Using Neural Networks for Prediction of Properties of Polymer Concrete with Fly Ash

Bărbuţă, Marinela; Diaconescu, Rodica-Mariana; Harja, Maria

doi:10.1061/(asce)mt.1943-5533.0000413

Cited by 36 publications

(12 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Polymer concrete is a relatively novel high-quality material. Compared with cement concrete, it has many advantages such as good mechanical strength, short curing period, high adhesion, wear resistance, weather resistance, waterproof, and high insulation performance [10][11][12][13][14]. Due to these properties, polymer concrete has widespread construction applications compared with conventional cement concrete, such as prefabricated walls; hydraulic structures including dikes, reservoirs, and piers; road surfaces and decks; and underground constructions [15][16][17].…”

Section: Polymer Substratesmentioning

confidence: 99%

Recent Progress in Polymer-Based Building Materials

Shen

Jiang

Lin

et al. 2020

International Journal of Polymer Science

View full text Add to dashboard Cite

With the development of human society, the requirements for building materials are becoming higher. The development of polymer materials and their application in the field of architecture have greatly enhanced and broadened the functions of building materials. With the development of material science and technology, many functional materials have been developed. Polymer materials have many excellent properties compared with inorganic materials, and they can also be improved to enhance functional properties by blending or adding various additives (such as flame retardants, antistatic agents, and antioxidants). In this paper, polymer-based building materials are introduced with three classes according to the applications, that is, substrates, coatings, and binders, and their recent signs of progress in the preparations and applications are carefully demonstrated.

show abstract

Section: Polymer Substratesmentioning

confidence: 99%

Recent Progress in Polymer-Based Building Materials

Shen

Jiang

Lin

et al. 2020

International Journal of Polymer Science

View full text Add to dashboard Cite

show abstract

“…An artificial neuron network (ANN), a type of machine learning, is a simplified mathematical model that can simulate the function of natural biological neural networks to learn from past experience for solving new problems [27,28]. Since a large amount of data, such as compositions and properties of concrete, needs to be processed, the ordinary statistical methods cannot be sufficiently applied to the prediction of concrete properties.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Aided Design and Prediction of Environmentally Friendly Rubberised Concrete

et al. 2021

View full text Add to dashboard Cite

Not only can waste rubber enhance the properties of concrete (e.g., its dynamic damping and abrasion resistance capacity), its rational utilisation can also dramatically reduce environmental pollution and carbon footprint globally. This study is the world’s first to develop a novel machine learning-aided design and prediction of environmentally friendly concrete using waste rubber, which can drive sustainable development of infrastructure systems towards net-zero emission, which saves time and cost. In this study, artificial neuron networks (ANN) have been established to determine the design relationship between various concrete mix composites and their multiple mechanical properties simultaneously. Interestingly, it is found that almost all previous studies on the ANNs could only predict one kind of mechanical property. To enable multiple mechanical property predictions, ANN models with various architectural algorithms, hidden neurons and layers are built and tailored for benchmarking in this study. Comprehensively, all three hundred and fifty-three experimental data sets of rubberised concrete available in the open literature have been collected. In this study, the mechanical properties in focus consist of the compressive strength at day 7 (CS7), the compressive strength at day 28 (CS28), the flexural strength (FS), the tensile strength (TS) and the elastic modulus (EM). The optimal ANN architecture has been identified by customising and benchmarking the algorithms (Levenberg–Marquardt (LM), Bayesian Regularisation (BR) and Scaled Conjugate Gradient (SCG)), hidden layers (1–2) and hidden neurons (1–30). The performance of the optimal ANN architecture has been assessed by employing the mean squared error (MSE) and the coefficient of determination (R2). In addition, the prediction accuracy of the optimal ANN model has ben compared with that of the multiple linear regression (MLR).

show abstract

“…The most important studies using artificial neural networks predict compressive strength in different concretes such as self-compacting concrete [ 13 , 14 , 15 , 16 , 17 ]; high-performance concrete [ 13 , 18 ]; recycled aggregate concrete [ 19 , 20 , 21 , 22 ]; cement mortars [ 23 ]; cement mortars containing nano and micro silica [ 24 ]; concrete containing rice husk ash as a partial replacement for cement and reclaimed asphalt pavement as a replacement for aggregates [ 25 ]; concrete under different temperatures [ 15 , 26 , 27 ] and relative humidity [ 15 ]; heavy weight concrete [ 28 ]; laterized concrete [ 29 ]; polymer concrete with various percentages of fly ash [ 30 ]; silica fume concrete [ 31 ]; high-strength concrete [ 32 ]; rubberized concrete [ 33 ]; clinker mortars [ 34 ]; lightweight concrete [ 27 ]; and self-consolidating high-strength concrete containing palm oil fuel ash [ 35 ].…”

Section: Introductionmentioning

confidence: 99%

Effect of Shrinkage Reducing Admixture on Drying Shrinkage of Concrete with Different w/c Ratios

et al. 2020

View full text Add to dashboard Cite

The reduction of the moisture content of concrete during the drying process reduces the concrete’s volume and causes it to shrink. In general, concrete shrinkage is a phenomenon that causes concrete volume to dwindle and can lead to durability problems. There are different types of this phenomenon, among them chemical shrinkage, autogenous shrinkage, drying shrinkage including free shrinkage and restrained shrinkage, and thermal contraction. Shrinkage-reducing admixtures are commercially available in different forms. The present study investigates the effect of liquid propylene glycol ether on mechanical properties and free shrinkage induced by drying at different water-cement (w/c) ratios. Furthermore, the effect of shrinkage-reducing admixtures on the properties of hardened concrete such as compressive and tensile strength, electrical resistivity, modulus of elasticity, free drying shrinkage, water absorption, and depth of water penetration was investigated. The results indicated that shrinkage reducing agents performed better in a low w/c ratio and resulted in up to 50% shrinkage reduction, which was due to the surface reduction of capillary pores. The prediction of free shrinkage due to drying was also performed using an artificial neural network.

show abstract

Using Neural Networks for Prediction of Properties of Polymer Concrete with Fly Ash

Cited by 36 publications

References 19 publications

Recent Progress in Polymer-Based Building Materials

Recent Progress in Polymer-Based Building Materials

Machine Learning Aided Design and Prediction of Environmentally Friendly Rubberised Concrete

Effect of Shrinkage Reducing Admixture on Drying Shrinkage of Concrete with Different w/c Ratios

Contact Info

Product

Resources

About