

• Periodical: Applied Mechanics and Materials (Volumes 321-324)
• Pages: 2177-2182
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.321-324.2177
• Online since: June 2013
• Authors: Yao Geng Tang, Song Gao, Xing Qu
• Keywords: Compensation Model, Least Squares Support Vector Machines (Ls-SVM), Nonlinear Characteristic, Particle Swarm Optimization (PSO), Thermocouple Vacuum Gauge

References

[1] Wang Chiluen, Thermocouple gauge for partial pressure measurements, Journal of Vacuum Science & Technology A, 1989, 7(3): 2393-2396.

[2] Dong Chuangang, Sun Tongjing, Nonlinear compensation of thermocouple circular canal sensor in the vacuum measuremen, Microcomputer Information, 2007, 23(4): 214 -217.

[3] Hamit Erdem, Implementation of software-based sensor linearization algorithms on low-cost microcontrollers, ISA Transactions,2010,49(4): 552–558.

DOI: 10.1016/j.isatra.2010.04.004

[4] Liying Xu, Nonlinear compensation of capacitance weighing sensors based on neural networks with orthonormal functions, Seventh International Conference on Natural Computation, Shanghai,2011:795-798.

DOI: 10.1109/icnc.2011.6022165

[5] Yu Along, New approach to non-linearity compensation of thermistor temperature transducer based on RBF neural network, Chinese Journal of Scientific Instrument, 2007, 28(5): 899-902.

[6] Yu Along ,Thermocouple sensor non-linearity compensation based on orthogonal polynomial basis functions neural network, Second International Conference on Mechanic Automation and Control Engineering, Hohhot ,2011:7074 – 7076.

DOI: 10.1109/mace.2011.5988679

[7] Zhou Hongwei, Liu Desheng and Zu Haiyan, Non-linearity compensation of eddy current sensor based on SVM inverse model, Transducer and Micro-system Technologies,2009,28(7):40-43.

[8] Xie Wenjun. A pressure sensor calibration model based on Support Vector Machine. 24th Chinese Control and Decision Conference, Taiyuan, 2012:3239 – 3242.

DOI: 10.1109/ccdc.2012.6244512

[9] Suykens J.A.K,J Vandewalle, Recurrent least squares support vector machines, IEEE Transactions on Circuits and SystemsI, 2000,47(7):1109-1114.

DOI: 10.1109/81.855471

[10] Kennedy J and Eberhart R C, Particle swarm optimization, Proc. IEEE Int. Conf. on Neural Networks, Perth,WA, 1995: 1942-1948.