Predictive Deep Neural Network Modeling of Sisko Nanofluid Transport in Peristaltic Flow System.
Saved in:
| Title: | Predictive Deep Neural Network Modeling of Sisko Nanofluid Transport in Peristaltic Flow System. |
|---|---|
| Authors: | Ishaq, Muhammad1 (AUTHOR) rashidishaq938@gmail.com, Ashraf, Muhammad Bilal1 (AUTHOR) |
| Source: | ZAMM -- Journal of Applied Mathematics & Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik. May2026, Vol. 106 Issue 5, p1-20. 20p. |
| Subjects: | Artificial neural networks, Nanofluids, Microfluidics, Magnetic field effects, Prediction models, Fluid flow, Biomedical engineering |
| Abstract: | This study is an analysis of irreversibility using an artificial neural network (ANN) for irreversible irreversibility in Sisko nanofluid flow through a peristaltic channel in the presence of magnetic field, motile micro‐organisms, and slip effects. The problem of the governing nonlinear partial differential equations is reduced to a set of ordinary differential equations by using the lubrication approximation along with the Debye–Hueckel transformation with suitable nondimensional variables. The resultant dimensionless ordinary differential equations are solved numerically by using the NDSolve routine to obtain the accurate numerical profiles of velocity, temperature, concentration, and bioconvection fields. These numerically computed solutions are used to create the datasets, which are used to train the ANN model. The ANN is implemented in Python with the ready‐made library TensorFlow 2.17.0, the network is built with one input layer, two hidden layers (each layer consisted of 64 neurons), and one output layer. A sigmoid activation function is used in the hidden layer, and an Adam optimizer is used for training models. Performance indicators such as the mean square error (MSE), root mean square error (RMSE), regression coefficient (R2$R^2$), error histogram, gradient, and relative error are examined in order to analyze the prediction ability of the network. The results show that the ANN gives high accuracy in the learning and prediction of the numerically obtained velocity, thermal, concentration, and bioconvection profiles. Furthermore, the results shown in the analysis indicate that the magnetic field parameter and Eckert number have a significant effect on the thermal profile while the velocity profile is highly affected by the magnetic field. The results of this work have implications for biomedical engineering applications involving transport in microfluidic systems and targeted drug delivery, and also hold potential relevance for processes in environmental engineering. [ABSTRACT FROM AUTHOR] |
| Copyright of ZAMM -- Journal of Applied Mathematics & Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 194139270 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Predictive Deep Neural Network Modeling of Sisko Nanofluid Transport in Peristaltic Flow System. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Ishaq%2C+Muhammad%22">Ishaq, Muhammad</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> rashidishaq938@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Ashraf%2C+Muhammad+Bilal%22">Ashraf, Muhammad Bilal</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22ZAMM+--+Journal+of+Applied+Mathematics+%26+Mechanics+%2F+Zeitschrift+für+Angewandte+Mathematik+und+Mechanik%22">ZAMM -- Journal of Applied Mathematics & Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik</searchLink>. May2026, Vol. 106 Issue 5, p1-20. 20p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Nanofluids%22">Nanofluids</searchLink><br /><searchLink fieldCode="DE" term="%22Microfluidics%22">Microfluidics</searchLink><br /><searchLink fieldCode="DE" term="%22Magnetic+field+effects%22">Magnetic field effects</searchLink><br /><searchLink fieldCode="DE" term="%22Prediction+models%22">Prediction models</searchLink><br /><searchLink fieldCode="DE" term="%22Fluid+flow%22">Fluid flow</searchLink><br /><searchLink fieldCode="DE" term="%22Biomedical+engineering%22">Biomedical engineering</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: This study is an analysis of irreversibility using an artificial neural network (ANN) for irreversible irreversibility in Sisko nanofluid flow through a peristaltic channel in the presence of magnetic field, motile micro‐organisms, and slip effects. The problem of the governing nonlinear partial differential equations is reduced to a set of ordinary differential equations by using the lubrication approximation along with the Debye–Hueckel transformation with suitable nondimensional variables. The resultant dimensionless ordinary differential equations are solved numerically by using the NDSolve routine to obtain the accurate numerical profiles of velocity, temperature, concentration, and bioconvection fields. These numerically computed solutions are used to create the datasets, which are used to train the ANN model. The ANN is implemented in Python with the ready‐made library TensorFlow 2.17.0, the network is built with one input layer, two hidden layers (each layer consisted of 64 neurons), and one output layer. A sigmoid activation function is used in the hidden layer, and an Adam optimizer is used for training models. Performance indicators such as the mean square error (MSE), root mean square error (RMSE), regression coefficient (R2$R^2$), error histogram, gradient, and relative error are examined in order to analyze the prediction ability of the network. The results show that the ANN gives high accuracy in the learning and prediction of the numerically obtained velocity, thermal, concentration, and bioconvection profiles. Furthermore, the results shown in the analysis indicate that the magnetic field parameter and Eckert number have a significant effect on the thermal profile while the velocity profile is highly affected by the magnetic field. The results of this work have implications for biomedical engineering applications involving transport in microfluidic systems and targeted drug delivery, and also hold potential relevance for processes in environmental engineering. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of ZAMM -- Journal of Applied Mathematics & Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194139270 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1002/zamm.70444 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 20 StartPage: 1 Subjects: – SubjectFull: Artificial neural networks Type: general – SubjectFull: Nanofluids Type: general – SubjectFull: Microfluidics Type: general – SubjectFull: Magnetic field effects Type: general – SubjectFull: Prediction models Type: general – SubjectFull: Fluid flow Type: general – SubjectFull: Biomedical engineering Type: general Titles: – TitleFull: Predictive Deep Neural Network Modeling of Sisko Nanofluid Transport in Peristaltic Flow System. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Ishaq, Muhammad – PersonEntity: Name: NameFull: Ashraf, Muhammad Bilal IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 05 Text: May2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 00442267 Numbering: – Type: volume Value: 106 – Type: issue Value: 5 Titles: – TitleFull: ZAMM -- Journal of Applied Mathematics & Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik Type: main |
| ResultId | 1 |
