• Computers and Concrete
• /
• v.32 no.3
• /
• pp.327-337
• /
• 2023

Concrete is the most widely used building material, with various types including high- and ultra-high-strength, reinforced, normal, and lightweight concretes. However, accurately predicting concrete properties is challenging due to the geotechnical design code's requirement for specific characteristics. To overcome this issue, researchers have turned to new technologies like machine learning to develop proper methodologies for concrete specification. In this study, we propose a highly accurate deep learning-based predictive model to investigate the compressive strength (UCS) of lightweight concrete with natural aggregates (pumice). Our model was implemented on a database containing 249 experimental records and revealed that water, cement, water-cement ratio, fine-coarse aggregate, aggregate substitution rate, fine aggregate replacement, and superplasticizer are the most influential covariates on UCS. To validate our model, we trained and tested it on random subsets of the database, and its performance was evaluated using a confusion matrix and receiver operating characteristic (ROC) overall accuracy. The proposed model was compared with widely known machine learning methods such as MLP, SVM, and DT classifiers to assess its capability. In addition, the model was tested on 25 laboratory UCS tests to evaluate its predictability. Our findings showed that the proposed model achieved the highest accuracy (accuracy=0.97, precision=0.97) and the lowest error rate with a high learning rate (R2=0.914), as confirmed by ROC (AUC=0.971), which is higher than other classifiers. Therefore, the proposed method demonstrates a high level of performance and capability for UCS predictions.

• Geomechanics and Engineering
• /
• v.37 no.1
• /
• pp.85-95
• /
• 2024

This study investigates the influence of nano-silica and basalt fiber content, curing duration, and freeze-thaw cycles on the static and dynamic properties of soil specimens. A comprehensive series of tests, including Unconfined Compressive Strength (UCS), static triaxial, and dynamic triaxial tests, were conducted. Additionally, scanning electron microscopy (SEM) analysis was employed to examine the microstructure of treated specimens. Results indicate that a combination of 1% fiber and 10% nano-silica yields optimal soil enhancement. The failure patterns of specimens varied significantly depending on the type of additive. Static triaxial tests revealed a notable reduction in the brittleness index (IB) with the inclusion of basalt fibers. Specimens containing 10% nano-silica and 1% fiber exhibited superior shear strength parameters and UCS. The highest cohesion and friction angle were obtained for treated specimens with 10% nano-silica and 1% fiber, 90 kPa and 37.8°, respectively. Furthermore, an increase in curing time led to a significant increase in UCS values for specimens containing nano-silica. Additionally, the addition of fiber resulted in a decrease in IB, while the addition of nano-silica led to an increase in IB. Increasing nano-silica content in stabilized specimens enhanced shear modulus while decreasing the damping ratio. Freeze-thaw cycles were found to decrease the cohesion of treated specimens based on the results of static triaxial tests. Specimens treated with 10% nano-silica and 1% fiber experienced a reduction in shear modulus and an increase in the damping ratio under freeze-thaw conditions. SEM analysis reveals dense microstructure in nano-silica stabilized specimens, enhanced adhesion of soil particles and fibers, and increased roughness on fiber surfaces.

• Tunnel and Underground Space
• /
• v.34 no.2
• /
• pp.143-153
• /
• 2024

Tunnel Boring Machine (TBM) method is a tunnel excavation method that produces lower levels of noise and vibration during excavation compared to drilling and blasting methods, and it offers higher stability. It is increasingly being applied to tunnel projects worldwide. The disc cutter is an excavation tool mounted on the cutterhead of a TBM, which constantly interacts with the ground at the tunnel face, inevitably leading to wear. In this study quantitatively predicted disc cutter wear using geological conditions, TBM operational parameters, and machine learning algorithms. Among the input variables for predicting disc cutter wear, the Uniaxial Compressive Strength (UCS) is considerably limited compared to machine and wear data, so the UCS estimation for the entire section was first conducted using TBM machine data, and then the prediction of the Coefficient of Wearing rate(CW) was performed with the completed data. Comparing the performance of CW prediction models, the XGBoost model showed the highest performance, and SHapley Additive exPlanation (SHAP) analysis was conducted to interpret the complex prediction model.

