Prediction of California bearing ratio of a black cotton soil stabilized with waste glass and eggshell powder using artificial neural network

The laboratory test process to determine the California bearing ratio (CBR) of black cotton soils
is not only overpriced but also time-consuming as well. Hence advanced prediction of CBR plays
a significant role as it is applicable in pavement design. The strength of soil or CBR can be
improved using eggshell and waste glass powder when they are mixed with the proper ratio. The
prediction of CBR of treated soil was executed by Artificial Neural Networks (ANNs) which is a
computational tool based on the properties of the biological neural systems. ANNs have been
used over the last few years in the modeling of different parameters. To observe CBR values,
combined eggshell and waste glass powder was added to soil as 2% ESP + 2% WGP, 4% ESP +
4% WGP, 6% ESP + 6% WGP, and 8% ESP + 8% WGP of the weights of the soil samples.
Accordingly, the necessary tests were conducted in order to get the required best model. From
the findings at 4%ESP +4%WGP dosage addition, the minimum LL, PL & PI were obtained as
53.95%, 40%, and 13.95 respectively. At the same percentage addition of ESP and WGP, the
minimum optimum moisture content and the maximum dry density were recorded as 23.37% and
1.62g/cm3 respectively. The maximum CBR value found as 5.8 at 4% ESP + 4% WGP addition.
This study evolved to develop a model that relates CBR values with index properties of black
cotton soil which is specific to a soil that is found in Addis Ababa Science and Technology
University. The model was developed using CBR as an output layer variable. CBR was
considered as a function of the joint effect of liquid limit, plastic limit, and plastic index,
optimum moisture content, and maximum dry density. 30 number of ANN architecture were
checked and the best model that has been found was ANN with 5, 6, and 1 neuron in the input,
hidden and output layer correspondingly. The performance of selected ANN has been 0.99996,
4.44E-05, 0.00353, and 0.0067 which are correlation coefficient (R), mean square error (MSE),
mean absolute error (MAE), and root mean square error (RMSE) respectively.