• 제목/요약/키워드: three-layer model

검색결과 806건 처리시간 0.025초

Two Layer Multiquadric-Biharmonic Artificial Neural Network for Area Quasigeoid Surface Approximation with GPS-Levelling Data

  • Deng, Xingsheng;Wang, Xinzhou
    • 한국항해항만학회:학술대회논문집
    • /
    • 한국항해항만학회 2006년도 International Symposium on GPS/GNSS Vol.2
    • /
    • pp.101-106
    • /
    • 2006
  • The geoidal undulations are needed for determining the orthometric heights from the Global Positioning System GPS-derived ellipsoidal heights. There are several methods for geoidal undulation determination. The paper presents a method employing a simple architecture Two Layer Multiquadric-Biharmonic Artificial Neural Network (TLMB-ANN) to approximate an area of 4200 square kilometres quasigeoid surface with GPS-levelling data. Hardy’s Multiquadric-Biharmonic functions is used as the hidden layer neurons’ activation function and Levenberg-Marquardt algorithm is used to train the artificial neural network. In numerical examples five surfaces were compared: the gravimetric geometry hybrid quasigeoid, Support Vector Machine (SVM) model, Hybrid Fuzzy Neural Network (HFNN) model, Traditional Three Layer Artificial Neural Network (ANN) with tanh activation function and TLMB-ANN surface approximation. The effectiveness of TLMB-ANN surface approximation depends on the number of control points. If the number of well-distributed control points is sufficiently large, the results are similar with those obtained by gravity and geometry hybrid method. Importantly, TLMB-ANN surface approximation model possesses good extrapolation performance with high precision.

  • PDF

Dynamic analysis by impact load in viscoelastic sandwich plates with FRP layer utilizing numerical method

  • Bayati, Mohammad Reza;Mazaheri, Hamid;Bidgoli, Mahmood Rabani
    • Steel and Composite Structures
    • /
    • 제43권2호
    • /
    • pp.229-240
    • /
    • 2022
  • The main objective of this work is presenting a mathematical model for the concrete slab with fiber reinforced polymer (FRP) layer under the impact load. Impacts are assumed to occur normally over the top slab and the interaction between the impactor and the structure is simulated using a new equivalent three-degree-of-freedom (TDOF) spring-mass-damper (SMD) model. The structure is assumed viscoelastic based on Kelvin-Voigt model. Based on the sinusoidal shear deformation theory (SSDT), energy method and Hamilton's principle, the motion equations are derived. Applying DQM, the dynamic deflection and contact force of the structure is calculated numerically so that the effects of mass, velocity and height of impactor, boundary conditions, FRP layer, structural damping and geometrical parameters of structure are shown on the dynamic deflection and contact force of system. Results show that considering structural damping leads to lower dynamic deflection and contact force. In addition, increasing the impact velocity of impactor yields to increases in the maximum contact force and deflection while the contact duration is decreased. The result shows that the contact force and the central deflection of the structure decreases and the contact time decreases with assuming FRP layer.

디스플레이용 SiO2/ITO 투명전도막의 반사특성 (Reflection Properties of SiO2/ITO Transparent and Conductive Thin Films for Display)

  • 신용욱;김상우;윤기현
    • 한국세라믹학회지
    • /
    • 제39권3호
    • /
    • pp.233-239
    • /
    • 2002
  • CRT의 전면에 전자파차폐, 정전기 방지 및 저반사 효과를 위해 코팅되는 $SiO_2$/ITO (Indium Tin Oxide) 이층박막의 반사특성에 관하여 연구하였다. 실리카층 및 ITO층의 두께를 변화시키며 나타나는 반사율의 경향을 고찰하고, 이론적인 2층, 3층 저반사코팅의 디자인에 적용시켜 보았다. 입자 상으로 코팅된 ITO는 두께가 증가할수록 기공에 의해 박막의 불균일성이 증가하면서 이론적인 반사모델과의 차이가 커졌다. 실리카와 ITO의 계면에 존재하는 혼합층의 영향으로 인하여 실제측정반사율은 2층으로 디자인한 이론반사율보다 $SiO_2$/$SiO_2$+ITO/ITO의 3층으로 디자인한 반사모델에 보다 잘 적용되었다. 이론적인 저반사 디자인은 근거로 $SiO_2$/ITO 박막의 두께를 90, 65 nm로 조절한 이층막은 기준파장에서 2.5%의 반사율을 나타내었고, 가시광선 영역에서 이론반사율과 유사한 거동을 보였다.

