•  
  •  
 

Authors

Mohammad Reza Chalak Qazani, Faculty of Computing and Information Technology, Sohar University, Sohar, 311, Oman
Ganesan Kadirgama, Faculty of Mechanical & Automotive Engineering Technology, University Malaysia Pahang Al-Sultan Abdullah, 26600 Pekan, Pahang, Malaysia; And Wisma TNB Kepong, Jalan Jinjang Permai 2, Kuala Lumpur, Malaysia
Navid Aslfattahi, Institute of Fluid Dynamics and Thermodynamics, Faculty of Mechanical Engineering, Czech Technical University in Prague, Technická 4, 166 07 Prague, Czech Republic
Devarajan Ramasamy, Faculty of Mechanical & Automotive Engineering Technology, University Malaysia Pahang Al-Sultan Abdullah, 26600 Pekan, Pahang, Malaysia
Lingenthiran Samylingam, Centre for Advanced Mechanical and Green Technology, Faculty of Engineering and Technology, Multimedia University, Jalan Ayer Keroh Lama, Bukit Beruang, 75450 Melaka, Malaysia
Kumaran Kadirgama, Faculty of Mechanical & Automotive Engineering Technology, University Malaysia Pahang Al-Sultan Abdullah, 26600 Pekan, Pahang, Malaysia; And Centre for Research in Advanced Fluid and Processes, University Malaysia Pahang Al-Sultan Abdullah, 26600 Pekan, Pahang, MalaysiaFollow
Chee Kuang Kok, Centre for Advanced Mechanical and Green Technology, Faculty of Engineering and Technology, Multimedia University, Jalan Ayer Keroh Lama, Bukit Beruang, 75450 Melaka, Malaysia
Mohd Fairusham Ghazali, Faculty of Mechanical Engineering, Industrial University of Ho Chi Minh City, 12 Nguyen Van Bao St, Go Vap, Ho Chi Minh City, VietnamFollow

Abstract

Developing more energy-efficient, environmentally friendly heat transfer solutions is necessary. As a result, the application of nanofluids has attracted an increasing amount of attention. This paper shows a new method for predicting the viscosity of hybrid alumina-copper oxide nanofluid. The Adaptive Neuro-Fuzzy Inference System (ANFIS) was used to predict the abovementioned physical property of the fluid dispersed in Therminol 55; a medium-temperature medium. The concentration of nanoparticles, temperature, and shear rate were found to be the major input factors. In comparison to Decision Trees (DT) and Support Vector Regression (SVR), the ANFIS method model was more effective, yielding a Root Mean Square Error (RMSE) of 1.0278. The Mean Squared Errors (MSE) for the DT and SVR models were 96.67% and 97.75% higher, respectively, compared to the ANFIS model. It was also discovered that the viscosity is higher at lower temperatures of 32.63° C and a maximal nanoparticle concentration of 1%. It reached 34.34 mPa.s. It may also be emphasized that hybrid nanofluids, such as those incorporating alumina-copper oxide nanoparticles, exhibit lower viscosities at elevated temperatures compared to single-nanoparticle fluids, indicating their potential for optimizing heat transfer applications. It implies that they can be used to optimize the heat transfer application described in this paper. In conclusion, ANFIS is a powerful tool for predicting viscosity. The use of such instruments allows designers to create more effective, as well as environmentally friendly heat transfer systems. This study is, therefore, another example of ``green engineering'' solutions.

First Page

40

Last Page

55

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Share

COinS