Predicting ultra-high-performance concrete compressive strength using gene expression programming method

Alabduljabbar, Hisham; Khan, Majid; Awan, Hamad Hassan; Eldin, Sayed M.; Alyousef, Rayed; Mohamed, Abdeliazim Mustafa

doi:10.1016/j.cscm.2023.e02074

Cited by 12 publications

(6 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…13 . This approach is commonly used by researchers [ 28 , 38 , 128 , 129 ] to assess the precision of ML models. Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Recently, researchers have turned to ANN as an alternative approaches for predicting the behavior of RC components, particularly in situations where code standards are unavailable. Among these approaches, evolutionary algorithms such as GEP and MEP hold an advantage over ANN because they can construct precise prediction models even with a relatively small database [ [27] , [28] , [29] ]. However, despite these advancements, there is still a disagreement in the current literature concerning the development of a concise predictive mathematical equation that effectively and accurately estimates the flexural behavior of FRP-strengthened RC beams.…”

Section: Introductionmentioning

confidence: 99%

“…In contrast, the GEP and MEP algorithms are not black-box models because the internal mechanisms and operations are well-defined and understood [ 31 , 32 ]. They follow specific rules and genetic functions, such as mutation, selection, and crossover, which are explicitly programmed [ 28 , 33 ]. Researchers and practitioners can see how the algorithms evolve and generate solutions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Intelligent prediction modeling for flexural capacity of FRP-strengthened reinforced concrete beams using machine learning algorithms

Khan,

Khan

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…13 . This approach is commonly used by researchers [ 28 , 38 , 128 , 129 ] to assess the precision of ML models. Fig.…”

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent prediction modeling for flexural capacity of FRP-strengthened reinforced concrete beams using machine learning algorithms

Khan,

Khan

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…In addition to ANN, several authors have employed other ML techniques in their studies, such as SVM and ANFIS 43 – 45 46 . Nevertheless, the use of the ANN approach has certain drawbacks and limitations in prediction modeling 47 – 50 . To begin with, the ANN is categorized as a black-box approach, offering limited interpretation in terms of how the model generates its estimations 51 – 53 .…”

Section: Introductionmentioning

confidence: 99%

“…Identifying the ideal setup can pose challenges and may necessitate extensive experimentation through trial and error 60 – 63 . To address these issues, evolutionary algorithms (EAs) and genetic algorithms (GA), which include gene expression programming (GEP) and multi-expression programming (MEP), are being utilized to forecast concrete properties 49 , 50 , 53 , 57 , 64 . The superiority of such algorithms is the generation of useful mathematical expressions, as well as their great reliability and predictive potential.…”

Section: Introductionmentioning

confidence: 99%

Computational prediction of workability and mechanical properties of bentonite plastic concrete using multi-expression programming

Khan,

Ali,

Najeh

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

Bentonite plastic concrete (BPC) demonstrated promising potential for remedial cut-off wall construction to mitigate dam seepage, as it fulfills essential criteria for strength, stiffness, and permeability. High workability and consistency are essential attributes for BPC because it is poured into trenches using a tremie pipe, emphasizing the importance of accurately predicting the slump of BPC. In addition, prediction models offer valuable tools to estimate various strength parameters, enabling adjustments to BPC mixing designs to optimize project construction, leading to cost and time savings. Therefore, this study explores the multi-expression programming (MEP) technique to predict the key characteristics of BPC, such as slump, compressive strength (fc), and elastic modulus (Ec). In the present study, 158, 169, and 111 data points were collected from the experimental studies for the slump, fc, and Ec, respectively. The dataset was divided into three sets: 70% for training, 15% for testing, and another 15% for model validation. The MEP models exhibited excellent accuracy with a correlation coefficient (R) of 0.9999 for slump, 0.9831 for fc, and 0.9300 for Ec. Furthermore, the comparative analysis between MEP models and conventional linear and non-linear regression models revealed remarkable precision in the predictions of the proposed MEP models, surpassing the accuracy of traditional regression methods. SHapley Additive exPlanation analysis indicated that water, cement, and bentonite exert significant influence on slump, with water having the greatest impact on compressive strength, while curing time and cement exhibit a higher influence on elastic modulus. In summary, the application of machine learning algorithms offers the capability to deliver prompt and precise early estimates of BPC properties, thus optimizing the efficiency of construction and design processes.

show abstract

Improved forecasting of the compressive strength of ultra‐high‐performance concrete (UHPC) via the CatBoost model optimized with different algorithms

Katlav,

Ergen

2024

Structural Concrete

View full text Add to dashboard Cite

This paper focuses on the applicability of CatBoost models constructed using various optimization techniques for improved forecasting the compressive strength of ultra‐high‐performance concrete (UHPC). Phasor particle swarm optimization (PPSO), dwarf mongoose optimization (DMO), and atom search optimization (ASO), which have been very popular recently, are preferred as optimization algorithms. A comprehensive and reliable data set is used to develop the CatBoost models, which include 785 test results with 15 input features. The performance of the CatBoost models (PPSO‐CatBoost, DMO‐CatBoost, and ASO‐CatBoost) optimized with different algorithms is thoroughly assessed by means of various statistical metrics and error analysis to determine the model with the best forecasting capability, and this model is compared with the models obtained from previous studies. In addition, Shapley additive exPlanations (SHAP) analysis is used to ensure the interpretability of the forecasting models and to overcome the “black box” problem of machine learning (ML) models. The obtained results demonstrate that all CatBoost models outstandingly forecast the compressive strength of UHPC. Among these models, the DMO‐CatBoost model stands out compared to the other models in various performance metrics, such as high coefficient of determination (R2) values, low root mean squared error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE) values, along with a smaller error ratio. In other words, the RMSE, R2, MAPE, and MAE values of the DMO‐CatBoost model for the training set are 3.67, 0.993, 0.019, and 2.35, respectively, whereas those for the test set are 6.15, 0.978, 0.038, and 4.51. Additionally, the performance ranking of the algorithms used to optimize the hyperparameters of the CatBoost model is as follows: DMO > PPSO > ASO. On the other hand, SHAP analysis showed that age, fiber dosage, and cement dosage significantly influence the compressive strength of UHPC. These findings can guide structural engineers in the design and optimization of UHPC, thus assisting them in developing strategies to improve the strength properties of the material. Finally, based on the best forecasting model developed in this work, a graphical user interface has been developed to easily forecast the compressive strength of UHPC in practical applications without additional tools or software.

show abstract

Predicting ultra-high-performance concrete compressive strength using gene expression programming method

Cited by 12 publications

References 75 publications

Intelligent prediction modeling for flexural capacity of FRP-strengthened reinforced concrete beams using machine learning algorithms

Intelligent prediction modeling for flexural capacity of FRP-strengthened reinforced concrete beams using machine learning algorithms

Computational prediction of workability and mechanical properties of bentonite plastic concrete using multi-expression programming

Improved forecasting of the compressive strength of ultra‐high‐performance concrete (UHPC) via the CatBoost model optimized with different algorithms

Contact Info

Product

Resources

About