Robust Machine Learning Framework for Modeling the Compressive Strength of SFRC: Database Compilation, Predictive Analysis, and Empirical Verification

Abstract

In recent years, the field of construction engineering has experienced a significant paradigm shift, embracing the integration of machine learning (ML) methodologies, with a particular emphasis on forecasting the characteristics of steel-fiber-reinforced concrete (SFRC). Despite the theoretical sophistication of existing models, persistent challenges remain—their opacity, lack of transparency, and real-world relevance for practitioners. To address this gap and advance our current understanding, this study employs the extra gradient (XG) boosting algorithm, crafting a comprehensive approach. Grounded in a meticulously curated database drawn from 43 seminal publications, encompassing 420 distinct records, this research focuses predominantly on three primary fiber types: crimped, hooked, and mil-cut. Complemented by hands-on experimentation involving 20 diverse SFRC mixtures, this empirical campaign is further illuminated through the strategic use of partial dependence plots (PDPs), revealing intricate relationships between input parameters and consequent compressive strength. A pivotal revelation of this research lies in the identification of optimal SFRC formulations, offering tangible insights for real-world applications. The developed ML model stands out not only for its sophistication but also its tangible accuracy, evidenced by exemplary performance against independent datasets, boasting a commendable mean target-prediction ratio of 99%. To bridge the theory–practice gap, we introduce a user-friendly digital interface, thoroughly designed to guide professionals in optimizing and accurately predicting the compressive strength of SFRC. This research thus contributes to the construction and civil engineering sectors by enhancing predictive capabilities and refining mix designs, fostering innovation, and addressing the evolving needs of the industry.

Prediction of the Compressive Strength of Vibrocentrifuged Concrete Using Machine Learning Methods

“…Discussing the results obtained and comparing them with the results previously obtained by other authors, it should be noted that the chosen question is unconditionally novel. The fact is that predicting the properties of concrete was previously known and described in works [6,11,15,17,18,20,21,[23][24][25][26][27][28]30,33,36,40,41,55]. The same study touches upon the topic of predicting the properties of special concretes, that is, variatropic concretes obtained using vibrocentrifuge technology.…”

“…Additionally, also with an increase in the data set, it will be possible to use more complex models. (6) The developed models can be offered to civil engineers, specialists in the field of materials science and materials technology as an additional source of information for making informed decisions regarding the development of improved concrete mix compositions and construction methods. These models can also be used for other materials that are exposed to aggressive environments.…”

“…Particular attention should also be paid to predicting the strength characteristics of vibrocentrifuged concrete. Structures made from vibrocentrifuged concrete must withstand extreme operating conditions, and accurate prediction of their properties is important, first of all, to ensure the required level of safety [6][7][8][9][10]. Along with traditional methods for calculating strength, which involve the formation of a sample and its subsequent testing in laboratory conditions, modern, fast and equally predictive methods of machine learning are used today [11][12][13][14].…”

Risk prediction model for postoperative brain metastasis in IIB-IIIB non-small cell lung cancer: based on radiomics and clinicopathology

“…Radiomics can use different machine learning algorithms to build models, but the main reason that affects the use of models is the complexity of these models themselves, and their operation process is di cult to explain, which brings great challenges to model users. Currently, several interpretability methods in machine learning can be used to understand and interpret the predictions made by models, such as partial dependence graphs (PDP) (Abbas et al 2023) and SHapley Additive exPlanations (SHAP) (Mitchell et al 2022). One disadvantage of PDP is that struggle to illustrate relationships between multiple features and predictions (Angelini et al 2023).…”

Analysis of Geometric Characteristics of Cracks and Delamination in Aerated Concrete Products Using Convolutional Neural Networks

“…[8], the authors compared ensemble models of deep neural networks in order to develop the most accurate approach to predicting the strength of concrete. Research on the development of neural networks for quality control and predicting the properties of various building materials is presented in [9][10][11][12][13][14][15][16] and covers concrete containing recycled coarse aggregate [9,10], roller-compacted concrete pavement [11], bricks [12], fiber-reinforced concrete [13] and ultra-high-performance concrete [14].…”