The Evaluation of Effect of Jet Grout Columns to the Settlements in Soils with Numerical Methods DOI Creative Commons
İrem Düzen, Aşkın Özocak, Sedat Sert

et al.

Sakarya University Journal of Science, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 21, 2024

Increasing population bring together the need for construction on weak soils. At this point, soil improvement methods gain importance in which problematic properties of soils aimed to enhance. Among these, jet grout columns are widely applied method and have advantages such as increasing bearing capacity, reducing settlements risk liquefaction. In paper, utilized reduce layers effect several parameters settlement examined. The analyzes, performed with Plaxis 2D 3D. grouts modeled both single composite region by changing length, diameter spacing. To assess soft clay effect, were socketed into different layers. results proved that reduces settlements, but change diameter, length spacing affects at rates. Through 3D analysis, up 22% reductions obtained case where longest assigned lowest spacings. most effective factor was found rather than diameter. increase after a certain value led lower performance due group effect. region, analyzes converge very much, so it would be practical perform analysis composites. However, ones modelled predicted more remained safe side. Additionally, better

Language: Английский

Prediction of the Effect of Fly Ash on the Unconfined Compressive Strength of Basalt Fiber Reinforced Clay Using Artificial Neural Networks DOI Open Access
Yasemin ASLAN TOPÇUOĞLU

Processes, Journal Year: 2025, Volume and Issue: 13(1), P. 157 - 157

Published: Jan. 8, 2025

In this study, the effects of fly ash (FA) and basalt fiber (BF) additives on unconfined compressive strength (qu) kaolin clay were experimentally investigated, a dataset was created based results. This used in an artificial neural network (ANN) model to predict qu additive ratio, water content, curing time. For purpose, samples prepared by adding 1% BF with length 24 mm FA at ratios 3%, 6%, 9%, 12%, 15% clay, followed addition 25% 30% water. Unconfined tests performed before after 28, 42, 56 days determine values. The evaluation obtained experimental results carried out creating ANN model. To validate prediction capabilities ANN, comparative analysis using various intelligence models, model’s overall performance assessed 5-fold cross-validation technique. evaluations revealed that model, data from studies, demonstrated highest accuracy close agreement According obtained, R value calculated as 0.97, while RMSE values found 0.09, 0.10, 0.06 0.04 for pre-curing, 28th day, 42nd day 56th respectively.

Language: Английский

Citations

2

Investigation of Screw Pile Behavior in Cohesive Soil Under Uplift and Compressive Forces by Experimental Studies and Numerical Analyses DOI
Talha Sarıcı, Mustafa Özcan

Arabian Journal for Science and Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 15, 2024

Language: Английский

Citations

4

Determination of Basalt Fiber Reinforcement in Kaolin Clay: Experimental and Neural Network-Based Analysis of Liquid Limit, Plastic Limit, and Unconfined Compressive Strength DOI Open Access
Yasemin ASLAN TOPÇUOĞLU, Zeynep Bala Duranay, Zülfü Gürocak

et al.

Processes, Journal Year: 2025, Volume and Issue: 13(2), P. 377 - 377

Published: Jan. 30, 2025

The use of basalt fibers, which are employed in various fields, such as construction, automotive, chemical, and petrochemical industries, the sports industry, energy engineering, is also increasingly common soil reinforcement studies, another application area geotechnical alongside their concrete. With this growing application, scientific studies on with fiber have gained momentum. This study establishes effects liquid limit, plastic strength properties soils, relationships among unconfined compressive soil. For purpose, 12 mm was used a material kaolin clay at ratios 1.0%, 1.5%, 2.0%, 2.5%, 3.0%. prepared samples were subjected to tests. As result experimental ratio that provided best improvement determined, established. results then input data for an artificial intelligence model. neural network (NN) trained obtain fiber-to-kaolin based strength. model enabled prediction provides maximum without need experiments. NN great agreement results, demonstrating providing can be identified using requiring studies. Moreover, performance reliability evaluated 5-fold cross-validation compared other AI methods. ANN demonstrated superior predictive accuracy, achieving highest correlation coefficient (R = 0.82), outperforming models terms both accuracy reliability.

Language: Английский

Citations

0

Estimation of Compressive Strength of Basalt Fiber-Reinforced Kaolin Clay Mixture Using Extreme Learning Machine DOI Open Access
Zeynep Bala Duranay, Yasemin ASLAN TOPÇUOĞLU, Zülfü Gürocak

et al.

