• Water for future
• /
• v.25 no.3
• /
• pp.105-113
• /
• 1992

The purpose of this paper is to introduce and to apply the artificial neural network theory to real hydrologic system for forecasting daily streamflows during flood periods. The hydrologic dynamic process of rainfall-runoff is identified by the iterated estimation of system parameters that are determined by adjusting the weights of the network according to the non-linear response characteristics which is formed the model. Back propagation algorithm of neural network model is applied for the estimation of system parameters with past daily rainfall and runoff series data, and streamflows are forecasted using the parameters. The forecasted results are analyzed by statistical methods for the comparison with the observed.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.185-193
• /
• 2022

This paper proposes an adaptive sliding mode control with radial basis function neural network(RBFNN) scheme to enhance the performance of position and attitude tracking control of quadrotor UAV. The RBFNN is utilized on the approximation of nonlinear function in the UAV dynmic model and the weights of the RBFNN are adjusted online according to adaptive law from the Lyapunov stability analysis to ensure the state hitting the sliding surface and sliding along it. In order to compensate the network approximation error and eliminate the existing chattering problems, the sliding mode control term is adjusted by adaptive laws, which can enhance the robust performance of the system. The simulation results of the proposed control method confirm the effectiveness of the proposed controller which applied for a nonlinear quadrotor UAV is presented. Form the results, it's shown that the developed control system is achieved satisfactory control performance and robustness.

• Journal of Advanced Marine Engineering and Technology
• /
• v.34 no.1
• /
• pp.102-108
• /
• 2010

The T-S fuzzy model of a ship is made from the nonlinear extension of Nomoto's 2nd-order model as the previous step before designing of the fuzzy type autopilot to consider the design specifications and the economic efficiency. The T-S fuzzy model is considered as a design variable of the heading angular velocity of ship. The linear models will be combined as "IF-THEN" fuzzy rules after get in this one area of the linear model(sub-system) by change of the heading angular velocity of a ship. The dynamic characteristic of a ship with the parameters of linear models and fuzzy membership functions are estimated to match by using the model adjustment technic with input/output data and a RCGA.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.11 no.6
• /
• pp.23-32
• /
• 2007

This study developed an analytical model for predicting nonlinear behavior of PT flat plate frames having slab-column connections with and without slab bottom reinforcement passing through the column. The developed model can predict the failure sequence until punching failure occurs. For verifying the analytical model, the test results of PT flat plate slab-column connections were compared with the results of the analysis. Moreover, the results of static pushover test and shaking table test of 2 story PT flat plate frame were compared with analysis results. For evaluating seismic performance of PT flat plate frame, this study conducted nonlinear response history analysis of the 2 story PT flat plate frame with and without slab bottom reinforcement passing through the column under 1940 El Centro ground motion scaled to have pseudo spectral acceleration of 0.3, 0.5, and 0.7g at the fundamental period of the frame. This study observed that as ground motion is more intense, seismic demands for the frame having the connections without slab bottom reinforcement passing through the column are larger than those without slab bottom reinforcement.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.9 no.4 s.44
• /
• pp.11-18
• /
• 2005

Inelastic seismic analysis is necessary for the seismic design due to the nonlinear behavior of a structure-soil system, and the importance of the performance based design considering the soil-structure interaction is recognized for the reasonable seismic design. In this study, elastic and inelastic seismic response analyses of a single degree of freedom system on the soft soil layer were peformed considering the nonlinearity of the soil for the 11 weak or moderate, and 5 strong earthquakes scaled to the nominal peak acceleration of 0.075g, 0.15g, 0.2g and 0.3g. Seismic response analyses for the structure-soil system were peformed in one step applying the earthquake motions to the bedrock In the frequency domain, using a pseudo 3-D dynamic analysis software. Study results indicate that it is necessary to consider the nonlinear soil-structure interaction effects and to perform the performance based seismic design for the various soil layers rather than to follow the routine procedures specified in the seismic design codes. Nonlinearity of the soft soil excited with the weak earthquakes also affected significantly to the elastic and inelastic responses due to the nonlinear soil amplification of the earthquake motions, and it was pronounced especially for the elastic ones.

