Artificial neural networks test for the prediction of chemical stability of pyroclastic deposits-based AAMs and comparison with conventional mathematical approach (MLR)

Abstract The investigation on the reticulation degree of volcanic alkali-activated materials, AAMs, were experimentally determined in terms of chemico-physical properties: weight loss after leaching test in water, ionic conductivity and pH of the leachate and compressive strength. Artificial neural network (ANN) was successfully applied to predict the chemical stability of volcanic alkali-activated materials. Nine input data per each chemico-physical parameter were used to train each ANN. The training series of specific volcanic precursors were tested also for the other one. Excellent correlations between experimental and calculated data of the same precursor type were found reaching values around one. The evidence of strong effect on chemical stability of the alkaline activator SiO2/Na2O molar ratio as well as the Si/Al ratio of precursor mixtures on the reticulation degree of ghiara-based formulation with respect to volcanic ash-based materials is presented. It must be noted that such effect was much less pronounced on the compressive strength values, appearing more insensitive the molar ratio of the alkaline activator. The comparison of the ANN results with more conventional multiple linear regression (MLR) testifies the higher prediction performance of the first method. MLRs results, less significant, are useful to confirm the powerful capacity of ANNs to identify the more suitable formulation using a set of experimental AAMs. This study, as few others, on the correlation between chemical stability and compressive strength of AAMs provide a great contribution in the direction of durability and in-life mechanical performance of these class of materials. Graphic abstract

Download Full-text

Machine Learning Approaches for Prediction of the Compressive Strength of Alkali Activated Termite Mound Soil

Applied Sciences ◽

10.3390/app11114754 ◽

2021 ◽

Vol 11 (11) ◽

pp. 4754

Author(s):

Assia Aboubakar Mahamat ◽

Moussa Mahamat Boukar ◽

Nurudeen Mahmud Ibrahim ◽

Tido Tiwa Stanislas ◽

Numfor Linda Bih ◽

...

Keyword(s):

Compressive Strength ◽

Construction Materials ◽

Curing Temperature ◽

Sustainable Construction ◽

Support Vector ◽

Learning Approaches ◽

Artificial Neural Network Ann ◽

Curing Regime ◽

Alkali Activated

Earth-based materials have shown promise in the development of ecofriendly and sustainable construction materials. However, their unconventional usage in the construction field makes the estimation of their properties difficult and inaccurate. Often, the determination of their properties is conducted based on a conventional materials procedure. Hence, there is inaccuracy in understanding the properties of the unconventional materials. To obtain more accurate properties, a support vector machine (SVM), artificial neural network (ANN) and linear regression (LR) were used to predict the compressive strength of the alkali-activated termite soil. In this study, factors such as activator concentration, Si/Al, initial curing temperature, water absorption, weight and curing regime were used as input parameters due to their significant effect in the compressive strength. The experimental results depict that SVM outperforms ANN and LR in terms of R2 score and root mean square error (RMSE).

Download Full-text

Modeling the influence of chemical composition on compressive strength behavior of alkali-activated phosphorus slag cement using statistical design

Canadian Journal of Civil Engineering ◽

10.1139/cjce-2018-0132 ◽

2018 ◽

Vol 45 (12) ◽

pp. 1073-1083 ◽

Cited By ~ 3

Author(s):

Hamideh Mehdizadeh ◽

Ebrahim Najafi Kani

Keyword(s):

Compressive Strength ◽

Chemical Composition ◽

Statistical Design ◽

Molar Ratio ◽

Statistical Experimental Design ◽

Molar Ratios ◽

Strength Behavior ◽

Optimum Chemical Composition ◽

Optimum Chemical ◽

Alkali Activated

In this study, a statistical experimental design based on response surface methodology (RSM) has been applied to predict and optimize the compressive strength of alkali-activated phosphorus slag in different ages (3, 7, and 28 days). For this purpose, the binder samples were prepared with different molar ratios of SiO2/Na2O (S/N), Na2O/Al2O3(Na/Al), and H2O/Al2O3(H/Al) as alkali activator. Results showed that S/N molar ratio plays its role in early ages of curing and Na/Al molar ratio, and showed its significant effect on 7 and 28 days of compressive strength. H/Al molar ratio had the most significant effect on compressive strength compared to the other parameters. The derived RSM models were statistically adequate and could be used to predict the compressive strength. The optimum chemical composition of activator to obtain the highest compressive strength was achieved as 0.39, 1.34, and 30 for S/N, Na/Al, and H/Al molar ratios, respectively, with compressive strength of 30, 65, and 100 MPa at 3, 7, and 28 days of curing.

