Prediction of Time of Capillary Rise in Porous Media Using Artificial Neural Network (ANN)
An Artificial Neural Network (ANN) was used to analyse the capillary rise in porous media. Wetting experiments were performed with fifteen liquids and fifteen different powders. The liquids covered a wide range of surface tension ( 15.45-71.99 mJ/m2 ) and viscosity (0.25-21 mPa.s). The powders...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Iranian Institute of Research and Development in Chemical Industries (IRDCI)-ACECR
2007-03-01
|
| Series: | Iranian Journal of Chemistry & Chemical Engineering |
| Subjects: | |
| Online Access: | http://www.ijcce.ac.ir/article_7843_c2fa35a6ea07d911cdbf2b6fa55b3076.pdf |
| _version_ | 1811284008608202752 |
|---|---|
| author | Samad Ahadian Siamak Moradian Farhad Sharif Mohammad Amani Tehran Mohsen Mohseni |
| author_facet | Samad Ahadian Siamak Moradian Farhad Sharif Mohammad Amani Tehran Mohsen Mohseni |
| author_sort | Samad Ahadian |
| collection | DOAJ |
| description | An Artificial Neural Network (ANN) was used to analyse the capillary rise in porous media. Wetting experiments were performed with fifteen liquids and fifteen different powders. The liquids covered a wide range of surface tension ( 15.45-71.99 mJ/m2 ) and viscosity (0.25-21 mPa.s). The powders also provided an acceptable range of particle size (0.012-45 μm) and surface free energy (25.54-63.90 mJ/m2). An artificial neural network was employed to predict the time of capillary rise for a known given height. The network's inputs were density, surface tension, and viscosity for the liquids and particle size, bulk density, packing density, and surface free energy for the powders. Two statistical parameters namely the product moment correlation coefficient (r2) and the performance factor (PF/3) were used to correlate the actual experimentally obtained times of capillary rise to: i) their equivalent values as predicted by a designed and trained artificial neural network; ii) their corresponding values as calculated by the Lucas-Washburn's equation as well as the equivalent values as calculated by its various other modified versions. It must be noted that for a perfect correlation r2=1 and PF/3=0. The results showed that only the present approach of artificial neural network was able to predict with superior accuracy (i.e. r2 = 0.91, PF/3=55) the time of capillary rise. The Lucas-Washburn's calculations gave the worst correlations (r2 = 0.11, PF/3 = 1016). Furthermore, some of the modifications of this equation as proposed by different workers did not seem to conspicuously improve the relationships giving a range of inferior correlations between the calculated and experimentally determined times of capillary rise (i.e. r2 = 0.24 to 0.44, PF/3 = 129 to 293). |
| first_indexed | 2024-04-13T02:22:11Z |
| format | Article |
| id | doaj.art-abe9c8a09503477f870837c5fdcfaf08 |
| institution | Directory Open Access Journal |
| issn | 1021-9986 1021-9986 |
| language | English |
| last_indexed | 2024-04-13T02:22:11Z |
| publishDate | 2007-03-01 |
| publisher | Iranian Institute of Research and Development in Chemical Industries (IRDCI)-ACECR |
| record_format | Article |
| series | Iranian Journal of Chemistry & Chemical Engineering |
| spelling | doaj.art-abe9c8a09503477f870837c5fdcfaf082022-12-22T03:06:55ZengIranian Institute of Research and Development in Chemical Industries (IRDCI)-ACECRIranian Journal of Chemistry & Chemical Engineering1021-99861021-99862007-03-0126171837843Prediction of Time of Capillary Rise in Porous Media Using Artificial Neural Network (ANN)Samad Ahadian0Siamak Moradian1Farhad Sharif2Mohammad Amani Tehran3Mohsen Mohseni4Department of Polymer and Color Engineering, Amirkabir University of Technology, P. O. Box 15875-4413 Tehran, I.R. IRANDepartment of Polymer and Color Engineering, Amirkabir University of Technology, P. O. Box 15875-4413 Tehran, I.R. IRANDepartment of Polymer and Color Engineering, Amirkabir