scholarly journals Non-Tuned Machine Learning Approach for Predicting the Compressive Strength of High-Performance Concrete

Materials ◽  
2020 ◽  
Vol 13 (5) ◽  
pp. 1023
Author(s):  
Abobakr Khalil Al-Shamiri ◽  
Tian-Feng Yuan ◽  
Joong Hoon Kim
Keyword(s):  
Machine Learning ◽  
Compressive Strength ◽  
Prediction Model ◽  
Extreme Learning Machine ◽  
High Performance ◽  
High Performance Concrete ◽  
Fine Aggregate ◽  
Input Variables ◽  
Prediction Reliability ◽  
Learning Machine

Compressive strength is considered as one of the most important parameters in concrete design. Time and cost can be reduced if the compressive strength of concrete is accurately estimated. In this paper, a new prediction model for compressive strength of high-performance concrete (HPC) was developed using a non-tuned machine learning technique, namely, a regularized extreme learning machine (RELM). The RELM prediction model was developed using a comprehensive dataset obtained from previously published studies. The input variables of the model include cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, and age of specimens. k-fold cross-validation was used to assess the prediction reliability of the developed RELM model. The prediction results of the RELM model were evaluated using various error measures and compared with that of the standard extreme learning machine (ELM) and other methods presented in the literature. The findings of this research indicate that the compressive strength of HPC can be accurately estimated using the proposed RELM model.

scholarly journals Effect of Mineral Aggregates and Chemical Admixtures as Internal Curing Agents on the Mechanical Properties and Durability of High-Performance Concrete

Materials ◽  
2020 ◽  
Vol 13 (9) ◽  
pp. 2090 ◽  
Author(s):  
Francisco Javier Vázquez-Rodríguez ◽  
Nora Elizondo-Villareal ◽  
Luz Hypatia Verástegui ◽  
Ana Maria Arato Tovar ◽  
Jesus Fernando López-Perales ◽  
...  
Keyword(s):  
Compressive Strength ◽  
Fly Ash ◽  
High Performance ◽  
High Performance Concrete ◽  
Chloride Ions ◽  
Internal Curing ◽  
Fine Aggregate ◽  
Pumice Stone ◽  
Chemical Admixtures ◽  
Mineral Aggregates

In the present work, the effect of mineral aggregates (pumice stone and expanded clay aggregates) and chemical admixtures (superplasticizers and shrinkage reducing additives) as an alternative internal curing technique was investigated, to improve the properties of high-performance concrete. In the fresh and hardened state, concretes with partial replacements of Portland cement (CPC30R and OPC40C) by pulverized fly ash in combination with the addition of mineral aggregates and chemical admixtures were studied. The physical, mechanical, and durability properties in terms of slump, density, porosity, compressive strength, and permeability to chloride ions were respectively determined. The microstructural analysis was carried out by scanning electronic microscopy. The results highlight the effect of the addition of expanded clay aggregate on the internal curing of the concrete, which allowed developing the maximum compressive strength at 28 days (61 MPa). Meanwhile, the replacement of fine aggregate by 20% of pumice stone allowed developing the maximum compressive strength (52 MPa) in an OPC-based concrete at 180 days. The effectiveness of internal curing to develop higher strength is attributed to control in the porosity and a high water release at a later age. Finally, the lowest permeability value at 90 days (945 C) was found by the substitutions of fine aggregate by 20% of pumice stone saturated with shrinkage reducing admixture into pores and OPC40C by 15% of pulverized fly ash. It might be due to impeded diffusion of chloride ions into cement paste in the vicinity of pulverized fly ash, where the pozzolanic reaction has occurred. The proposed internal curing technology can be considered a real alternative to achieve the expected performance of a high-performance concrete since a concrete with a compressive strength range from 45 to 67 MPa, density range from 2130 to 2310 kg/m3, and exceptional durability (< 2000 C) was effectively developed.

scholarly journals The use of ceramics as an internal curing agent in high performance concrete with variable temperature curing to improve mechanical characteristics

2022 ◽  
Vol 961 (1) ◽  
pp. 012024
Author(s):  
Abdulrasool Thamer Abdulrasool ◽  
Noor R. Kadhim ◽  
Safaa S. Mohammed ◽  
Ahmed Abdulmueen Alher
Keyword(s):  
Compressive Strength ◽  
High Performance ◽  
Mechanical Characteristics ◽  
High Performance Concrete ◽  
Variable Temperature ◽  
Porous Ceramic ◽  
Autogenous Shrinkage ◽  
Internal Curing ◽  
Fine Aggregate ◽  
Fine Aggregates

