• 한국신재생에너지학회:학술대회논문집
• /
• 2010.11a
• /
• pp.83.1-83.1
• /
• 2010

A Dead-end mode operation is one of the best way to maximize the gas usage rate. But, some components of fuel cell stack like gas diffusion layer(GDL) or membrane can be damaged in dead-end mode operation. In this study, a Large Scale Polymer electrolyte membrane fuel cell(PEMFC) for a dead-end operation has been developed. The stack is composed with 4 cells which has over 400cm2 of active area. Hydrogen is used as a fuel, and oxygen is used as a oxidant. The dead-end operation performance was evaluated by a long-term dead-end mode operation. The fuel cell stack is operated over 1,500 hours in dead-end mode operating fuel cell test station. And the performance change of the fuel cell stack was investigated.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09b
• /
• pp.122-125
• /
• 2003

By advent of NNC(Neural Network Chip), it is possible that process in parallel and discern the importance of signal with learning oneself by experience in external signal. So, the design of general purpose operation unit using VHDL(VHSIC Hardware Description Language) on the existing FPGA(Field Programmable Gate Array) can replaced EN(Expert Network) and learning algorithm. Also, neural network operation unit is possible various operation using learning of NN(Neural Network). This paper present general purpose operation unit using hierarchical structure of EN EN of presented structure learn from logical gate which constitute a operation unit, it relocated several layer The overall structure is hierarchical using a module, it has generality more than FPGA operation unit.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.9
• /
• pp.444-452
• /
• 2024

This study proposes a deep learning architecture optimized for fire detection derived through Layer Importance Evaluation. In order to solve the problem of unnecessary complexity and operation of the existing Convolutional Neural Network (CNN)-based fire detection system, the operation of the inner layer of the model based on the weight and activation values was analyzed through the Layer Importance Evaluation technique, the layer with a high contribution to fire detection was identified, and the model was reconstructed only with the identified layer, and the performance indicators were compared and analyzed with the existing model. After learning the fire data using four transfer learning models: Xception, VGG19, ResNet, and EfficientNetB5, the Layer Importance Evaluation technique was applied to analyze the weight and activation value of each layer, and then a new model was constructed by selecting the top rank layers with the highest contribution. As a result of the study, it was confirmed that the implemented architecture maintains the same performance with parameters that are about 80% lighter than the existing model, and can contribute to increasing the efficiency of fire monitoring equipment by outputting the same performance in accuracy, loss, and confusion matrix indicators compared to conventional complex transfer learning models while having a learning speed of about 3 to 5 times faster.

• Journal of Mechanical Science and Technology
• /
• v.16 no.6
• /
• pp.757-761
• /
• 2002

When a layer of cylindrical composite component containing an axisymmetric residual stress state is removed from the inner or outer surface, the dimension of the remaining material changes to balance internal forces. Therefore, in order to machine cylindrical composite components within tolerances, it is important to know dimensional changes caused by residual stress redistribution in the body. In this study, analytical solutions for dimensional changes and the redistribution of residual stresses due to the layer removal from a residually stressed cylindrically orthotropic cylinder were developed. The cylinder was assumed to have axisymmetric radial, tangential and axial residual stresses. The result of this study is useful in cases where the initial residual stress distribution in the component has been measured by a non-destructive technique such as neutron diffraction with no information on the effect of layer removal operation on the dimensional changes.

• Journal of information and communication convergence engineering
• /
• v.6 no.2
• /
• pp.204-206
• /
• 2008

In this paper, we proposed the recognition method that automatically extracts cracks from a surface image acquired by a digital camera and recognizes the directions (horizontal, vertical, -45 degree, and 45 degree) of cracks using the fuzzy single layer perceptron. We compensate an effect of light on a concrete surface image by applying the closing operation, which is one of the morphological techniques, extract the edges of cracks by Sobel masking, and binarize the image by applying the iterated binarization technique. Two times of noise reduction are applied to the binary image for effective noise elimination. After the specific regions of cracks are automatically extracted from the preprocessed image by applying Glassfire labeling algorithm to the extracted crack image, the cracks of the specific region are enlarged or reduced to $30{\times}30$ pixels and then used as input patterns to the fuzzy single layer perceptron. The experiments using concrete crack images showed that the cracks in the concrete crack images were effectively extracted and the fuzzy single layer perceptron was effective in the recognition of the extracted cracks directions.