• Journal of the Korean Geotechnical Society
• /
• v.17 no.5
• /
• pp.115-128
• /
• 2001

본 논문에서는 반복하중이나 지진하중을 받는 지반-구조물 시스템의 설계에 필수적인 변수인 전단탄성계수와 감쇠비에 대한 연구를 국내에 존재하는 비점성토 지반에 대하여 수행하였다. 국내 퇴적토지반 및 풍화토지반에서 채취된 자연시료와 입도분포를 조정하여 제작한 시료를 포함하여 총 60개의 시료에 대하여 20kPa에서 500kPa의 구속응력 범위에서 공진주 시험을 수행하고, 이를 조립질 사질토, 실트 및 실트질 모래, 풍화토의 3개의 그룹으로 나누어 결과를 정리하였다. 저변형률 영역의 변형특성인 최대전단탄성계수와 최소감쇠비에 대하여 구속응력의 영향을 확인하였다. 최대전단탄성계수를 예측하는 경험식을 3개의 그룹별로 제안하였다. 최소감쇠비는 구속응력에 따른 분포영역을 제시하였다. 세립분이 적은 조립질 사질토의 경우, 비선형 변형특성이 구속응력의 영향을 뚜렷이 받고 있어 이를 주요한 변수로 고려하여 대표곡선과 분포영역을 제안하였다. 구속응력의 영향을 적게 받는 실트 및 실트질 모래와 풍화토는 구속응력에 관계없이 대표곡선과 분포영역을 제안하였다. 제안된 각 시료의 대표곡선과 기존의 Vucetic-Dobry와 Seed-Idriss가 제안한 곡선과 비교하였다. 본 논문의 연구결과는 국내지반의 비점성토 지반에 대한 지진해석이나 동하중을 받는 시스템의 해석시 유용하게 사용될 것으로 판단된다.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.7 no.4
• /
• pp.15-22
• /
• 2003

Seismic design codes developed taking into account the strong earthquakes may result in unnecessary economical loss in the low seismic area, and the importance of the performance based design considering the soil-structure interaction is recognized for the reasonable seismic design. In this study. elastic and inelastic seismic response analyses of a single degree of freedom system on the soft soil layer were performed considering the nonlinearity of the soil for the 1 weak earthquakes scaled to the nominal peak accelerations of 0.07g and 0.11g. The seismic response analyses were performed in one step applying the earthquake motions to the bedrock, utilizing a pseudo 3-D dynamic analysis software of the soil-structure system. The study results indicated that seismic response spectra of a system assuming the rigid base or the linear soil layer does not represent the true behavior of a structure-soil system, and it is necessary to take into account the nonlinear soil-structure interaction effects and to perform the performance based seismic design for the various soil layers, having different characteristics, rather than to follow the routine design procedures specified in the design codes for the reasonable seismic design. The nonlinearity of the soft soil excited with the weak seismic motions also affected significantly on the elastic and inelastic seismic response spectra of a system due to the nonlinear soil amplification of the earthquake motions, and it was pronounced especially for the elastic response spectra.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.9 no.1
• /
• pp.171-180
• /
• 2005

In this study the seismic performance of a three-story knee-braced moment-resisting frame (KBMRF), which is typically employed to support pipelines for oil or gas, was investigated. Nonlinear static pushover analyses were performed first to observe the force-displacement relationship of KBMRF under increasing seismic load. The results show that, when the maximum inter-story drift reached 1.5% of the story height, the main structural members, such as beams and columns, still remained elastic. Then nonlinear dynamic time-history analyses were carried out using eight earthquake ground motion time-histories scaled to at the design spectrum of UBC-97. It turned out that the maximum inter-story drift was smaller than the drift limit of 1.5 % of the structure height, and that the columns remained elastic. Based on these analytical results, it can be concluded that the seismic performance of the structure satisfies all the requirements regulated in the seismic code.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.3
• /
• pp.347-352
• /
• 2010

Under harsh environments in which remote control is impossible, wire-guided control technology is effective for controlling distant underwater vehicles that serve mother ships in missions, such as exploration and installation. When the fiber is unwound from the spool, tension fluctuations occur in the fiber because of the relative velocity of the moving vehicles and unwinding velocity of the fiber. As a result, fiber cables exhibit complicated behaviors, become entangled, and may get cut. In this study, a spool-like design for winding tens of kilometers of fiber cables is proposed by analyzing cable winding. The unwinding performance of the designed spool is estimated by performing nonlinear dynamics analysis of the nonlinear behavior and tension fluctuations observed during the unwinding of the fiber.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.3
• /
• pp.303-314
• /
• 2020

The hydrological characteristics of watersheds and hydraulic systems of urban and river floods are highly nonlinear and contain uncertain variables. Therefore, the predicted time series of rainfall-runoff data in flood analysis is not suitable for existing neural networks. To overcome the challenge of prediction, a NARX (Nonlinear Autoregressive Exogenous Model), which is a kind of recurrent dynamic neural network that maximizes the learning ability of a neural network, was applied to forecast a flood in real-time. At the same time, NARX has the characteristics of a time-delay neural network. In this study, a hydrological model was constructed for the Taehwa river basin, and the NARX time-delay parameter was adjusted 10 to 120 minutes. As a result, we found that precise prediction is possible as the time-delay parameter was increased by confirming that the NSE increased from 0.530 to 0.988 and the RMSE decreased from 379.9 ㎥/s to 16.1 ㎥/s. The machine learning technique with NARX will contribute to the accurate prediction of flow rate with an unexpected extreme flood condition.