Abstract Concrete curing is one of the most significant factors in the development of compressive strength, and a high temperature difference during curing may reduce strength. The microcracks created in the concrete as a result of the constant temperature change cause this exudation. Internal curing has become popular for decreasing the risk of early-age cracking in high-performance concrete by limiting autogenous shrinkage (HPC). This study looks at the effectiveness of internal wet curing offered by a new kind of aggregate called “recycled waste porous ceramic fine aggregates”. The evolution of measured mechanical characteristics is examined on three distinct HPCs, both with and without internal curing materials. Ceramic fine aggregates were used to replace two different quantities of regular weight fine aggregate. Ceramic fine aggregates were shown to be quite beneficial for internal cure. It has been discovered that incorporating 20% ceramic fine aggregates into HPC improves the properties of the material, resulting in low internal stress and a large improvement in compressive strength. It should be emphasized that, unlike some traditional lightweight aggregates, no loss in compressive strength has been seen for the various quantities of ceramic fine aggregates introduced at either early or later ages.

High Performance Concrete (HPC) Compressive Strength Prediction With Advanced Machine Learning Methods

2020 ◽  
pp. 118-140
Author(s):  
Melda Yucel ◽  
Ersin Namlı
Keyword(s):  
Machine Learning ◽  
Compressive Strength ◽  
Prediction Model ◽  
High Performance Concrete ◽  
Prediction Method ◽  
Structural Features ◽  
Strength Prediction ◽  
Concrete Compressive Strength ◽  
Learning Methods ◽  
Machine Learning Methods

In this chapter, prediction applications of concrete compressive strength values were realized via generation of various hybrid models, which are based on decision trees as main prediction method, by using different artificial intelligence and machine learning techniques. In respect to this aim, a literature research was presented. Used machine learning methods were explained together with their developments and structural features. Various applications were performed to predict concrete compressive strength, and then feature selection was applied to prediction model in order to determine primarily important parameters for compressive strength prediction model. Success of both models was evaluated with respect to correct and precision prediction of values with different error metrics and calculations.

scholarly journals Predicting Ultra-High-Performance Concrete Compressive Strength Using Tabular Generative Adversarial Networks

Materials ◽  
2020 ◽  
Vol 13 (21) ◽  
pp. 4757
Author(s):  
Afshin Marani ◽  
Armin Jamali ◽  
Moncef L. Nehdi
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Compressive Strength ◽  
High Performance ◽  
High Performance Concrete ◽  
Synthetic Data ◽  
Generative Adversarial Networks ◽  
Ultra High Performance Concrete ◽  
Adversarial Networks ◽  
Insight Into

There have been abundant experimental studies exploring ultra-high-performance concrete (UHPC) in recent years. However, the relationships between the engineering properties of UHPC and its mixture composition are highly nonlinear and difficult to delineate using traditional statistical methods. There is a need for robust and advanced methods that can streamline the diverse pertinent experimental data available to create predictive tools with superior accuracy and provide insight into its nonlinear materials science aspects. Machine learning is a powerful tool that can unravel underlying patterns in complex data. Accordingly, this study endeavors to employ state-of-the-art machine learning techniques to predict the compressive strength of UHPC using a comprehensive experimental database retrieved from the open literature consisting of 810 test observations and 15 input features. A novel approach based on tabular generative adversarial networks was used to generate 6513 plausible synthetic data for training robust machine learning models, including random forest, extra trees, and gradient boosting regression. While the models were trained using the synthetic data, their ability to generalize their predictions was tested on the 810 experimental data thus far unknown and never presented to the models. The results indicate that the developed models achieved outstanding predictive performance. Parametric studies using the models were able to provide insight into the strength development mechanisms of UHPC and the significance of the various influential parameters.

scholarly journals Producing Heavyweight High-Performance Concrete by Using Black Sand as Newly Shielding Construction Material

