• 한국지능시스템학회논문지
• /
• 제21권2호
• /
• pp.192-197
• /
• 2011

본 논문은 선형 상태 관측기의 성능 및 실용화 검증을 위하여 도립진자 시스템의 출력 피드백 제어 실험을 수행하였다. 도립진자 시스템으로는 (주)셈웨어의 CEM-IP-01를 실험에 사용하였다. 동역학 해석을 위하여 라그랑지안 방정식 및 자코비안 선형화 방법을 이용하였고, 모의실험을 통하여 일반 상태 피드백 제어기의 출력 응답과 제안된 제어기의 출력 응답을 먼저 비교 분석하였다. 마지막으로 실제 도립진자 시스템에 적용함으로써 제어기 구현에서 발생하는 문제점을 파악하고 해결함으로써 실용화 가능성을 직접 확인하였다.

• 한국마린엔지니어링학회:학술대회논문집
• /
• 한국마린엔지니어링학회 2001년도 춘계학술대회 논문집
• /
• pp.243-248
• /
• 2001

The stabilization control of Inverted Pendulum(IP) system is difficult because of its nonlinearity and structural unstability. Thus, in this paper, an Evolving Neural Network Controller(ENNC) without Error Back Propagation(EBP) is presented. An ENNC is described simply by genetic representation using an encoding strategy for types and slope values of each active functions, biases, weights and so on. By an evolutionary programming which has three genetic operation; selection, crossover and mutation, the predetermine controller is optimally evolved by updating simultaneously the connection patterns and weights of the neural networks. The performances of the proposed ENNC(PENNC) are compared with the ones of conventional optimal controller and the conventional evolving neural network controller(CENNC) through the simulation and experimental results. And we showed that the finally optimized PENNC was very useful in the stabilization control of an IP system.

• 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.

• 한국지능시스템학회논문지
• /
• 제20권6호
• /
• pp.768-773
• /
• 2010

본 논문에서는 도립진자 시스템을 이용한 최적 상태 되먹임 제어기 설계 및 성능 검증을 소개한다. 제안하고 있는 최적 상태 되먹임 제어기는 최적제어 이론을 기반으로 입력크기와 응답성능의 최적값을 고려하였고 뿐만 아니라, 적분제어기법을 도입함으로써 정상상태오차를 줄이도록 하였다. 실험에 사용된 도립진자 시스템은 (주)셈웨어의 PC기반 CEM-IP-01으로써 제안된 제어기를 적용한다. 마지막으로 제안된 제어기와 일반 상태 되먹임 제어기를 모의실험과 실험을 통하여 비교함으로써 제안된 제어기의 성능을 검증한다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제49권3호
• /
• pp.157-163
• /
• 2000

In this paper, an Evolving Neural Network Controller(ENNC) which its structure and its connection weights are optimized simultaneously by Real Variable Elitist Genetic Algoithm(RVEGA) was presented for stabilization of an Inverter Pendulum(IP) system with nonlinearity. This proposed ENNC was described by a simple genetic chromosome. And the deletion of neuron, the determinations of input or output neuron, the deleted neuron and the activation functions types are given according to the various flag types. Therefore, the connection weights, its structure and the neuron types in the given ENNC can be optimized by the proposed evolution strategy. Through the simulations, we showed that the finally acquired optimal ENNC was successfully applied to the stabilization control of an IP system.

• Journal of Advanced Marine Engineering and Technology
• /
• 제25권2호
• /
• pp.383-394
• /
• 2001

The stabilization control of inverted pendulum (IP) system is difficult because of its nonlinearity and structural unstability. In this paper, an Evolving Neural Network Controller (ENNC) without Error Back Propagation (EBP) is presented. An ENNC is described simply by genetic representation using an encoding strategy for types and slope values of each active functions, biases, weights and so on. By an evolutionary programming which has three genetic operation; selection, crossover and mutation, the predetermine controller is optimally evolved by updating simultaneously the connection patterns and weights of the neural networks. The performances of the proposed ENNC(PENNC)are compared with the one of conventional optimal controller and the conventional evolving neural network controller (CENNC) through the simulation and experimental results. And we showed that the finally optimized PENNC was very useful in the stabilization control of an IP system.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.3013-3015
• /
• 2000

