Comparison of <i>MLR</i>, <i>MNLR,</i> and <i>ANN</i> Models for Estimation of Young’s Modulus (<i>E</i><sub>50</sub>) and Poisson’s Ratio (<i>υ</i>) of Rock Materials Using Non-Destructive Measurement Methods
In this study, the static <i>E</i><sub>50</sub> and <i>υ</i> parameters of rock materials were investigated using <i>P-S</i> wave velocities and Shore hardness (<i>SH</i>), using non-destructive measurement methods. In this study, the multi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-09-01
|
| Series: | Mining |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-6489/4/3/36 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In this study, the static <i>E</i><sub>50</sub> and <i>υ</i> parameters of rock materials were investigated using <i>P-S</i> wave velocities and Shore hardness (<i>SH</i>), using non-destructive measurement methods. In this study, the multiple linear regression (<i>MLR</i>), multiple non-linear regression (<i>MNLR</i>), and artificial neural network (<i>ANN</i>) models were used to estimate and determine the static <i>E</i><sub>50</sub> and <i>υ</i> parameters. When comparing the models defined by <i>MLR</i>, <i>MNLR</i>, and <i>ANN</i> to the <i>R</i><sup>2</sup> values, it was found that the <i>ANN</i> models, which estimate the <i>E</i><sub>50</sub> and <i>υ</i> parameters of rock materials using non-destructive methods (<i>V<sub>p</sub></i>, <i>V<sub>s</sub></i>, <i>V<sub>p</sub></i>/<i>V<sub>s</sub></i>, <i>ρ<sub>d</sub></i>, and <i>SH</i>), achieved higher accuracy than the <i>MLR</i> and <i>MNLR</i> models. The originality of this study is rooted in the fact that ores such as galena, chromite, and barite were studied for the first time from a rock mechanics perspective, providing an innovative viewpoint. In addition, the use of all non-destructive measurement methods, <i>V<sub>p</sub></i>, <i>V<sub>s</sub></i>, and Shore hardness tests, also increases the importance of the study findings. |
|---|---|
| ISSN: | 2673-6489 |