Application of machine learning in predicting the rate-dependent compressive strength of rocks
Accurate prediction of compressive strength of rocks relies on the rate-dependent behaviors of rocks, and correlation among the geometrical, physical, and mechanical properties of rocks. However, these properties may not be easy to control in laboratory experiments, particularly in dynamic compressi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-10-01
|
| Series: | Journal of Rock Mechanics and Geotechnical Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S167477552200049X |
| _version_ | 1798000207195013120 |
|---|---|
| author | Mingdong Wei Wenzhao Meng Feng Dai Wei Wu |
| author_facet | Mingdong Wei Wenzhao Meng Feng Dai Wei Wu |
| author_sort | Mingdong Wei |
| collection | DOAJ |
| description | Accurate prediction of compressive strength of rocks relies on the rate-dependent behaviors of rocks, and correlation among the geometrical, physical, and mechanical properties of rocks. However, these properties may not be easy to control in laboratory experiments, particularly in dynamic compression experiments. By training three machine learning models based on the support vector machine (SVM), back-propagation neural network (BPNN), and random forest (RF) algorithms, we isolated different input parameters, such as static compressive strength, P-wave velocity, specimen dimension, grain size, bulk density, and strain rate, to identify their importance in the strength prediction. Our results demonstrated that the RF algorithm shows a better performance than the other two algorithms. The strain rate is a key input parameter influencing the performance of these models, while the others (e.g. static compressive strength and P-wave velocity) are less important as their roles can be compensated by alternative parameters. The results also revealed that the effect of specimen dimension on the rock strength can be overshadowed at high strain rates, while the effect on the dynamic increase factor (i.e. the ratio of dynamic to static compressive strength) becomes significant. The dynamic increase factors for different specimen dimensions bifurcate when the strain rate reaches a relatively high value, a clue to improve our understanding of the transitional behaviors of rocks from low to high strain rates. |
| first_indexed | 2024-04-11T11:16:30Z |
| format | Article |
| id | doaj.art-ce8ceb5d790d45e883eb47d2dcfc21bb |
| institution | Directory Open Access Journal |
| issn | 1674-7755 |
| language | English |
| last_indexed | 2024-04-11T11:16:30Z |
| publishDate | 2022-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Rock Mechanics and Geotechnical Engineering |
| spelling | doaj.art-ce8ceb5d790d45e883eb47d2dcfc21bb2022-12-22T04:27:11ZengElsevierJournal of Rock Mechanics and Geotechnical Engineering1674-77552022-10-0114513561365Application of machine learning in predicting the rate-dependent compressive strength of rocksMingdong Wei0Wenzhao Meng1Feng Dai2Wei Wu3School of Civil and Environmental Engineering, Nanyang Technological University, SingaporeSchool of Civil and Environmental Engineering, Nanyang Technological University, SingaporeState Key Laboratory of Hydraulics and Mountain River Engineering, College of Water Resource and Hydropower, Sichuan University, Chengdu, 610065, ChinaSchool of Civil and Environmental Engineering, Nanyang Technological University, Singapore; Corresponding author.Accurate prediction of compressive strength of rocks relies on the rate-dependent behaviors of rocks, and correlation among the geometrical, physical, and mechanical properties of rocks. However, these properties may not be easy to control in laboratory experiments, particularly in dynamic compression experiments. By training three machine learning models based on the support vector machine (SVM), back-propagation neural network (BPNN), and random forest (RF) algorithms, we isolated different input parameters, such as static compressive strength, P-wave velocity, specimen dimension, grain size, bulk density, and strain rate, to identify their importance in the strength prediction. Our results demonstrated that the RF algorithm shows a better performance than the other two algorithms. The strain rate is a key input parameter influencing the performance of these models, while the others (e.g. static compressive strength and P-wave velocity) are less important as their roles can be compensated by alternative parameters. The results also revealed that the effect of specimen dimension on the rock strength can be overshadowed at high strain rates, while the effect on the dynamic increase factor (i.e. the ratio of dynamic to static compressive strength) becomes significant. The dynamic increase factors for different specimen dimensions bifurcate when the strain rate reaches a relatively high value, a clue to improve our understanding of the transitional behaviors of rocks from low to high strain rates.http://www.sciencedirect.com/science/article/pii/S167477552200049XMachine learningRock dynamicsCompressive strengthStrain rate |
| spellingShingle | Mingdong Wei Wenzhao Meng Feng Dai Wei Wu Application of machine learning in predicting the rate-dependent compressive strength of rocks Journal of Rock Mechanics and Geotechnical Engineering Machine learning Rock dynamics Compressive strength Strain rate |
| title | Application of machine learning in predicting the rate-dependent compressive strength of rocks |
| title_full | Application of machine learning in predicting the rate-dependent compressive strength of rocks |
| title_fullStr | Application of machine learning in predicting the rate-dependent compressive strength of rocks |
| title_full_unstemmed | Application of machine learning in predicting the rate-dependent compressive strength of rocks |
| title_short | Application of machine learning in predicting the rate-dependent compressive strength of rocks |
| title_sort | application of machine learning in predicting the rate dependent compressive strength of rocks |
| topic | Machine learning Rock dynamics Compressive strength Strain rate |
| url | http://www.sciencedirect.com/science/article/pii/S167477552200049X |
| work_keys_str_mv | AT mingdongwei applicationofmachinelearninginpredictingtheratedependentcompressivestrengthofrocks AT wenzhaomeng applicationofmachinelearninginpredictingtheratedependentcompressivestrengthofrocks AT fengdai applicationofmachinelearninginpredictingtheratedependentcompressivestrengthofrocks AT weiwu applicationofmachinelearninginpredictingtheratedependentcompressivestrengthofrocks |