• Journal of Korean Association for Spatial Structures
• /
• v.20 no.2
• /
• pp.51-58
• /
• 2020

Recently, deep learning that is the most popular and effective class of machine learning algorithms is widely applied to various industrial areas. A number of research on various topics about structural engineering was performed by using artificial neural networks, such as structural design optimization, vibration control and system identification etc. When nonlinear semi-active structural control devices are applied to building structure, a lot of computational effort is required to predict dynamic structural responses of finite element method (FEM) model for development of control algorithm. To solve this problem, an artificial neural network model was developed in this study. Among various deep learning algorithms, a recurrent neural network (RNN) was used to make the time history response prediction model. An RNN can retain state from one iteration to the next by using its own output as input for the next step. An eleven-story building structure with semi-active tuned mass damper (TMD) was used as an example structure. The semi-active TMD was composed of magnetorheological damper. Five historical earthquakes and five artificial ground motions were used as ground excitations for training of an RNN model. Another artificial ground motion that was not used for training was used for verification of the developed RNN model. Parametric studies on various hyper-parameters including number of hidden layers, sequence length, number of LSTM cells, etc. After appropriate training iteration of the RNN model with proper hyper-parameters, the RNN model for prediction of seismic responses of the building structure with semi-active TMD was developed. The developed RNN model can effectively provide very accurate seismic responses compared to the FEM model.

• 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.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.965-968
• /
• 2005

Roll drafting operation causes variations in the linear density of bundles because the bundle flow cannot be controlled completely by roll pairs. Defects occurring in this operation bring about many problems successively in the next processes. In this paper, we attempt to analyze the draft dynamics and the linear density irregularity based on the governing equation of a bundle motion that has been suggested in our previous studies. For analyzing the dynamic characteristics of the roll drafting operation, it is indispensable to investigate a transient state in time domain before the bundle flux reaches a steady state. However, since governing equations of bundle flow consisting of continuity and motion equations turn out to be nonlinear, and coupled between variables, the solutions for a transient state cannot be obtained by an analytical method. Therefore, we use the Finite Difference Method(FDM), particularly, the FTBS(Forward-Time Backward-Space) difference method. Then, the total equations system yields to an algebraic equations system and is solved under given initial and boundary conditions in an iterative fashion. From the simulation results, we confirm that state variables show different behavior in the transient state; e.g., the velocity distribution in the flow field changes more quickly the linear density distribution. During a transient flow in a drafting zone, the output irregularity is influenced differently by the disturbances, e.g., the variation in input bundle thickness, the drafting speed, and the draft ratio.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.18 no.11
• /
• pp.1262-1270
• /
• 2007

In this paper, we propose a new distortion cancellation mechanism for a balanced power amplifier structure using the carrier cancellation loop of a feedforward and post-distortion technique. The proposed cross post-distortion balanced linear amplifier can reduce nonlinear components as much as the conventional feedforward amplifier through the output dynamic range and broad bandwidth. Also the proposed system provides higher efficiency than the feedforward. The capacities of power amplifier and error power amplifier in the proposed system are analyzed and compared with those of feedforward amplifier. Also the operation mechanisms of the three kind loops are explained. The proposed cross post-distortion balanced linear power amplifier is implemented at the IMT-2000($f_0=2.14\;GHz$) band. With the commercial high power amplifiers of total power of 240 W peak envelope power fer base-station application, the adjacent channel leakage ratio measurement with wideband code division multiple access 4FA signal shows 18.6 dB improvement at an average output power of 40 dBm. The efficiency of fabricated amplifier Improves about 2 % than the conventional feedforward amplifier.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.103-123
• /
• 1999

Input filtering as a preprocessing method is so much crucial to get good performance in time series forecasting. There are a few preprocessing methods (i.e. ARMA outputs as time domain filters, and Fourier transform or wavelet transform as time-frequency domain filters) for handling time series. Specially, the time-frequency domain filters describe the fractal structure of financial markets better than the time domain filters due to theoretically additional frequency information. Therefore, we, first of all, try to describe and analyze specially some issues on the effectiveness of different filtering methods from viewpoint of the performance of a neural network based forecasting. And then we discuss about neural network model architecture issues, for example, what type of neural network learning architecture is selected for our time series forecasting, and what input size should be applied to a model. In this study an input selection problem is limited to a size selection of the lagged input variables. To solve this problem, we simulate on analyzing and comparing a few neural networks having different model architecture and also use an embedding dimension measure as chaotic time series analysis or nonlinear dynamic analysis to reduce the dimensionality (i.e. the size of time delayed input variables) of the models. Throughout our study, experiments for integration methods of joint time-frequency analysis and neural network techniques are applied to a case study of daily Korean won / U. S dollar exchange returns and finally we suggest an integration framework for future research from our experimental results.

