Prediction of the Chloride Resistance of Concrete Modified with High Calcium Fly Ash Using Machine Learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Marks M
PROVIDER: S-EPMC5458865 | biostudies-other | 2015 Dec
REPOSITORIES: biostudies-other
Similar Datasets
Project description:Every year, a large amount of solid waste such as fly ash and slag is generated worldwide. If these solid wastes are used in concrete mixes to make concrete, it can effectively save resources and protect the environment. The compressive strength of concrete is an essential indicator for testing its quality, and its prediction is affected by many factors. It is difficult to predict its strength accurately. Therefore, based on the current popular machine learning supervised learning algorithms: Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVR), three models established a nonlinear mapping between multi-factor features and target feature concrete compressive strength. Using the three completed training models, we validated the test set with 206 example sets, and the Root Mean Square Error (RMSE), fitting coefficient (R2), and Mean Absolute Error (MAE) were used as evaluation metrics. The validation results showed that the values of RMSE, R2, and MAE for the RF model were 0.1, 0.9, and 0.21, respectively; the values of XGBoost model were 0.05, 0.95, and 0.15, respectively. The values of SVR were 0.15, 0.86, and 0.3, respectively. As a result, Extreme Gradient Boosting (XGBoost) has better generalization ability and prediction accuracy than the other two algorithms.
| S-EPMC9794082 | biostudies-literature
Project description:Owing to its importance in the assessment of reinforced concrete structures, it is essential to determine the chloride diffusivity of fly ash concrete. This paper presents an investigation into the diffusion characteristics of chloride ions in fly ash concrete. Through experiment, the relationship between chloride diffusivity and curing age up to 1800 days is measured and the effects of curing age, water/binder ratio, aggregate volume fraction, and fly ash content (i.e., percentage of total cementitious material by mass) on chloride diffusivity are evaluated. It is found that the chloride diffusivity decreases with the increase of curing age, aggregate volume fraction, and fly ash content, but increases with the increase of water/binder ratio. In analytical modeling, an equivalent aggregate model is constructed and the equivalent interfacial transition zone (ITZ) thickness is derived analytically. With the equivalent aggregate model, three-phase fly ash concrete reduces to a two-phase composite material. By extending the Maxwell method, the chloride diffusivity of fly ash concrete is formulated. Finally, the validity of the analytical method is verified by experimental results.
| S-EPMC7079598 | biostudies-literature
Project description:The objective of this paper is to examine the possible use of new blended cements containing calcareous fly ash in structural concrete, potentially adequate for structural elements of nuclear power plants. The investigation included five new cements made with different contents of non-clinker constituents: calcareous fly ash, siliceous fly ash, ground granulated blastfurnace slag, and a reference cement-ordinary Portland cement. The influence of innovative cements on the resistance of concrete to chloride and carbonation exposure was studied. Additionally, an evaluation of the microstructure was performed using optical microscopy on concrete thin sections. Test results revealed a substantial improvement of the resistance to chloride ion penetration into concrete containing blended cements. The resistance was higher for increased clinker replacement levels and increased with curing time. However, concrete made with blended cements exhibited higher depth of carbonation than the Portland cement concrete, except the Portland-fly ash cement with 14.3% of calcareous fly ash. The thin sections analysis confirmed the values of the carbonation depth obtained from the phenolphthalein test. Test results indicate the possible range of application for new cements containing calcareous fly ash.
| S-EPMC5456527 | biostudies-other
Project description:This work aims to study the effect of Ca(C18H35O2)2 (calcium stearate) on the properties of concrete by using Portland composite cement (PCC) and fly ash as binders. The calcium stearate content used in the concrete here consists of 0, 1, 5, and 10 kg per m3 of concrete volume, or alternatively, 0 to 2.85% by the weight of cement. We have performed several tests for each of the contents, namely, compressive strength, water absorption, chloride ion infiltration, and accelerated corrosion tests. According to the testing, we have found that with the addition of calcium stearate at 1 kg/m3 in self-compacting concrete (SCC) with 10% fly ash, the mechanical and physical properties of SCC can be improved significantly when compared to the SCC without fly ash and calcium stearate, resulting in a stable compressive strength, lower water absorption, lower chloride ion infiltration, and lower degree of corrosion attack.
| S-EPMC7143480 | biostudies-literature
Project description:Concrete is a cost-effective construction material widely used in various building infrastructure projects. High-performance concrete, characterized by strength and durability, is crucial for structures that must withstand heavy loads and extreme weather conditions. Accurate prediction of concrete strength under different mixtures and loading conditions is essential for optimizing performance, reducing costs, and enhancing safety. Recent advancements in machine learning offer solutions to challenges in structural engineering, including concrete strength prediction. This paper evaluated the performance of eight popular machine learning models, encompassing regression methods such as Linear, Ridge, and LASSO, as well as tree-based models like Decision Trees, Random Forests, XGBoost, SVM, and ANN. The assessment was conducted using a standard dataset comprising 1030 concrete samples. Our experimental results demonstrated that ensemble learning techniques, notably XGBoost, outperformed other algorithms with an R-Square (R2) of 0.91 and a Root Mean Squared Error (RMSE) of 4.37. Additionally, we employed the SHAP (SHapley Additive exPlanations) technique to analyze the XGBoost model, providing civil engineers with insights to make informed decisions regarding concrete mix design and construction practices.