Download Full-text

Prediction of Compressive Strength of Concrete in Wet-Dry Environment by BP Artificial Neural Networks

Advances in Materials Science and Engineering ◽

10.1155/2018/6204942 ◽

2018 ◽

Vol 2018 ◽

pp. 1-11 ◽

Cited By ~ 7

Author(s):

Chengyao Liang ◽

Chunxiang Qian ◽

Huaicheng Chen ◽

Wence Kang

Keyword(s):

Neural Networks ◽

Compressive Strength ◽

Artificial Neural Networks ◽

Statistical Analysis ◽

Influencing Factors ◽

Mechanical Performance ◽

Tidal Zone ◽

Structure Degradation ◽

Compressive Strength Of Concrete ◽

Artificial Neural

Engineering structure degradation in the marine environment, especially the tidal zone and splash zone, is serious. The compressive strength of concrete exposed to the wet-dry cycle is investigated in this study. Several significant influencing factors of compressive strength of concrete in the wet-dry environment are selected. Then, the database of compressive strength influencing factors is established from vast literature after a statistical analysis of those data. Backpropagation artificial neural networks (BP-ANNs) are applied to establish a multifactorial model to predict the compressive strength of concrete in the wet-dry exposure environment. Furthermore, experiments are done to verify the generalization of the BP-ANN model. This model turns out to give a high accuracy and statistical analysis to confirm some rules in marine concrete mix and exposure. In general, this model is practical to predict the concrete mechanical performance.

Download Full-text

One-Part Alkali-Activated Pastes and Mortars Prepared with Metakaolin and Biomass Ash

Applied Sciences ◽

10.3390/app10165610 ◽

2020 ◽

Vol 10 (16) ◽

pp. 5610

Author(s):

Alessandra Mobili ◽

Francesca Tittarelli ◽

Hubert Rahier

Keyword(s):

Compressive Strength ◽

Reaction Kinetics ◽

Isothermal Calorimetry ◽

Molar Ratio ◽

Alkaline Solutions ◽

Strength Increase ◽

Biomass Ash ◽

Solid Ratio ◽

User Friendly ◽

Alkali Activated

Common alkali-activated materials (AAMs) are usually manufactured with highly alkaline solutions. However, alkaline solutions are dangerous for workers who must wear gloves, masks, and glasses when handling them. This issue makes common (or two-part) AAMs not user-friendly and problematic for bulk production if no safety procedures are followed. In this paper, the possibility of manufacturing alkali-activated pastes and mortars without alkaline solution is investigated. These innovative one-part AAMs have been prepared with metakaolin as the aluminosilicate precursor, potassium-rich biomass ash as the alkaline activator, and water. AAMs have been prepared by varying the K/Al molar ratio: pastes have been studied in terms of reaction kinetics, through isothermal calorimetry, and mortars have been tested in terms of mechanical compressive strength. Results show that the K/Al molar ratio governs both the reaction kinetics and the mechanical strength of these innovative materials. The highest compressive strength is obtained when the K/Al ratio is equal to 2.5 and the water/solid ratio is equal to 0.49. If biomass ash is heated at 700 °C to decompose the calcium carbonate, its reactivity and the final compressive strength increase.

Download Full-text

High Strength Alkali Activated Slag Cements with Controlled Setting Times and Early Strength Gain

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.1100.44 ◽

2015 ◽

Vol 1100 ◽

pp. 44-49 ◽

Cited By ~ 3

Author(s):

Pavel Krivenko ◽

Oleg Petropavlovsky ◽

Vit Petranek ◽

Vasiliy Pushkar ◽

Grigorii Vozniuk

Keyword(s):

Compressive Strength ◽

Blast Furnace ◽

Water Glass ◽

High Strength ◽

Strength Gain ◽

Setting Times ◽

Alkaline Activator ◽

Early Strength ◽

Activated Slag ◽

Alkali Activated

The paper discusses approaches to compositional build-up of high strength alkali activated cements made using water glass as alkaline activator represented by commercial products in a form of powder and liquid. The purpose was to study the influence of fineness of ground granulated blast-furnace slags, admixtures and additives, compatible with alkali activated cements, water glass and mode of manufacturing technology in order to reach high compressive strength (≥ 80 MPa at standard age (28 days)) and early strength (≥ 20 MPa after 3 h of hardening in normal conditions).

