Research Article
A Machine Learning Model for Pile Settlement Prediction Using Majority Voting-Based Feature Selection
Hafeez Husain Bello*
,
You Wang,
Shamsudeen Lawal
Issue:
Volume 10, Issue 3, June 2025
Pages:
104-114
Received:
25 March 2025
Accepted:
6 May 2025
Published:
11 June 2025
DOI:
10.11648/j.jccee.20251003.11
Downloads:
Views:
Abstract: Pile foundations are deep foundations commonly employed in bridge construction, high-rise buildings, trains, and situations requiring high bearing capacity and minimal settlement. Accurate prediction of pile settlement is essential for ensuring the safety and stability of deep foundations, yet traditional methods like in-situ load tests are often costly and impractical. The cone penetration test (CPT) is one of the most frequent in-situ tests for pile analysis because, like a model pile, the measured cone resistance and sleeve fiction can be used to estimate pile unit toe and shaft resistances, respectively. In this paper, a machine learning (ML) framework for pile settlement prediction with a genetic algorithm (GA) majority voting (MV) feature selection (FS) strategy to enhance model performance is presented. Three tree-based algorithms, each with a unique approach for tree development and feature handling—categorical boosting (CB), light gradient boosting (LGB), and random forest (RF) are selected for this purpose. The dataset was compiled from fifty-six pile case histories in different countries have been compiled including static loading tests which include maintained load tests and constant rate of penetration tests, shaft, and toe resistances which comprise CPT and CPTu (undrained CPT) sounding, the pile geometric and mechanical properties, the loads applied from the load tests as the model inputs, and recorded settlement values for the piles from the tests as the model output to be predicted. The CB model, coupled with the GA-MV approach, achieved the best predictive accuracy, yielding an R² of 0.926 and RMSE of 5.92 mm upon testing, while feature importance analysis identifies applied load (P) and pile length (L) as key predictors of settlement. Also, an overall decrease of the RMSE by 11.19% was observed between the CB-GAMV model (5.92 mm) and the CB-All features model (6.68 mm), and 9.41% between the CB-GAMV model and the CB-GA model (6.54 mm) on the validation set.
Abstract: Pile foundations are deep foundations commonly employed in bridge construction, high-rise buildings, trains, and situations requiring high bearing capacity and minimal settlement. Accurate prediction of pile settlement is essential for ensuring the safety and stability of deep foundations, yet traditional methods like in-situ load tests are often c...
Show More
Research Article
Effectiveness of Silica Fume as a Partial Cement Replacement in Recycled Aggregate Concrete
Issue:
Volume 10, Issue 3, June 2025
Pages:
115-122
Received:
9 May 2025
Accepted:
22 May 2025
Published:
20 June 2025
DOI:
10.11648/j.jccee.20251003.12
Downloads:
Views:
Abstract: Recycled concrete aggregate (RAC) can be used in structural concrete to lessen the environmental impact of waste concrete and the use of natural resources. The current study summarized the mechanical performances of concrete and assessed the synergistic impacts of recycled aggregate, likely at 100% content, with silica fume (SF) partially substituting cement. The study's primary variables included the dosage of silica fume used as a partial replacement of ordinary Portland cement (OPC) at five different percentages: 0%, 4%, 8%, 12%, and 16% by weight. Five distinct mixtures, designated RACSF-0, RACSF-4, RACSF-8, RACSF-12, and RACSF-16, were made using differing concentrations of silica fume for M30 concrete. The workability of concrete mixes was examined using the slump test. After increasing the proportion of SF, a declining trend was observed in the test results. The mechanical characteristics of RACSF were examined at 7 and 28 days using compressive and splitting tensile tests. The results demonstrated that adding SF enhanced RACSF's performance at both early and later curing ages, with the highest results occurring at 12% SF addition. As a result, it is advised to partially substitute 12% SF for cement in RAC.
Abstract: Recycled concrete aggregate (RAC) can be used in structural concrete to lessen the environmental impact of waste concrete and the use of natural resources. The current study summarized the mechanical performances of concrete and assessed the synergistic impacts of recycled aggregate, likely at 100% content, with silica fume (SF) partially substitut...
Show More
