• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.4
• /
• pp.15-26
• /
• 1998

Full car model is needed for investigating as a entire dynamics of vehicle. In this study, 7DOF of full car model's dynamics is selected. This paper proposes the output feedback controller based on optimal control theory. Input data and output data from the optimal controller are used for neural network system identification of the suspension system. To do system identification, neural network which has robustness against nonlinearities and disturbances is adapted. This study uses back-propagation algorithm to train a multil-layer neural network. After obtaining a neural network model of a suspension system, a neuro-controller is designed. Neuro-controller controls suspension system with off-line learning method and multistep ahead prediction model based on the neural network model and a neuro-controller. The optimal controller and the neuro-controller are designed and then, both performances are compared through. For simulation, sinusoidal and rectangular virtual bumps are selected.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.5
• /
• pp.533-538
• /
• 2004

This paper proposes a systematic method to develop short-term electrical load forecasting systems using neuro-fuzzy models. The proposed system predicts the electrical loads with the lead times of 1 hour, 24 hour, and 168 hour. To do so, the load forecasting system first builds an initial structure off-line for each hour of four day types and then stores the resultant initial structures in the initial structure bank. 96 initial structures are constructed for each prediction lead time. Whenever a prediction needs to be made, the proposed system initializes the neuro-fuzzy model with the appropriate initial structure stored and trains the initialized prediction modell. To improve the performance of the prediction system in terms of accuracy and reliability at the same time, the prediction model employs only two inputs. It makes possible to interpret the fuzzy rules to be learned. In order to demonstrate the viability of the proposed method, we develop a load forecasting system by using the real load data collected during 1996 and 1997 at KEPCO. Simulation results reveal that the prediction system developed in this paper can achieve a remarkable improvement on both accuracy and reliability

• Journal of Korean Society of Transportation
• /
• v.14 no.3
• /
• pp.7-26
• /
• 1996

The estimation of real-time Origin-Destination(O-D) parameters, which gives travel demand between combinations of origin and destination points on a urban freeway network, from on-line surveillance traffic data is essential in developing an efficient ATMS strategy. On this need a real-time O-D parameter estimation model is formulated as a parameter adaptive filtering model based on the extended Kalman Filter. A Monte Carlo test have shown that the estimation of time-varying O-D parameter is possible using only traffic counts. Tests with field data produced the interesting finding that off-ramp volume predictions generated using a constant freeway O-D matrix was replaced by real-time estimates generated using the parameter adaptive filter.

• Journal of Welding and Joining
• /
• v.25 no.6
• /
• pp.64-70
• /
• 2007

Recently, several models to control weld quality, productivity and weld properties in arc welding process have been developed and applied. Also, the applied model to make effective use of the robotic GMA(Gas Metal Arc) welding process should be given a high degree of confidence in predicting the bead dimensions to accomplish the desired mechanical properties of the weldment. In this study, a development of the on-line learning neural network models that investigate interrelationships between welding parameters and bead width as well as apply for the on-line quality control system for the robotic GMA welding process has been carried out. The developed models showed an excellent predicted results comparing with the predicted ability using off-line learning neural network. Also, the system will extend to other welding process and the rule-based expert system which can be incorporated with integration of an optimized system for the robotic welding system.

• Corrosion Science and Technology
• /
• v.9 no.4
• /
• pp.159-163
• /
• 2010

Precise coating weight control is very important issue on quality and minimizing operating costs on continuous galvanizing line. These days, many steel making companies are having a new understanding of cost importance by rise raw material prices and customer's requirement for cost reduction. Dongbu steel also meets these situations and decided to develop the technologies. Dongbu Steel developed Integrated coating weight control system jointly with Objective Control Ltd. and installed 2CGL and 4CGL. Several technological functions were developed and realized to achieve true hands-off operation and maximum cost benefit by combining model-based preset and dynamic prediction models. We also installed it on 1 CGL on April, 2008. This paper will present the interface, functions and application result of the integrated coating weight control system including Zn saving and coating weight uniformity.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.238-238
• /
• 2016

