Доступ предоставлен для: Guest

ISSN Online: 2379-1748

7th Thermal and Fluids Engineering Conference (TFEC)
SJR: 0.152 SNIP: 0.14 CiteScore™:: 0.5

Indexed in

Clarivate CPCI (Proceedings) Scopus
May, 15-18, 2022 , Las Vegas, NV, USA

Classifying Thermal Conductivity of Fluids with Artificial Neural Networks

Get access (open in a dialog) pages 457-465
DOI: 10.1615/TFEC2022.emt.040940


The objective of this paper is to discuss the capability of an Artificial Neural Network to classify the thermal conductivity of glycol concentrations in water. This was done by creating a COMSOL model of a micropipette thermal sensor in an infinite media and simulating a 500 µs laser pulse at the tip. Parameter approximation of the 2nd order heat transfer PDE permits concentration classification. The temperature profile dataset generated would then be fed into a trained ANN to classify the thermal conductivity, whose value would be used to distinguish the glycol concentration difference of up to 10%. Training of the ANN yielded an overall classification accuracy of 99.99% after 108 epochs.