Materials, Journal Year: 2025, Volume and Issue: 18(2), P. 245 - 245

Published: Jan. 8, 2025

Background: In this study, the unconfined compressive strength (qu) of a mixture consisting clay reinforced with 24 mm-long basalt fiber was estimated using extreme learning machine (ELM). The aim study is to estimate results closest data obtained through experimental studies without need for studies. literature review reveals that ELM technique has not been applied predict fiber-reinforced clay, and aims provide novel contribution in area. Methods: included derived from series mixtures where water contents 20%, 25%, 30%, 35% were combined kaolin at reinforcement rates 0%, 1%, 2%, 3%. Based on these mixtures, an model developed qu. Results: ELM, recognized its computational efficiency high predictive accuracy, demonstrated exceptional performance application, achieving R value 0.9976 RMSE 0.0001. Furthermore, includes figure representation illustrating ELM-based predictions align closely results, underscoring reliability. Conclusions: To further validate performance, compared other artificial intelligence models 5-fold cross-validation approach. analysis revealed outperformed counterparts, remarkable 0.000174, thereby solidifying capability accurately soil under varying content conditions. Thus, it aimed save labor, material, time.

Language: Английский

Citations

0

Performance assessment of a foundation resting on reinforced collapsible Sabkha soil by deep soil mixing columns using machine learning analyses DOI

Mohamed B. D. Elsawy,

Abderrahim Lakhouit,

Turki S. Alhmari

et al.

Alexandria Engineering Journal, Journal Year: 2025, Volume and Issue: 118, P. 591 - 605

Published: Jan. 28, 2025

Language: Английский

Citations

0

Effect of multicollinearity in assessing the compaction and strength parameters of lime-treated expansive soil using artificial intelligence techniques DOI
Amit Kumar Jangid, Jitendra Khatti, Kamaldeep Singh Grover

et al.

Multiscale and Multidisciplinary Modeling Experiments and Design, Journal Year: 2024, Volume and Issue: 8(1)

Published: Nov. 18, 2024

Language: Английский

Citations

3

A sustainable solution for soil improvement: a decision tree model combined with metaheuristic optimizations for fiber reinforced clays DOI
Eylem Arslan, Ekin Ekıncı, Zeynep Garip

et al.

Environment Development and Sustainability, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 18, 2024

Language: Английский

Citations

2

Evaluation of the Changes in the Strength of Clay Reinforced with Basalt Fiber Using Artificial Neural Network Model DOI Creative Commons
Yasemin ASLAN TOPÇUOĞLU, Zeynep Bala Duranay, Zülfü Gürocak

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(22), P. 10362 - 10362

Published: Nov. 11, 2024

In this research, the impact of basalt fiber reinforcement on unconfined compressive strength clay soils was experimentally analyzed, and collected data were utilized in an artificial neural network (ANN) to predict based ratio length. For purpose, two different lengths (6 mm 12 mm) added unreinforced bentonite at ratios 0%, 1%, 2%, 3%, 4%, 5%, tests performed prepared reinforced samples determine (qu) values. The evaluation obtained experimental results carried out by creating ANN models. To validate prediction capabilities ANN, a comparative analysis using linear regression, support vector machines, Gaussian process regression Ultimately, five-fold cross-validation technique employed objectively evaluate overall performance model. evaluations revealed that model predictions from studies showed highest accuracy close agreement with results.

Language: Английский

Citations

2

The Evaluation of Effect of Jet Grout Columns to the Settlements in Soils with Numerical Methods DOI Creative Commons
İrem Düzen, Aşkın Özocak, Sedat Sert

et al.

Sakarya University Journal of Science, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 21, 2024

Increasing population bring together the need for construction on weak soils. At this point, soil improvement methods gain importance in which problematic properties of soils aimed to enhance. Among these, jet grout columns are widely applied method and have advantages such as increasing bearing capacity, reducing settlements risk liquefaction. In paper, utilized reduce layers effect several parameters settlement examined. The analyzes, performed with Plaxis 2D 3D. grouts modeled both single composite region by changing length, diameter spacing. To assess soft clay effect, were socketed into different layers. results proved that reduces settlements, but change diameter, length spacing affects at rates. Through 3D analysis, up 22% reductions obtained case where longest assigned lowest spacings. most effective factor was found rather than diameter. increase after a certain value led lower performance due group effect. region, analyzes converge very much, so it would be practical perform analysis composites. However, ones modelled predicted more remained safe side. Additionally, better

Language: Английский

Citations

1