Application of adaptive neuro-fuzzy technique and regression models to predict the compressive strength of geopolymer composites

Yadollahi, Mehrzad Mohabbi; Benli, Ahmet; Demirboğa, Ramazan

doi:10.1007/s00521-015-2159-6

Cited by 40 publications

(8 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A list of recent studies applying AI techniques to polymer modeling is shown in Table 3. Among these applications, the most important and greatly mentioned aspect is the prediction of polymer properties while mechanical properties are the most studied [73][74][75][76][77][78][79]. Prediction procedure usually consists of a training process, testing the performance of models, adjusting the parameters and weights, and a predictive process using the optimized and trained model to predict new solutions.…”

Section: Application Of Ai Techniques For Modeling Of Polymers and Their Compositesmentioning

confidence: 99%

Artificial Intelligence in Materials Modeling and Design

Huang

Liew

Ademiloye

et al. 2020

Arch Computat Methods Eng

View full text Add to dashboard Cite

In recent decades, the use of artificial intelligence (AI) techniques in the field of materials modeling has received significant attention owing to their excellent ability to analyze a vast amount of data and reveal correlations between several complex interrelated phenomena. In this review paper, we summarize recent advances in the applications of AI techniques for numerical modeling of different types of materials. AI techniques such as machine learning and deep learning show great advantages and potential for predicting important mechanical properties of materials and reveal how changes in certain principal parameters affect the overall behavior of engineering materials. Furthermore, in this review, we show that the application of AI techniques can significantly help to improve the design and optimize the properties of future advanced engineering materials. Finally, a perspective on the challenges and prospects of the applications of AI techniques for material modeling is presented. Highlights We present an up to date review of the application of artificial intelligence in materials modeling and design.  We comprehensively discuss past and recent applications in modeling and design of polymers, metals, ceramics and other materials. We identify current research focal points, challenges, and opportunities for the application of artificial intelligence in materials modeling and design.

show abstract

Section: Application Of Ai Techniques For Modeling Of Polymers and Their Compositesmentioning

confidence: 99%

Artificial Intelligence in Materials Modeling and Design

Huang

Liew

Ademiloye

et al. 2020

Arch Computat Methods Eng

View full text Add to dashboard Cite

show abstract

“…5 Therefore, in order to alleviate the problems associated with Portland cement production and as an alternative to OPC, environmentally friendly hybrid alkali cements and low-carbon alkali-activated materials have been developed in recent years and it is thought that these materials will contribute to the reduction of CO 2 emissions. [6][7][8][9] In alkali activation systems, mostly fly ash and GBFS as industrial waste aluminosilicate materials, which are rich in rich in amorphous alumina (Al 2 O 3 ) and Silica (SiO 2 ) activated with alkali activators, are used to partially or completely replace the cement. [10][11][12][13] In alkali activation reactions, aluminosilicate minerals are dissolved with alkali hydroxide and alkali silicate solutions before precipitation reactions forming a gel or gelation and hardening (polycondensation) and polymerization.…”

Section: Introductionmentioning

confidence: 99%

Insulating and fire‐resistant performance of slag and brick powder based one‐part alkali‐activated lightweight mortars

