• Title/Summary/Keyword: layer-by-layer method

Search Result 6,949, Processing Time 0.04 seconds

Tension Estimation of Tire using Neural Networks and DOE (신경회로망과 실험계획법을 이용한 타이어의 장력 추정)

  • Lee, Dong-Woo;Cho, Seok-Swoo
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.28 no.7
    • /
    • pp.814-820
    • /
    • 2011
  • It takes long time in numerical simulation because structural design for tire requires the nonlinear material property. Neural networks has been widely studied to engineering design to reduce numerical computation time. The numbers of hidden layer, hidden layer neuron and training data have been considered as the structural design variables of neural networks. In application of neural networks to optimize design, there are a few studies about arrangement method of input layer neurons. To investigate the effect of input layer neuron arrangement on neural networks, the variables of tire contour design and tension in bead area were assigned to inputs and output for neural networks respectively. Design variables arrangement in input layer were determined by main effect analysis. The number of hidden layer, the number of hidden layer neuron and the number of training data and so on have been considered as the structural design variables of neural networks. In application to optimization design problem of neural networks, there are few studies about arrangement method of input layer neurons. To investigate the effect of arrangement of input neurons on neural network learning tire contour design parameters and tension in bead area were assigned to neural input and output respectively. Design variables arrangement in input layer was determined by main effect analysis.

A Layer-by-Layer Learning Algorithm using Correlation Coefficient for Multilayer Perceptrons (상관 계수를 이용한 다층퍼셉트론의 계층별 학습)

  • Kwak, Young-Tae
    • Journal of the Korea Society of Computer and Information
    • /
    • v.16 no.8
    • /
    • pp.39-47
    • /
    • 2011
  • Ergezinger's method, one of the layer-by-layer algorithms used for multilyer perceptrons, consists of an output node and can make premature saturations in the output's weight because of using linear least squared method in the output layer. These saturations are obstacles to learning time and covergence. Therefore, this paper expands Ergezinger's method to be able to use an output vector instead of an output node and introduces a learning rate to improve learning time and convergence. The learning rate is a variable rate that reflects the correlation coefficient between new weight and previous weight while updating hidden's weight. To compare the proposed method with Ergezinger's method, we tested iris recognition and nonlinear approximation. It was found that the proposed method showed better results than Ergezinger's method in learning convergence. In the CPU time considering correlation coefficient computation, the proposed method saved about 35% time than the previous method.

ARAS coating with a conducting polymer (전도성 고분자를 이용한 ARAS 코팅)

  • 김태영;이보현;김종은;서광석
    • Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
    • /
    • 2001.07a
    • /
    • pp.1039-1042
    • /
    • 2001
  • A method for designing antireflection (AR) and antistatic (AS) films by the use of conducting polymer as an electrically conductive transparent layer is proposed. The conducting AR film is composed of four-layer with alternating high and low refractive index layer: silicon dioxide (n=1.44) and titanium dioxide (n=2.02) prepared at low temperature by sol-gel method are used as the low and high refractive index layer, respectively. The 3,4-polyethylenedioxythiophene (PEDOT) which has the sheet resistance of 10$^4$$\Omega$/$\square$ is used as a conductive layer. Optical constant of ARAS film was measured by the spectroscopic ellipsometer and from the measured optical constants the spectral properties such as reflectance and transmittance were simulated in the visible region. The reflectance of ARAS films on glass substrate was below 0.8 %R and the transmittance was higher than 95 % in the visible wavelength (400-700 nm). The measured AR spectral properties was very similar to its simulated results.

