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.
Keywords:
miscellaneous fill, dynamic compaction, vibration velocity, BP neural network, Sobol sensitivity analysisPublished Online
How to Cite
Issue
Section
License
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (see The Effect of Open Access). As soon as the paper is accepted, finally submitted and edited, the paper will appear in the "OnlineFirst" page of the journal, thus from this point no other internet-based publication is necessary.

