Mapping soil nail loads using Federal Highway Administration (FHWA) simplified models and artificial neural network technique

Abstract

This study compiles a broad database containing 312 measured maximum soil nail loads under operational conditions. The database is used to re-assess the prediction accuracies of the default Federal Highway Administration (FHWA) nail load model and its modified version previously reported in the literature. Predictions using the default and modified FHWA models are found to be highly dispersive. Moreover, the prediction accuracy is statistically dependent on the magnitudes of the predicted nail load and several model input parameters. The modified FHWA model is then recalibrated by introducing extra empirical terms to account for the influences of wall geometry, nail design configuration, and soil shear strength parameters on the evolvement of nail loads. The recalibrated FHWA model is demonstrated to have much better prediction accuracy compared to the default and modified models. Next, an artificial neural network (ANN) model is developed for mapping soil nail loads, which is shown to be the most advantageous one as it is accurate on average and the dispersion in prediction is low. The abovementioned dependency issue is also not present in the ANN model. The practical value of the ANN model is highlighted by applying it to reliability-based designs of soil nails against internal limit states.