• Geomechanics and Engineering
• /
• v.12 no.1
• /
• pp.85-109
• /
• 2017

The paper presents the laboratory study of clayey soil stabilized with Pond ash (PA), Rice husk ash (RHA), cement and their combination used as stabilizers to develop and evaluate the performance of clayey soil. The effect of stabilizer types and dosage on fresh and mechanical properties is evaluated through compaction tests, unconfined compressive strength tests (UCS) and Split tensile strength tests (STS) performed on raw and stabilized soil. In addition SEM (scanning electron microscopy) and XRD (X-ray diffraction) tests were carried out on certain samples in order to study the surface morphological characteristics and hydraulic compounds, which were formed. Specimens were cured for 7, 14 and 28 days after which they were tested for unconfined compression tests and split tensile strength tests. The moisture and density curves indicate that addition of RHA and pond ash results in an increase in optimum moisture content (OMC) and decrease in maximum dry density (MDD). The replacement of clay with 40% PA, 10% RHA and 4% cement increased the strength (UCS and STS) of overall mix in comparison to the mixes where PA and RHA were used individually with cement. The improvement of 336% and 303% in UCS and STS respectively has been achieved with reference to clay only. Developed stabilized soil mixtures have shown satisfactory strength and can be used for low-cost construction to build road infrastructures.

• Geomechanics and Engineering
• /
• v.13 no.3
• /
• pp.371-384
• /
• 2017

Physical and mechanical properties of rocks are of interest in many fields, including materials science, petrophysics, geophysics and geotechnical engineering. Uniaxial compressive strength UCS is one of the key mechanical properties, while density and porosity are important physical parameters for the characterization of rocks. The economic interest of carbonate rocks is very important in chemical or biological procedures and in the field of construction. Carbonate rocks exploitation depends on their quality and their physical, chemical and geotechnical characteristics. A fast, economic and reliable technique would be an evolutionary advance in the exploration of carbonate rocks. This paper discusses the ability of ultrasonic wave velocity to evaluate some mechanical and physical parameters within carbonate rocks (collected from different regions within Tunisia). The ultrasonic technique was used to establish empirical correlations allowing the estimation of UCS values, the density and the porosity of carbonate rocks. The results illustrated the behavior of ultrasonic pulse velocity as a function of the applied stress. The main output of the work is the confirmation that ultrasonic velocity can be effectively used as a simple and economical non-destructive method for a preliminary prediction of mechanical behavior and physical properties of rocks.

• Geomechanics and Engineering
• /
• v.18 no.5
• /
• pp.471-480
• /
• 2019

The constructions of engineering structures such as airports, highways and railway on clayey soils may create many problems. The economic losses and damages caused by these soils have led researchers to do many studies using different chemical additives for the stabilization of them. Lime is a popular additive used to stabilize the clayey soils. When the base course is stabilized by mixing with an additive, inevitable delays may occur during compaction due to reasons like insufficient workers, breakdown of compaction equipment, etc. The main purpose of this study is to research the effect of compaction delay time (7 days) on the strength, compaction, and dynamic properties of a clay soil stabilized with lime content of 0, 3, 6, 9, 12 and 15% by dry weight of soil. Compaction characteristics of these mixes were determined immediately after mixing, and after 7 days from the end of mixing process. Within this context, unconfined compressive strength (UCS) under the various curing periods (uncured, 7 and 28 days) and dynamic triaxial tests were performed on the compacted specimens. The results of UCS and dynamic triaxial tests showed that delayed compaction on the strength of the lime-stabilized clay soil were significantly effective. Especially with the lime content of 9%, the increase in the shear modulus (G) and UCS of 28 days curing were more prominent after 7 days mellowing period. Because of the complex forms of hysteresis loops caused by the lime additive, the damping ratio (D) values differed from the trends presented in the literature and showed a scattered relationship.

• Computers and Concrete
• /
• v.31 no.6
• /
• pp.501-511
• /
• 2023

The strengthening efficiency of biopolymer treated soil depends on biopolymer type, concentration ratio, soil type, initial water content, curing time and mixing method. In this study, the physical and mechanical properties of xanthan gum (XG) treated kaolinite were investigated through compaction test, Atterberg limit test, triaxial test and unconfined compression test. The results indicated that the optimum water content (OWC) increased from 30.3% of untreated clay to 33.5% of 5% XG treated clay, while the maximum dry density has a slight increase from 13.96 kg/m³ to 14 kg/m³ of 0.2% XG treated clay and decrease to 2.7 kg/m³ of 5% XG treated clay. Meanwhile, the plastic limit of XG treated clay increased with the increase of XG concentration, while 0.5% XG treated clay can be observed the maximum liquid limit with 79.5%. Moreover, there are the ideal water content about 1.3-1.5 times of the optimum water content achieving the maximum dry density and curing time to obtain the maximum compressive strength for different XG contents, which the UCS is 1.52 and 2.07 times of the maximum UCS of untreated soil for 0.5% and 1% XG treated clay, respectively. In addition, hot-dry mixing can achieve highest UCS than other mixing methods (e.g., dry mixing, wet mixing and hot-wet mixing).

