Advances in Nano Research, Vol. 12, No. 5 (2022) 000-000 https://doi.org/10.12989/anr.2022.12.5.000 Copyright © 2022 Techno-Press, Ltd. http://www.techno-press.org/?journal=journal=anr&subpage=5 ISSN: 2287-237X (Print), 2287-2388 (Online) 1. Introduction High-temperature stream/equipment of industrial processes are often required to cool down using an appropriate working/operating fluid (Ebadian and Lin 2011). It is widely accepted that a liquid-based cooling technology can effectively cool down high-temperature equipment (Ebadian and Lin 2011). Deionized water, ethylene glycol, high heat capacity oils, and propane are the most commonly used liquids in cooling cycles (Lai et al. 2009). Unfortunately, these traditional cooling media often fail to transfer heat adequately flux due to their weak thermophysical characteristics (Kazemi and Nasr 2014). On the other hand, some devices are needed to cool down as quickly and efficiently as possible by removing a massive heat flux (Ebadian and Lin 2011). The addition of nano-sized metal and non-metallic particles to the traditional cooling liquids (i.e., nanofluid synthesis) has been proposed to improve their thermo- Corresponding author, Professor, E-mail: behzad.vaferi@gmail.com physical properties and heat removal efficiency (Khalifeh and Vaferi 2019). Nanoparticles Brownian motion (Iqbal et al. 2021) and their higher thermal conductivity than the traditional fluids (Ibrahim et al. 2021) are responsible for this improvement. Generally, nanofluids are fabricated by homogenized dispersion of single or combined nano- particles in a pure (Pandit and Sharma 2020) or mixture (Asadi et al. 2021) of traditional liquid. Nanofluids have already approved their potential advantages to cover the limitations of conventional fluids in heat transfer applications (Abid et al. 2020, Sharif et al. 2021a, b). Nano-scale particles (Kaabipour and Hemmati 2021) have been gradually engaged in different applications ranging from wastewater treatment (Keshtkar et al. 2021, Alibak et al. 2022), nanocomposite fabrication (Arani et al. 2021, Esmaeili-Faraj et al. 2021, Nezhad et al. 2021), tunable polymer-protein (Seaberg et al. 2020), antibacterial media (Baláž et al. 2019), energy generation (Chu et al. 2021) and management (Chu et al. 2020a, b, Gul et al. 2020, Haq et al. 2021), reforming process (Deng et al. 2019), porous media (Esfe et al. 2020, Sheikholeslami et al. 2021), nanofluid synthesis (İpek and Mermerdaş 2020, Khan et al. 2021, Ali et al. 2021) to trace gold separation Differentiation among stability regimes of alumina-water nanofluids using smart classifiers Bahador Daryayehsalameh 1 , Mohamed Arselene Ayari 2,3 , Abdelouahed Tounsi 4,5 , Amith Khandakar 6 and Behzad Vaferi 7 1 School of Chemical Engineering, Iran University of Science and Technology (IUST), I.R. Iran 2 Department of Civil and Architectural Engineering, College of Engineering, Qatar University, Doha 2713, Qatar 3 Technology Innovation and Engineering Education Unit, Qatar University, Doha 2713, Qatar 4 YFL (Yonsei Frontier Lab), Yonsei University, Seoul, Korea 5 Material and Hydrology Laboratory, University of Sidi Bel Abbes, Faculty of Technology, Civil Engineering Department, Algeria 6 Department of Electrical Engineering, College of Engineering, Qatar University, 2713, Doha, Qatar 7 Department of Chemical Engineering, Shiraz Branch, Islamic Azad University, Shiraz, Iran (Received August 10, 2021, Revised February 14, 2022, Accepted March 2, 2022) Abstract. Nanofluids have recently triggered a substantial scientific interest as cooling media. However, their stability is challenging for successful engagement in industrial applications. Different factors, including temperature, nanoparticles and base fluids characteristics, pH, ultrasonic power and frequency, agitation time, and surfactant type and concentration, determine the nanofluid stability regime. Indeed, it is often too complicated and even impossible to accurately find the conditions resulting in a stabilized nanofluid. Furthermore, there are no empirical, semi-empirical, and even intelligent scenarios for anticipating the stability of nanofluids. Therefore, this study introduces a straightforward and reliable intelligent classifier for discriminating among the stability regimes of alumina-water nanofluids based on the Zeta potential margins. In this regard, various intelligent classifiers (i.e., deep learning and multilayer perceptron neural network, decision tree, GoogleNet, and multi-output least squares support vector regression) have been designed, and their classification accuracy was compared. This comparison approved that the multilayer perceptron neural network (MLPNN) with the SoftMax activation function trained by the Bayesian regularization algorithm is the best classifier for the considered task. This intelligent classifier accurately detects the stability regimes of more than 90% of 345 different nanofluid samples. The overall classification accuracy and misclassification percent of 90.1% and 9.9% have been achieved by this model. This research is the first try toward anticipting the stability of water-alumin nanofluids from some easily measured independent variables. Keywords: alumina-water nanofluids; artificial intelligent classifiers; classification accuracy; multilayer perceptron; stability regime