  • PDF

Surface Plasmon Resonance Multisensing Using Thickness Difference of Additional Layer (부가층의 두께 차이를 이용한 표면플라즈몬공명 멀티센싱)

  • Kim, Young-Gyu;Oh, Myung-Hwan;Lee, Seung-Ki
    • The Transactions of the Korean Institute of Electrical Engineers C
    • /
    • v.55 no.10
    • /
    • pp.492-498
    • /
    • 2006
  • A novel surface plasmon resonance(SPR) multisensing method, which does not require imaging apparatus such as CCD, has been proposed and implemented experimentally. The proposed method is based on the multichannel SPR and the separation of signals by use of additional layers whose thickness is controlled. SPR signals are influenced by the thickness of sensing layer as well as the optical condition of sensing surface. As the SPR signals from different ligands are usually positioned closely, the reflected light from sensing surface does not provide us with the clear differences of resonance signal depending on the kinds of ligands. It was found from our experiments that SPR signals from each ligand that is located on the additional layer with different thickness can be separated clearly enough to identify various signals from different ligands. Proposed method with theoretical design and simulation has been verified experimentally by using $SiO_2$ thin film layer as additional layer.

Performance Analysis of Layer Pruning on Sphere Decoding in MIMO Systems

  • Karthikeyan, Madurakavi;Saraswady, D.
    • ETRI Journal
    • /
    • v.36 no.4
    • /
    • pp.564-571
    • /
    • 2014
  • Sphere decoding (SD) for multiple-input and multiple-output systems is a well-recognized approach for achieving near-maximum likelihood performance with reduced complexity. SD is a tree search process, whereby a large number of nodes can be searched in an effort to find an estimation of a transmitted symbol vector. In this paper, a simple and generalized approach called layer pruning is proposed to achieve complexity reduction in SD. Pruning a layer from a search process reduces the total number of nodes in a sphere search. The symbols corresponding to the pruned layer are obtained by adopting a QRM-MLD receiver. Simulation results show that the proposed method reduces the number of nodes to be searched for decoding the transmitted symbols by maintaining negligible performance loss. The proposed technique reduces the complexity by 35% to 42% in the low and medium signal-to-noise ratio regime. To demonstrate the potential of our method, we compare the results with another well-known method - namely, probabilistic tree pruning SD.

Characteristics of Bi2212 Thin Film Fabricated by Layer-by-Layer Deposition at an Ultra Low Growth rate (초저속 순차증착으로 제작한 Bi2212 박막의 특성)

  • Lee, Hee-Kab;Park, Yong-Pil;Cheon, Min-Woo
    • Proceedings of the KIEE Conference
    • /
    • 2002.11a
    • /
    • pp.119-121
    • /
    • 2002
  • $Bi_2Sr_2CuO_x$ thin films were fabricated by atomic layer-by-layer deposition using an ion beam sputtering method, 10 wt% and 90 wt% ozone mixed with oxygen were used with ultraviolet light irradiation to assist oxidation. At early stages of the atomic layer by layer deposition, two dimensional epitaxial growth which covers the substrate surface would be suppressed by the stress and strain caused by the lattice misfit, then three dimensional growth takes place. Since Cu element is the most difficult to oxidize, only Sr and Bi react with each other predominantly, and forms a buffer layer on the substrate in an amorphous-like structure, which is changed to $SrBi_2O_4$ by in-situ anneal.

  • PDF

A Study on the Epitaxial Growth of Superconducting Thin Film (초전도 박막의 에피택셜 성장에 관한 연구)

  • Lee, Hee-Kab;Park, Yong-Pil;Kim, Gwi-Yeol
    • Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
    • /
    • 2002.05c
    • /
    • pp.208-211
    • /
    • 2002
  • $Bi_2Sr_2CuO_x$(Bi-2201) thin films were fabricated by atomic layer-by-layer deposition using an ion beam sputtering method. 10 wt% and 90 wt% ozone mixed with oxygen were used with ultraviolet light irradiation to assist oxidation. At early stages of the atomic layer by layer deposition, two dimensional epitaxial growth which covers the substrate surface would be suppressed by the stress and strain caused by the lattice misfit, then three dimensional growth takes place. Since Cu element is the most difficult to oxidize, only Sr and Bi react with each other predominantly, and forms a buffer layer on the substrate in an amorphous-like structure, which is changed to $SrBi_2O_4$ by in-situ anneal.

