A Framework for Determining the Optimal Vibratory Frequency of Graded Gravel Fillers Using Hammering Modal Approach and ANN

To address the uncertainty of optimal vibratory frequency of high-speed railway graded gravel ( ) and achieve high-precision prediction of the , the following research was conducted. Firstly, commencing with vibratory compaction experiments and the hammering modal analysis method, the resonance frequency of fillers, varying in compactness , was initially determined. The correlation between and was revealed through vibratory compaction experiments conducted at different vibratory frequencies. This correlation was established based on the compaction physical-mechanical properties of fillers, encompassing maximum dry density , stiffness , and bearing capacity coefficient . Secondly, the gray relational analysis algorithm was used to determine the key feature influencing the based on the quantified relationship between the filler feature and . Finally, the key features influencing the were used as input parameters to establish the artificial neural network prediction model ( ) for . The predictive performance of was evaluated from the ablation study, prediction accuracy, and prediction error. The results showed that the , , and all obtained optimal states when was set as for different gradation fillers. Furthermore, it was found that the key features influencing the were determined to be the maximum particle diameter , gradation parameters and , flat and elongated particles in coarse aggregate , and the Los Angeles abrasion of coarse aggregate . Among them, the influence of on the predictive performance was the most significant. On the training and testing sets, the goodness-of-fit of all exceeded 0.95, and the prediction errors were small, which indicated that the accuracy of predictions was relatively high. In addition, it was clear that the exhibited excellent robust performance. The research results provide a novel method for determining the of subgrade fillers and provide theoretical guidance for the intelligent construction of high-speed railway subgrades.