• Journal of the Korean Society of Clothing and Textiles
• /
• v.26 no.1
• /
• pp.152-159
• /
• 2002

Neural networks are used to predict the sense of touch of polyurethane coated fabrics. In this study, we used the multi layer perceptron (MLP) neural networks in Neural Connection. The learning algorithm for neural networks is back-propagation algorithm. We used 29 polyurethane coated fabrics to train the neural networks and 4 samples to test the neural networks. Input variables are 17 mechanical properties measured with KES-FB system, and output variable is the sense of touch of polyurethane coated fabrics. The influence of MLF function, the number of hidden layers, and the number of hidden nodes on the prediction accuracy is investigated. The results were as follows: MLP function, the number of hidden layer and the number of hidden nodes have some influence on the prediction accuracy. In this work, tangent function, the architecture of the double hidden layers and the 24-12-hidden nodes has the best prediction accuracy with the lowest RMS error. Using the neural networks to predict the sense of touch of polyurethane coated fabrics has hotter prediction accuracy than regression approach used in our previous study.

• Tribology and Lubricants
• /
• v.31 no.3
• /
• pp.86-94
• /
• 2015

We perform lacquer formation experiments with various combinations of marine fuel oils and lubricant oils. We also investigate the influences of base number (BN) in lubricant oil and sulfur content in fuel oil. A dissolution test with 10% dilute sulfuric acid and pull-off force test are accomplished to distinguish whether the residual layers are lacquering or not. The lacquering layers are dissolved by dilute sulfuric acid and have a strong pull-off force. Moreover, the calcium content detected in the residual layers is compared by energy dispersive x-ray spectroscopy (EDS). More calcium is detected in the lacquer layers than in other residual layers. Distillate fuels containing low sulfur levels are more prone to lacquering when mixed with lubricant oil with a high BN. On the other hand, residual fuels with a high sulfur content do not form lacquer. We investigate the effect of mixture volume ratio. The mixture with higher fuel oil content is more prone to generate lacquer. These experiments indicate that a lubricant with an appropriate BN should be used to prevent lacquer forming on the surfaces such as cylinder liners depending on the sulfur content of fuel oil.

• Structural Engineering and Mechanics
• /
• v.24 no.4
• /
• pp.479-491
• /
• 2006

This paper deals with optimal fibre orientations of symmetrically laminated fibre reinforced composite structures for maximising the fundamental frequency of small-amplitude. A set of fiber orientation angles in the layers are considered as design variable. The Modified Feasible Direction method is used in order to obtain the optimal designs. The effects of number of layers, boundary conditions, laminate thicknesses, aspect ratios and in-plane loads on the optimal designs are studied.

• Proceedings of the KIEE Conference
• /
• 2005.11a
• /
• pp.136-138
• /
• 2005

Merocyanine dye (MD) has been extensively investigated due to its marked potential application to photo-electric devices. We fabricated the number of layers to control its optical characteristics using the Langmuir-Blodgett (LB) method. We evaluated the morphology and optical characteristics of MD LB films using Atomic Force Microscopy (AFM) and UV spectroscopy, PL spectroscopy. As a result, we obtained the quantitative morphology and optical characteristics of LB films from controlling the deposided layers.

• Proceedings of the KIEE Conference
• /
• 1999.07d
• /
• pp.1744-1746
• /
• 1999

In this paper, we give pressure stimulation into organic ultra thin films and detected the induced displacement current properties, and then manufacture a device under the accumulation condition. In processing of a device manufacture, we can see the process is good from the change of a surface pressure and transfer ratio of area per molecule of organic ultra thin films. The structure of manufactured device is MIM(Au/polyimide LB films/AU), the number of accumulated 19 layers. I-V characteristic of the device is measured from -5[V] to +5[V]. The maximum value of measured current is increased as the number of accumulated layers are decreased. The insulation of a thin film is better as the interval between electrodes is larger, and the insulation properties of a thin film is better as the distance between electrodes is larger.

