• Structural Engineering and Mechanics
• /
• v.70 no.6
• /
• pp.671-681
• /
• 2019

This paper examines the applicability of artificial neural network (ANN) and multivariate adaptive regression splines (MARS) to predict the compressive strength of bacteria incorporated geopolymer concrete (GPC). The mix is composed of new bacterial strain, manufactured sand, ground granulated blast furnace slag, silica fume, metakaolin and fly ash. The concentration of sodium hydroxide (NaOH) is maintained at 8 Molar, sodium silicate ($Na_2SiO_3$) to NaOH weight ratio is 2.33 and the alkaline liquid to binder ratio of 0.35 and ambient curing temperature ($28^{\circ}C$) is maintained for all the mixtures. In ANN, back-propagation training technique was employed for updating the weights of each layer based on the error in the network output. Levenberg-Marquardt algorithm was used for feed-forward back-propagation. MARS model was developed by establishing a relationship between a set of predictors and dependent variables. MARS is based on a divide and conquers strategy partitioning the training data sets into separate regions; each gets its own regression line. Six models based on ANN and MARS were developed to predict the compressive strength of bacteria incorporated GPC for 1, 3, 7, 28, 56 and 90 days. About 70% of the total 84 data sets obtained from experiments were used for development of the models and remaining 30% data was utilized for testing. From the study, it is observed that the predicted values from the models are found to be in good agreement with the corresponding experimental values and the developed models are robust and reliable.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2019.11a
• /
• pp.27-28
• /
• 2019

In this study, the characteristics of compressive strength of ultra high strength concrete supplied with moisture from outside by vacuum water absorbing curing method were investigated. Specimens were prepared by replacing the binder(Silifa fume and GGBS) by 25 wt% with respect to the weight of cement at W/B 0.16. Each specimen was subjected to water Vacuum absorbing curing time 0 min, 30 min, 60 min, 90 min and 120 minutes immediately after the demolding. Curing was performed at $20^{\circ}C$ Air-dry curing, $90^{\circ}C$ steam curing, $90^{\circ}C$ steam curing and $180^{\circ}C$ autoclave curing. Experimental results showed that water absorbing degree increased with increasing water absorbing curing time, and BS25 sample had higher water absorbing degree than SF25 sample at same time. Compressive strength tended to increase up to about 40% in water absorbing degree, but compressive strength decreased again in water absorbing more than 40%.

• Computers and Concrete
• /
• v.27 no.1
• /
• pp.21-28
• /
• 2021

The Artificial Neural Network (ANN) is a system, which is utilized for solving complicated problems by using nonlinear equations. This study aims to investigate compressive strength, rebound hammer number (RN), and ultrasonic pulse velocity (UPV) of sustainable concrete containing various amounts of fly ash, silica fume, and blast furnace slag (BFS). In this study, the artificial neural network technique connects a nonlinear phenomenon and the intrinsic properties of sustainable concrete, which establishes relationships between them in a model. To this end, a total of 645 data sets were collected for the concrete mixtures from previously published papers at different curing times and test ages at 3, 7, 28, 90, 180 days to propose a model of nine inputs and three outputs. The ANN model's statistical parameter R2 is 0.99 of the training, validation, and test steps, which showed that the proposed model provided good prediction of compressive strength, RN, and UPV of sustainable concrete with the addition of cement.

• Journal of the Regional Association of Architectural Institute of Korea
• /
• v.21 no.5
• /
• pp.117-124
• /
• 2019

When manufacturing concrete, several mineral admixture is added to improve the basic physical property and durability and to make economical concrete. Such mineral admixture includes fly ash, granulated blast furnace slag, silica fume, etc., and not only the studies about mixing these mineral admixtures but also the studies for the development of new materials have been steadily in progress. Recently, some researchers have found, as a part of the development of new materials, the rice straw ash can also be used as a pozzolanic material for concrete considering similar chemical properties of rice straw ash to that of rice husk ash. But there has been insufficient amount of study about it. So, this study was to investigate the possibility as mineral admixture of agriculture by-product, by analyzing properties of concretes using rice straw ash with replacement ratio in comparison with other mineral admixture. In order to measure amount of SiO2 of rice straw ash, XRF(X-ray fluorescence) analysis was tested. For the measure pozzolanic reaction of rice straw ash, pH change and color change was tested according to curing day. Also to evaluate properties of concrete using rice straw ash, slump test, air contents test and compressive strength was tested.

