Prediction of CBR Value of Fine Grained Soils of Bengal Basin by Genetic Expression Programming, Artificial Neural Network and Krigging Method

For designing of pavements, California Bearing Ratio (CBR) value is an important parameter which is used to determine the strength of the subgrade soils. However, it is to be mentioned that, CBR test is tedious and laborious. Thus, in the present paper an attempt has been made to develop relationshi...

Full description

Saved in:
Bibliographic Details
Published inJournal of the Geological Society of India Vol. 95; no. 2; pp. 190 - 196
Main Authors Alam, Sk Kamrul, Mondal, Abhijit, Shiuly, Amit
Format Journal Article
LanguageEnglish
Published New Delhi Geological Society of India 01.02.2020
Springer Nature B.V
Subjects
Alluvial soils
Artificial neural networks
California bearing ratio
Dry density
Earth and Environmental Science
Earth Sciences
Fine-grained soils
Geology
Hydrogeology
Mathematical analysis
Moisture content
Neural networks
Optimization
Penetration tests
Plastic limit
Properties
Soil
Soil density
Soil moisture
Soil properties
Soil strength
Specific gravity
Water content
Online AccessGet full text

Cover

More Information
Summary:For designing of pavements, California Bearing Ratio (CBR) value is an important parameter which is used to determine the strength of the subgrade soils. However, it is to be mentioned that, CBR test is tedious and laborious. Thus, in the present paper an attempt has been made to develop relationships between CBR and various soil index properties such as specific gravity (G), coefficient of uniformity (Cu), coefficient of curvature (Cc), liquid limit (LL), plastic limit (PL), plasticity index (PI), optimum moisture content (OMC) and maximum dry density (MDD) for alluvial soil in West Bengal, India. Empirical relationships have been proposed for both soaked and un-soaked CBR values as a function of these soil index properties by Genetic Expression Programing (GEP). Further, the same index properties have been used to predict CBR values by artificial neural network (ANN) and krigging method. The results clearly reveals that the GEP and ANN and krigging methods can be successfully used for predicting both the soaked and un-soaked CBR values by using the index properties of soil. Moreover, the developed relationships have been compared with the past available relationships. Furthermore, a multi objective optimization has been carried out for getting maximum CBR values.
ISSN:0016-7622
0974-6889
DOI:10.1007/s12594-020-1409-0