Köksal

Bayraktar

Bodur

et al. 2022

Structural Concrete

Self Cite

View full text Add to dashboard Cite

Waste brick powder (WBP) has enough pozzolanic characteristics to be employed as a supplemental cementing material in Portland cement-based concrete or as a precursor in the manufacture of alkali activated materials.This study was aimed to study the strength, thermal, microstructural and durability properties of ground blast furnace slag (GBFS) and WBP based one-part alkali-activated lightweight mortars (AAMs) produced with expanded vermiculite.One-part AAM mixtures were produced by using GBFS and WBP as binary precursors. Sodium metasilicate powder was used as the alkali activator. Two curing regimes namely heat curing at 75 C for 24 h and air curing at ambient conditions were adopted. GBFS was used as main binder and WBP was added at the rates of 0%, 10%, 25%, and 50% instead of GBFS. Four different mixtures were prepared by replacing GBFS at the rates of 0%, 10%, 25%, and 50% with WBP for each curing regime (totally eight mixtures). Expanded vermiculite powder were used as lightweight aggregates in all mixtures. The effects of WBP on AAM mixtures properties, including flowability, compressive strength, flexural strength, dry bulk density, thermal conductivity, porosity, and water absorption were studied. The effects of WBP and curing regime on drying shrinkage, sorptivity were also investigated. High temperature performance of the produced mixtures were determined.Results showed that air-cured WBP incorporated AAM mixtures exhibited better compressive strength, flexural strength, shrinkage, and sorptivity performance than the heat-cured WBP incorporated AAM mixtures. The air-cured AAM mixtures containing 25% WBP achieved the best results of 5.69 and 1.43 MPa for compressive strength and flexural strength at test age of 28 days. The heat-cured 50% WBP incorporated AAM mixture showed the best high temperature resistance and the lowest thermal conductivity. K E Y W O R D Scuring regimes, expanded vermiculite powder, ground blast furnace slag, one-part alkaliactivated, waste brick powder

show abstract

“…Yadollahi et al [21] used ANN to predict the CS of geopolymer composites. Yadollahi et al [22] predicted the CS of geopolymer composites using adaptive network-based fuzzy inference systems (ANFIS), two linear and nonlinear regression models. Yaseen et al [23] predicted the CS of lightweight foamed concretes using extreme learning machine (ELM) and M5 tree models.…”

Section: Introductionmentioning

confidence: 99%

Compressive Strength Prediction of Ferrochrome Slag Based Geopolymer Concretes Produced Under Different Curing Conditions by Using Prediction Methods

Kalkan¹,

Karakoç²,

Özcan³

2021

Deu Muhendislik Fakultesi Fen Ve Muhendislik

View full text Add to dashboard Cite

In this study, compressive strength (CS) values of ferrochrome slag (FS) based geopolymer concretes in different curing conditions were investigated. Ground FS was activated with the mixture of sodium hydroxide and sodium silicate. The silica modulus (Ms) of the geopolymer concrete samples were selected as 1.25, 1.50 and 1.75. Also, samples were prepared by substituting 0%, 10% and 20% silica fume (SF) replacement the FS. Thus, 9 groups geopolymer concrete samples were produced. The CS values of the samples were determined on different curing times (24, 48, 72 and 96 hours) and curing temperatures (23, 40, 60, 80 and 100 °C). At the same time, multilayer perceptron neural network (MLPNN), extreme learning machine neural network (ELMNN) and M5 model tree were modeled for the CS prediction of the samples, the predict and experimental results were compared. According to the experiment results, it was determined that the CS values generally increased as the curing time increased, but with the addition of SF, the CS values generally decreased. The highest CS was obtained in the sample containing 100% FS that had silica modulus of 1.25 and cured at 100 °C for 24-48-72 or 96 hours. The R 2 values of MLPNN, ELMNN and M5 model tree in testing phase were 0.956, 0.935 and 0.922, respectively. MLPNN, the model that gave the best predict result, had root mean square error (RMSE) of 0.723 and normalized root mean square error (NMRSE) of 26.485 in testing.

show abstract

Application of adaptive neuro-fuzzy technique and regression models to predict the compressive strength of geopolymer composites

Cited by 40 publications

References 31 publications

Artificial Intelligence in Materials Modeling and Design

Artificial Intelligence in Materials Modeling and Design

Insulating and fire‐resistant performance of slag and brick powder based one‐part alkali‐activated lightweight mortars

Compressive Strength Prediction of Ferrochrome Slag Based Geopolymer Concretes Produced Under Different Curing Conditions by Using Prediction Methods

Contact Info

Product

Resources

About