• Steel and Composite Structures
• /
• v.45 no.2
• /
• pp.281-291
• /
• 2022

Surmounting complexities in analyzing the mechanical parameters of concrete entails selecting an appropriate methodology. This study integrates a novel metaheuristic technique, namely satin bowerbird optimizer (SBO) with artificial neural network (ANN) for predicting uniaxial compressive strength (UCS) of concrete. For this purpose, the created hybrid is trained and tested using a relatively large dataset collected from the published literature. Three other new algorithms, namely Henry gas solubility optimization (HGSO), sunflower optimization (SFO), and vortex search algorithm (VSA) are also used as benchmarks. After attaining a proper population size for all algorithms, the Utilizing various accuracy indicators, it was shown that the proposed ANN-SBO not only can excellently analyze the UCS behavior, but also outperforms all three benchmark hybrids (i.e., ANN-HGSO, ANN-SFO, and ANN-VSA). In the prediction phase, the correlation indices of 0.87394, 0.87936, 0.95329, and 0.95663, as well as mean absolute percentage errors of 15.9719, 15.3845, 9.4970, and 8.0629%, calculated for the ANN-HGSO, ANN-SFO, ANN-VSA, and ANN-SBO, respectively, manifested the best prediction performance for the proposed model. Also, the ANN-VSA achieved reliable results as well. In short, the ANN-SBO can be used by engineers as an efficient non-destructive method for predicting the UCS of concrete.

• Structural Engineering and Mechanics
• /
• v.88 no.2
• /
• pp.179-188
• /
• 2023

The mechanical behaviours of biopolymer-treated soil depend on the formation of soil-biopolymer matrices. In this study, various biopolymers(e.g., xanthan gum (XG), locust bean gum (LBG), sodium alginate (SA), agar gum (AG), gellan gum (GE) and carrageenan kappa gum (KG) are selected to treat three types of natural soil at different concentrations (e.g., 1%, 2% and 3%) and curing time (e.g., 4-365 days), and reveal the reinforcement effect on natural soil by using unconfined compression tests. The results show that biopolymer-treated soil obtains the maximum unconfined compressive strength (UCS) at curing 14-28 days. Although the UCS of biopolymer-treated soil has a 20-30% reduction after curing 1-year compared to the maximum value, it is still significantly larger than untreated soil. In addition, the UCS increment ratio of biopolymer-treated soil decreases with the increase of biopolymer concentration, and there exists the optimum concentration of 1%, 2-3%, 2%, 1% and 2% for XG, SA, LBG, KG and AG, respectively. Meanwhile, the optimum initial moisture content can form uniformly biopolymer-soil matrices to obtain better reinforcement efficiency. Furthermore, the best performance in increasing soil strength is XG following SAand LBG, which are significantly better than AG, KG and GE.

• Journal of the Korean Geotechnical Society
• /
• v.29 no.4
• /
• pp.45-56
• /
• 2013

In this study, a blast furnace slag with latent hydraulic property is used to cement granular soils without using Portland cement. When the blast furnace slag reacts with an alkaline activator, it can cement soils. The effect of amounts of blast furnace slag and types of alkaline activator on soil strength was investigated for resource recycling. Four different amounts of slag and six different activators (two naturals and four chemicals) were used for preparing specimens. The specimens were air-cured for 3 or 7 days and then tested for unconfined compressive strength (UCS). The UCS of cemented sand with slag increased, in the order of specimens mixed with potassium carbonate, calcium hydroxide, sodium hydroxide and potassium hydroxide. Chemical alkaline activator was better than natural alkaline activator. The maximum UCS of 3-days cured specimens was 3 MPa for 16% of slag with potassium hydroxide, which corresponded to 37% of one with 16% of high-early strength portland cement. As the amount of slag increased, the UCS and dry density of a specimen increased for all alkaline activator cases. As the curing time increased from 3 days to 7 days, the UCS increased up to 97%. C-S-H hydrates were found in the cemented specimens from XRD analyses. Cement hydrates were more generated with increasing amount of slag and they surrounded sand particles, which resulted in higher density.