Soft Sensing Method Of LS-SVM Using Temperature Time Series For Gas Flow Measurements

• Autorzy: Xu W. , Fan Z. , Cai M. , Shi Y. , Tong X. , Sun J.

Identyfikatory

DOI

10.1515/mms-2015-0028

• Języki publikacji: EN

Abstrakty

EN

This paper proposes a soft sensing method of least squares support vector machine (LS-SVM) using temperature time series for gas flow measurements. A heater unit has been installed on the external wall of a pipeline to generate heat pulses. Dynamic temperature signals have been collected upstream of the heater unit. The temperature time series are the main secondary variables of soft sensing technique for estimating the flow rate. A LS-SVM model is proposed to construct a non-linear relation between the flow rate and temperature time series. To select its inputs, parameters of the measurement system are divided into three categories: blind, invalid and secondary variables. Then the kernel function parameters are optimized to improve estimation accuracy. The experiments have been conducted both in the single-pulse and multiple-pulse heating modes. The results show that estimations are acceptable.

Słowa kluczowe

EN

gas flow; soft sensor; support vector machine (SVM); temperature time series

• Wydawca: Komitet Metrologii i Aparatury Naukowej PAN
• Czasopismo: Metrology and Measurement Systems
• Rocznik: 2015
• Tom: Vol. 22, nr 3
• Strony: 383--392
• Opis fizyczny: Bibliogr. 24 poz., rys., tab., wykr., wzory

Twórcy

autor

Xu W.

• Beihang University (BUAA), School of Automation Science and Electrical Engineering, Xueyuan Road 37, Haidian 100191, Beijing, China

autor

Fan Z.

• Beihang University (BUAA), School of Automation Science and Electrical Engineering, Xueyuan Road 37, Haidian 100191, Beijing, China

autor

Cai M.

• Beihang University (BUAA), School of Automation Science and Electrical Engineering, Xueyuan Road 37, Haidian 100191, Beijing, China

autor

Shi Y.

• Beihang University (BUAA), School of Automation Science and Electrical Engineering, Xueyuan Road 37, Haidian 100191, Beijing, China

autor

Tong X.

• Beihang University (BUAA), School of Automation Science and Electrical Engineering, Xueyuan Road 37, Haidian 100191, Beijing, China

autor

Sun J.

• Beihang University (BUAA), School of Automation Science and Electrical Engineering, Xueyuan Road 37, Haidian 100191, Beijing, China

Bibliografia

• [1] Cai, M.L., Kawashima, K., Kagawa, T. (2006). Power Assessment of Flowing Compressed Air. Trans. ASME J. Fluids Eng., 128(2006), 402-405.
• [2] Olczyk, A. (2008). Specific mass flow rate measurement in a pulsating flow of gas. Metrol. Meas. Syst., 15(2), 165-176.
• [3] Benson, J.M., et al. (1970). Thermal mass flowmeter. Instrum. Control Syst., 43, 85-87.
• [4] Laub, J.H. (1957). Measuring mass flow with the boundary-layer flowmeter. Control Engng., 4, 112-117.
• [5] Kolahi, K., Gast, T., Röck, H. (1994). Coriolis mass flow measurement of gas under normal conditions. Flow Meas. Instrum., 5, 275-383.
• [6] Keita, N.M. (1994). Behaviour of straight pipe Coriolis mass flowmeters in the metering of gas: theoretical predictions with experimental verification. Flow Meas. Instrum., 5, 289-294.
• [7] Webster, J.G. (1999). The Measurement, Instrumentation and Sensors Handbook. Boca Raton, 28.1-28.11.
• [8] Viswanathan, M., Kandaswamy, A., Sreekala, S.K., Sajna, K.V. (2002). Development, modeling and certain investigations on thermal mass flow meters. Flow. Meas. Instr. 12, 353-360.
• [9] Kei, T., Isao, S., Koichi, I. (1996). Simple temperature compensation of thermal air-flow sensor. Sensors and Actuators A: Physical, 57, 197-201.
• [10] Kim, D.K., Han, I.Y., Kim, S.J. (2007). Study on the steady-state characteristics of the sensor tube of a thermal mass flow meter. International Journal of Heat and Mass Transfer., 50, 1206-1211.
• [11] Sazhin, O. (2013). Novel mass air flow meter for automobile industry based on thermal flow microsensor. I. Analytical model and microsensor. Flow Measurement and Instrumentation, 30, 60-65.
• [12] Abdul, R., Rahiman, M.H., Chan, K.S., Nawawi, S.W. (2007). Non-invasive imaging of liquid/gas flow using ultrasonic transmission-mode tomography. Sensors and Actuators A: Physical., 135, 337-345.
• [13] Janka, K. (1984). Ion deflection air flow meter with constant deflection. Rev. Sci. Instrum., 55, 976-982.
• [14] Dyakowski, T. (1996). Process tomography applied to multi-phase flow measurement. Meas. Sci. Technol., 7, 343-353.
• [15] Joseph, B. (1999). Tutorial on inferential control and its applications. Proc. IEEE American Control Conference, San Diego, US, 3106-3118.
• [16] Liu, L.C., Kuo, S.M., Zhou, M.C. (2009). Virtual Sensing Techniques and Their Applications. Proc. IEEE Int. Conf. on Networking, Sensing and Control, Okayama, Japan.
• [17] Cherkassky, W., Mulier, F. (1998). Learning from Data. US: John Wiley & Sons.
• [18] Vapnik, V. (1995). The nature of statistical learning theory. New York: Springer Verlag.
• [19] Saunders, C., Gammerman, A., Vovk, V. (1998). Ridge regression learning algorithm in dual variables. Proc. Int. Conf. on Machine Learning, Madison, Wisconsin.
• [20] Suykens, J.A.K., Vandewalle, J. (1999). Least Squares Support Vector Machine classifiers. Neural Processing Letters, 9, 293-300.
• [21] Muller, K., et al. (1997). Predicting Time Series with Support Vector Machines. Proc. Int. Conf. on Artificial Neural Networks, Lausanne, Switzerland, 999-1004.
• [22] Fan, Z.C., Cai, M.L., Xu, W.Q. (2012). Non-invasive and non-intrusive gas flow measurement based on the dynamic thermal characteristics of a pipeline. Meas. Sci. Technol., 23, 105303.
• [23] Joseph, B. (1978). Brosilow Inferential control of processes. Part I. Steady state analysis and design, 24, 485-492.
• [24] Fan, Z.C., Cai, M.L., Wang, H.H. (2012). An improved denoising algorithm based on wavelet transform modulus maxima for non-intrusive measurement signals. Meas. Sci. Technol., 23, 045007.

Uwagi

EN

The authors wish to express their gratitude for the financial support from a Grant (51375028) of the National Natural Science Foundation of China.