RNN모델에서 하이퍼파라미터 변화에 따른 정확도와 손실 성능 분석 (Analysis of Accuracy and Loss Performance According to Hyperparameter in RNN Model)

  • 김준용;박구락
    • 융합정보논문지
    • /
    • 제11권7호
    • /
    • pp.31-38
    • /
    • 2021
  • 본 논문은 감성 분석에 사용되는 RNN 모델의 최적화를 얻기 위한 성능분석을 위하여 하이퍼파라미터 튜닝에 따른 손실과 정확도의 추이를 관찰하여 모델과의 상관관계를 연구하였다. 연구 방법으로는 시퀀셜데이터를 처리하는데 가장 최적화된 LSTM과 Embedding layer로 히든레이어를 구성한 후, LSTM의 Unit과 Batch Size, Embedding Size를 튜닝하여 각각의 모델에 대한 손실과 정확도를 측정하였다. 측정 결과, 손실은 41.9%, 정확도는 11.4%의 차이를 나타내었고, 최적화 모델의 변화추이는 지속적으로 안정적인 그래프를 보여 하이퍼파라미터의 튜닝이 모델에 지대한 영향을 미침을 확인하였다. 또한 3가지 하이퍼파라미터 중 Embedding Size의 결정이 모델에 가장 큰 영향을 미침을 확인하였다. 향후 이 연구를 지속적으로 이어나가 모델이 최적의 하이퍼파라미터를 직접 찾아낼 수 있는 알고리즘에 대한 연구를 지속적으로 이어나갈 것이다.

제주도 주변 해역 고등어 포착망의 연구 - 2 . 이중조에 있어서 망의 변형에 관한 모형실험 - (Studies on the Mackerel Purse Seine Operating in the Sea Area of Cheju Island - 2 . Model Experiment ob the Deformation of Net in Two Layer Current)

  • 박정식
    • 수산해양기술연구
    • /
    • 제22권4호
    • /
    • pp.32-40
    • /
    • 1986
  • A model experiment of purse seine by the circulating water tank was carried out on the changes of net shape and the tension of purseline under operation in two layer current. In the circular tank, the two layer current was made by cutting off the current of upper layer and producing the bottom current by the equipment shown in Fig. 1. The model experiment of purse sein was made on a reduced scale 1 :400, and the experiment was carried out according to the Tauti's model law. When the bottom current of O. 5 knot flows to lower part of three-eighths of net, following results are derived. The depth of sinkerline reached only about 80% of that of no current set. The horizontal shift of sinker line caused by the bottom current is maximized in tight set. The enclosed area by the floatIine immediately after the completion of set net is 61. 5% in tight set, 50. 0 % in loose set and 54. 1 % in lateral set of those in the case of no current. In the first half period of pursing, the tension of the purseline is enhenced by the bottom current and the pattern of increasing is irregular in the tension curves.

  • PDF

퍼지 TAM 네트워크를 이용한 건설협력업체 핵심역량모델의 패턴분석 (Pattern Analysis of Core Competency Model for Subcontractors of Construction Companies Using Fuzzy TAM Network)

  • 김성은;황승국
    • 한국지능시스템학회논문지
    • /
    • 제16권1호
    • /
    • pp.86-93
    • /
    • 2006
  • 생물학적으로 동기가 되는 신경망 모델에 기반한 TAM 네트워크는 특별히 패턴분석에 효과적인 모델이다. TAM 네트워크는 입력층, 카테고리층, 출력층으로 구성되어 있다. 입력 및 출력 데이터에 대한 퍼지룰은 TAM 네트워크에서 얻어진다. 각 층에서 링크와 노드를 감소하기 위한 3가지의 프루닝룰을 사용하는 TAM 네트워크를 퍼지 TAM 네트워크라고 한다. 본 논문에서는 퍼지 TAM 네트워크를 건설협력업체의 핵심역량모델의 패턴분석에 적용하고 그 유용성을 보인다.

