Methods and models of neural networks for approximation of calibration characteristics of NTC-thermistors

Authors

DOI:

https://doi.org/10.20535/SRIT.2308-8893.2022.3.07

Keywords:

accuracy, measuring data, calibration, NTC-thermistor, operating temperature range, transformation function, neural network approximation, RBF-network

Abstract

The hypothesis about the expediency of using RBF-networks to improve the accuracy of constructing the calibration characteristics of NTC-thermistors in the operating temperature range without dividing it into subranges is confirmed. It has been established that the error of the neural network approximation of the calibration characteristics of NTC-thermistors based on RBF-networks is at least one and a half times less than the permissible error of approximation of the third-order polynomial model, which is used in the software of modern systems for collecting and processing measurement information. A technique has been developed for processing measurement information using adaptive RBF-networks to automate constructing individual calibration characteristics and periodic calibration of NTC-thermistors.

Author Biographies

Serhii Fedin, National Transport University, Kyiv

Doctor of Technical Sciences, a professor at the Department of Information Systems and Technologies of the National Transport University, Kyiv, Ukraine.

Irina Zubretska, “Trade City”, Kyiv

Information technology specialist at “Trade City”, Kyiv, Ukraine.

References

Metrology in industry: the key for quality; edited by French College of Metrology. Paris, 2006, 270 p.

E.S. Polishchuk, V.M. Vanko, M.M. Dorozhovets, V.O. Yatsuk, and Yu.V. Yatsuk, Measuring transducers (sensors): textbook. Lviv: National Lviv Polytechnic University, 2015, 584 p.

V.M. Sharapov et al., Sensors: ref. allowance. M.: Technosphere, 2012, 624 p.

R.I. Baitsar and S.S. Warsaw, Semiconductor microsensors: academic. manual. Lviv: National Lviv Polytechnic University, 2001, 290 p.

Y.T. Lutsik, O.P. Guk, O.I. Lakh, and B.I. Stadnyk, Temperature measurement. Theory and practice. Lviv: Beskyd Bit, 2006, 580 p.

John S. Steinhart and Stanley R. Hart, “Calibration curves for thermistors,” Deep Sea Research and Oceanographic Abstracts, vol. 15, issue 4, August 1968, pp. 497–503.

Agilent 34970 A Data Acquisition. Switch Unit User Guide Edition 3.0. Agilent Technologies, Inc., 2003, 434 p.

S. Khaikin, Neural networks: a complete course; ed. 2nd. M.: Williams, 2006, 1104 p.

O.A. Gerashchenko et al., Temperature measurements: a reference book. K.: Naukova dumka, 1989, 704 p.

V.A. Granovsky and T.N. Siraya, Methods of processing experimental data during measurements. L: Energoatomizdat, 1990, 288 p.

R.G. Jackson, The latest sensors. M: Technosfera, 2007, 384 p.

V.T. Kondratov, Fundamentals of the theory of automatic correction of systematic changes in the correction of physical quantities with an unstable and non-linear function of the sensor transformation: abstract of the thesis. thesis. Dr. tech. Sciences: 05.11.15 and 05.11.01. Kyiv, 2001, 36 p.

J. Frieden, Modern sensors: a reference book. M: Technosfera, 2005, 592 p.

O.V. Zaporozhets, V.A. Korotenko, and T.A. Ovcharova, “Compensation for the nonlinearity of the conversion function of measuring devices using an artificial neural network,” Management, Navigation and Communication Systems, no. 4(16), pp. 99–103, 2010.

A.V. Degtyarev, O.V. Zaporozhets, and T.A. Ovcharova, “Adaptive system for compensating the nonlinearity of the conversion function of measuring devices based on a three-layer perceptron,” Electrical And Computer Systems, no. 6, pp. 235–241, 2012.

O.V. Zaporozhets, T.A. Ovcharova, and I.V. Ruzhentsev, “Compensation for non-linearity of a semiconductor thermistor using an artificial neural network,” Information Processing Systems, no. 6(131), pp. 64–67, 2015.

Nicholas J. Cotton and Bogdan M. Wilamowski, “Compensation of Sensors Nonlinearity with Neural Networks,” 24th IEEE International Conference on Advanced Information Networking and Applications, 2010, pp. 1210–1216.

T.D. Dongale and R.K. Kamat, “Modelling of NTC-thermistor using artificial neural network for nonlinearity compensation,” Informatics Engineering, an International Journal (IEIJ), 2013, vol. 1, pp. 15–20.

Shakeb A. Khan, Tarikul Islam, and Gulshan, “Artificial Neural Network based online sensor calibration and compensation,” Computing, vol. 6, no. 3, pp. 74–78, 2007.

S.S. Fedin and I.S. Zubretska, “Ensuring the accuracy of approximation of the R/T-characteristic of an NTC-thermistor based on neural network modeling,” Technology and Design in Electronic Equipment, no. 4, pp. 28–35, 2015.

N.A. Zubretska, S.S. Fedin, and I.S. Zubretska, “Construction of calibration characteristics of temperature sensors using neural networks,” Bulletin of the Engineering Academy of Ukraine, no. 1, pp. 130–136, 2015.

M.J.D. Powell, “The theory of radial basis function approximation in 1990,” in W. Light, ed., Advances in Numerical Analysis Vol. II: Wavelets, Subdivision Algorithms and Radial Basis Functions. Oxford: Oxford Science Publications, 1992, pp. 105–210.

Information Technology. Glossary of terms: DSTU ISO/IEC 2382:2017. K.: SE “UkrNDNC”, 2020, 464 p.

S. Osovsky, Neural networks for information processing. M.: Finance and statistics, 2004, 344 p.

S.S. Fedin and I.S. Zubretska, Neural network approximation of calibration characteristics of NTC-thermistors: monograph. K.: Interservice, 2017, 196 p.

S.S. Fedin, I.S. Zubretska, and O.O. Polikarpov, “Ensuring the accuracy of construction of calibration characteristics of NTC-thermistors based on neural networks with radial basis functions,” Metrology and Devices, no. 1(63), pp. 37–46, 2017.

Published

2022-10-30

Issue

Section

Theoretical and applied problems of intelligent systems for decision making support