Development of a Machine Learning (ML)-Based Computational Model to Estimate the Engineering Properties of Portland Cement Concrete (PCC)

Arabian Journal for Science and Engineering, Journal Year: 2024, Volume and Issue: 49(10), P. 14351 - 14365

Published: May 3, 2024

Abstract Portland cement concrete (PCC) is the construction material most used worldwide. Hence, its proper characterization fundamental for daily-basis engineering practice. Nonetheless, experimental measurements of PCC’s properties (i.e., Poisson’s Ratio - v -, Elastic Modulus E Compressive Strength -ComS-, and Tensile -TenS-) consume considerable amounts time financial resources. Therefore, development high-precision indirect methods fundamental. Accordingly, this research proposes a computational model based on deep neural networks (DNNs) to simultaneously predict , ComS, TenS. For purpose, Long-Term Pavement Performance database was employed as data source. In regard, mix design parameters PCC are adopted input variables. The performance DNN evaluated with 1:1 lines, goodness-of-fit parameters, Shapley additive explanations assessments, running analysis. results demonstrated that proposed exhibited an exactitude higher than 99.8%, forecasting errors close zero (0). Consequently, machine learning-based designed in investigation helpful tool estimating when laboratory tests not attainable. Thus, main novelty study creating robust determine TenS by solely considering parameters. Likewise, central contribution state-of-the-art achieved present effort public launch developed through open-access GitHub repository, which can be utilized engineers, designers, agencies, other stakeholders.

Language: Английский

---

Comprehensive review on predicting CBR values using machine learning techniques

Asian Journal of Civil Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: May 27, 2025

Language: Английский

---

Prediction of California bearing ratio and modified proctor parameters using deep neural networks and multiple linear regression: A case study of granular soils

Case Studies in Construction Materials, Journal Year: 2023, Volume and Issue: 20, P. e02800 - e02800

Published: Dec. 19, 2023

The California Bearing Ratio (CBR) and modified proctor parameters belong to the soil geotechnical properties used assess behaviour. Direct measurement of these can be quite time-consuming in large-scale applications or when immediate results are required. Therefore, significant research efforts have been made literature develop indirect methods for their estimation. However, some gaps state-of-the-art highlighted topics, such as deficiency computational models calculate maximum dry unit weight (γd(max)), optimum moisture content (wopt) CBR, lack that consider intrinsic influence on each other. Hence, this investigation, mathematical were created obtain above-mentioned variables from grain size distribution. model was based Multiple Linear Regression (MLR) correlations. Meanwhile, constructed a custom-made Deep Neural Networks (DNNs) architecture. Subsequently, accuracy validated with an experimental case study. demonstrated proposed study more precise than previous approaches literature. Accordingly, main contribution manuscript industry is formation high exactness predict γd(max), wopt CBR granular soils.

Language: Английский

---

Efficient predictive modeling of resilient modulus in stabilized clayey soil using automated machine learning

Construction and Building Materials, Journal Year: 2024, Volume and Issue: 442, P. 137678 - 137678

Published: Aug. 1, 2024

Language: Английский

---

Predicting resilient modulus for pavement design: a comprehensive review of artificial neural network applications

International Journal of Pavement Engineering, Journal Year: 2024, Volume and Issue: 25(1)

Published: Nov. 11, 2024

The Resilient Modulus (MR) is an essential parameter describing the mechanical behaviour of pavement materials, but tests to obtain it are time-consuming and costly. Therefore, machine learning, especially Artificial Neural Networks (ANN), has recently been effective alternative for predicting MR. Although there increase in articles on ANN MR, no systematic review yet categorised publications, algorithm structures, predictive parameters, model accuracy. This provides a comprehensive overview studies using predict MR materials. It examines various subtypes addressing gap understanding these models identifying prevalent parameters. Twenty-five peer-reviewed published English-language journals were identified keywords related neural networks For fine soils, all reviewed use moisture content as parameter. In contrast, granular soils typically include stress state physical characteristics recycled or stabilised significant variability inputs. underscores potential enhancing engineering, pointing towards future research application refinement this area study.

Language: Английский

---

California bearing ratio and compaction parameters prediction using advanced hybrid machine learning methods

Asian Journal of Civil Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 2, 2024

Language: Английский

---