• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.7
• /
• pp.36-45
• /
• 1999

In order to control the flow of traffics in ATM networks and optimize the usage of network resources, an efficient control mechanism is necessary to cope with congestion and prevent the degradation of network performance caused by congestion. In this paper, Buffered Leaky Bucket which applies the same control scheme to a variety of traffics requiring the different QoS(Quality of Service) and Neural Networks lead to the effective buffer utilization and QoS enhancement in aspects of cell loss rate and mean transfer delay. And the cell scheduling algorithms such as DWRR and DWEDF for multiplexing the incoming traffics are enhanced to get the better fair delay. The network congestion information from cell scheduler is used to control the predicted traffic loss rate of Neural Leaky Bucket, and token generation rate and buffer threshold are changed by the predicted values. The prediction of traffic loss rate by neural networks can enhance efficiency in controlling the cell loss rate and cell transfer delay of next incoming cells and also be applied for other traffic controlling schemes. Computer simulation results performed for random cell generation and traffic prediction show that QoSs of the various kinds of traffcis are increased.

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 2003.05a
• /
• pp.372-377
• /
• 2003

센서리스 제어는 고정자 전압과 전류, 역기전력 등과 같은 정보를 이용하여 회전자의 속도 및 위치를 추종하는 방법이다. 센서리스는 수학적 모델, 물리적인 현상 및 제어 이론을 이용하는 방법으로 분류되어 연구되고 있다. 수학적인 모델을 이용하는 방법에는 고정자 전압에서 고정자 저항에 의한 전압 강하분을 제거한 항을 적분하여 자속의 위치를 추정한다.［1］ 물리적인 현상을 이용하는 방법에는 INFORM 방법과 고주파 전압을 주입하는 방법 등이 있다. 제어이론을 이용하는 방법은 MRAC, EKF 및 상태관측기［2］등을 이용하는 방법이다.(중략)

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.856-860
• /
• 1991

This paper proposes a modified fuzzy controller using a neural network. This controller can automatically identify expert's control rules and tune membership functions utilizing expert's control data. Identificaton capability of the fuzzy controller is examined using simple numerical data. The results show that the network in this paper can identify nonlinear systems more precisely than conventional fuzzy controller using neural network.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.230-235
• /
• 1992

We propose a method of generating data to train a neural network controller. The data can be prepared directly by an iterative learning technique which repeatedly adjusts the control input to improve the tracking quality of the desired trajectory. Instead of storing control input data in memory as in iterative learning control, the neural network stores the mapping between the control input and the desired output. We apply this concept to the trajectory control of a two link robot manipulator with a feedforward neural network controller and a feedback linear controller. Simulation results show good generalization of the neural network controller.

• Journal of Advanced Marine Engineering and Technology
• /
• v.30 no.1
• /
• pp.169-175
• /
• 2006

This paper describes how an Artificial Neural Network(ANN) can be employed to improve a speed estimation in a vector controlled induction motor drive. The system uses the ANN to estimate changes in the motor resistance, which enable the sensorless speed control method to work more accurately. Flux Observer is used for speed estimation in this system. Obviously the accuracy of the speed control of motor is dependent upon how well the parameters of the induction machine are known. These parameters vary with the operating conditions of the motor; both stator resistance(Rs) and rotor resistance(Rr) change with temperature, while the stator leakage inductance varies with load. This paper proposes a parameter compensation technique using artificial neural network for accurate speed estimation of induction motor and simulation results confirm the validity of the proposed scheme.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.8 no.5
• /
• pp.70-75
• /
• 1999

Adaptive control in the robotic GMA(Gas Metal Arc) welding is employed to monitor the information about weld characteristics and process paramters as well as modification of those parameters to hold weld quality within the acceptable limits. Typical characteristics are the bead geometry composition micrrostructure appearance and process parameters which govern the quality of the final weld. The main objectives of this paper are to realize the mapping characteristicso f penetration through the learning. After learning the neural network can predict the pene-traition desired from the learning mapping characteristic. The design parameters of the neural network estimator(the number of hidden layers and the number of nodes in a layer) were chosen from an error analysis. partial-penetration single-pass bead-on-plate welds were fabricated in 12mm mild steel plates in order to verify the performance of the neural network estimator. The experimental results show that the proposed neural network estimator can predict the penetration with reasonable accuracy and gurarantee the uniform weld quality.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.2
• /
• pp.140-147
• /
• 2008

This paper describes a Neural Network based PD control scheme for motion control of pneumatic servo cylinder. Pneumatic systems have inherent nonlinearities such as compressibility of air and nonlinear frictions present in cylinder. The conventional linear controller is limited in some applications where the affection of nonlinear factor is dominant. A self-excited oscillation method is applied to derive the dynamic design parameters of linear model. Based on the parameters thus identified, a PD feedback compensator is designed first and then a neural network is incorporated. The experiments of a trajectory tracking control using the proposed control scheme are performed and a significant reduction in tracking error is achieved by comparing with those of a PD control.

• IE interfaces
• /
• v.10 no.1
• /
• pp.37-45
• /
• 1997

본 연구에서는 웨이퍼 팹공정에서 웨이퍼 로트들이 뱃치공정을 위해 확률적으로 도착되는 상황에서 최적 뱃치크기를 결정하는 뱃칭문제를 다루고 있다. 뱃치공정이란 여러 개의 웨이퍼 로트들을 기계의 용량을 넘지 않는 한도 내에서 하나의 뱃치로 구성하여 한꺼번에 가공하는 공정을 말한다. 목적함수는 생산율을 높이고 재공재고 및 사이클타임을 줄이기 위해 웨이퍼 로트들의 평균 대기시간의 최소화를 채택하였다. 문제의 해결을 위해서, 확률적인 상황변동 하에서 실시간 제어를 위해 많이 활용되고 있는 신경회로망 중 다층 퍼셉트론을 이용한 뱃치크기 결정 모델을 제시하였다. 제시한 모델의 효율성을 확인하기 위해 기존에 잘 알려져 있는 최저뱃치크기(MBS) 규칙과 실험, 비교하였다.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.3 no.3
• /
• pp.256-262
• /
• 1998

The torque of SRM depends on phase current and the derivative of inductance. But the inductance of SRM is nonlinearly changed according to rotor position angle and phase current because of saturation in magnetic circuit, and it is difficult to control the desired torque. This paper proposes inductance modeling method using ANN(Artificial Neural Network) that is used to simulate the inductance which is nonlinearly varied with rotor position and current. The torque ripple is analyzed and input voltage and current condition to reduce torque ripple is simulated by inductance model.

• Journal of Industrial Technology
• /
• v.24 no.A
• /
• pp.99-107
• /
• 2004

This paper considers reinforcement learning control with the self-organizing map. Reinforcement learning uses the observable states of objective system and signals from interaction of the system and the environments as input data. For fast learning in neural network training, it is necessary to reduce learning data. In this paper, we use the self-organizing map to parition the observable states. Partitioning states reduces the number of learning data which is used for training neural networks. And neural dynamic programming design method is used for the controller. For evaluating the designed reinforcement learning controller, an inverted pendulum of the cart system is simulated. The designed controller is composed of serial connection of self-organizing map and two Multi-layer Feed-Forward Neural Networks.