  • PDF

The Effect of Using Nano NiO Powder Made by Pulsed Wire Evaporation (PWE) Method on SOFC Anode Functional Layer (Pulsed Wire Evaporation(PWE) Method으로 제조된 나노 NiO 분말의 SOFC 연료극 기능성층으로의 적용)

  • Kim, Hae-Won;Kim, Dong-Ju;Park, Seok-Joo;Lim, Tak-Hyoung;Lee, Seung-Bok;Shin, Dong-Ryul;Yoon, Soon-Gil;Song, Rak-Hyun
    • Transactions of the Korean hydrogen and new energy society
    • /
    • v.20 no.6
    • /
    • pp.485-491
    • /
    • 2009
  • In present work, NiO/YSZ anode functional layer was prepared by nano NiO powder and 8YSZ powder. The nano NiO powders were made by Pulsed wire evaporation (PWE) method. Nano NiO- YSZ functional layer was sintered at the temperature of $900-1400^{\circ}C$. The prepared functional layer was characterized by scanning electron microscopy (SEM) and electrochemical impedance spectroscopy. The nano NiO- YSZ anode functional layer sintered at $1300^{\circ}C$ shows the lowest polarization resistance. Nano NiO- YSZ anode functional layer shows about two times smaller polarization resistance than the anode functional layer made by commercial NiO-YSZ powders. Based on these experimental results, it is concluded that the nano NiO-YSZ cermet is suitable as a anode functional layer operated at $800^{\circ}C$.

Spatio-temporal Charge Distribution in Electric Double Layer Capacitors observed by pulsed Electro Acoustic Method

  • Sung, Youl-Moon
    • Transactions on Electrical and Electronic Materials
    • /
    • v.8 no.4
    • /
    • pp.182-187
    • /
    • 2007
  • The use of the pulsed electro acoustic (PEA) method allowed us to perform the direct observations of spatio-temporal charge distributions in Electric double layer capacitors (EDLCs) based on polarizable nanoporous carbonaceous electrode. The negative charge density became the maximum, about $205C/m^3$ at the region where was near to collector layer in EDLCs for case $V_{DC}=2.5V$, while the positively charged density became the maximum, about $61.1C/m^3$ at the region where it was located around the cathode layer. The performance of the best sample was found to be better in terms of the charge density (Cs) and specific energy ($E_s$) with a maximum value of ${\sim}8.4F/g$ and 26 Wh/kg. The $C_s$ obtained from the PEA method agreed well with that from the energy conversion method. The PEA measurement used here is a very useful method to quantitively investigates the spatio-temporal charge distribution in EDLCs.

A Method to Determine Optimum Viscoelastic Layer Thickness of Sandwich Plate for Maximum Modal Damping (샌드위치 평판의 모드 감쇠 최대화를 위한 점탄성층 두께 결정법)

  • Nam, Dae-Ho;Shin, Yun-Ho;Kim, Kwang-Joon
    • Transactions of the Korean Society for Noise and Vibration Engineering
    • /
    • v.16 no.7 s.112
    • /
    • pp.690-696
    • /
    • 2006
  • Thickness of damping layer in sandwich plate needs to be optimized in order to make modal loss factor of the sandwich plate maximum. Since previous studies were interested in noise reductions over high frequency range, the modal properties were derived based on simply supported boundaries. This conventional formula is approximately applicable to other boundary conditions over high frequency range only. The purpose of this study is to propose a method to determine optimum damping layer thickness of sandwich plate for maximum modal damping in low frequency range when the boundary condition is not a simple support. The conventional RKU equation based on simply supported boundary is modified to reflect other boundary conditions and the modified RKU equation is subsequently applied to determine the optimum damping layer thickness for arbitrary conditions. In order to reflect frequency-dependent characteristics of elastic modulus of the damping layer, an iteration method is proposed in determining the modal properties. Test results on sandwich plates for optimum damping layer thickness are compared with predictions by the proposed method and conventional method.