• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.179-179
• /
• 2023

This study suggests a new approach of water level forecasting for extended lead times using original data preprocessing with variational mode decomposition (VMD). Here, two machine learning algorithms including light gradient boosting machine (LGBM) and random forest (RF) were considered to incorporate extended lead times (i.e., 5, 10, 15, 20, 25, 30, 40, and 50 days) forecasting of water levels. At first, the original data at two water level stations (i.e., SW173 and SW269 in Bangladesh) and their decomposed data from VMD were prepared on antecedent lag times to analyze in the datasets of different lead times. Mean absolute error (MAE), root mean squared error (RMSE), and mean squared error (MSE) were used to evaluate the performance of the machine learning models in water level forecasting. As results, it represents that the errors were minimized when the decomposed datasets were considered to predict water levels, rather than the use of original data standalone. It was also noted that LGBM produced lower MAE, RMSE, and MSE values than RF, indicating better performance. For instance, at the SW173 station, LGBM outperformed RF in both decomposed and original data with MAE values of 0.511 and 1.566, compared to RF's MAE values of 0.719 and 1.644, respectively, in a 30-day lead time. The models' performance decreased with increasing lead time, as per the study findings. In summary, preprocessing original data and utilizing machine learning models with decomposed techniques have shown promising results for water level forecasting in higher lead times. It is expected that the approach of this study can assist water management authorities in taking precautionary measures based on forecasted water levels, which is crucial for sustainable water resource utilization.

• 한국음향학회지
• /
• 제27권6호
• /
• pp.319-324
• /
• 2008

본 논문에서는 변별적 가중치 학습 (discriminative weight training) 기반의 3GPP2 Selectable Mode Vocoder (SMV) 실시간 음성/음악 분류 성능을 향상 시키는 방법을 제안한다. SMV의 음성/음악 실시간 분류 알고리즘에서 사용된 특징벡터와 분류방법을 분석하고, 이를 기반으로 분류성능향상을 위해 MCE (minimum classification error)방법을 도입하여, 각 특징 백터별로 다른 가중치를 적용하는 음성/음악 결정법 (decision rule)을 제시한다. 구체적으로 SMV의 음성/음악 분류알고리즘에서 사용되어진 특징벡터만을 선택적으로 사용하여 가중치를 적용한 값을 기하 평균한 값을 문턱값과 비교하는 실시간 분류기법이 제시되었다. SMV의 음성/음악 분류에 제안한 방법의 성능 평가를 위해 SMV 원래의 분류알고리즘과 비교하였으며, 다양한 음악장르에 대해 시스템의 성능을 평가한 결과 가중치를 적용하였을 때 기존의 SMV의 방법보다 우수한 음성/음악 분류 성능을 보였다.

• 대한기계학회논문집
• /
• 제18권8호
• /
• pp.2088-2100
• /
• 1994

Considerable attention has been given to controller designs that utilize the variable structure system theory in order to achieve robust tracking performance of robotic manipulators subjected to parameter variations and extraneous disturbances. However, the theory has not had wide spread acceptance in practical control engineering community due mainly to the worry of chattering which is inherently ever-existing in the variable structure system. This paper presents a novel type of fuzzy-sliding mode controller to alleviate the chattering problem. A sliding mode controller for robust robot control is firstly synthesized with an assumption that the imposed system uncertainties satisfy matching conditions so that certain deterministic performances can parameters and control rules are obtained from a relation between predetermined sliding surfaces and representative points in the error state space. A two degree-of-freedom robotic manipulator subjected to a variable payload and a torque disturbance is considered in order to demonstrate superior tracking performance accrued from the proposed methodology.

