• Steel and Composite Structures
• /
• v.45 no.2
• /
• pp.205-218
• /
• 2022

Proper calculation of splitting tensile strength (STS) of concrete has been a crucial task, due to the wide use of concrete in the construction sector. Following many recent studies that have proposed various predictive models for this aim, this study suggests and tests the functionality of three hybrid models in predicting the STS from the characteristics of the mixture components including cement compressive strength, cement tensile strength, curing age, the maximum size of the crushed stone, stone powder content, sand fine modulus, water to binder ratio, and the ratio of sand. A multi-layer perceptron (MLP) neural network incorporates invasive weed optimization (IWO), cuttlefish optimization algorithm (CFOA), and electrostatic discharge algorithm (ESDA) which are among the newest optimization techniques. A dataset from the earlier literature is used for exploring and extrapolating the STS behavior. The results acquired from several accuracy criteria demonstrated a nice learning capability for all three hybrid models viz. IWO-MLP, CFOA-MLP, and ESDA-MLP. Also in the prediction phase, the prediction products were in a promising agreement (above 88%) with experimental results. However, a comparative look revealed the ESDA-MLP as the most accurate predictor. Considering mean absolute percentage error (MAPE) index, the error of ESDA-MLP was 9.05%, while the corresponding value for IWO-MLP and CFOA-MLP was 9.17 and 13.97%, respectively. Since the combination of MLP and ESDA can be an effective tool for optimizing the concrete mixture toward a desirable STS, the last part of this study is dedicated to extracting a predictive formula from this model.

• Journal of the Korean Ceramic Society
• /
• v.31 no.7
• /
• pp.772-776
• /
• 1994

Using two kinds of ZrO2 powder stabilized by 8 mol% and 3 mol% of Y2O3 several microstructures were designed; two single composition specimens of 8 mol% Y2O3-ZrO3 and 3 mol% Y2O3-ZrO2 and five mixture specimens with multi-layered structure and particulate mixture structure at a mixing ratio of 1:1 by weight. Electrical conductivities were measured from 250 to 75$0^{\circ}C$ in air using an impedance analyser, and fracture toughness at room temperature using the indentation method. Making the mixture structures was more effective in enhancing fracture toughness than electrical conductivity. At low temperatures 3 mol% Y2O3-ZrO2 showed the highest values in both electrical conductivity and fracture toughness, while at high temperature the specimens of alternately stacked planar and coarse granulated structure were most favorable.

• Macromolecular Research
• /
• v.17 no.9
• /
• pp.651-657
• /
• 2009

This study examined the optimum compositions of binder, photo-acid generator (PAG) and sensitizer for the cationic ring opening polymerization of 1,3-bis[2-(3-{7-oxabicyclo-[4.1.0]heptyl})]-tetramethyldisiloxane in the presence of polydimethylsiloxane with four epoxide moieties as a co-monomer. When diffractive efficiency (DE) values were compared quantitatively to analyze the effect of the binder on holographic photopolymerization, DE was affected by the viscosity of the binders and miscibility with the monomer mixture. Extremely low DE values were observed when the immiscible dimethyl silicone was used as a binder. Therefore, methylphenyl silicone, which is miscible with the monomer mixture, was used as the binder for further studies. The optimal conditions were a binder viscosity between 250 to 390 cP, and contents of the binder, PAG, and sensitizer were 75-125 wt%, > 6 wt% and 0.05 wt% to the total monomer mixture, respectively.

• Korean Journal of Remote Sensing
• /
• v.26 no.6
• /
• pp.681-691
• /
• 2010

LiDAR waveform decomposition plays an important role in LiDAR data processing since the resulting decomposed components are assumed to represent reflection surfaces within waveform footprints and the decomposition results ultimately affect the interpretation of LiDAR waveform data. Decomposing the waveform into a mixture of Gaussians involves two related problems; 1) determining the number of Gaussian components in the waveform, and 2) estimating the parameters of each Gaussian component of the mixture. Previous studies estimated the number of components in the mixture before the parameter optimization step, and it tended to suggest a larger number of components than is required due to the inherent noise embedded in the waveform data. In order to tackle these issues, a new LiDAR waveform decomposition algorithm based on the sequential approach has been proposed in this study and applied to the ICESat waveform data. Experimental results indicated that the proposed algorithm utilized a smaller number of components to decompose waveforms, while resulting IMP value is higher than the GLA14 products.

• Korean Chemical Engineering Research
• /
• v.51 no.6
• /
• pp.677-684
• /
• 2013

A mixed refrigerant cycle (MRC) has been widely used in liquefaction of natural gas because it is simple and easily operable with reasonable equipment costs. One of the important techniques in MRC is selection of a refrigerant mixture and decision of its optimum mixing ratio. In this work, it is examined whether mixture components (refrigerants) and their mixing ratio influence performance of general MRC processes. In doing this, mixture design and response surface method, which are well-known statistical techniques, are used to find optimal mixture refrigerants and their optimal mixing ratio that minimize total energy consumption of the entire liquefaction process. A MRC process using several refrigerants and various mixing ratios is simulated by Aspen HYSYS and mixture design and response surface method are implemented using Minitab. According to the results, methane ($C_1$), ethane ($C_2$), propane ($C_3$) and nitrogen ($N_2$) are selected as best mixture refrigerants and the determined mixture ratio (mole ration) can reduce total energy consumption by up to 50%.

