Preliminary feasibility study on using a nano-composition in enhanced oil recovery process: neural network modeling

• Published in: Neural computing & applications Vol. 33; no. 16; pp. 10111 - 10127
• Main Authors: Hemmat Esfe, Mohammad, Saedodin, Seyfolah, Bahiraei, Mehdi, Esfandeh, Saeed
• Format: Journal Article
• Language: English
• Published: London Springer London 01.08.2021; Springer Nature B.V
• Subjects: Artificial Intelligence; Artificial neural networks; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Enhanced oil recovery; Feasibility studies; Image Processing and Computer Vision; Nanomaterials; Nanoparticles; Neural networks; Original Article; Probability and Statistics in Computer Science; Reduction; Response surface methodology; Rheological properties; Titanium dioxide; Viscosity; Hybrid nano-oil; Artificial neural network; Response surface methodology; Enhanced oil recovery
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-021-05775-4

In the present work, a 5W50 oil as an oil and petroleum derivative is used to check its viscosity behavior after adding nano-compositions to it. Viscosity reduction in an oil derivative after adding a specific mixture of nanomaterials is a trump card in the enhanced oil recovery process. So, a composition of MWCNT and TiO 2 nanoparticles with the composition ratio of 2/3 is added to the mentioned oil derivative. Interestingly, a 15% reduction in the viscosity in comparison with the pure oil is observed at a temperature of 45 °C and a concentration of 0.05%. The more viscosity reduction will result in a more significant oil recovery. Hence, satisfactory results of viscosity behavior at 45 °C could keep the scientific groups hopeful to have more viscosity reduction at higher temperatures and especially at oil well temperature. The selected solid volume fraction of 0.05%, as the lowest studied amount, makes the proposed composition more economic and reasonable. The suitable performance of the introduced nano-composition encouraged the present research group to predict its rheological behavior by using the response surface method and artificial neural network.