• 조명전기설비학회논문지
• /
• 제27권6호
• /
• pp.59-67
• /
• 2013

This paper presents a neural net type process model for enhancing learning compensation function in hot strip finishing rolling mill. Adequate input and output variables of process model are chosen, the proposed model was designed as single layer neural net. Equivalent carbon content, strip thickness and rolling speed are suggested as input variables, and looper's manipulation variable is proposed as output variable. According to simulation result using process data to show the validity of the proposed process model, neural net type process model's outputs give almost similar data to process output under same input conditions.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국제학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.534-540
• /
• 1993

In this paper, we present an iterative learning method of compensating for position sensor error. The previously known compensation algrithms need a special perfect position sensor or a priori information about error sources, while ours does not. To our best knowledge, any iterative learning approach has not been taken for sensor error compensation. Furthermore, our iterative learning algorithm does not have the drawbacks of the existing iterative learning control theories. To be more specific, our algorithm learns a uncertain function inself rather than its special time-trajectory and does not request the derivatives of measurement signals. Moreover, it does not require the learning system to start with the same initial condition for all iterations. To illuminate the generality and practical use of our algorithm, we give the rigorous proof for its convergence and some experimental results.

• 한국컴퓨터정보학회논문지
• /
• 제23권10호
• /
• pp.23-31
• /
• 2018

Recently, there have been many studies on machine learning. Among them, studies on reinforcement learning are actively worked. In this study, we propose a controller to control bicycle using DDPG (Deep Deterministic Policy Gradient) algorithm which is the latest deep reinforcement learning method. In this paper, we redefine the compensation function of bicycle dynamics and neural network to learn agents. When using the proposed method for data learning and control, it is possible to perform the function of not allowing the bicycle to fall over and reach the further given destination unlike the existing method. For the performance evaluation, we have experimented that the proposed algorithm works in various environments such as fixed speed, random, target point, and not determined. Finally, as a result, it is confirmed that the proposed algorithm shows better performance than the conventional neural network algorithms NAF and PPO.

• 전자공학회논문지B
• /
• 제31B권9호
• /
• pp.57-66
• /
• 1994

In this paper, we present an iterative learning method of compensating for position sensor error. The previously known compensation algorithms need a special perfect position sensor or a priori information about error sources, while ours does not. to our best knowledge, any iterative learning approach has not been taken for sensor error compensation. Furthermore, our iterativelearning algorithm does not have the drawbacks of the existing interativelearning control theories. To be more specivic, our algorithm learns an uncertain function itself rather than its special time-trajectory and does not reuquest the derivatives of measurement signals. Moreover, it does not require the learning system to start with the same initial condition for all iterations. To illuminate the generality and practical use of our algorithm, we give the rigorous proof for its convergence and some experimental results.

• 한국통신학회논문지
• /
• 제21권9호
• /
• pp.2456-2469
• /
• 1996

A digital satellite communication channel has a nonlinearity with memory due to saturation characeristis of the high poer amplifier in the satellite and transmitter/receiver linear filter used in the overall system. In this paper, we propose a complex radial basis function network(CRBFN) based adaptive equalizer for compensation of nonlinearities in digital satellite communication channels. The proposed CRBFN untilizes a complex-valued hybrid learning algorithm of k-means clustering and LMS(least mean sequare) algorithm that is an extension of Moody Darken's algorithm for real-valued data. We evaluate performance of CRBFN in terms of symbol error rates and mean squared errors nder various noise conditions for 4-PSK(phase shift keying) digital modulation schemes and compare with those of comples pth order inverse adaptive Volterra filter. The computer simulation results show that the proposed CRBFN ehibits good equalization, low computational complexity and fast learning capabilities.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 추계학술대회 논문집 학회본부
• /
• pp.386-388
• /
• 1996

This paper presents the learning controller for robot manipulators to track the desired trajectory exactly. The learning controller, based on the Lyapunov theory, consists of a fixed PD action and a repetitive action for the purpose of feedforward compensation which is adjusted utilizing a linear combination of the velocity and position errors. The learning controller Is often used In case of the desired trajectories are periodic tasks, and has advantage that it periodically converges to zero even if we don't know the exact dynamic parameters. In this paper, we show that the position and velocity errors of robot manipulators converge to zero sa time goes infinite for the input is periodic function and show a good trajectory tracking performance In the cartesian space.