The stabilization control of Inverted Pendulum(IP) system is difficult because of its nonlinearity and structural unstability. Futhermore, a series of conventional techniques such as the pole placement and the optimal control based on the local linearizations have narrow stabilizable regions, At the same time, the fine tunings of their gain parameters are also troublesome, Thus, in this paper, an Evolving Neural Network ControlleY(ENNC) which its structure and its connection weights are optimized simultaneously by Real Variable Elitist Genetic Algorithm (RVEGA) was presented for stabilization of an IP system with nonlinearity, This proposed ENNC was described by a simple genetic chromosome. Through the simulation and experimental results, we showed that the finally acquired optimal ENNC was very useful in the stabilization control of IP system.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1470-1473
• /
• 2003

In this paper the networked control systems (NCS) problem is discussed where plants and controllers are distributed and interconnected by a common network. NCS is designed with LQ regulator and applied to an inverted pendulum accounting for the multiple time delays. We are to deals with a networked control system with a single controller, multiple sensors and multiple actuators. Since these parts are distributed, they are interconnected by communication networks. An NCS with LQ regulator is designed and applied to an inverted pendulum as a benchmark plant to check its performance under time delays induced by the network. Network induced delays are composed of two parts. One is the delay from controller to plant, and another is from plant to controller. They are assumed to be constant in this paper, and the plant and controller are discretized. To apply the LQ regulator the NCS model is transformed to a standard model with delayed states as state variable. And real network induced delay is measuring in TCP/IP network assuming that two delays are constant.

• 조명전기설비학회논문지
• /
• 제14권3호
• /
• pp.68-76
• /
• 2000

로켓이나 2족 보행 로봇(Biped Robots)의 자세 제어에 응용되는 도립진자 시스템(Inverted Penduhum System)은 대표적 비선행 시스템으로 수학적 모델링이 대단히 어려우며, 모델링올 하였다 하더라도 복잡한 구조가 된다. 이의 해결을 위한 고전적인 제어 기법으로 1970년대 이후부터는, 신경회로망과 퍼지, 카오스, 유전 알고리증을 이용한 제어 기법들이 도립진자의 안정화 제어에 적용되어져고 있으며, 최근 신경회로망의 자동설계 기법들과 유전 또는 전화 알고리즘올 이용한 신경회로망의 구축 기법인 종래의 진화형 선정회로 제어기(ENNC : Evohing Neural Network Controller)가 시도되어지고 있다. 그러나 종래의 ENNC의 전화방식은 노드(뉴런)단위로 교배하며, 특히, 활성화 함수를 지닌 은닉층의 뉴런이 입력층의 뉴런으로 대체되는 경우, 입력층 뉴런과 출력층 뉴런 사이의 결합 가중치가 삭제되지 않는 등의 문제점이 지적될 수 있다. 따라서, 본 논문에서는 도립진자 시스템의 안정화 제어를 위하여 선택, 교배, 돌연변이의 진화 연산자에 의해 일시에 최적의 구조와 결합가중치로 진화시켜 가능 새로운 형태의 ENNC를 제안하고자 한디. 또한, 다양한 초기치에 적응된 최적 구조와 결합가중치를 갖는 새로운 형태의 ENNC를 시뮬레이션율 통하여 얻고, 이를 ADA-2310보드 및 80586 마이크로 프로세서로 실현하여, 도립진자 시스템의 안정화 제어에 적용함으로써 본 논운에서 제안한 ENNC의 우수성과 강인성을 입증하고자 한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년 학술대회 논문집 정보 및 제어부문
• /
• pp.136-138
• /
• 2006

Recently, network systems are widely used in several areas, and some considerable attentions have been directed to the Networked Control System(NCS). In NCS, network-induced delays are inevitable, and they sometimes degrade the performance of networked control systems to be a source of potential instability. In this paper, We proposes a compensation method for networked control system subject to network-induced delays by using a simple method, which is based on a sort of predictive strategy. To evaluate its feasibility and effectiveness, a real-time NCS for a rotary inverted pendulum is implemented via an Ethernet. Based on the experimental results. we show that the proposed simple method can be a practical and feasible solution to NCS design.