Application of Non-Destructive Test Results to Estimate Rock Mechanical Characteristics—A Case Study
Accurately determining rock elastic modulus (EM) and uniaxial compressive strength (UCS) using laboratory methods requires considerable time and cost. Hence, the development of models for estimating the mechanical properties of rock is a very attractive alternative. The current research was conducte...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Minerals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-163X/13/4/472 |
| _version_ | 1797604153410715648 |
|---|---|
| author | Zhichun Fang Jafar Qajar Kosar Safari Saeedeh Hosseini Mohammad Khajehzadeh Moncef L. Nehdi |
| author_facet | Zhichun Fang Jafar Qajar Kosar Safari Saeedeh Hosseini Mohammad Khajehzadeh Moncef L. Nehdi |
| author_sort | Zhichun Fang |
| collection | DOAJ |
| description | Accurately determining rock elastic modulus (EM) and uniaxial compressive strength (UCS) using laboratory methods requires considerable time and cost. Hence, the development of models for estimating the mechanical properties of rock is a very attractive alternative. The current research was conducted to predict the UCS and EM of sandstone rocks using quartz%, feldspar%, fragments%, compressional wave velocity (PW), the Schmidt hardness number (SN), porosity, density, and water absorption via simple regression, multivariate regression (MVR), K-nearest neighbor (KNN), support vector regression (SVR) with a radial basis function, the adaptive neuro-fuzzy inference system (ANFIS) using the Gaussian membership (GM) function, and the back-propagation neural network (BPNN) based on various training algorithms. The samples were categorized as litharenite and feldspathic litharenite. By increasing the feldspar% and quartz% and decreasing the fragments%, the static properties increased. The results of the statistical analysis showed that the SN and porosity have the greatest effect on the UCS and EM, respectively. Among the Levenberg–Marquardt (LM), Bayesian regularization, and Scaled Conjugate Gradient training algorithms using the BPNN method, the LM achieved the best results in forecasting the UCS and EM. The ideal obtained BPNN, using a trial-and-error process, contains four neurons in a hidden layer with eight inputs. All five models attained acceptable accuracy (correlation coefficient greater than 70%) for estimating the static properties. By comparing the methods, the ANFIS showed higher precision than the other methods. The UCS and EM of the samples can be determined with very high accuracy (R<sup>2</sup> > 99%). |
| first_indexed | 2024-03-11T04:42:20Z |
| format | Article |
| id | doaj.art-2edee47e0f074dc8a3b6775ee2c03d2a |
| institution | Directory Open Access Journal |
| issn | 2075-163X |
| language | English |
| last_indexed | 2024-03-11T04:42:20Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Minerals |
| spelling | doaj.art-2edee47e0f074dc8a3b6775ee2c03d2a2023-11-17T20:35:09ZengMDPI AGMinerals2075-163X2023-03-0113447210.3390/min13040472Application of Non-Destructive Test Results to Estimate Rock Mechanical Characteristics—A Case StudyZhichun Fang0Jafar Qajar1Kosar Safari2Saeedeh Hosseini3Mohammad Khajehzadeh4Moncef L. Nehdi5State Key Laboratory of Mechanical Behavior and System Safety of Traffic Engineering Structures, Shijiazhuang Tiedao University, Shijiazhuang 050043, ChinaSchool of Chemical and Petroleum Engineering, Shiraz University, Shiraz 71557-13876, IranDepartment of Aerospace Engineering, Khaje Nasir Toosi University of Technology, Tehran 16569-83911, IranDepartment of Geology, Payame Noor University, Tehran 19395-3697, IranDepartment of Civil Engineering, Anar Branch, Islamic Azad University, Anar 77419-88706, IranDepartment of Civil Engineering, McMaster University, Hamilton, ON L8S 4M6, CanadaAccurately determining rock elastic modulus (EM) and uniaxial compressive strength (UCS) using laboratory methods requires considerable time and cost. Hence, the development of models for estimating the mechanical properties of rock is a very attractive alternative. The current research was conducted to predict the UCS and EM of sandstone rocks using quartz%, feldspar%, fragments%, compressional wave velocity (PW), the Schmidt hardness number (SN), porosity, density, and water absorption via simple regression, multivariate regression (MVR), K-nearest neighbor (KNN), support vector regression (SVR) with a radial basis function, the adaptive neuro-fuzzy inference system (ANFIS) using the Gaussian membership (GM) function, and the back-propagation neural network (BPNN) based on various training algorithms. The samples were categorized as litharenite and feldspathic litharenite. By increasing the feldspar% and quartz% and decreasing the fragments%, the static properties increased. The results of the statistical analysis showed that the SN and porosity have the greatest effect on the UCS and EM, respectively. Among the Levenberg–Marquardt (LM), Bayesian regularization, and Scaled Conjugate Gradient training algorithms using the BPNN method, the LM achieved the best results in forecasting the UCS and EM. The ideal obtained BPNN, using a trial-and-error process, contains four neurons in a hidden layer with eight inputs. All five models attained acceptable accuracy (correlation coefficient greater than 70%) for estimating the static properties. By comparing the methods, the ANFIS showed higher precision than the other methods. The UCS and EM of the samples can be determined with very high accuracy (R<sup>2</sup> > 99%).https://www.mdpi.com/2075-163X/13/4/472sandstone rocksmineralogymechanical propertiesmachine learningstatistical analysis |
| spellingShingle | Zhichun Fang Jafar Qajar Kosar Safari Saeedeh Hosseini Mohammad Khajehzadeh Moncef L. Nehdi Application of Non-Destructive Test Results to Estimate Rock Mechanical Characteristics—A Case Study Minerals sandstone rocks mineralogy mechanical properties machine learning statistical analysis |
| title | Application of Non-Destructive Test Results to Estimate Rock Mechanical Characteristics—A Case Study |
| title_full | Application of Non-Destructive Test Results to Estimate Rock Mechanical Characteristics—A Case Study |
| title_fullStr | Application of Non-Destructive Test Results to Estimate Rock Mechanical Characteristics—A Case Study |
| title_full_unstemmed | Application of Non-Destructive Test Results to Estimate Rock Mechanical Characteristics—A Case Study |
| title_short | Application of Non-Destructive Test Results to Estimate Rock Mechanical Characteristics—A Case Study |
| title_sort | application of non destructive test results to estimate rock mechanical characteristics a case study |
| topic | sandstone rocks mineralogy mechanical properties machine learning statistical analysis |
| url | https://www.mdpi.com/2075-163X/13/4/472 |
| work_keys_str_mv | AT zhichunfang applicationofnondestructivetestresultstoestimaterockmechanicalcharacteristicsacasestudy AT jafarqajar applicationofnondestructivetestresultstoestimaterockmechanicalcharacteristicsacasestudy AT kosarsafari applicationofnondestructivetestresultstoestimaterockmechanicalcharacteristicsacasestudy AT saeedehhosseini applicationofnondestructivetestresultstoestimaterockmechanicalcharacteristicsacasestudy AT mohammadkhajehzadeh applicationofnondestructivetestresultstoestimaterockmechanicalcharacteristicsacasestudy AT monceflnehdi applicationofnondestructivetestresultstoestimaterockmechanicalcharacteristicsacasestudy |