Abstract
Three-point bending (TPB) tests were conducted on prismatic Nestos marble (Greece) specimens. The specimens were instrumented with piezoelectric sensors, and comprehensive recordings of acoustic emission (AE) signals were obtained. Machine learning in the form of artificial neural networks (ANNs) was then applied in an effort to investigate whether specimen load evolution can be predicted as a function of AE signals. A number of ANN models were developed, and the optimum model was selected based on the highest coefficient of determination (CoD) value as well as the lowest root mean square error (RMSE) value that was calculated for each model. The best performing ANN model exhibits accuracy above 99% with an RMSE value below 4%. It can be concluded that ANNs can potentially be applied to predict rock behavior under load especially when such loads lead to failure.
| Original language | English |
|---|---|
| Pages (from-to) | 2037-2045 |
| Number of pages | 9 |
| Journal | Mining, Metallurgy and Exploration |
| Volume | 39 |
| Issue number | 5 |
| DOIs | |
| State | Published - 2022 |
Bibliographical note
Publisher Copyright:© 2022, Society for Mining, Metallurgy & Exploration Inc.
Keywords
- Acoustic emission signals
- Artificial neural networks
- Improved b-value
- Load evolution prediction
- Three-point bending test
ASJC Scopus subject areas
- Control and Systems Engineering
- General Chemistry
- Geotechnical Engineering and Engineering Geology
- Mechanical Engineering
- Metals and Alloys
- Materials Chemistry