• Journal of Advanced Marine Engineering and Technology
• /
• 제29권8호
• /
• pp.842-848
• /
• 2005

The decoupling control using state feedback was once intensively studied during 1960's by many researchers. However, this control scheme was sensitive to the disturbance and Parameter variations. SMC(sliding mode control) is known as a robust control methodology to overcome such a disturbance. In this paper. the decoupling control by means of SM(sliding mode) for a trajectory control of a two-degrees-of- freedom manipulator was discussed. The position and velocity of manipulator tip were adopted to compose a nonlinear error functions. The reference inputs of the controller can be decided by switching function combined with the desired position and velocity. Simulation result is provided to verify the effectiveness of the proposed control scheme.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1988년도 추계학술대회 논문집 학회본부
• /
• pp.76-79
• /
• 1988

The sliding mode control in an effective method to eatablish robustness against parameter variation and disturbance. But. In sliding mode strategy, the control function is discontinuous on the hyperplane. However the discontinuous change in control structure caves the controller input to chaffer and gives non-zero steady state error. Consequently, a multiloop feedback control system supplemented by a complelmentary controller is used to improved the drive performence of a DC servo motor and reduce sensitivity to parameter variation, nonlinear effects, and other disturbances.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2003년도 International Meeting on Information Display
• /
• pp.531-534
• /
• 2003

The electro-optical characteristics of the In-Plane switching Twisted nematic (IT) mode were studied. The advantage of this mode is not only the wide viewing angle characteristics without adopting any compensation films, but also the wide cell gap error margin. The electro-optical characteristics of IT mode were evaluated by the experiments and computer simulation. In this paper, we studied the viewing angle characteristics, color-shift and response time.

• 대한전기학회논문지:전기기기및에너지변환시스템부문B
• /
• 제55권4호
• /
• pp.224-230
• /
• 2006

The conventional way to implement a bidirectional converter with boost/buck has been to use two general purpose PWM ICs with a single supply voltage. In this case, when one direction mode is in operation, the other is disabled and the output of the error amplifier of the disabled IC may be saturated to a maximum value or zero. Therefore, during mode transition, a circuit which can disable the switching operation for a certain time interval is required making it impossible to get a seamless transition. In this paper, the limitations of the conventional 42V/14V bi-directional DC/DC converter implemented with general current mode PWM ICs with a single supply voltage are reviewed and a new current mode PWM controller circuit with a dual voltage system is proposed. The validity of the proposed circuit is investigated through simulation. and experiments.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.340-342
• /
• 2005

This paper describes the speed-sensorless vector control system of a three-phase induction motor using sliding mode flux/speed observer. The sliding mode observer estimates the rotor speed. The error between the actual and observed currents converges to zero which guarantees the accuracy of the flux observer. The convergence of nonlinear time-varying observer along with the asymptotic stability of the controller was analyzed. To define the control action which maintains the motion on the sliding manifold, an "equivalent control" concept was used. It was simulated and implemented on a sensorless indirect vector drive for 750[W] three-phase induction motor. The simulation and experimental results demonstrated the effectiveness of the proposed estimation method.

• Journal of Mechanical Science and Technology
• /
• 제19권2호
• /
• pp.567-577
• /
• 2005

Several methods for improving the interlaminar strength and fracture toughness of composite materials are developed. Through-the-thickness stitching is considered one of the most common ways to prevent delamination. Stitching significantly increases the Mode I fracture toughness and moderately improves the Mode II fracture toughness. An analytical model has been developed for simulating the behavior of stitched double cantilever beam specimen under various loading conditions. For z-directional load and moment about the y-axis the numerical solutions are compared with the exact solutions. The derived formulation shows good accuracy when the relative error of displacement and rotation between numerical and exact solution were calculated. Thus we can use the present model with confidence in analyzing other problems involving stitched beams.

• 제어로봇시스템학회논문지
• /
• 제6권4호
• /
• pp.305-312
• /
• 2000

This paper presents a new control scheme using a sliding mode controller with a multilayer neural network for the robot manipulator operating under the sea which has large uncertainties such as the buoyancy and the added mass/moment of inertia. The multilayer neural network using the error back propagation loaming algorithm acts as a compensator of the conventional sliding mode controller to improve the control performance when the initial assumptions of uncertainty bounds are not valid. Computer simulation results show that the proposed control scheme gives an effective path way to cope with the unexpected large uncertainties in the underwater robot manipulator.