Effects of binder proportion and curing condition on the mechanical characteristics of volcanic ash- and slag-based geopolymer mortars; machine learning integrated experimental study

Nofalah, Mohammad-Hossein; Ghadir, Pooria; Hasanzadehshooiili, Hadi; Aminpour, Mohammad; Javadi, Akbar A.; Nazem, Majidreza

doi:10.1016/j.conbuildmat.2023.132330

Cited by 12 publications

(3 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of course, other studies have also reported similar performance. At the same time, it is important to note that the datasets and machine learning methods used in each study are different, so direct comparison of performance values may not always be appropriate [79]. Nevertheless, it is obvious that the optimal model RBF constructed in this study using the basic hypothesis-the three-level characteristic interaction hypothesis-and the basic method-the new method of parameter expansion classification-provides accurate predictions with the largest R 2 value and relatively low RMSE value.…”

Section: Model Comparison and Limitation Analysismentioning

confidence: 99%

Prediction of the Unconfined Compressive Strength of Salinized Frozen Soil Based on Machine Learning

Zhao,

Bing

2024

Buildings

View full text Add to dashboard Cite

Unconfined compressive strength (UCS) is an important parameter of rock and soil mechanical behavior in foundation engineering design and construction. In this study, salinized frozen soil is selected as the research object, and soil GDS tests, ultrasonic tests, and scanning electron microscopy (SEM) tests are conducted. Based on the classification method of the model parameters, 2 macroscopic parameters, 38 mesoscopic parameters, and 19 microscopic parameters are selected. A machine learning model is used to predict the strength of soil considering the three-level characteristic parameters. Four accuracy evaluation indicators are used to evaluate six machine learning models. The results show that the radial basis function (RBF) has the best UCS predictive performance for both the training and testing stages. In terms of acceptable accuracy and stability loss, through the analysis of the gray correlation and rough set of the three-level parameters, the total amount and proportion of parameters are optimized so that there are 2, 16, and 16 macro, meso, and micro parameters in a sequence, respectively. In the simulation of the aforementioned six machine learning models with the optimized parameters, the RBF still performs optimally. In addition, after parameter optimization, the sensitivity proportion of the third-level parameters is more reasonable. The RBF model with optimized parameters proved to be a more effective method for predicting soil UCS. This study improves the prediction ability of the UCS by classifying and optimizing the model parameters and provides a useful reference for future research on salty soil strength parameters in seasonally frozen regions.

show abstract

Section: Model Comparison and Limitation Analysismentioning

confidence: 99%

Prediction of the Unconfined Compressive Strength of Salinized Frozen Soil Based on Machine Learning

Zhao,

Bing

2024

Buildings

View full text Add to dashboard Cite

show abstract

“…In the XRD pattern, FA exhibits many sharp peaks, whereas GGBS exhibits a broad peak between 15° and 35° (2θ), with only a few weak sharp peaks. In comparable conditions, the compressive strength of FA geopolymer is typically 40% to 70% of that of GGBS geopolymer [ 29 , 50 ]. Mao et al [ 51 ] demonstrated this by alkali-activating fine basalt powder containing only 4% amorphous content.…”

Section: Geopolymer Materialsmentioning

confidence: 99%

Lunar Regolith Geopolymer Concrete for In-Situ Construction of Lunar Bases: A Review

Zheng,

Zhao,

Sun

et al. 2024

Polymers

View full text Add to dashboard Cite

The construction of lunar bases represents a fundamental challenge for deep space exploration, lunar research, and the exploitation of lunar resources. In-situ resource utilization (ISRU) technology constitutes a pivotal tool for constructing lunar bases. Using lunar regolith to create geopolymers as construction materials offers multiple advantages as an ISRU technique. This paper discusses the principle of geopolymer for lunar regolith, focusing on the reaction principle of geopolymer. It also analyzes the applicability of geopolymer under the effects of the lunar surface environment and the differences between the highland and mare lunar regolith. This paper summarizes the characteristics of existing lunar regolith simulants and the research on the mechanical properties of lunar regolith geopolymers using lunar regolith simulants. Highland lunar regolith samples contain approximately 36% amorphous substances, the content of silicon is approximately 28%, and the ratios of Si/Al and Si/Ca are approximately 1.5 and 2.6, respectively. They are more suitable as precursor materials for geopolymers than mare samples. The compressive strength of lunar regolith geopolymer is mainly in the range of 18~30 MPa. Sodium silicate is the most commonly utilized activator for lunar regolith geopolymers; alkalinity in the range of 7% to 10% and modulus in the range of 0.8 to 2.0 are suitable. A vacuum environment and multiple temperature cycles reduce the mechanical properties of geopolymers by 8% to 70%. Future research should be concentrated on the precision control of the lunar regolith’s chemical properties and the alkali activation efficacy of geopolymers in the lunar environment.

show abstract

“…According to the available literature, numerous research studies have delved into the chemo-mechanical properties of geopolymers based on fly ash (FA) and slag (SG) [46][47][48][49]. However, there is a noticeable scarcity of publications addressing the transport characteristics of these geopolymers.…”

Section: Introductionmentioning

confidence: 99%

Influence of Blast Furnace Slag on Pore Structure and Transport Characteristics in Low-Calcium Fly-Ash-Based Geopolymer Concrete

Azimi,

Toufigh

2023

Sustainability

View full text Add to dashboard Cite

Alkali-activated fly ash slag (AAFS) has emerged as a novel and environmentally sustainable construction material, garnering substantial attention due to its commendable mechanical attributes and minimal ecological footprint. This investigation delves into the influence of slag incorporation on the strength, pore structure, and transport characteristics of AAFS, encompassing various levels of fly ash replacement with slag. To assess the mechanical properties of AAFS concrete, unconfined compression and ultrasonic pulse velocity tests were conducted. Meanwhile, microstructural and mineralogical alterations were scrutinized through porosity, N2-adsorption/desorption, and SEM/EDX assessments. In addition, transport properties were gauged using electrical surface resistivity, water permeability, and water vapor permeability tests. According to the results, a remarkable refinement in the pore volume was found by increasing the slag content. The volume of the gel pores and surface area increased significantly associated with the increase in tortuosity. Accordingly, Ca inclusion in the cross-linked sodium aluminosilicate hydrate gel remarkably reduced the transport properties.

show abstract

Effects of binder proportion and curing condition on the mechanical characteristics of volcanic ash- and slag-based geopolymer mortars; machine learning integrated experimental study

Cited by 12 publications

References 81 publications

Prediction of the Unconfined Compressive Strength of Salinized Frozen Soil Based on Machine Learning

Prediction of the Unconfined Compressive Strength of Salinized Frozen Soil Based on Machine Learning

Lunar Regolith Geopolymer Concrete for In-Situ Construction of Lunar Bases: A Review

Influence of Blast Furnace Slag on Pore Structure and Transport Characteristics in Low-Calcium Fly-Ash-Based Geopolymer Concrete

Contact Info

Product

Resources

About