• 한국전산유체공학회:학술대회논문집
• /
• 2011.05a
• /
• pp.46-53
• /
• 2011

Water is continuously produced in polymer electrolyte membrane fuel cell (PEMFC), and is transported and exhausted through polymer electrolyte membrane (PEM), catalyst layer (CL), microporous layer (MPL), and gas diffusion layer (GDL). The low operation temperatures of PEMFC lead to the condensation of water, and the condensed water hinders the transport of reactants in porous layers (MPL and GDL). Thus, water flooding is currently one of hot issues that should be solved to achieve higher performance of PEMFC. This research aims to study liquid water transport in porous layers of PEMFC by using pore-network model, while the microscale pore structure and hydrophilic/hydrophobic surface properties of GDL and MPL were fully considered.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2004.03a
• /
• pp.26-33
• /
• 2004

In this study, a boundary-layer bleeding and a two-staged fuel injection were applied to a scramjet engine for suppressing unstart transition and improving the thrust performance under Mach 6 flight conditions. With the boundary-layer bleeding, the engine could operate without unstart transition around at the fuel equivalence ratio of unity ($\Phi$ = 1). The thrust increment from the no fuel condition (dF) increased to 2460 N, which was about 1.4 times as large as that of the case without the bleeding and maximum in our Mach 6 tests. It was confirmed that the boundary-layer bleeding suppressed the separation during the engine operation. The two-staged fuel injection was less effective for improving the thrust performance com-pared with the single-staged one with the bleeding at Mach 6.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.24 no.3
• /
• pp.445-452
• /
• 1987

In this paper, a model for characteristics in the AlxGa1-xAs layer of MODFET's is presented. The characteristics of conduction band in the AlxGa1-xAs layer is analyzed with the Fermi-Dirac statistics. And using the conduction band energy which is calculated with the numerical calculation method (false-Positon method), the variations of the electric-field distribution, the ionized donor concentration, and the two-dimensional electron gas density with gate voltage are calculated, respectively. The channel formation process for the parasitic MESFET operation in the MOD structure is also analyzed, and the characteristics in the AlxGa1-xAs layer is analytically modeled. The throretical results describe well the general characteristics in the MOD structure.

• Korean Chemical Engineering Research
• /
• v.49 no.6
• /
• pp.775-780
• /
• 2011

5-cell DMFC stack was fabricated and operated with the load of 4 A for 4000 hrs. After 4000 hrs operation peak power density of the stack reduced by 27.3%. Two of the five cells did now show performance degradation, the performance of other two was reduced by 40% and the performance of the other decreased by 60%. The amount of performance degradation of each cell by long-term operation did not correlate with the position in the stack. Platinum particle size in the anode catalyst layer of the MEA with the strongest degradation increased and the increase was severer on the position of methanol inlet than on the position of methanol outlet. However, platinum particle size in the cathode catalyst layers did not changed for all the MEA'. Ruthenium crossover from the anode catalyst layer to the cathode catalyst layer through the membrane was observed after 4,000 hrs operation by SEM-EDX and it occurred for all MEA' regardless of the degree of performance degradation. Atomic ratio of ruthenium to platinum in the cathode catalyst layer was the highest in the MEA with the strongest performance degradation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.8B
• /
• pp.1460-1468
• /
• 2000

The goal of this research is the real-time implementation of MPEG-1 Layer III audio decoder using the fixed-point digital signal processor of TMS320C6201 The main job for this work is twofold: one is to convert floating-point operation in the decoder into fixed-point operation while maintaining the high resolution, and the other is to optimize the program to make it run in real-time with memory size as small as possible. We, especially, devote much time to the descaling module in the decoder for conversion of floating-point operation into fixed-point operation with high accuracy. The inverse modified cosine transform(IMDCT) and synthesis polyphase filter bank modules are optimized in order to reduce the amount of computation and memory size. After the optimization process, in this paper, the implemented decoder uses about 26% of maximum computation capacity of TMS320C6201. The program memory, data ROM, data RAM used in the decoder are about 6.77kwords, 3.13 kwords and 9.94 kwords, respectively. Comparing the PCM output of fixed-point computation with that of floating-point computation, we achieve the signal-to-noise ratio of more than 60 dB. A real-time operation is demonstrated on the PC using the sound I/O and host communication functions in the EVM board.