The use of neural networks for the prediction of the settlement of pad and one way strip footings on cone penetration test results

Settlement of cohesionless soils, the load is applied in a very short period of time occurs. Even if such a saturated soils, a portion of the water leaking out of gaps, due to the high permeability occur as soon as possible. Grained soils are very difficult to get the sample of undisturbed soils, predictions are calculated with the in situ tests.In this study, artificial neural networks (ANNs) were used to predict the settlement of a single or pad footing and one-way strip footings. For this purpose, a computer programme was developed in the Matlab programming environment to calculate the settlement of foundations from two traditional settlement prediction methods, such as Schmertmann (1978) and Terzaghi (1996). In this programme, the footing geometry (L and B), the footing embedment depth, Df, the bulk unit weight, ?n, of the cohesionless soil, the footing applied pressure, Qk, and cone penetration test avarage result, Qcort, varied during the settlement analysis and the settlement value of each pad footing and one-way strip footing was calculated for each method. Then, an ANN model was developed for each traditional method to predict the settlement. The settlement values predicted from the ANN model were compared with the settlement values calculated from the traditional method for performance of the ANN models.The predicted values were found to be quite close to the calculated values. In addition, several performance indices such as determination coefficient (R2), variance account for (VAF), mean absolute error (MAE), and root mean square error (RMSE) were calculated to check the prediction capacity of the ANN models. According to performance analysis, ANN models developed have realistic estimation results and the ANN models can be used at the preliminary stage of designing pad and one-way strip footings on cohesionless soils. Sensitivity analyses were also carried out to examine the relative importance of the factors affecting settlement prediction.