Experimental Study and Soft Computing Modeling of the Unconfined Compressive Strength of Limestone Rocks Considering Dry and Saturation Conditions

Alzabeebee, Saif; Mohammed, Diyari Abdalrahman; Alshkane, Younis M.

doi:10.1007/s00603-022-02948-y

Cited by 19 publications

(6 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two error criteria (i.e., RMSE and MAE) measured the error based on the difference between the expected and predicted SVs and ROC curves were plotted to measure the accuracy. However, there are other indicators (e.g., a20 107 and error level-cumulative frequency plot 108 ) that can be used in the subsequent efforts to support these results.…”

Section: Resultsmentioning

confidence: 93%

Integrated machine learning for modeling bearing capacity of shallow foundations

Liu,

Liang

2024

Sci Rep

View full text Add to dashboard Cite

Analyzing the stability of footings is a significant step in civil/geotechnical engineering projects. In this work, two novel predictive tools are suggested based on an artificial neural network (ANN) to analyze the bearing capacity of a footing installed on a two-layered soil mass. To this end, backtracking search algorithm (BSA) and equilibrium optimizer (EO) are employed to train the ANN for approximating the stability value (SV) of the system. After executing a set of finite element analyses, the settlement values lower/higher than 5 cm are considered to indicate the stability/failure of the system. The results demonstrated the efficiency of these algorithms in fulfilling the assigned task. In detail, the training error of the ANN (in terms of root mean square error—RMSE)) dropped from 0.3585 to 0.3165 (11.72%) and 0.2959 (17.46%) by applying the BSA and EO, respectively. Moreover, the prediction accuracy of the ANN climbed from 93.7 to 94.3% and 94.1% (in terms of area under the receiving operating characteristics curve—AUROC). A comparison between the elite complexities of these algorithms showed that the EO enjoys a larger accuracy, while BSA is a more time-effective optimizer. Lastly, an explicit mathematical formula is derived from the EO-ANN model to be conveniently used in predicting the SV.

show abstract

Section: Resultsmentioning

confidence: 93%

Integrated machine learning for modeling bearing capacity of shallow foundations

Liu,

Liang

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Finally, an error analysis is carried out to compare the accuracy of the new EPR-MOGA model with the available equations in the literature. This was done by obtaining and plotting the relationship between the cumulative frequency and error level using the methodology employed by many previous studies (e.g., [11,15,33]. The results are presented in Fig.…”

Section: Error Analysismentioning

confidence: 99%

Multiscale soft computing-based model of shear strength of steel fibre-reinforced concrete beams

Alzabeebee

Qiu

Nassr

et al. 2023

Innov. Infrastruct. Solut.

Self Cite

View full text Add to dashboard Cite

Concrete is weak in tension, so steel fibres are added to the concrete members to increase shear capability. The shear capacity of steel fibre-reinforced concrete (SFRC) beams is crucial when building reinforced concrete structures. Creating a precise equation to determine the shear resistance of SFRC beams is challenging since many factors can influence the shear capacity of these beams. In addition, the precision available equations to predict the shear capacity are examined. The current research aims to examine the available equations and propose novel and more accurate model to predict the shear capacity of SFRC beams. An innovative evolutionary polynomial regression analysis (EPR- MOGA) is utilized to propose the new equation. The proposed equation offered improved prediction and increased accuracy compared to available equations, where it scored a lower mean absolute error ($$\mathrm{MAE}$$ MAE ) and root mean square error ($$\mathrm{RMSE}$$ RMSE ), a mean ($$\mu$$ μ ) close to the optimum value of 1.0 and a higher coefficient of determination ($${R}^{2}$$ R 2 ) when a comparison with literature was conducted. Therefore, the new equation can be employed to assure more resilient and optimized design calculations due to their improved performance.

show abstract

“…In this paper we were selected the following elements to evaluate the model's performance: the explained variance score (EVS); the mean squared error (MSE); the mean absolute error (MAE); the correlation coefficient (R); the ratio of predictions with an error within the range of ±20% of the total predictions (a20-index); and the percentage of prediction within an error range of ±30% (P30) [49][50][51][52][53]. The EVS value range is [0, 1]; the closer this value is to 1, the more the independent variable can explain the observed variance change of the dependent variable.…”

Section: Evaluation and Interpretation Of The Modelmentioning

confidence: 99%

Efficient Machine Learning Models for the Uplift Behavior of Helical Anchors in Dense Sand for Wind Energy Harvesting

Wang

Chen

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

Helical anchors are widely used in engineering to resist tension, especially during offshore wind energy harvesting, and their uplift behavior in sand is influenced by many factors. Experimental studies are often used to investigate these anchors; however, scale effects are inevitable in 1× g model tests, soil conditions for in situ tests are challenging to control, and centrifuge tests are expensive and rare. To make full use of the limited valid data and to gain more knowledge about the uplift behaviors of helical anchors in sand, a prediction model integrating gradient-boosting decision trees (GBDT) and particle swarm optimization (PSO) was proposed in this study. Data obtained from a series of centrifuge tests formed the dataset of the prediction model. The relative density of soil, embedment ratio, helix spacing ratio, and the number of helices were used as input parameters, while the anchor mobilization distance and the ultimate monotonic uplift resistance were set as output parameters. A GBDT algorithm was used to construct the model, and a PSO algorithm was used for hyperparameter tuning. The results show that the optimal GBDT model accurately predicted the anchor mobilization distance and the ultimate monotonic uplift resistance of helical anchors in dense fine silica sand. By analyzing the relative importance of influencing variables, the embedment ratio was found to be the most significant variable in the model, while the relative density of the fine silica sand soil, the helix spacing ratio, and the number of helices had relatively minor influence. In particular, the helix spacing ratio was found to have no influence on the capacity of adjacent helices when S/D > 6.

show abstract

Experimental Study and Soft Computing Modeling of the Unconfined Compressive Strength of Limestone Rocks Considering Dry and Saturation Conditions

Cited by 19 publications

References 45 publications

Integrated machine learning for modeling bearing capacity of shallow foundations

Integrated machine learning for modeling bearing capacity of shallow foundations

Multiscale soft computing-based model of shear strength of steel fibre-reinforced concrete beams

Efficient Machine Learning Models for the Uplift Behavior of Helical Anchors in Dense Sand for Wind Energy Harvesting

Contact Info

Product

Resources

About