토양수분, 증발산량, 유출량 등의 고해상도 수문기상요소 산출을 위한 지면모델 활용 기술은 기상 및 수문분야에서 널리 활용 중에 있다. 본 연구에서는 미국 국립대기과학연구소(NCAR)에서 개발된 기상-수문 결합모델 WRF-Hydro(Weather Research and Forecasting Model Hydrological modeling extension package)을 활용하여 낙동강 유역에서 발생한 돌발홍수 사례 실험에 적용하여 강우량 및 수문기상요소 전체를 모의함으로써 기상-수문-지면 결합모델을 활용한 수문기상요소 산출하고자 하였다. 이를 기존의 기상모델로부터 입력강제자료를 제공받아 Off-line 형태로 결합된 지면모델(TOPLATS, TOPmodel-based Land Atmosphere Transfer Scheme) 결과와 비교하였고 기상-수문 결합모델의 국내 적용성을 검토하였다. 기상-수문-지면 결합모델(WRF-Hydro)의 초기장 및 경계장은 기상청 현업 모델에서 생성된 국지예보모델자료 1.5km 자료(LDAPS, Local Data Assimilation and Prediction System)를 사용하였으며, 모델의 적분기간은 돌발홍수 사례에 따라 24~36시간을 수행하였다. WRF-Hydro 모델의 물리모수화 방안은 작년까지 기상청에서 현업운영되는 KWRF의 방안들을 준용하였으며, WRF-Hydro 수행을 위해 Advanced Spaceborne Thermal Emission and Reflection Radiometer(ASTER)에서 제공되는 30 m 해상도의 수치표고자료를 GIS(Geographic Information System)를 활용하여 지표유출방향을 설정하였다.

• Journal of Auto-vehicle Safety Association
• /
• v.11 no.3
• /
• pp.30-36
• /
• 2019

This paper suggests a car-following algorithm for urban environment, with multiple target candidates. Until now, advanced driver assistant systems (ADASs) and self-driving technologies have been researched to cope with diverse possible scenarios. Among them, car-following driving has been formed the groundwork of autonomous vehicle for its integrity and flexibility to other modes such as smart cruise system (SCC) and platooning. Although the field has a rich history, most researches has been focused on the shape of target trajectory, such as the order of interpolated polynomial, in simple single-lane situation. However, to introduce the car-following mode in urban environment, realistic situation should be reflected: multi-lane road, target's unstable driving tendency, obstacles. Therefore, the suggested car-following system includes both in-lane preceding vehicle and other factors such as side-lane targets. The algorithm is comprised of three parts: path candidate generation and optimal trajectory selection. In the first part, initial guesses of desired paths are calculated as polynomial function connecting host vehicle's state and vicinal vehicle's predicted future states. In the second part, final target trajectory is selected using quadratic cost function reflecting safeness, control input efficiency, and initial objective such as velocity. Finally, adjusted path and control input are calculated using model predictive control (MPC). The suggested algorithm's performance is verified using off-line simulation using Matlab; the results shows reasonable car-following motion planning.

• Journal of Korea Water Resources Association
• /
• v.53 no.3
• /
• pp.181-191
• /
• 2020

In order to produce accurate initial condition of soil moisture for global Numerical Weather Prediction (NWP), spin-up experiment is carried out using Noah Land Surface Model (LSM). The model is run repeatedly through 10 years, under the atmospheric forcing condition of 2008-2017 until climatological land surface state is achieved. Spin-up time for the equilibrium condition of soil moisture exhibited large variability across Koppen-Geiger climate classification zone and soil layer. Top soil layer took the longgest time to equilibrate in polar region. From the second layer to the fourth layer, arid region equilibrated slower (7 years) than other regions. This result means that LSM reached to equilibrium condition within 10 year loop. Also, spin-up time indicated inverse correlation with near surface temperature and precipitation amount. Initialized from the equilibrium state, LSM was spun up to obtain land surface state in 2018. After 6 months from restarted run, LSM simulates soil moisture, skin temperature and evaportranspiration being similar land surface state in 2018. Based on the results, proposed LSM spin-up system could be used to produce proper initial soil moisture condition despite updates of physics or ancillaries for LSM coupled with NWP.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1730-1747
• /
• 2018

Multi-view video plus depth (MVD) is a mainstream format of 3D scene representation in free viewpoint video systems. The advanced 3D extension of the high efficiency video coding (3D-HEVC) standard introduces new prediction tools to improve the coding performance of depth video. However, the depth video in 3D-HEVC is time consuming. To reduce the complexity of the depth video inter coding, we propose a fast coding unit (CU) size and mode decision algorithm. First, an off-line trained Bayesian model is built which the feature vector contains the depth levels of the corresponding spatial, temporal, and inter-component (texture-depth) neighboring largest CUs (LCUs). Then, the model is used to predict the depth level of the current LCU, and terminate the CU recursive splitting process. Finally, the CU mode search process is early terminated by making use of the mode correlation of spatial, inter-component (texture-depth), and inter-view neighboring CUs. Compared to the 3D-HEVC reference software HTM-10.0, the proposed algorithm reduces the encoding time of depth video and the total encoding time by 65.03% and 41.04% on average, respectively, with negligible quality degradation of the synthesized virtual view.