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

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.

[1]  Babu Joseph,et al.  Inferential control of processes: Part I. Steady state analysis and design , 1978 .

[2]  MengChu Zhou,et al.  Virtual sensing techniques and their applications , 2009, 2009 International Conference on Networking, Sensing and Control.

[3]  S. Kim,et al.  Study on the steady-state characteristics of the sensor tube of a thermal mass flow meter , 2007 .

[4]  S. K. Sreekala,et al.  Development, modeling and certain investigations on thermal mass flow meters , 2002 .

[5]  Vladimir Cherkassky,et al.  Learning from data , 1998 .

[6]  Babu Joseph,et al.  A tutorial on inferential control and its applications , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[7]  N. M. Kéita,et al.  Behaviour of straight pipe Coriolis mass flowmeters in the metering of gas: theoretical predictions with experimental verification , 1994 .

[8]  K. Janka.  Ion deflection air flow meter with constant deflection , 1984 .

[9]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[10]  Kenji Kawashima,et al.  Power Assessment of Flowing Compressed Air , 2006 .

[11]  Tomasz Dyakowski,et al.  Process tomography applied to multi-phase flow measurement , 1996 .

[12]  A. Olczyk.  Specific mass flow rate measurements in a pulsating flow of gas , 2008 .

[13]  John G. Webster,et al.  The Measurement, Instrumentation and Sensors Handbook , 1998 .

[14]  Maolin Cai,et al.  An improved denoising algorithm based on wavelet transform modulus maxima for non-intrusive measurement signals , 2012 .

[15]  O. Sazhin.  Novel mass air flow meter for automobile industry based on thermal flow microsensor. I. Analytical model and microsensor , 2013 .

[16]  K. Toda,et al.  Simple temperature compensation of thermal air-flow sensor , 1996 .

[17]  M. Cai,et al.  Non-invasive and non-intrusive gas flow measurement based on the dynamic thermal characteristics of a pipeline , 2012 .

[18]  R. A. Rahim,et al.  Non-invasive imaging of liquid/gas flow using ultrasonic transmission-mode tomography , 2007 .

[19]  Th. Gast,et al.  Coriolis mass flow measurement of gas under normal conditions , 1994 .

[20]  Vladimir Cherkassky,et al.  Learning from Data: Concepts, Theory, and Methods , 1998 .

[21]  Alexander Gammerman,et al.  Ridge Regression Learning Algorithm in Dual Variables , 1998, ICML.

[22]  张金龙,et al.  Thermal mass flowmeter , 2008 .

[23]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[24]  Gunnar Rätsch,et al.  Predicting Time Series with Support Vector Machines , 1997, ICANN.