• Smart Structures and Systems
• /
• v.33 no.1
• /
• pp.65-91
• /
• 2024

The use of five optimization techniques for the prediction of a strength-based concrete mixture's best-fit model is examined in this work. Five optimization techniques are utilized for this purpose: Slime Mold Algorithm (SMA), Black Hole Algorithm (BHA), Multi-Verse Optimizer (MVO), Vortex Search (VS), and Whale Optimization Algorithm (WOA). MATLAB employs a hybrid learning strategy to train an artificial neural network that combines least square estimation with backpropagation. Thus, 72 samples are utilized as training datasets and 31 as testing datasets, totaling 103. The multi-layer perceptron (MLP) is used to analyze all data, and results are verified by comparison. For training datasets in the best-fit models of SMA-MLP, BHA-MLP, MVO-MLP, VS-MLP, and WOA-MLP, the statistical indices of coefficient of determination (R²) in training phase are 0.9603, 0.9679, 0.9827, 0.9841 and 0.9770, and in testing phase are 0.9567, 0.9552, 0.9594, 0.9888 and 0.9695 respectively. In addition, the best-fit structures for training for SMA, BHA, MVO, VS, and WOA (all combined with multilayer perceptron, MLP) are achieved when the term population size was modified to 450, 500, 250, 150, and 500, respectively. Among all the suggested options, VS could offer a stronger prediction network for training MLP.

• Food Science and Biotechnology
• /
• v.14 no.6
• /
• pp.747-751
• /
• 2005

Microencapsulation of pine flavors was investigated to determine the optimum wall material and spray drying condition. ${\beta}$-Cyclodextrin, maltodextrin, and a 3:1 mixture of maltodextrin and gum arabic were evaluated as wall materials. The latter mixture was determined to be the best wall material based on dispersion capacity and flavor yield. Spray drying effectiveness was evaluated using a $3^3$ fraction factorial design and statistical analysis. The optimum operation condition was an inlet air temperature of $175^{\circ}C$, inlet airflow rate of $0.65\;m^3/min$ and atomizing pressure of 180 kPa, which resulted in a 93% flavor yield. The best particle shape observed by SEM was a round globular shape obtained under the above spray drying condition, whereas lower temperatures and higher inlet airflow rates resulted in initial and full collapses, respectively. The round globular shapes remained stable for at least one month.

• Journal of the Korean Institute of Gas
• /
• v.18 no.5
• /
• pp.60-65
• /
• 2014

The flash point is the major physical property used to characterize the fire hazard of flammable liquid solutions. In the present study, the main focus is on measuring and estimating the flash points for binary flammable mixture. The flash points for n-propanol+propionic acid were measured by Seta flash closed cup apparatus. The experimental data were correlated with the van Laar and NRTL equations through the optimization method. The results estimated by these correlations were compared with the values calculated by the method based on Raoult's law. The optimization method were found to be better than the method based on the Raoult's law.

• Computers and Concrete
• /
• v.32 no.3
• /
• pp.233-246
• /
• 2023

Accurate prediction of concrete compressive strength can minimize the need for extensive, time-consuming, and costly mixture optimization testing and analysis. This study attempts to enhance the prediction accuracy of compressive strength using stacking ensemble machine learning (ML) with feature engineering techniques. Seven alternative ML models of increasing complexity were implemented and compared, including linear regression, SVM, decision tree, multiple layer perceptron, random forest, Xgboost and Adaboost. To further improve the prediction accuracy, a ML pipeline was proposed in which the feature engineering technique was implemented, and a two-layer stacked model was developed. The k-fold cross-validation approach was employed to optimize model parameters and train the stacked model. The stacked model showed superior performance in predicting concrete compressive strength with a correlation of determination (R²) of 0.985. Feature (i.e., variable) importance was determined to demonstrate how useful the synthetic features are in prediction and provide better interpretability of the data and the model. The methodology in this study promotes a more thorough assessment of alternative ML algorithms and rather than focusing on any single ML model type for concrete compressive strength prediction.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.3
• /
• pp.1002-1007
• /
• 2012

The manufacturing method of the pillar is one of the main process where it is used in vacuum glazing and semi-conductor display field. Pillar can be arranged by screen printing method. However it may unable to spread all pattern of metal mask according to the ingredient of the mixture. In addition, spreaded mixture doesn't maintain the original shape according to the viscosity. In this research, the pillar tried to be arranged through the screen printing by using the inorganic compound of the alumina and silica base. This study suggested a method in which it can decrease the test frequency and design the composition of the vacuum glass pillar by using the mixture design.