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

• DOI: 10.3311/ppci.37967
• Publication Date: 2025-03-18T17:51:57Z
• Authors: Jianmin Zhu; Jianguo Zheng; Yongtang Yu; Baozhi Dong; Yuguo Wang; Weiwei Zhang

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