Analytical study on seepage behavior of a small-scale capillary barrier system under lateral no-flow condition

  • Byeong-Su Kim
    • Geomechanics and Engineering
    • /
    • 제35권1호
    • /
    • pp.13-27
    • /
    • 2023
  • The model production for large-scale (lateral length ≥ 2.0 m) capillary barrier (CB) model tests is time and cost-intensive. To address these limitations, the framework of a small-scale CB (SSCB) model test under the lateral no-flow condition has been established. In this study, to validate the experimental methodology of the SSCB model test, a series of seepage analyses on the SSCB model test and engineered slopes in the same and additional test conditions was performed. First, the seepage behavior and diversion length (LD) of the CB system were investigated under three rainfall conditions. In the seepage analysis for the engineered slopes with different slope angles and sand layer thicknesses, the LD increased with the increase in the slope angle and sand layer thickness, although the increase rate of the LD with the sand layer thickness exhibited an upper limit. The LD values from the seepage analysis agreed well with the results estimated from the laboratory SSCB mode test. Therefore, it can be concluded that the experimental methodology of the SSCB model test is one of the promising alternatives to efficiently evaluate the water-shielding performance of the CB system for an engineered slope.

Thermal Striping 해석 난류모델 평가 (EVALUATION OF TURBULENCE MODELS FOR ANALYSIS OF THERMAL STRIPING)

  • 최석기;김세윤;김성오
    • 한국전산유체공학회지
    • /
    • 제10권4호통권31호
    • /
    • pp.1-11
    • /
    • 2005
  • A numerical study of the evaluation of turbulence models for thermal striping phenomenon is performed. The turbulence models chosen in the present study are the two-layer model, the shear stress transport (SST) model and the V2-f model. These three models are applied to the analysis of the triple-jet flow with the same velocity but different temperatures. The unsteady Reynolds-averaged Navier-Stokes (URANS) equation method is used together with the SIMPLEC algorithm. The results of the present study show that the temporal oscillation of temperature is predicted by the SST and V2-f models, and the accuracy of the mean velocity, the turbulent shear stress and the mean temperature is a little dependent on the turbulence model used. In addition, it is shown that both the two-layer and SST models have nearly the same capability predicting the thermal striping, and the amplitude of the temperature fluctuation is predicted best by the V2-f model.

Stability analysis of a three-layer film casting process

  • Lee, Joo-Sung;Shin, Dong-Myeong;Jung, Hyun-Wook;Hyun, Jae-Chun
    • Korea-Australia Rheology Journal
    • /
    • 제19권1호
    • /
    • pp.27-33
    • /
    • 2007
  • The co-extrusion of multi-layer films has been studied with the focus on its process stability. As in the single-layer film casting process, the productivity of the industrially important multi-layer film casting and the quality of thus produced films have often been hampered by various instabilities occurring in the process including draw resonance, a supercritical Hopfbifurcation instability, frequently encountered when the draw ratio is raised beyond a certain critical value. In this study, this draw resonance instability along with the neck-in of the film width has been investigated for a three-layer film casting using a varying width non-isothermal 1-D model of the system with Phan-Thien and Tanner (PTT) constitutive equation known for its robustness in portraying extensional deformation processes. The effects of various process conditions, e.g., the aspect ratio, the thickness ratio of the individual film layers, and cooling of the process, on the stability have been examined through the nonlinear stability analysis.

Design of intelligent estimation of composite fluid-filled shell for three layered active control structure

  • Ghamkhar, Madiha;Hussain, Muzamal;Khadimallah, Mohamed A.;Ayed, Hamdi;Naz, Muhammad Yasin;Tounsi, Abdelouahed
    • Computers and Concrete
    • /
    • 제29권2호
    • /
    • pp.117-126
    • /
    • 2022
  • The vibrational characteristic of three-layered cylindrical shell (CS) submerged in fluid with the ring support has been studied. The inner and outer layer is supposed to construct by isotropic layer. The composition of central layer is of functionally graded material type. Acoustic Wave condition has been utilized to present the impact of fluid. The central layer of cylindrical shell (CS) varies by volume fraction law that has been expressed in terms of polynomial. The main shell frequency equation has been obtained by theory of Love's shell and Rayleigh-Ritz technique. The oscillation of natural frequency has been examined under a variety of end conditions. The dependence of axial model has been executed with the help of characteristic beam function. The natural frequencies (NFs) of functionally graded material (FGM) shell have been observed of cylindrical shell along the shell axial direction. Different physical parameters has been used to examine the vibration characteristics due to the effect of volume fraction law. MATLAB software has been used to get result.