Download Full-text

Properties of Alkli-Activated Slag Cement Compounded with Soluble Glasses with a High Silicate Modulus

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.712-715.905 ◽

2013 ◽

Vol 712-715 ◽

pp. 905-908

Author(s):

Qun Pan ◽

Bin Zhu ◽

Xiao Huang ◽

Lin Liu

Keyword(s):

Compressive Strength ◽

Cement Mortar ◽

Strength Characteristics ◽

Slag Cement ◽

Alkali Activated Slag ◽

Cement Mortars ◽

Alkaline Activator ◽

Activated Slag ◽

Alkali Activated ◽

High Silicate

Properties of alkali-activated slag cements compounded with soluble glasse with a high silicate modulus Ms=2.6 were detailedly studied in this paper, including compressive strength and flexure strength characterictics at the ages of 3,7,28 days and flow values of fresh cement mixtures on a jolting table. As a result, with the compressive strength at the age of 28 days of 95.6-107.8 MPa has been developed, and the flow values and strength characteristics of alkali-activated slag cement mortars increased with increase in a water to cement (alkaline activator solution to slag) ratio, and the flow value (determined on the cement mortar mixtures) would reach 145 mm. Moreover, the development speed of strength characteristics of mortar specimens would be affected negatively by increasing of water demand (requirement).

Download Full-text

Artificial neural network (ANN) prediction of compressive strength of VARTM processed polymer composites

Computational Materials Science ◽

10.1016/j.commatsci.2004.11.001 ◽

2005 ◽

Vol 34 (1) ◽

pp. 99-105 ◽

Cited By ~ 28

Author(s):

A. Tugˇrul Seyhan ◽

Gökmen Tayfur ◽

Murat Karakurt ◽

Metin Tanogˇlu

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Compressive Strength ◽

Polymer Composites ◽

Artificial Neural ◽

Artificial Neural Network Ann

Download Full-text

Prediction of Compressive Strength of Plain Concrete Confined with Ferrocement using Artificial Neural Network (ANN) and Comparison with Existing Mathematical Models

American Journal of Civil Engineering and Architecture ◽

10.12691/ajcea-1-1-2 ◽

2013 ◽

Vol 1 (1) ◽

pp. 7-14 ◽

Cited By ~ 6

Author(s):

S. U. Khan ◽

T. Ayub ◽

S. F. A. Rafeeqi

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Compressive Strength ◽

Mathematical Models ◽

Plain Concrete ◽

Artificial Neural ◽

Artificial Neural Network Ann

Download Full-text

Effect of Sodium Aluminate Dosage as a Solid Alkaline Activator on the Properties of Alkali-Activated Slag Paste

Advances in Materials Science and Engineering ◽

10.1155/2021/6658588 ◽

2021 ◽

Vol 2021 ◽

pp. 1-13

Author(s):

Bin Chen ◽

Jun Wang ◽

Jinyou Zhao

Keyword(s):

Mechanical Properties ◽

Compressive Strength ◽

Setting Time ◽

Sodium Aluminate ◽

Hydration Reaction ◽

Hydration Products ◽

Alkali Activated Slag ◽

Alkaline Activator ◽

Activated Slag ◽

Alkali Activated

Extensive research into alkali-activated slag as a green gel material to substitute for cement has been done because of the advantages of low-carbon dioxide emissions and recycling of industrial solid waste. Alkali-activated slag usually has good mechanical properties, but the too fast setting time restricted its application and promotion. Changing the composition of alkaline activator could optimize setting time, usually making it by adding sodium carbonate or sodium sulfate but this would cause insufficient hydration reaction power and hinder compressive strength growth. In this paper, the effect of sodium aluminate dosage as an alkaline activator on the setting time, fluidity, compressive strength, hydration products, and microstructures was studied through experiments. It is fair to say that an appropriate amount of sodium aluminate could obtain a suitable setting time and better compressive strength. Sodium aluminate provided enough hydroxyl ions for the paste to promote the hydration reaction process that ensured obtaining high compressive strength and soluble aluminium formed precipitate wrapped on the surface of slag to inhibit the hydration reaction process in the early phase that prolonged setting time. The hydration mechanism research found that sodium aluminate played a key role in the formation of higher cross-linked gel hydration products in the late phase of the process. Preparing an alkali-activated slag with excellent mechanical properties and suitable setting time will significantly contribute to its application and promotion.

Download Full-text