• Structural Engineering and Mechanics
• /
• v.77 no.1
• /
• pp.103-114
• /
• 2021

Ultra high strength concrete (UHSC) originally proposed by Richards and Cheyrezy (1995) composed of cement, silica fume, quartz sand, quartz powder, steel fibers, superplasticizer etc. Later, other ingredients such as fly ash, GGBS, metakaoline, copper slag, fine aggregate of different sizes have been added to original UHSC. In the present investigation, the combined effect of coarse aggregate (6mm - 10mm) and steel fibers (0.50%, 1.0% and 1.5%) has been studied on UHSC mixes to evaluate mechanical and fracture properties. Compressive strength, split tensile strength and modulus of elasticity were determined for the three UHSC mixes. Size dependent fracture energy was evaluated by using RILEM work of fracture and size independent fracture energy was evaluated by using (i) RILEM work of fracture with tail correction to load - deflection plot (ii) boundary effect method. The constitutive relationship between the residual stress carrying capacity (σ) and the corresponding crack opening (w) has been constructed in an inverse manner based on the concept of a non-linear hinge from the load-crack mouth opening plots of notched three-point bend beams. It was found that (i) the size independent fracture energy obtained by using above two approaches yielded similar value and (ii) tensile stress increases with the increase of % of fibers. These two fracture properties will be very much useful for the analysis of cracked concrete structural components.

• Corrosion Science and Technology
• /
• v.21 no.5
• /
• pp.327-339
• /
• 2022

The water-jet technique started by Bridgman can cut metal and alloys without harmful gas and fume. However, while this technique is convenient to cut metals and alloys, in the case of coated pipe, water jet induces the degradation of coatings on the pipes, and may facilitate structural failure, leakage, and loss of products. While there are many reports on the effect of water jet on cut metals and the damage of metallic materials, research on the effect of water impingement on the epoxy coatings has been little studied. In this work, we therefore control the velocity of water jet, distance between nozzle and specimen, and water temperature, and discuss the effect of water impingement on the epoxy coatings. Increasing water velocity and water temperature and reducing nozzle distance increased the degradation rates of three epoxy coatings were increased. Among three test parameters - water velocity, nozzle distance and water temperature, water temperature was relatively effective to increase the degradation rate of epoxy coatings.

• Structural Engineering and Mechanics
• /
• v.82 no.2
• /
• pp.163-172
• /
• 2022

Zinc-rich epoxy (ZRE) is used to overcome corrosion problems in reinforced concrete (RC) beams and coat steel rebars to protect them from humidity and chlorides. An extra coating layer of Sikadur-31 epoxy (SDE) is utilised to increase bond strength because the use of ZRE reduces the bond strength between concrete and steel rebars. However, the low melting point of SDE indicates that concrete specimens are vulnerable to fire. An experimental investigation on flexural performance of RC beams incorporating ZRE-SDE coating of steel rebars that were destroyed by fire is performed in this study. Twenty beams of five concrete mixes with different cementitious contents were tested to compare fire exposure for coated and uncoated rebars of the same beams at room temperature and determine the optimal cementitious content. Scanning electron microscopy (SEM) was also applied to investigate characteristics of fired mixture samples. Results showed that the use of SDE-ZRE at room temperature improves flexural strengths of the five mixes compared with uncoated rebars with percentages ranging from 8.5% to 12.3%. All beams with SDE-ZRE lost approximately 50% of their flexural strength due to firing. Moreover, the mix incorporating SF (silica fume) of 15% and cement content of 400 kg/m³ introduces optimum behaviour compared with other mixes. All results were supported and verified by the SEM analysis and compressive strength of cubic specimens of the same mixes.

