A review on properties and multi-objective performance predictions of concrete based on machine learning models

Materials Today Communications, Год журнала: 2025, Номер unknown, С. 112017 - 112017

Опубликована: Фев. 1, 2025

Язык: Английский

---

Innovative hybrid machine learning models for estimating the compressive strength of copper mine tailings concrete

Case Studies in Construction Materials, Год журнала: 2024, Номер 21, С. e03869 - e03869

Опубликована: Окт. 16, 2024

Язык: Английский

---

AI-Driven Prediction of Compressive Strength in Self-Compacting Concrete: Enhancing Sustainability through Ultrasonic Measurements

Sustainability, Год журнала: 2024, Номер 16(15), С. 6644 - 6644

Опубликована: Авг. 3, 2024

This study investigates the application of artificial intelligence (AI) to predict compressive strength self-compacting concrete (SCC) through ultrasonic measurements, thereby contributing sustainable construction practices. By leveraging advancements in computational techniques, specifically neural networks (ANNs), we developed highly accurate predictive models forecast SCC based on pulse velocity (UPV) measurements. Our findings demonstrate a clear correlation between higher UPV readings and improved quality, despite general trend decreased with increased air-entraining admixture (AEA) concentrations. The ANN show exceptional effectiveness predicting strength, coefficient (R2) 0.99 predicted actual values, providing robust tool for optimizing mix designs ensuring quality control. AI-driven approach enhances sustainability by improving material efficiency significantly reducing need traditional destructive testing methods, thus offering rapid, reliable, non-destructive alternative assessing properties.

Язык: Английский

---

Machine learning approach to predict the early-age flexural strength of sensor-embedded 3D-printed structures

Progress in Additive Manufacturing, Год журнала: 2025, Номер unknown

Опубликована: Фев. 21, 2025

Abstract The absence of formwork in 3D-printed concrete, unlike conventional mold-cast introduces greater variability curing conditions, posing significant challenges accurately estimating the early-age mechanical strength. Therefore, common non-destructive techniques such as maturity method fail to deliver a generalized predictive model for strength structures. In this study, multiple machine learning (ML) algorithms, including linear regression (LR), support vector (SVR), and artificial neural network (ANN), were developed estimate flexural beams under varying utilizing data collected from embedded sensors. Six input variables employed ML models, relative permittivity, internal temperature, method. For development, 144 points an extensive experimental statistical metrics evaluate proposed models. ANN outperformed other models predicting strength, achieving coefficient determination 95.1%. Furthermore, variable analysis highlighted most influential factor affecting beams.

Язык: Английский

---

Predictive Modelling of Mechanical Properties of Concrete Using Machine Learning with Secondary Treated Waste Water and Fly Ash

Cleaner Waste Systems, Год журнала: 2025, Номер unknown, С. 100296 - 100296

Опубликована: Апрель 1, 2025

Язык: Английский

---