Comparison of MLR, MNLR, and ANN Models for Estimation of Young’s Modulus (E50) and Poisson’s Ratio (υ) of Rock Materials Using Non-Destructive Measurement Methods
Year: 2024
Type: article
Abstract: In this study, the determination of static E50 and υ parameters of rock materials was investigated using P-S wave velocities and Shore hardness (SH), non-destructive measurement methods. We used multiple linear regression (MLR), multiple non-linear regression (MNLR) and artificial neural network (ANN) models to estimate and determine these parameters. When the models defined by MLR, MNLR, and ANN were compared to the R2 values, ANN models that estimate E50 and υ parameters of rock materials using non-destructive methods (Vp, Vs, Vp/Vs, d, and SH) could be determined with higher accuracy than MLR and MNLR models. The study’s originality is based on the fact that ores such as galena, chromite, and barite have been studied for the first time on rock mechanics, and in this respect, it offers an innovative perspective. In addition, the use of all non-destructive measurement methods, Vp, Vs, and Shore hardness tests, also increases the originality of the study.
Source: Mining
Authors: Orcun Tugay Deniz, Vedat Deniz
Institutions: Montanuniversität Leoben, Hitit Üniversitesi
Language: English
Topic: Rock Mechanics and Modeling
Subfield: Mechanics of Materials
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,137
OpenAlex ID: W4402308111