Materials ◽  
2021 ◽  
Vol 14 (18) ◽  
pp. 5353
Author(s):  
Khaled A. Eltawil ◽  
Mohamed G. Mahdy ◽  
Osama Youssf ◽  
Ahmed M. Tahwia
Keyword(s):  
Compressive Strength ◽  
High Performance ◽  
Elevated Temperatures ◽  
Gamma Ray ◽  
High Performance Concrete ◽  
Construction Material ◽  
Construction Materials ◽  
Linear Attenuation Coefficient ◽  
Fine Aggregate ◽  
Black Sand

Experimental work was carried out to study new fine aggregate shielding construction materials, namely black sand (BS). The BS effect on the mechanical, durability, and shielding characteristics of heavyweight high-performance concrete (HWHPC) was evaluated. This study aimed at improving various HWHPC properties, concertedly. Fifteen mixtures of HWHPC were made, with various variables, including replacing 10% and 15% of the cement with fly ash (FA) and replacing normal sand by BS at various contents (15%, 30%, 45%, 60%, 75%, and 100%). The test specimens were subjected to various exposure conditions, including elevated temperatures, which ranged from 250 °C to 750 °C, for a duration of 3 h; magnesium sulfate (MS) exposure; and gamma-ray exposure. The effects of elevated temperature and sulfate resistance on concrete mass loss were examined. The results revealed that BS is a promising shielding construction material. The BS content is the most important factor influencing concrete compressive strength. Mixes containing 15% BS demonstrated significantly better strength compared to the control mixes. Exposure to 250 °C led to a notable increase in compressive strength. BS showed a significant effect on HWHPC fire resistance properties, especially at 750 °C and a significant linear attenuation coefficient. Using 10% FA with 15% BS was the most effective mixing proportion for improving all HWHPC properties concertedly, especially at greater ages.

Study on early Mechanical Performance of High Performance Concrete with Low Clinker Influenced by Rubber Powder

2014 ◽  
Vol 584-586 ◽  
pp. 1738-1741
Author(s):  
Qing Hai Meng ◽  
Li Hua Lv ◽  
Xu Yan
Keyword(s):  
Compressive Strength ◽  
Flexural Strength ◽  
High Performance ◽  
Bending Strength ◽  
Mechanical Performance ◽  
High Performance Concrete ◽  
Fine Aggregate ◽  
Rubber Powder ◽  
Concrete Mechanical Properties ◽  
Strength And Ductility

Selecting rubber powders, which is divided into 80 mesh and 150 mesh, as the research object, to understand the influence of high performance of lower clinker concrete mechanical properties of rubber powder with different varieties and volume. Taking the compressive strength, flexural strength and ratio of flexural strength to compressive strength as an indicator, the thesis explores the influence of the high performance concrete with low clinker, which rubber powder are mixed into as fine aggregate, on the compressive strength bending strength and ductility.

Estimating Distribution of Concrete Strength Using Quantile Regression Neural Networks

2014 ◽  
Vol 584-586 ◽  
pp. 1017-1025 ◽  
Author(s):  
I Cheng Yeh
Keyword(s):  
Neural Networks ◽  
Compressive Strength ◽  
Quantile Regression ◽  
Blast Furnace Slag ◽  
High Performance ◽  
Coarse Aggregate ◽  
High Performance Concrete ◽  
Concrete Strength ◽  
Fine Aggregate ◽  
Furnace Slag

This paper is aimed at demonstrating the possibilities of adaptingQuantile Regression Neural Network (QRNN) to estimate the distribution ofcompressive strength of high performance concrete (HPC). The databasecontaining 1030 compressive strength data were used to evaluate QRNN. Each dataincludes the amounts of cement, blast furnace slag, fly ash, water,superplasticizer, coarse aggregate, fine aggregate (in kilograms per cubicmeter), the age, and the compressive strength. This study led to the followingconclusions: (1) The Quantile Regression Neural Networks can buildaccurate quantile models and estimate the distribution of compressive strengthof HPC. (2) The various distributions of prediction of compressive strength of HPCshow that the variance of the error is inconstant across observations, whichimply that the prediction is heteroscedastic. (3) The logarithmic normaldistribution may be more appropriate than normal distribution to fit thedistribution of compressive strength of HPC. Since engineers should not assumethat the variance of the error of prediction of compressive strength isconstant, the ability of estimating the distribution of compressive strength ofHPC is an important advantage of QRNN.

Sign in / Sign up

Export Citation Format

Share Document