Zinc oxide nanofluid conductivity modeling using artificial neural Networks

Hussain, Muzaffar and Ansari, M. Ahmad and Mir, Feroz A. (2026) Zinc oxide nanofluid conductivity modeling using artificial neural Networks. POLLACK PERIODICA: AN INTERNATIONAL JOURNAL FOR ENGINEERING AND INFORMATION SCIENCES, 21 (2). pp. 50-55. ISSN 1788-1994

Text 606-article-p50.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

This paper explores ways to enhance the electrical conductivity of transformer oil using zinc oxide-based nanofluids. An artificial neural network was trained on data collected at temperatures ranging from 20 to 100 °C and zinc oxide concentrations varying from 0 to 0.3 g L −1 , achieving an R 2 value exceeding 0.9999. The maximum increase in conductivity was observed at a concentration of 0.1 g L; higher concentrations led to nanoparticle agglomeration, which decreased efficiency. These findings demonstrate the potential of the artificial neural network in optimizing the performance of transformer oil and making accurate predictions regarding the properties of nanofluids.

Actions (login required)

Edit Item