• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권1호
• /
• pp.38-44
• /
• 2001

This paper investigates the direct adaptive control of nonlinear systems using RBFN(radial basis function networks). The structure of the controller consists of a fixed PD controller and a RBFN controller in parallel. An adaptation law for the parameters of RBFN is developed based on the Lyapunov stability theory to guarantee the stability of the overall control system. The filtered tracking error between the system output and the desired output is shown to be UUB(uniformly ultimately bounded). To evaluate the performance of the controller, the proposed method is applied to the trajectory contro of the two-link manipulator.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 G
• /
• pp.2992-2994
• /
• 1999

This paper investigates the direct adaptive control of nonlinear systems using RBFN(radial basis function networks). The structure of the controller consists of a fixed PD controller and a RBFN controller in parallel. An adaptation law for the weight adjustment is developed based on the Lyapunov stability theory to guarantee the stability of the overall control scheme. Also, the tracking errors between the system outputs and the desired outputs converge to zero asymptotically. To evaluate the performance of the controller, the proposed method is applied to the trajectory control of the two-link manipulator.

• 조명전기설비학회논문지
• /
• 제15권4호
• /
• pp.14-22
• /
• 2001

본 논문에서는 전력계통의 저주파 진동 억제와 안정도 향상을 위해 적응 뉴로-퍼지 전 보상기(Adaptive Neuro-Fuzzy Precompensator, ANFP)를 설계하였다. 여기서 ANFP는 종래의 전력계통 안정화 장치(Power System Stabilizer, PSS)를 보상하도록 설계되며, 이 설계기법은 기존의 PSS 최적 파라미터를 구하는 방식과는 달리 현재 사용중인 PSS 파라미터를 고정시켜놓고, ANFP만을 추가하는 구조적인 장점을 나타낸다. 먼저, 학습 능력을 가지는 퍼지 전 보상기가 구성되며, 이는 발전 유니트의 입출력 데이터로부터 학습된다. ANFP는 학습의 특성을 가지기 때문에 보상기의 퍼지규칙과 소속함수는 학습 알고리즘에 의해 자동으로 동조될 수 있다 학습은 ANFP와 목표 제어기(desired controller)의 출력을 비교하여 평가되는 오차를 최소화하도록 수행된다. 사례 연구 들에서 다양한 동작 조건들 상에서 전력계통의 우수한 제동을 제공할 수 있었으며, 시스템의 동특성을 향상시킬 수 있었다

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.169-177
• /
• 2024

Interacting Spherical tank has maximum storage capacity is broadly utilized in industries because of its high storage capacity. This two tank level system has the nonlinear characteristics due to its varying surface area of cross section of tank. The challenging tasks in industries is to manage the flow rate of liquid. This proposed work plays a major role in controlling the liquid level in avoidance of time delay and error. Several researchers studied and investigated about reducing the nonlinearity problem and their approaches do not provide better result. Different types of controllers with various techniques are implemented by the proposed system. Intelligent Adaptive Neuro Fuzzy Inference System (ANFIS) based Sliding Mode Controller (SMC) with Fractional order PID controller is a novel technique which is developed for a liquid level control in a interacting spherical tank system to avoid the external disturbances perform better result in terms of rise time, settling time and overshoot reduction. The performance of the proposed system is obtained by analyzing the simulation result obtained from the controller. The simulation results are obtained with the help of FOMCON toolbox with MATLAB 2018. Finally, the performance of the conventional controller (FOPID, PID-SMC) and proposed ANFIS based SMC-FOPID controllers are compared and analyzed the performance indices.