• Steel and Composite Structures
• /
• v.43 no.3
• /
• pp.389-401
• /
• 2022

This study investigated the flowability and mechanical properties of cost-effective steel fiber reinforced ultra-high performance concrete (UHPC) by using locally available materials for field-cast application. To examine the effect of mixture constituents, five mixtures with different fractions of silica fume, silica powder, ground granulated blast furnace slag (GGBS), silica sand, and crushed natural sand were proportionally prepared. Comprehensive experiments for different mixture designs were conducted to evaluate the fresh- and hardened-state properties of self-consolidating UHPC. The results showed that the proposed UHPC had similar mechanical properties compared with conventional UHPC while the flow retention over time was enhanced so that the field-cast application seemed appropriately cost-effective. The self-consolidating UHPC with high flowability and low viscosity takes less total mixing time than conventional UHPC up to 6.7 times. The X-ray computed tomographic imaging was performed to investigate the steel fiber distribution inside the UHPC by visualizing the spatial distribution of steel fibers well. Finally, the tensile stress-strain curve for the proposed UHPC was proposed for the implementation to the structural analysis and design.

• International Journal of Korean Welding Society
• /
• v.2 no.2
• /
• pp.51-56
• /
• 2002

The weld seam tracking system for arc welding process uses various kinds of sensors such as arc sensor, vision sensor, laser displacement sensor and so on. Among the variety of sensors available, electro-magnetic sensor is one of the most useful methods especially in sheet metal butt-joint arc welding, primarily because it is hardly affected by the intense arc light and fume generated during the welding process, and also by the surface condition of weldments. In this study, a dual-electromagnetic sensor, which utilizes the induced current variation in the sensing coil due to the eddy current variation of the metal near the sensor, was developed for arc welding of sheet metal I-butt joints. The dual-electromagnetic sensor thus detects the offset displacement of weld line from the center of sensor head even though there's no clearance in the joint. A set of design variables of the sensor was determined far the maximum sensing capability through the repeated experiments. Seam tracking is performed by correcting the position of sensor to the amount of offset displacement every sampling period. From the experimental results, the developed sensor showed the excellent capability of weld seam detection when the sensor to workpiece distance is near less than 5 ㎜, and it was revealed that the system has excellent seam tracking ability for the I-butt joint of sheet metal.

• Advances in nano research
• /
• v.13 no.5
• /
• pp.499-512
• /
• 2022

This study investigates the efficiency of ensemble machine learning for predicting the lightweight-aggregate concrete (LWC) characteristics. A stacking ensemble (STEN) approach was proposed to estimate the dry density (DD) and 28 days compressive strength (Fc-28) of LWC using two meta-models called random forest regressor (RFR) and extra tree regressor (ETR), and two novel ensemble models called STEN-RFR and STEN-ETR, were constructed. Four standalone machine learning models including artificial neural network, gradient boosting regression, K neighbor regression, and support vector regression were used to compare the performance of the proposed models. For this purpose, a sum of 140 LWC mixtures with 21 influencing parameters for producing LWC with a density less than 1000 kg/m³, were used. Based on the experimental results with multiple performance criteria, it can be concluded that the proposed STEN-ETR model can be used to estimate the DD and Fc-28 of LWC. Moreover, the STEN-ETR approach was found to be a significant technique in prediction DD and Fc-28 of LWC with minimal prediction error. In the validation phase, the accuracy of the proposed STEN-ETR model in predicting DD and Fc-28 was found to be 96.79% and 81.50%, respectively. In addition, the significance of cement, water-cement ratio, silica fume, and aggregate with expanded glass variables is efficient in modeling DD and Fc-28 of LWC.