Abstract
ANN-based models for predicting tunnel blasting-induced peak particle velocity (PPV) were developed using 221 field-measured datasets collected from 5 different tunnels. Controllable, uncontrollable, and semi-controllable factors affecting PPV generation were employed in model development. The most reliable ANN-based models were transformed into user-friendly closed-form equations for easier reproduction and practical engineering applications. Variable importance analysis was performed to evaluate the impacts of predictor variables on tunnel blasting-induced PPV.
| Original language | English |
|---|---|
| Pages (from-to) | 2711-2737 |
| Number of pages | 27 |
| Journal | Rock Mechanics and Rock Engineering |
| Volume | 58 |
| Issue number | 3 |
| DOIs | |
| State | Published - 2025.03 |
Keywords
- Artificial neural networks
- Blasting-induced ground vibration
- Metaheuristic optimization
- Tunnel excavation
- Variable importance analysis
Quacquarelli Symonds(QS) Subject Topics
- Earth & Marine Sciences
- Engineering - Civil & Structural
- Geophysics
- Engineering - Petroleum
- Geology
- Engineering - Mineral & Mining
Fingerprint
Dive into the research topics of 'Blasting-Induced Ground Vibration Modeling in Tunnel Excavation: A Comparative Study of ANN, Hybrid ANNs, and Empirical Models'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver