Selection of suitable backcalculation technique and prediction of laboratory resilient modulus from NDT devices

This study aims to analyse the backcalculated cohesive subgrade moduli using various backcalculation approaches. A series of in situ and laboratory investigations have been carried out on 190 test locations from 30 pavement sections of cohesive soils using Falling Weight Deflectometer (FWD), Light Weight Deflectometer (LWD), and Repeated Load Triaxial to determine backcalculated resilient moduli (M-R_back), composite resilient moduli (M-R_comp), and laboratory resilient modulus (M-R_lab). The comparative analysis was performed for M-R_back by LWD (M-R_back_LWD), M-R_comp by LWD on subgrade (M-R_comp_LWD), and M-R_back by FWD (M-R_back_FWD) with M-R_lab values to assess the level of agreement. M-R_back_FWD and M-R_back_LWD values of different soils by using Artificial Neural Network and Support Vector Machine techniques have shown the mean percentage variation (1.16-59.63%), correlation in terms of R-2 value (0.628-0.824), and RMSE value (0.51-20.49%) with M-R_lab values. In contrast, M-R_comp_LWD values have shown good agreement with M-R_lab values among M-R_back_LWD and M-R_comp_LWD. This study also suggested adjustment factors (0.308-0.974) for predicting M-R_lab values from M-R_back_FWD and M-R_back_LWD for cohesive soils. Thus, this study recommends an appropriate backcalculation technique and suggests adjustment factors to the cohesive type of soils for realistic prediction of resilient characteristics of subgrade.