• 한국인터넷방송통신학회논문지
• /
• 제14권3호
• /
• pp.63-68
• /
• 2014

본 논문은 다중 경로 페이딩과 대역폭 제한 특성을 갖는 채널에서 부호간 간섭을 제거시킬 수 있는 CMA 적응 등화기에서 위상 보상이 가능한 I-CMA (Improved-CMA) 알고리즘에 관한 것이다. 기존 CMA 알고리즘의 오차신호를 얻기 위한 비용 함수를 개량하여 진폭과 위상의 동시 제거가 가능토록 새로운 비용 함수가 제안되며 이의 성능을 컴퓨터 시뮬레이션 확인하였다. 알고리즘의 단순성과 등화 후 위상 보상을 위한 별도의 PLL을 제거할 수 있는 장점을 가지며, 이를 위해 수신측에서의 등화기 출력 신호인 복원된 신호 성상도, 수렴 성능을 나타내는 성능 지수인 잔류 isi 및 MD (Maximum Distortion) 특성 곡선과 채널과 등화기의 종합 주파수 특성을 사용하였다. 시뮬레이션 결과 I-CMA가 복원 성상도에서 진폭과 위상 보상 능력이 CMA보다 우월하였지만, 수렴 시간에서는 동시 위상 보상으로 인하여 CMA보다 늦어짐을 알 수 있었다.

• Journal of Power Electronics
• /
• 제11권6호
• /
• pp.922-930
• /
• 2011

In this paper, two radial basis function neural networks (RBFNNs) are used to dynamically identify harmonics content in converter waveforms based on the p-q (real power-imaginary power) theory. The converter waveforms are analyzed and the types of harmonic content are identified over a wide operating range. Constant power and sinusoidal current compensation strategies are investigated in this paper. The RBFNN filtering training algorithm is based on a systematic and computationally efficient training method called the hybrid learning method. In this new methodology, the RBFNN is combined with the p-q theory to extract the harmonics content in converter waveforms. The small size and the robustness of the resulting network models reflect the effectiveness of the algorithm. The analysis is verified using MATLAB simulations.

• 대한의용생체공학회:의공학회지
• /
• 제11권1호
• /
• pp.157-162
• /
• 1990

In this study, a peripheral auditory model is used as a frequency feature extractor and a recurrent network which has recurrent links on input nodes is constructed in order to show the reliability of the recurrent network as a recognizer by executing recognition tests for 4 Korean place names and syllables. In the case of using the general learning rule, it is found that the weights are diverged for a long sequence because of the characteristics of the node function in the hidden and output layers. So, a refined weight compensation method is proposed and, using this method, it is possible to improve the system operation and to use long data. The recognition results are considerably good, even if time worping and endpoint detection are omitted and learning patterns and test patterns are made of average length of data. The recurrent network used in this study reflects well time information of temporal speech signal.

• 한국정밀공학회지
• /
• 제15권11호
• /
• pp.76-82
• /
• 1998

In this study, the Ball screw and Servo motor Mechanism is considered as a High Speed Tool Feed System for the machining of a piston of a reciprocating engine. For the machining of a piston, that shapes oval, high speed servo mechanism is needed as a positioning of a cutting tool, and the stroke of tool is 0.1 mm ~ 1 mm. Ball screw and servo motor Mechanism is available very much because this mechanism is used widely in general machine. This Mechanism has been designed with the use of the decrease in mass and partial wear of the ball screw for high speed positioning of tool. Also the periodic learning control method with the inverse transfer function compensation has been applied to the positioning control for the high accuracy positioning of tool. These applications lead the achievement of the machining of a piston with an accuracy of 5${\mu}{\textrm}{m}$ at 2500 rpm in CNC turning.