Session: K20-01: APPLICATIONS OF MACHINE LEARNING/AI FOR HEAT TRANSFER
Paper Number: 130949
130949 - Flow Measurement Through Machine Learning: A Novel Non-Intrusive Volumetric Flow Meter
Abstract:
An innovative non-intrusive flow meter is designed for the water flow measurement at ambient temperature under steady-state conditions. The device features a band heater positioned outside of the pipe, complemented by three thermocouples that monitor the outer wall's temperature. The procedure involves activating the band heater for 60 seconds, followed by deactivation and the recording of temperatures over the subsequent 120 seconds. Multiple tests are conducted for each mass flow rate, ranging from 8.5 gpm to 40 gpm. Arduino-based data collection is employed to record the temperature response for the system. Statistically, three temperature parameters are evaluated: maximum temperature, average temperature differences during heating, and average temperature differences during cooling. Regression learner methods are utilized to establish correlations between volumetric flow rates and temperature parameters. Several regression learner models are considered to have the best Root Mean Square error. This paper aims to identify the most accurate model for predicting volumetric flow rates. Subsequently, the achieved resolution, degree of uncertainty, cost considerations, and flow range capabilities of this novel flow meter will be benchmarked against those of existing non-intrusive flow meters currently available in the market. This comparative assessment promises to yield valuable insights into the effectiveness and performance of our innovative flow measurement solution.
Presenting Author: Ramon Peruchi Pacheco Da Silva The University of Alabama
Presenting Author Biography: Ramon Peruchi Pacheco da Silva is a PhD student at the Mechanical Engineering Department of The University of Alabama.
Authors:
Ramon Peruchi Pacheco Da Silva The University of AlabamaForooza Samadi The University of Alabama
Keith Woodbury The University of Alabama
Joseph Carpenter The University of Alabama
Flow Measurement Through Machine Learning: A Novel Non-Intrusive Volumetric Flow Meter
Paper Type
Technical Paper Publication