Predicting the ingredients of self compacting concrete using artificial neural network

Yaman, Mahmoud Abu; Elaty, Metwally Abd Allah Abd; Taman, Mohamed

doi:10.1016/j.aej.2017.04.007

Cited by 133 publications

(45 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, machine learning methods have been applied to predict material properties, which can reduce time and cost for discovering new materials [24,25]. Compared with the conventional regression-based data-driven methods [26], machine learning methods are capable of dealing with complicated datasets with various input and output variables [27] while achieving desired accuracy [28]. Machine learning has been applied to predict the compressive strength [29][30][31][32] and the modulus of elasticity [33][34][35][36] of concrete.…”

Section: Introductionmentioning

confidence: 99%

Predicting Mechanical Properties of High-Performance Fiber-Reinforced Cementitious Composites by Integrating Micromechanics and Machine Learning

Guo

Meng

et al. 2021

Materials

View full text Add to dashboard Cite

Current development of high-performance fiber-reinforced cementitious composites (HPFRCC) mainly relies on intensive experiments. The main purpose of this study is to develop a machine learning method for effective and efficient discovery and development of HPFRCC. Specifically, this research develops machine learning models to predict the mechanical properties of HPFRCC through innovative incorporation of micromechanics, aiming to increase the prediction accuracy and generalization performance by enriching and improving the datasets through data cleaning, principal component analysis (PCA), and K-fold cross-validation. This study considers a total of 14 different mix design variables and predicts the ductility of HPFRCC for the first time, in addition to the compressive and tensile strengths. Different types of machine learning methods are investigated and compared, including artificial neural network (ANN), support vector regression (SVR), classification and regression tree (CART), and extreme gradient boosting tree (XGBoost). The results show that the developed machine learning models can reasonably predict the concerned mechanical properties and can be applied to perform parametric studies for the effects of different mix design variables on the mechanical properties. This study is expected to greatly promote efficient discovery and development of HPFRCC.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting Mechanical Properties of High-Performance Fiber-Reinforced Cementitious Composites by Integrating Micromechanics and Machine Learning

Guo

Meng

et al. 2021

Materials

View full text Add to dashboard Cite

show abstract

“…The replacement of GGBFS does not significantly affect the bleeding issues for concrete. The risk factor and important issue of the "Autogenously Increasing Temperature" for SCC and major associated "Thermal stresses" and "Cracking" are also considered upon addition of slag elements in SCC [11,25,26]. Setting period for GGBFS concrete mainly depends on the reactivity of the slag used and its employed percentage present in the mix.…”

mentioning

confidence: 99%

Analysis of Mechanical Properties of Self Compacted Concrete by Partial Replacement of Cement with Industrial Wastes under Elevated Temperature

Mansoor¹,

Shah

Khan

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

Self-Compacting Concrete (SCC) differs from the normal concrete as it has the basic capacity to consolidate under its own weight. The increased awareness regarding environmental disturbances and its hazardous effects caused by blasting and crushing procedures of stone, it becomes a delicate and obvious issue for construction industry to develop an alternative remedy as material which can reduce the environmental hazards and enable high-performance strength to the concrete, which would make it durable and efficient for work. A growing trend is being established all over the world to use industrial byproducts and domestic wastes as a useful raw material in construction, as it provides an eco-friendly edge to the construction process and especially for concrete. This study aims to enlighten the use and comparative analysis for the performance of concrete with added industrial byproducts such as Ground Granulated Blast Furnace Slag (GGBFS), Silica fumes (SF) and Marble Powder (MP) in the preparation of SCC. This paper deals with the prediction of mechanical properties (i.e., compressive, tensile and flexural Strength) of self-compacting concrete by considering four major factors such as type of additive, percentage additive replaced, curing days and temperature using Artificial Neural Networks (ANNs). way to counter the hazardous effects of such materials. By using different percentages of materials as replacement for cement in concrete mix of grade M20 (Mix ratio 1:1.5:3) and a suitable water-cement (w/c) ratio 0.40, there is a broad analysis of performance of such high strength concrete with respect to the different adding ratios by testing the mechanical properties of concrete such as its compressive strength, split tensile strength and flexural strength [2]. Fresh properties for the SCC have also been monitored and examined, including the V-Funnel test, J-Ring test and Slump test. All these were carried out for the detail examination of fresh concrete behavior. Tests for hardened concrete were carried out using samples of different ratios of materials as a replacement in hardened cylinder and cube form. Many samples were casted for the comprehensive testing process. The samples with replacement ratios of 5%, 10%, 15%, 20% and 25% are tested thoroughly to analyze the hardened properties of mixes. By the utilization of these industrial byproducts and waste materials, an elevated level of pollution treatment can be achieved by the construction industry all over the world. This induction of materials in concrete tends to provide efficient and high strength ranging concrete mixes and is eco-friendly, too [3]. Previously much discussion was had on replacement of cement with Fly Ash and Marble Powder [4-9], but Ground Granulated Blast Furnace Slag (GGBFS) [4] was limited in use. Therefore, this research has contributed the comparison of Fly Ash and Marble powder with GGBFS not only at room temperature but also at elevated temperature. Furthermore, most previous studies only major focused on compressive strength [4][5][6...

show abstract

“…ANNs are used in a wide variety of problems such as recalling data, classifying patterns, performing general mapping from input to output patterns, grouping similar patterns, or solving constrained optimization problems [ 29 ]. Neural networks learn from parallel examples of input and output pairs and make generalizations [ 29 , 30 , 31 ], i.e., identifies causality between the input and the output through iterative training and using it to conduct forecast [ 4 ]. The ability to give correct or nearly correct responses to incomplete tasks and noisy or poor data makes ANNs a powerful tool for solving many civil engineering problems [ 5 , 32 ].…”

Section: Introductionmentioning

confidence: 99%

Application of Artificial Neural Networks for Prediction of Mechanical Properties of CNT/CNF Reinforced Concrete

Kekez

Kubica

2021

Materials

View full text Add to dashboard Cite

Prominence of concrete is characterized by its high mechanical properties and durability, combined with multifunctionality and aesthetic appeal. Development of alternative eco-friendly or multipurpose materials has conditioned improvements in concrete mix design to optimize concrete production speed and price, as well as carbon footprint. Artificial neural networks represent a new and efficient tool in achieving optimal concrete mixtures according to its intended function. This paper addresses concrete mix design and the application of artificial neural networks (ANNs) for self-sensing concrete. The authors review concrete mix design methods and the development of ANNs for prediction of properties for various types of concrete. Furthermore, the authors present developments and applications of ANNs for prediction of compressive strength and flexural strength of carbon nanotubes/carbon nanofibers (CNT/CNF) reinforced concrete using experimental results for the learning process. The goal is to bring the ANN approach closer to a variety of concrete researchers and possibly propose the implementation of ANNs in the civil engineering practice.

show abstract

Predicting the ingredients of self compacting concrete using artificial neural network

Cited by 133 publications

References 39 publications

Predicting Mechanical Properties of High-Performance Fiber-Reinforced Cementitious Composites by Integrating Micromechanics and Machine Learning

Predicting Mechanical Properties of High-Performance Fiber-Reinforced Cementitious Composites by Integrating Micromechanics and Machine Learning

Analysis of Mechanical Properties of Self Compacted Concrete by Partial Replacement of Cement with Industrial Wastes under Elevated Temperature

Application of Artificial Neural Networks for Prediction of Mechanical Properties of CNT/CNF Reinforced Concrete

Contact Info

Product

Resources

About