| S-EPMC10646149 | biostudies-literature
Project description:Geopolymer concrete (GPC) has drawn widespread attention as a universally accepted ideal green material to improve environmental conditions in recent years. The present study systematically quantifies and compares the environmental impact of fly ash GPC and ordinary Portland cement (OPC) concrete under different strength grades by conducting life cycle assessment (LCA). The alkali activator solution to fly ash ratio (S/F), sodium hydroxide concentration (CNaOH), and sodium silicate to sodium hydroxide ratio (SS/SH) were further used as three key parameters to consider their sensitivity to strength and CO2 emissions. The correlation and influence rules were analyzed by Multivariate Analysis of Variance (MANOVA) and Gray Relational Analysis (GRA). The results indicated that the CO2 emission of GPC can be reduced by 62.73%, and the correlation between CO2 emission and compressive strength is not significant for GPC. The degree of influence of the three factors on the compressive strength is CNaOH (66.5%) > SS/SH (20.7%) > S/F (9%) and on CO2 emissions is S/F (87.2%) > SS/SH (10.3%) > CNaOH (2.4%). Fly ash GPC effectively controls the environmental deterioration without compromising its compressive strength; in fact, it even in favor.
| S-EPMC8658180 | biostudies-literature
Project description:High-calcium fly ash (FH) is the combustion residue from electric power plants burning lignite or sub-bituminous coal. As a mineral admixture, FH can be used to produce high-strength concrete and high-performance concrete. The development of chemical and mechanical properties is a crucial factor for appropriately using FH in the concrete industry. To achieve sustainable development in the concrete industry, this paper presents a theoretical model to systematically evaluate the property developments of FH blended concrete. The proposed model analyzes the cement hydration, the reaction of free CaO in FH, and the reaction of phases in FH other than free CaO. The mutual interactions among cement hydration, the reaction of free CaO in FH, and the reaction of other phases in FH are also considered through the calcium hydroxide contents and the capillary water contents. Using the hydration degree of cement, the reaction degree of free CaO in FH, and the reaction degree of other phases in FH, the proposed model evaluates the calcium hydroxide contents, the reaction degree of FH, chemically bound water, porosity, and the compressive strength of hardening concrete with different water to binder ratios and FH replacement ratios. The evaluated results are compared to experimental results, and good consistencies are found.
| S-EPMC5512662 | biostudies-other
Project description:This paper presents research on the impact of fly ash addition on selected physical and mechanical parameters of concrete made with slag cement. Experimental tests were carried out to measure the migration of chloride ions in concrete, the tightness of concrete exposed to water under pressure, and the compressive strength and tensile strength of concrete during splitting. Six series of concrete mixes made with CEM IIIA 42.5 and 32.5 cement were tested. The base concrete mix was modified by adding fly ash as a partial cement substitute in the amounts of 25% and 33%. A comparative analysis of the obtained results indicates a significant improvement in tightness, especially in concrete based on CEM IIIA 32.5 cement and resistance to chloride ion penetration for the concretes containing fly ash additive. In the concretes containing fly ash additive, a slower rate of initial strength increase and high strength over a long period of maturation are shown. In accordance with the presented research results, it is suggested that changes to the European standardization system be considered, to allow the use of fly ash additive in concrete made with CEM IIIA 42.5 or 32.5 cement classes. Such a solution is not currently acceptable in standards in some European Countries.
| S-EPMC7435652 | biostudies-literature
Project description:Compressive and flexural strength are the crucial properties of a material. The strength of recycled aggregate concrete (RAC) is comparatively lower than that of natural aggregate concrete. Several factors, including the recycled aggregate replacement ratio, parent concrete strength, water-cement ratio, water absorption, density of the recycled aggregate, etc., affect the RAC's strength. Several studies have been performed to study the impact of these factors individually. However, it is challenging to examine their combined impact on the strength of RAC through experimental investigations. Experimental studies involve casting, curing, and testing samples, for which substantial effort, price, and time are needed. For rapid and cost-effective research, it is critical to apply new methods to the stated purpose. In this research, the compressive and flexural strengths of RAC were predicted using ensemble machine learning methods, including gradient boosting and random forest. Twelve input factors were used in the dataset, and their influence on the strength of RAC was analyzed. The models were validated and compared using correlation coefficients (R2), variance between predicted and experimental results, statistical tests, and k-fold analysis. The random forest approach outperformed gradient boosting in anticipating the strength of RAC, with an R2 of 0.91 and 0.86 for compressive and flexural strength, respectively. The models' decreased error values, such as mean absolute error (MAE) and root-mean-square error (RMSE), confirmed the higher precision of the random forest models. The MAE values for the random forest models were 4.19 MPa and 0.56 MPa, whereas the MAE values for the gradient boosting models were 4.78 MPa and 0.64 MPa, for compressive and flexural strengths, respectively. Machine learning technologies will benefit the construction sector by facilitating the evaluation of material properties in a quick and cost-effective manner.
| S-EPMC9025364 | biostudies-literature
Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status. RNA was isolated from 199 primary breast cancer patients. A machine learning classifier was built to predict ER status using only three gene features.
2013-01-01 | E-GEOD-29210 | biostudies-arrayexpress