• 전자공학회논문지SC
• /
• 제41권4호
• /
• pp.21-28
• /
• 2004

본 논문에서는 다변수 비선형 시스템에 적응할 수 있는 신경회로망을 이용한 직접 다변수 자기동조 제어기를 제안한다. 제어기에 적용되는 플랜트는 고차이고 잡음, 시간지연과 상호결합 항이 존재하며 파라미터가 변하는 다변수 비선형 비최소위상 시스템이다. 비선형성은 전체적인 유계라 가정하며, 시스템은 선형부분과 비선형부분으로 분리한 형태로 구성한다. 다변수 비선형 자기동조 제어기의 제어 출력은 신경회로망으로 직접 추정된 제어기 파라미터로부터 얻어진다. 제어 알고리듬의 타당성을 확인하기 위해 시간지연이 있고 일정한 시간이 경과한 후 시스템의 파라미터가 변하는 고차 다변수 비선형 비최소위상 시스템에 대해 컴퓨터 시뮬레이션을 하였다. 그리고 신경회로망을 이용한 직접 다변수 적응 제어기와 비교하였다.

• 전력전자학회논문지
• /
• 제5권2호
• /
• pp.192-199
• /
• 2000

본 논문은 고주파 유도 가열기의 전력조절을 위해 뉴로-퍼지 알고리즘을 이용하고, IGBT를 사용한 위상 전이 펄스변조(PSPM)와 주파수 추종 펄스변조(FEPM) 가 조절되는 공진 고주파 인버터를 응용한 유도가열기를 설명한다. 이는 실제로 산업 현장에서 20KHz~500KHz 유도 가열 및 유도 용해 전원장치용으로 쓰인다. 위상 전이 펄스변조 (PSPM) 정전력 조절 기술을 바탕으로 한 적응 주파수 추종기법은 스위칭 손실을 최소화하고 전력조절을 용이하게 하기 위해 소개되어졌다. 뉴로-퍼지제어기를 사용하여 만들어진 실험장치는 성공적인 논증과 토의가 되어졌다.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2000년도 봄 학술발표회논문집
• /
• pp.271-276
• /
• 2000

Optimal neuro-control algorithm is extended to the control of a multi-degree-of-freedom structure. An active mass driver(AMD) system on the top roof used as a controller. The control signals are made by a multi-layer perceptron(MLP) which is trained by minimizing a sub-optimal performance index. The performance index is a function of both the output responses and the control signals. Structure having nonlinear hysteretic behavior is also trained and controlled by using proposed control algorithm. Bothe the time delay effect and the dynamics of hydraulic actuator are included in the simulation. Example shows that optimal neuro-control algorithm can be applicable to the multi-degree of freedom structures.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.691-695
• /
• 1998

Most of systems has nonlinearity . And also accurate modelings of these uncertain nonlinear systems are very difficult. In this paper, a fuzzy modeling technique for the stabilization control of an IP(inverted pendulum) system with nonlinearity was proposed. The fuzzy modeling was acquired on the basis of ANFIS(Adaptive Neuro Fuzzy Infernce System) which could learn using a series of input-output data pairs. Simulation results showed its superiority to the PID controller. We believe that its applicability can be extended to the other nonlinear systems.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1997년도 추계학술발표회논문집(1)
• /
• pp.299-304
• /
• 1997

A neuro-fuzzy control algorithm is applied for xenon spatial oscillations in a pressurized water reactor. The consequent and antecedent parameters of the fuzzy rules are tuned by the gradient descent mettled. The reactor model used for computer simulations is a two-point xenon oscillation model. The reactor core is axially divided into two regions and each region has one input and one output and is coupled with the other region. The interaction between the regions of the reactor core is treated by a decoupling scheme. This proposed control of mettled exhibits very fast responses to a step or a ramp change of target axial offset without any residual flux oscillations.

• Structural Engineering and Mechanics
• /
• 제62권2호
• /
• pp.237-246
• /
• 2017

In the present paper a new Neuro-Wavelet control algorithm is proposed based on a cost function to actively control the vibrations of structures under earthquake loads. A wavelet neural network (WNN) was developed to train the control algorithm. This algorithm is designed to control multi-degree-of-freedom (MDOF) structures which consider the geometric and material non-linearity, structural irregularity, and the incident direction of an earthquake load. The training process of the algorithm was performed by using the El-Centro 1940 earthquake record. A numerical model of a three dimensional (3D) three story building was used to accredit the control algorithm under three different seismic loads. Displacement responses and hysteretic behavior of the structure before and after the application of the controller showed that the proposed strategy can be applied effectively to suppress the structural vibrations.