Predictive Modelling for Concrete Failure at Anchorages Using Machine Learning Techniques
Anchorage to concrete plays a significant role in various aspects of modern construction. The structural performance of anchors under direct tensile load can lead to failure by concrete cone breakout. Concrete related failure modes are quasi-brittle, and as such, they may develop without prior warni...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/14/1/62 |
| _version_ | 1797543524466425856 |
|---|---|
| author | Panagiotis Spyridis Oladimeji B. Olalusi |
| author_facet | Panagiotis Spyridis Oladimeji B. Olalusi |
| author_sort | Panagiotis Spyridis |
| collection | DOAJ |
| description | Anchorage to concrete plays a significant role in various aspects of modern construction. The structural performance of anchors under direct tensile load can lead to failure by concrete cone breakout. Concrete related failure modes are quasi-brittle, and as such, they may develop without prior warning indications of damage, while it also exposes the bearing component to damage propagation. As such, an adequate reliability assessment of anchors against concrete cone failure is of high importance, and improved precision and minimisation of uncertainty in the predictive model are critical. This contribution develops predictive models for the tensile breakout capacity of fastening systems in concrete using the Gaussian Process Regression (GPR) and the Support Vector Regression (SVR) machine learning (ML) algorithms. The models were developed utilising a set of 864 experimental anchor tests. The efficiency of the developed models is assessed by statistical comparison to the state-of-practice semi-empirical predictive model, which is embedded in international design standards. Furthermore, the algorithms were evaluated based on a newly introduced Model Explainability concept based on Analogous Rational and Mechanical phenomena (MEARM). Finally, a discussion is provided regarding the developed ML models’ suitability for use as General Probabilistic Models in a reliability framework. |
| first_indexed | 2024-03-10T13:46:50Z |
| format | Article |
| id | doaj.art-ccd5da65fdf44a6c8a139b960c569714 |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-10T13:46:50Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-ccd5da65fdf44a6c8a139b960c5697142023-11-21T02:33:36ZengMDPI AGMaterials1996-19442020-12-011416210.3390/ma14010062Predictive Modelling for Concrete Failure at Anchorages Using Machine Learning TechniquesPanagiotis Spyridis0Oladimeji B. Olalusi1Faculty of Architecture and Civil Engineering, Technical University of Dortmund, 44227 Dortmund, GermanyStructural Engineering & Computational Mechanics Group (SECM), Department of Civil Engineering, University of KwaZulu-Natal, Durban 4001, South AfricaAnchorage to concrete plays a significant role in various aspects of modern construction. The structural performance of anchors under direct tensile load can lead to failure by concrete cone breakout. Concrete related failure modes are quasi-brittle, and as such, they may develop without prior warning indications of damage, while it also exposes the bearing component to damage propagation. As such, an adequate reliability assessment of anchors against concrete cone failure is of high importance, and improved precision and minimisation of uncertainty in the predictive model are critical. This contribution develops predictive models for the tensile breakout capacity of fastening systems in concrete using the Gaussian Process Regression (GPR) and the Support Vector Regression (SVR) machine learning (ML) algorithms. The models were developed utilising a set of 864 experimental anchor tests. The efficiency of the developed models is assessed by statistical comparison to the state-of-practice semi-empirical predictive model, which is embedded in international design standards. Furthermore, the algorithms were evaluated based on a newly introduced Model Explainability concept based on Analogous Rational and Mechanical phenomena (MEARM). Finally, a discussion is provided regarding the developed ML models’ suitability for use as General Probabilistic Models in a reliability framework.https://www.mdpi.com/1996-1944/14/1/62concretefractureanchoragefastenersmachine learningsupport vector machine |
| spellingShingle | Panagiotis Spyridis Oladimeji B. Olalusi Predictive Modelling for Concrete Failure at Anchorages Using Machine Learning Techniques Materials concrete fracture anchorage fasteners machine learning support vector machine |
| title | Predictive Modelling for Concrete Failure at Anchorages Using Machine Learning Techniques |
| title_full | Predictive Modelling for Concrete Failure at Anchorages Using Machine Learning Techniques |
| title_fullStr | Predictive Modelling for Concrete Failure at Anchorages Using Machine Learning Techniques |
| title_full_unstemmed | Predictive Modelling for Concrete Failure at Anchorages Using Machine Learning Techniques |
| title_short | Predictive Modelling for Concrete Failure at Anchorages Using Machine Learning Techniques |
| title_sort | predictive modelling for concrete failure at anchorages using machine learning techniques |
| topic | concrete fracture anchorage fasteners machine learning support vector machine |
| url | https://www.mdpi.com/1996-1944/14/1/62 |
| work_keys_str_mv | AT panagiotisspyridis predictivemodellingforconcretefailureatanchoragesusingmachinelearningtechniques AT oladimejibolalusi predictivemodellingforconcretefailureatanchoragesusingmachinelearningtechniques |