Predicting Maximum Dry Density, Optimum Moisture Content and California Bearing Ratio (CBR) Through Soil Index using Ordinary Least Squares (OLS) and Artificial Neural Networks (ANNS)
Ajalloeian Rassoul1, Kiani Mojtaba2
1Dr. Ajalloeian Rassoul, Department of Geology, The University, Isfahan, Geology, Isfahan Iran.
2Kiani Mojtaba, Department of Geology, The University, Isfahan, Geology, Isfahan Iran.
Manuscript received on 17 August 2015 | Revised Manuscript received on 25 August 2015 | Manuscript Published on 30 August 2015 | PP: 1-5 | Volume-5 Issue-3, August 2015 | Retrieval Number: C1770084314/15©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Soil compaction and California bearing Ratio (CBR) tests are the common methods in determining the bearing capacity of linear construction like roads, railroads and airfield pavement in designing the different layers of their select fill. Rapid access to the results of these tests contributes to the project management with respect to implementation, time and savings. Attempt is made here to estimate the maximum value of dry density (MDD), optimum moisture Content (OMC), soaked CBR (CBRS), un soaked CBR (CBRU) and swelling percentage through OLS and Multi-layer Perception network (MLP) of ANNS with respect to more common and simple tests which include percentage of organic content (OC), liquid limit (LL), plastic limit (PL), Percentage Passing No. 200 and No. 4 sieves. Also results obtained from the processed data indicate that the ANN method not only performs better than OLS but also provides acceptable and reliable outcomes with respect to the predicted objectives’ materialization.
Keywords: ANN, CBR, Maximum Dry Density, Optimum Moisture Content.
Scope of the Article: Artificial Intelligence