• Proceedings of the KIEE Conference
• /
• 1998.11c
• /
• pp.807-809
• /
• 1998

We give pressure stimulation into organic thin films and detect the induced displacement current, In processing of a device manufacture, we can see the process is good from the change of a surface pressure for organic thin films and transfer ratio of area per molecule. The structure of manufactured device is Au/organic thin films(Kapton-Polyimide)/Au and I-V properties of the device is measured from 0(V) to +5(V). The maximum value of measured current is increased as the number of accumulated layers are decreased. The resistance for the number of accumulated layers, the energy density for an input voltage show desired results.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2018.05a
• /
• pp.130-131
• /
• 2018

The compressive strength of concrete is determined by various influencing factors. However, the conventional method for estimating the compressive strength of concrete has been suggested by considering only 1 to 3 specific influential factors as variables. In this study, nine influential factors (W/B ratio, Water, Cement, Aggregate(Coarse, Fine), Fly ash, Blast furnace slag, Curing temperature, and humidity) of papers opened for 10 years were collected at 4 conferences in order to know the various correlations among data and the tendency of data. The selected mixture and compressive strength data were learned using the Deep Learning Algorithm to derive an estimated function model. The purpose of this study is to investigate the effect of the number of hidden layers on the prediction performance in the process of estimating the compressive strength for an arbitrary combination.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.114-117
• /
• 2000

In this paper, Fuzzy Self-organizing Neural Networks(FSONN) based on Fuzzy Neural Networks(FNN) is proposed to overcome some problems, such as the conflict between ovefitting and good generation, and low reliability. The proposed FSONN consists of FNN and SONN. Here, FNN is used as the premise part of FSONN and SONN is the consequnt part of FSONN. The FUN plays the preceding role of FSONN. For the fuzzy reasoning and learning method in FNN, Simplified fuzzy reasoning and backpropagation learning rule are utilized. The number of layers and the number of nodes in each layers of SONN that is based on the GMDH method are not predetermined, unlike in the case of the popular multi layer perceptron structure and can be generated. Also the partial descriptions of nodes can use various forms such as linear, modified quadratic, cubic, high-order polynomial and so on. In this paper, the optimal design procedure of the proposed FSONN is shown in each step and performance index related to approximation and generalization capabilities of model is evaluated and also discussed.

• Structural Engineering and Mechanics
• /
• v.66 no.4
• /
• pp.439-444
• /
• 2018

This paper presents a numerical study on the behavior of continuous hollow steel beam strengthened using carbon fiber reinforced polymers (CFRP). Most previous studies on the CFRP strengthening of steel beams have been carried out on the steel beams with simple boundary conditions. No independent study, to the researcher's knowledge, has studied on the CFRP strengthening of square hollow section (SHS) continuous steel beam. However, this study explored the effect of the use of adhesively bonded CFRP flexible sheets on the behavior of the continuous SHS steel beams. Finite Element Method (FEM) has been employed for modeling. Eleven specimens, ten of which were strengthened using CFRP sheets, were analyzed under different coverage length, the number of layers, and the location of CFRP composite. ANSYS software was used to analyze the SHS steel beams. The results showed that the coverage length, the number of layers, and the location of CFRP composite are effective in increasing the ultimate load capacity of the continuous SHS steel beams. Application of CFRP composite also caused the ductility increase some strengthened specimens.

• Macromolecular Research
• /
• v.13 no.2
• /
• pp.107-113
• /
• 2005

We developed an algorithm to simulate the generation of virtual nanowebs using the Monte Carlo method. To evaluate the pore size of the simulated multi-layered nanoweb, an estimation algorithm was developed using a ghost particle having zero volume and mass. The penetration time of the ghost particle through the virtual nanoweb was dependent on the pore size. By using iterative ghost particle penetrations, we obtained reliable data for the evaluation of the pore size and distribution of the virtual nanowebs. The penetration time increased with increasing number of layers and area ratio, whereas it decreased with increasing fiber diameter. Dimensional analysis showed that the penetration time can be expressed as a function of the fiber diameter, area ratio and number of layers.