Assessment and calibration of two models for estimation of soil nail loads and system reliability analysis of soil nails against internal failures

This study first presents accuracy assessments of two default models proposed in two popular soil nail wall design specifications and their calibrated versions for estimation of maximum soil nail loads under operational conditions. The assessments are based on a general nail load database reported in the literature. Evaluation results showed that predictions using the default and calibrated models are unsatisfactory as the dispersions are high to extremely high. Simple calibration terms are introduced to the calibrated models for performance enhancement. The recalibrated models are shown to be accurate on average, and the prediction dispersions are significantly reduced. The model biases for the above six models are demonstrated to be lognormal random variables. Individual reliability-based designs for the nail pullout and nail-in-tension limit states using the six models are carried out. System reliability of nails against internal failures is also explored. The correlation between the two limit states is investigated, and its influences on system reliability evaluation are discussed. The practical value of model calibration is demonstrated as using the recalibrated models for nail designs leads to the most cost-effective design outcomes. This study represents a solid step toward development of reliability-based design framework for soil nail walls.