Neural Network Modeling and Sensitivity Analysis of Factors Influencing Dynamic Compaction Vibration Velocity

Abstract

Dynamic compaction vibrations (DCV) cause significant environmental impacts. Quantifying key influencing factors is essential for mitigation. This study examines how tamper radius, tamping energy, tamping times, and tamping settlement affect DCV velocity (4000-25000 kN·m energy range) in a miscellaneous fill site. A BP neural network model was developed with these four parameters as inputs and vibration velocity as output, and the influence of each factor on vibration velocity was evaluated in combination with Sobol sensitivity analysis. The results show that Vibration velocity and tamper radius follow a negative exponential power function relationship. 97% of total vibration attenuation occurs within a 60 m radius. Vibration velocity growth rate decelerates with increasing tamping energy. 98% of velocities are below 30 mm/s, demonstrating strong data clustering. With the increase of tamping times or tamping settlement, the vibration velocity first rises to the "peak point", and the peak point corresponds to 4-6 tamping times and tamping settlement at 0.68-0.82 m and 3.08-4.30 m, and then declines or stabilizes. The tamper radius is the main factor affecting the vibration velocity. Optimizing or controlling the tamper radius can significantly reduce the vibration of DCV. The influence of tamping settlement is second, and the tamping energy and tamping times have a smaller impact.