Soft calibration technique with SVM for intelligent flow measurement

Abstract

Design of an adaptive soft calibration circuit with support vector machine (SVM) for flow measurement using orifice flowmeter is reported in this paper. The objectives of the present work are the following: (i) to extend linearity range of measurement to 100 % of full-scale input range and (ii) to make measurement technique adaptive to variations in ratio of orifice hole to pipe diameter (β), liquid density, and liquid temperature. SVM model is trained to map output voltage of data conversion unit to produce linear characteristics with input flow rate, and independent of variations in ratio of orifice hole to pipe diameter, liquid density, and liquid temperature all within certain range. Further, the proposed technique is tested with simulated data. Results show that the proposed technique has fulfilled its set objectives.