Shear strength parameters prediction of rock materials using hybrid machine learning model.
Saved in:
| Title: | Shear strength parameters prediction of rock materials using hybrid machine learning model. |
|---|---|
| Authors: | Cheng, Yanhui1 (AUTHOR), He, Dongliang1 (AUTHOR), Liu, Hongwei2 (AUTHOR) liuhongweicsu@163.com, Wang, Guoxian3 (AUTHOR) |
| Source: | Nondestructive Testing & Evaluation. Feb2026, Vol. 41 Issue 2, p896-919. 24p. |
| Subjects: | Cohesion, Internal friction, Particle swarm optimization, Petrology, Shear strength, Rock properties, Ensemble learning, Artificial neural networks |
| Abstract: | Cohesion and internal friction angle are critical parameters for evaluating the suitability of stone. To build a reliable model to predict the cohesion and internal friction angle of rock, dataset containing 597 rock samples were collected and their petrological characteristics were investigated. In this study, artificial neural network (ANN) and particle swarm optimisation (PSO) algorithm are hybridised to establish a new hybrid machine learning (ML) model for predicting cohesion and internal friction angle based on petrological features. By comparing other five ML models, the efficiency of this model are assessed. Four statistical metrics such as correlation coefficient (R2) and root-mean-square error (RMSE) were used to evaluate the model. The results show that the hybridisation of ANN and PSO significantly improves the prediction and generalisation ability of the hybrid ML model. Compared with other models, this model was the most effective model for predicting cohesion and internal friction angle, with R2 value of 0.976 (Cohesion), 0.942 (Internal friction angle), RMSE of 0.697 (Cohesion), 0.935 (Internal friction angle). In addition, feature importance analysis showed that density and P-wave velocity were the most influential factors on cohesion, and uniaxial compressive strength, tensile strength and P-wave velocity were the most influential factors on internal friction angle. [ABSTRACT FROM AUTHOR] |
| Copyright of Nondestructive Testing & Evaluation is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 190955067 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Shear strength parameters prediction of rock materials using hybrid machine learning model. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Cheng%2C+Yanhui%22">Cheng, Yanhui</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22He%2C+Dongliang%22">He, Dongliang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Hongwei%22">Liu, Hongwei</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> liuhongweicsu@163.com</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Guoxian%22">Wang, Guoxian</searchLink><relatesTo>3</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Nondestructive+Testing+%26+Evaluation%22">Nondestructive Testing & Evaluation</searchLink>. Feb2026, Vol. 41 Issue 2, p896-919. 24p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Cohesion%22">Cohesion</searchLink><br /><searchLink fieldCode="DE" term="%22Internal+friction%22">Internal friction</searchLink><br /><searchLink fieldCode="DE" term="%22Particle+swarm+optimization%22">Particle swarm optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Petrology%22">Petrology</searchLink><br /><searchLink fieldCode="DE" term="%22Shear+strength%22">Shear strength</searchLink><br /><searchLink fieldCode="DE" term="%22Rock+properties%22">Rock properties</searchLink><br /><searchLink fieldCode="DE" term="%22Ensemble+learning%22">Ensemble learning</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Cohesion and internal friction angle are critical parameters for evaluating the suitability of stone. To build a reliable model to predict the cohesion and internal friction angle of rock, dataset containing 597 rock samples were collected and their petrological characteristics were investigated. In this study, artificial neural network (ANN) and particle swarm optimisation (PSO) algorithm are hybridised to establish a new hybrid machine learning (ML) model for predicting cohesion and internal friction angle based on petrological features. By comparing other five ML models, the efficiency of this model are assessed. Four statistical metrics such as correlation coefficient (R2) and root-mean-square error (RMSE) were used to evaluate the model. The results show that the hybridisation of ANN and PSO significantly improves the prediction and generalisation ability of the hybrid ML model. Compared with other models, this model was the most effective model for predicting cohesion and internal friction angle, with R2 value of 0.976 (Cohesion), 0.942 (Internal friction angle), RMSE of 0.697 (Cohesion), 0.935 (Internal friction angle). In addition, feature importance analysis showed that density and P-wave velocity were the most influential factors on cohesion, and uniaxial compressive strength, tensile strength and P-wave velocity were the most influential factors on internal friction angle. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Nondestructive Testing & Evaluation is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=190955067 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1080/10589759.2025.2476113 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 24 StartPage: 896 Subjects: – SubjectFull: Cohesion Type: general – SubjectFull: Internal friction Type: general – SubjectFull: Particle swarm optimization Type: general – SubjectFull: Petrology Type: general – SubjectFull: Shear strength Type: general – SubjectFull: Rock properties Type: general – SubjectFull: Ensemble learning Type: general – SubjectFull: Artificial neural networks Type: general Titles: – TitleFull: Shear strength parameters prediction of rock materials using hybrid machine learning model. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Cheng, Yanhui – PersonEntity: Name: NameFull: He, Dongliang – PersonEntity: Name: NameFull: Liu, Hongwei – PersonEntity: Name: NameFull: Wang, Guoxian IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 02 Text: Feb2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 10589759 Numbering: – Type: volume Value: 41 – Type: issue Value: 2 Titles: – TitleFull: Nondestructive Testing & Evaluation Type: main |
| ResultId | 1 |
