Support Vector Machine based Adaptive Flow Measurement Technique using Venturi

Santhosh , K V and Roy, B K (2014) Support Vector Machine based Adaptive Flow Measurement Technique using Venturi. In: Proceedings of International Conference on Emerging Reaserch in Computing, Information, Communication and Applications, August 1st and 2nd 2014, NMIT, Yelahanka, Bangalore, India.

[img] PDF
Paper 8.pdf - Published Version
Restricted to Registered users only

Download (438kB) | Request a copy

Abstract

A flow measurement technique using an adaptive calibration technique is proposed using Support Vector Machine (SVM) is reported in this paper. The objectives of the present work are: (i) to extend the linearity range of measurement to 100% of full scale input range, (ii) to make the measurement technique adaptive to variations in discharge coefficient, diameter ratio of venturi nozzle and pipe (β), and liquid density. A block designed using SVM is added, in place of conventional calibration circuit, in cascade to data conversion unit. To produce outputs linear to input flow for the entire input range, and adaptive to variations in discharge coefficient, diameter ratio, and liquid density. Results show that the proposed technique has fulfilled the objectives with a root mean square of percentage error of 0.043%.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Adaptation, Venturi flow meter, Intelligence, Support Vector Machine.
Subjects: Engineering > MIT Manipal > Instrumentation and Control
Depositing User: MIT Library
Date Deposited: 16 Dec 2014 09:18
Last Modified: 16 Dec 2014 09:18
URI: http://eprints.manipal.edu/id/eprint/141288

Actions (login required)

View Item View Item