Artificial Neural Networks Analysis of Treatment Process of Gypseous Soils
Artificial Neural Networks (ANNs) are used to relate the properties of gypseous soilsand evaluate the values of compression of soils under different conditions. Therefore, onelayerperception training using back propagation algorithm is used to assess the validity ofapplication of ANNs for modelling...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Unviversity of Technology- Iraq
2009-06-01
|
| Series: | Engineering and Technology Journal |
| Subjects: | |
| Online Access: | https://etj.uotechnology.edu.iq/article_37864_38fe5052ceafc407013c2e241fbecc64.pdf |
| _version_ | 1827358174805491712 |
|---|---|
| author | Mohammad M. Al-Ani Mohammad Y. Fattah Mahmoud T. A. Al-Lamy |
| author_facet | Mohammad M. Al-Ani Mohammad Y. Fattah Mahmoud T. A. Al-Lamy |
| author_sort | Mohammad M. Al-Ani |
| collection | DOAJ |
| description | Artificial Neural Networks (ANNs) are used to relate the properties of gypseous soilsand evaluate the values of compression of soils under different conditions. Therefore, onelayerperception training using back propagation algorithm is used to assess the validity ofapplication of ANNs for modelling the settlement ratio for wetting process, (S/B)w, and thesettlement ratio for soaking process, (S/B)s.It was found that ANNs have the ability to predict the compression of gypseous soildue to soaking, washing process with high degree of accuracy. Also, performance of ANNsshowed that one hidden layer with one hidden nodes is practically enough for the neuralnetwork analysis.The sensitivity analysis indicates that the viscosity and specific gravity have themost significant effect on the predicated settlement ratio and the density of injection materialand void ratio have moderate impact on the settlement ratio. The results also show that theinitial gypsum content, stress and time have the smallest impact on settlement ratio.It was concluded that the artificial neural networks (ANNs) have the ability topredict the settlement ratio for wetting process (S/B)w, and settlement ratio for soakingprocess (S/B)s of gypseous soil with high degree of accuracy. The equations obtained using(ANNs) for (S/B)w, and (S/B)s showed excellent correlation with experimental results wherethe coefficients of correlation are (0.9541) and (0.991), respectively. |
| first_indexed | 2024-03-08T06:06:57Z |
| format | Article |
| id | doaj.art-c77592d862ac4093840dd92c4546c2e9 |
| institution | Directory Open Access Journal |
| issn | 1681-6900 2412-0758 |
| language | English |
| last_indexed | 2024-03-08T06:06:57Z |
| publishDate | 2009-06-01 |
| publisher | Unviversity of Technology- Iraq |
| record_format | Article |
| series | Engineering and Technology Journal |
| spelling | doaj.art-c77592d862ac4093840dd92c4546c2e92024-02-04T17:49:27ZengUnviversity of Technology- IraqEngineering and Technology Journal1681-69002412-07582009-06-012791811183210.30684/etj.27.9.1337864Artificial Neural Networks Analysis of Treatment Process of Gypseous SoilsMohammad M. Al-AniMohammad Y. FattahMahmoud T. A. Al-LamyArtificial Neural Networks (ANNs) are used to relate the properties of gypseous soilsand evaluate the values of compression of soils under different conditions. Therefore, onelayerperception training using back propagation algorithm is used to assess the validity ofapplication of ANNs for modelling the settlement ratio for wetting process, (S/B)w, and thesettlement ratio for soaking process, (S/B)s.It was found that ANNs have the ability to predict the compression of gypseous soildue to soaking, washing process with high degree of accuracy. Also, performance of ANNsshowed that one hidden layer with one hidden nodes is practically enough for the neuralnetwork analysis.The sensitivity analysis indicates that the viscosity and specific gravity have themost significant effect on the predicated settlement ratio and the density of injection materialand void ratio have moderate impact on the settlement ratio. The results also show that theinitial gypsum content, stress and time have the smallest impact on settlement ratio.It was concluded that the artificial neural networks (ANNs) have the ability topredict the settlement ratio for wetting process (S/B)w, and settlement ratio for soakingprocess (S/B)s of gypseous soil with high degree of accuracy. The equations obtained using(ANNs) for (S/B)w, and (S/B)s showed excellent correlation with experimental results wherethe coefficients of correlation are (0.9541) and (0.991), respectively.https://etj.uotechnology.edu.iq/article_37864_38fe5052ceafc407013c2e241fbecc64.pdfgypseous soiltreatmentartificial neural network |
| spellingShingle | Mohammad M. Al-Ani Mohammad Y. Fattah Mahmoud T. A. Al-Lamy Artificial Neural Networks Analysis of Treatment Process of Gypseous Soils Engineering and Technology Journal gypseous soil treatment artificial neural network |
| title | Artificial Neural Networks Analysis of Treatment Process of Gypseous Soils |
| title_full | Artificial Neural Networks Analysis of Treatment Process of Gypseous Soils |
| title_fullStr | Artificial Neural Networks Analysis of Treatment Process of Gypseous Soils |
| title_full_unstemmed | Artificial Neural Networks Analysis of Treatment Process of Gypseous Soils |
| title_short | Artificial Neural Networks Analysis of Treatment Process of Gypseous Soils |
| title_sort | artificial neural networks analysis of treatment process of gypseous soils |
| topic | gypseous soil treatment artificial neural network |
| url | https://etj.uotechnology.edu.iq/article_37864_38fe5052ceafc407013c2e241fbecc64.pdf |
| work_keys_str_mv | AT mohammadmalani artificialneuralnetworksanalysisoftreatmentprocessofgypseoussoils AT mohammadyfattah artificialneuralnetworksanalysisoftreatmentprocessofgypseoussoils AT mahmoudtaallamy artificialneuralnetworksanalysisoftreatmentprocessofgypseoussoils |