PREDICTION OF CBR VALUE OF COARSE GRAINED SOILS BY SOFT COMPUTING TECHNIQUES

Abstract

To overcome this situation, it is appreciable to predict CBR value of subgrade soil with simple properties of soils such as index properties which include grain size analysis (% Gravel, % Sand, % Fines), Liquid Limit (LL), and  Maximum Dry Density (MDD) and Optimum Moisture Content (OMC) from Modified Compaction test. This paper presents the application of Artificial Neural Network (ANN) and Multiple Regression Analysis (MLR) to estimate California Bearing Ratio (CBR) of coarse grained soils. The prediction models were developed to correlate CBR with properties of soil viz. optimum moisture content and maximum dry density, (OMC and MDD from modified proctor compaction test), liquid limit (LL), and Coarse fraction. Out of total Fifty four soil data sets, 38 were used for training and 16 were used for testing. It was observed that prediction of CBR from the properties of soil was better through ANN than MLR. The performance of the developed ANN model has been validated by actual laboratory tests and a good correlation of 0.89 was obtained.