Md Munirul, Hasan and Md Mustafizur, Rahman and Suraya, Abu Bakar and Kabir, Muhammad Nomani and Ramasamy, Devarajan and A. H. M., Saifullah Sadi (2025) Performance evaluation of various training functions using ANN to predict the thermal conductivity of EG/water-based GNP/CNC hybrid nanofluid for heat transfer application. Journal of Thermal Analysis and Calorimetry, 150 (3). pp. 1907-1932. ISSN 1388-6150. (Published)
![[img]](http://umpir.ump.edu.my/style/images/fileicons/other.png) |
Pdf
Performance evaluation of various training functions using ANN.pdf Restricted to Repository staff only Download (4MB) | Request a copy |
Abstract
Thermal management efciency is still a signifcant problem in many industries and techniques due to the ultimate limitations in the performance of conventional heat transfer fuids. The present research focuses on predicting the thermophysical properties of hybrid graphene nanoplatelet (GNP) and cellulose nanocrystal (CNC) nanoparticles to improve the thermal performance of heat transfer systems. Resolving the thermal management issues can be critical for saving energy, enhancing the efectiveness of the systems, and advancing the existing and emerging technologies needed to handle high temperatures. GNP-CNC/ethylene glycol–water hybrid nanofuids were prepared in volume concentrations from 0.01 to 0.2%. Thermal conductivity was measured from 30 to 80 °C, providing comprehensive data for analysis. The most important resolution was formulated at 0.1% volume concentration within a 60:40 volume ratio of ethylene glycol and water, with UV–Vis analysis showing absorption peaks in the highest order at 0.10% and 0.2% concentrations. Thermogravimetric analysis has shown an increase towards thermal resilience, with the mass decline beginning at 130 °C and full degradation at 500 °C. An interesting observation was invested for 0.20% GNP: CNC, where the onset of degradation occurred at 150 °C, providing an increased variety of potential high temperatures. An artifcial neural network (ANN) model was implemented to predict thermal conductivity, and 15 training functions were examined for the ANN structure. The model's best prediction results were obtained by utilizing tansig and Purlin transfer functions in a single hidden layer with ten neurons, which employed the Bayesian regularization function. It reached R2=99.99%, MSE=4.8352× 10−7, and RMSE=1.2083× 10−3, which is superior to other functions, e.g. trainlm. The novelty is successfully synthesizing a stable GNP-CNC hybrid nanofuid with excellent thermophysical properties and establishing a highly accurate predictive model. The impact could be widespread in various industries, from better cooling to more efcient energy systems, and even the applicability of this efect in improving industrial processes.
| Item Type: | Article |
|---|---|
| Additional Information: | Indexed by Scopus |
| Uncontrolled Keywords: | Artificial neural network; BR; LM; Thermal conductivity; Training functions |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > TJ Mechanical engineering and machinery T Technology > TP Chemical technology |
| Faculty/Division: | Institute of Postgraduate Studies Faculty of Computing Faculty of Mechanical and Automotive Engineering Technology |
| Depositing User: | Mrs. Nurul Hamira Abd Razak |
| Date Deposited: | 16 Jun 2025 08:28 |
| Last Modified: | 16 Jun 2025 08:28 |
| URI: | http://umpir.ump.edu.my/id/eprint/44826 |
| Download Statistic: | View Download Statistics |
Actions (login required)
 |
View Item |