University of Technology, P. O. Box 15875-4413 Tehran, I.R. IRANDepartment of Textile Engineering, Amirkabir University of Technology, P. O. Box 15875-4413 Tehran, I.R. IRANDepartment of Polymer and Color Engineering, Amirkabir University of Technology, P. O. Box 15875-4413 Tehran, I.R. IRANAn Artificial Neural Network (ANN) was used to analyse the capillary rise in porous media. Wetting experiments were performed with fifteen liquids and fifteen different powders. The liquids covered a wide range of surface tension ( 15.45-71.99 mJ/m2 ) and viscosity (0.25-21 mPa.s). The powders also provided an acceptable range of particle size (0.012-45 μm) and surface free energy (25.54-63.90 mJ/m2). An artificial neural network was employed to predict the time of capillary rise for a known given height. The network's inputs were density, surface tension, and viscosity for the liquids and particle size, bulk density, packing density, and surface free energy for the powders. Two statistical parameters namely the product moment correlation coefficient (r2) and the performance factor (PF/3) were used to correlate the actual experimentally obtained times of capillary rise to: i) their equivalent values as predicted by a designed and trained artificial neural network; ii) their corresponding values as calculated by the Lucas-Washburn's equation as well as the equivalent values as calculated by its various other modified versions. It must be noted that for a perfect correlation r2=1 and PF/3=0. The results showed that only the present approach of artificial neural network was able to predict with superior accuracy (i.e. r2 = 0.91, PF/3=55) the time of capillary rise. The Lucas-Washburn's calculations gave the worst correlations (r2 = 0.11, PF/3 = 1016). Furthermore, some of the modifications of this equation as proposed by different workers did not seem to conspicuously improve the relationships giving a range of inferior correlations between the calculated and experimentally determined times of capillary rise (i.e. r2 = 0.24 to 0.44, PF/3 = 129 to 293).http://www.ijcce.ac.ir/article_7843_c2fa35a6ea07d911cdbf2b6fa55b3076.pdfimbibitionporous medialucas-washburn's equationartificial neural network (ann)time prediction of capillary rise |
| spellingShingle | Samad Ahadian Siamak Moradian Farhad Sharif Mohammad Amani Tehran Mohsen Mohseni Prediction of Time of Capillary Rise in Porous Media Using Artificial Neural Network (ANN) Iranian Journal of Chemistry & Chemical Engineering imbibition porous media lucas-washburn's equation artificial neural network (ann) time prediction of capillary rise |
| title | Prediction of Time of Capillary Rise in Porous Media Using Artificial Neural Network (ANN) |
| title_full | Prediction of Time of Capillary Rise in Porous Media Using Artificial Neural Network (ANN) |
| title_fullStr | Prediction of Time of Capillary Rise in Porous Media Using Artificial Neural Network (ANN) |
| title_full_unstemmed | Prediction of Time of Capillary Rise in Porous Media Using Artificial Neural Network (ANN) |
| title_short | Prediction of Time of Capillary Rise in Porous Media Using Artificial Neural Network (ANN) |
| title_sort | prediction of time of capillary rise in porous media using artificial neural network ann |
| topic | imbibition porous media lucas-washburn's equation artificial neural network (ann) time prediction of capillary rise |
| url | http://www.ijcce.ac.ir/article_7843_c2fa35a6ea07d911cdbf2b6fa55b3076.pdf |
| work_keys_str_mv | AT samadahadian predictionoftimeofcapillaryriseinporousmediausingartificialneuralnetworkann AT siamakmoradian predictionoftimeofcapillaryriseinporousmediausingartificialneuralnetworkann AT farhadsharif predictionoftimeofcapillaryriseinporousmediausingartificialneuralnetworkann AT mohammadamanitehran predictionoftimeofcapillaryriseinporousmediausingartificialneuralnetworkann AT mohsenmohseni predictionoftimeofcapillaryriseinporousmediausingartificialneuralnetworkann |