• International Journal of Aeronautical and Space Sciences
• /
• v.18 no.4
• /
• pp.623-640
• /
• 2017

The full nonlinear equations of an unmanned aerial vehicle ground taxiing mathematical dynamic model are built based on a type of unmanned aerial vehicle data in LMS Virtual.Lab Motion. The flexible landing gear model is considered to make the aircraft ground motion more accurate. The electric braking control system is established in MATLAB/Simulink and the experiment of it verifies that the electric braking model with the pressure sensor is fitted well with the actual braking mechanism and it ensures the braking response speediness. The direction rectification control law combining the differential brake and the rudder with 30% anti-skid brake is built to improve the directional stability. Two other rectifying control laws are demonstrated to compare with the designed control law to verify that the designed control is of high directional stability and high braking efficiency. The lateral displacement increases by 445.45% with poor rectification performance under the only rudder rectifying control relative to the designed control law. The braking distance rises by 36m and the braking frequency increases by 85.71% under the control law without anti-skid brake. Different landing conditions are simulated to verify the good robustness of the designed rectifying control.

• Journal of Navigation and Port Research
• /
• v.34 no.4
• /
• pp.271-279
• /
• 2010

The Mobile Harbor(MH) is a new transportation platform that can load and unload containers to and from very large container ships in the sea. This loading and unloading by crane can be performed with only very small movements of the MH in waves because MH is operated outside of the harbor. For this reason, an anti-rolling tank(ART) and an active mass driving system(AMD) were designed to reduce MH's roll motion, especially at the natural frequency of MH. In the conceptual design stage, it is difficult to confirm the design result of theses anti-rolling devices without modeling and simulation tools. Therefore, the coupled MH and anti-rolling devices' dynamic equations in waves were derived and a simulation program that can analyze the roll reduction performance in various conditions, such as sea state, wave direction, and so on, was developed. The coupled equations are constructed as an eight degrees of freedom (DOF) motion that consists of MH's six DOF dynamics and the ART's and AMD's control variables. In order to conveniently include the ART's and AMD's control dynamics in the time domain, MH's radiated wave force was described by an impulse response function derived by the damping coefficient obtained in the frequency domain, and wave exciting forces such as Froude-Krylov force and diffraction force and nonlinear buoyancy were calculated at every simulation time interval. Finally, the roll reduction performances of the designed anti-rolling devices were successfully assessed in the various loading and wave conditions by using a developed simulation program.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.36D no.1
• /
• pp.8-14
• /
• 1999

The active devices used at microwave frequency have the different phase shift according to input power. Especially, The difference of the phase shift is large in the saturation region of the amplifier. In this paper, we disigned the phase control system for fixing the different phase shift at device. With the high frequency nonlinear amplifier, we fabricated such system that the phase shift to be fixed automatically using the varible phase shifter. The variable phase shifter fixed total phase variation of the circuit using the information that was obtained from the comparison of imputsignal phase with output signal phase. Even though the input signal is 2-tone or FM type, we could estimate and also fix the phase variation on DUT Dynamic range is about 10dB. It has been experimented at 1960MHz using Teflon (H=31mil, ${\varepsilon}r$=3.2)

• Structural Engineering and Mechanics
• /
• v.61 no.4
• /
• pp.527-538
• /
• 2017

The evaluation of the loss-of-support conditions of frictional beam-to-column connections using simplified numerical models describing the transverse response of a portal-like structure is presented in this paper considering the effects of the seismic-hazard disaggregation. Real earthquake time histories selected from European Strong-motion Database (ESD) are used to show the effects of the seismic-hazard disaggregation on the beam loss-of-support conditions. Seismic events are classified according to different values of magnitudes, epicentral distances and soil conditions (stiff or soft soil) highlighting the importance of considering the characteristics of the seismic input in the assessment of the loss-of-support conditions of frictional beam-to-column connections. A rigid and an elastic model of a frame of a precast industrial building (2-DoF portal-like model) are presented and adopted to find the minimum required friction coefficient to avoid sliding. Then, the mean value of the minimum required friction coefficient with an epicentral distance bin of 10 km is calculated and fitted with a linear function depending on the logarithm of the epicentral distance. A complete parametric analysis varying the horizontal and vertical period of vibration of the structure is performed. Results show that the loss-of-support condition is strongly influenced by magnitude, epicentral distance and soil conditions determining the frequency content of the earthquake time histories and the correlation between the maxima of the horizontal and vertical components. Moreover, as expected, dynamic characteristics of the structure have also a strong influence. Finally, the effect of the column nonlinear behavior (i.e. formation of plastic hinges at the base) is analyzed showing that the connection and the column are a series system where the maximum force is limited by the element having the minimum strength. Two different longitudinal reinforcement ratios are analyzed demonstrating that the column strength variation changes the system response.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.19 no.2
• /
• pp.17-28
• /
• 2015

In this paper, it is accomplished to design a control method for such an actuation system of simplified ON/OFF mechanism with actuation command limit. First of all, based on experimental data, the modeling works for nonlinear/linear actuation dynamics are performed, which are govern by PWM command as a control input. Using the linearized model, a classical PI control method is designed to satisfy the aimed control performance requirements, and a control algorithm is proposed to realize the required control performance in the effective control region through resolving the issue for the PWM command limit which reduces the control performance. Finally, through control simulations, the design method is verified and the corresponding control performance improvement is evaluated.