• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.956-959
• /
• 1996

In this study, we propose a neuro-genetic controller combined with a linear controller in parallel to improve the tracking performance of the Line of Sight(LOS) stabilization system and reject the effect of disturbances. A Genetic Algorithm(GA) is used to optimize weights of the neuro-genetic controller since this algorithm can search a global minimum without derivatives or other auxiliary knowledge. The LOS system is very complex and has limited measurable output data. Under these specific circumstances GA solves many problems that other training methods have. Computer simulation results show that the, proposed controller makes better tracking response and rejection of disturbance than a linear controller.

• 한국지능시스템학회논문지
• /
• 제10권5호
• /
• pp.395-400
• /
• 2000

본 논문에서는 강화학습에 기반한 새로운 뉴로-퍼지 제어기를 제안한다. 시스템은 개체의 행동을 결정하는 뉴로-퍼지 제어기와 그 행동을 평가하는 동적 귀환 신경회로망으로 구성된다. 뉴로-퍼지 제어기의 후건부 소속함수는 강화학습을 한다. 한편, 유전자 알고리즘을 통하여 진화하는 동적 귀환 신경회로망은 환경으로부터 받는 외부 강화신호와 로봇의 상태로부터 내부강화 신호를 만들어낸다. 이 출력(내부강화신호)은 뉴로-퍼지 제어기의 교사신호로 사용되어 제어기가 학습을 지속하도록 만든다. 제안한 시스템은 미지의 환경에서 제어기의 최적화 및 적응에 사용할 수 있다. 제안한 알고리즘은 컴퓨터 시뮬레이션 상에서 자율 이동로봇의 장애물 회피에 적용하여 그 유효성을 확인한다.

• 한국지능시스템학회논문지
• /
• 제4권1호
• /
• pp.35-49
• /
• 1994

It is well known that, for nominimum phase systems, a conventional linear controller of PID type or an adaptive controller of this structure shows limitation in achieving a satisfactory performance under tight specifications. In this paper, we combine a neuro-controller with a PI-controller with off-line learning capability provided by the Genetic Algorithm to propose a novel neuro-controller to control nonminimum phase systems effectively. The simulation results show that our proposed model is more efficient with faster rising time and less undershoot effect when the performances of the proposed controller and a conventional form are compared.

• 정보처리학회 논문지
• /
• 제13권2호
• /
• pp.13-17
• /
• 2024

본 논문에서는 규칙의 수를 줄여 간결한 지식 기반을 보장할 수 있는 합 기반의 전건부를 가지는 뉴로-퍼지 제어기를 제안하였다. 제안된 뉴로-퍼지 제어기는 모든 입력 변수의 AND 조합을 전건부로 하는 구조의 퍼지 규칙보다 더 큰 입력 영역을 커버하기 위해 전건부에 입력 퍼지 집합의 합집합 연산을 허용하였다. 이러한 뉴로-퍼지 제어기를 구성하기 위해 본 논문에서는 OR 및 AND 퍼지 뉴런으로 구성된 multiple-term unified logic processor (MULP)를 고려하였다. 이러한 OR 및 AND 퍼지 뉴런은 조정 가능한 연결 강도 집합을 가지므로 학습을 통하여 최적의 연결 강도 집합을 찾을 수 있다. 초기 최적화 단계에서 유전 알고리즘은 제안된 뉴로 퍼지 제어기의 최적화된 이진 구조를 구성하고, 이후 확률에 기반한 강화 학습은 성능 지수를 더욱 향상시켜서 유전 알고리즘에 의해 최적화된 제어기의 이진 연결을 개선하였다. 역진자 시스템을 제어하기 위한 모의실험 및 실험을 통해 제안된 방법의 유효성을 검증하였다.

• KIEE International Transaction on Systems and Control
• /
• 제12D권1호
• /
• pp.17-26
• /
• 2002

In this paper, a new design methodology of the fuzzy controller is presented. The performance of the fuzzy controller is sensitive to the variety of scaling factors. The design procedure is based on evolutionary computing (more specifically, a genetic algorithm) and estimation algorithm to adjust and estimate scaling factors respectively. The tuning of the soiling factors of the fuzzy controller is essential to the entire optimization process. And then we estimate scaling factors of the fuzzy controller by means of two types of estimation algorithms such as HCM (Hard C-Means) and Neuro-Fuzzy model[7]. The validity and effectiveness of the proposed estimation algorithm for the fuzzy controller are demonstrated by the inverted pendulum system.

• International Journal of Control, Automation, and Systems
• /
• 제5권4호
• /
• pp.436-443
• /
• 2007

In this paper, an intelligent method called BELBIC (Brain Emotional Learning Based Intelligent Controller) is used to control of Locally Linear Neuro-Fuzzy Model (LOLIMOT) of Washing Machine. The Locally Linear Neuro-Fuzzy Model of Washing Machine is obtained based on previously extracted data. One of the important issues in using BELBIC is its parameters setting. On the other hand, the controller design for Washing Machine is a multi objective problem. Indeed, the two objectives, energy consumption and effectiveness of washing process, are main issues in this problem, and these two objectives are in contrast. Due to these challenges, a Multi Objective Genetic Algorithm is used for tuning the BELBIC parameters. The algorithm provides a set of non-dominated set points rather than a single point, so the designer has the advantage of selecting the desired set point. With considering the proper parameters after using additional assumptions, the simulation results show that this controller with optimal parameters has very good performance and considerable saving in energy consumption.

• 제어로봇시스템학회논문지
• /
• 제5권2호
• /
• pp.189-199
• /
• 1999

This paper presents an optimization algorithm for a stable Self Dynamic Neural Network(SDNN) using genetic algorithm. Optimized SDNN is applied to a problem of controlling nonlinear dynamical systems. SDNN is dynamic mapping and is better suited for dynamical systems than static forward neural network. The real-time implementation is very important, and thus the neuro controller also needs to be designed such that it converges with a relatively small number of training cycles. SDW has considerably fewer weights than DNN. Since there is no interlink among the hidden layer. The object of proposed algorithm is that the number of self dynamic neuron node and the gradient of activation functions are simultaneously optimized by genetic algorithms. To guarantee convergence, an analytic method based on the Lyapunov function is used to find a stable learning for the SDNN. The ability and effectiveness of identifying and controlling a nonlinear dynamic system using the proposed optimized SDNN considering stability is demonstrated by case studies.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.416-419
• /
• 2001

In this paper a new approach to estimate scaling factors of fuzzy controllers such as the fuzzy PID controller and the fuzzy PD controller is presented. The performance of the fuzzy controller is sensitive to the variety of scaling factors[1]. The desist procedure dwells on the use of evolutionary computing(a genetic algorithm) and estimation algorithm for dynamic systems (the inverted pendulum). The tuning of the scaling factors of the fuzzy controller is essential to the entire optimization process. And then we estimate scaling factors of the fuzzy controller by means of two types of estimation algorithms such as Neuro-Fuzzy model, and regression polynomial [7]. This method can be applied to the nonlinear system as the inverted pendulum. Numerical studies are presented and a detailed comparative analysis is also included.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2005년도 학술발표회 논문집
• /
• pp.469-476
• /
• 2005

To date, many viable smart base isolation systems have been proposed. In this study, a novel friction pendulum system (FPS) and an MR damper are employed as the isolator and supplemental damping device, respectively. A fuzzy logic controller (FLC) is used to modulate the MR damper. A genetic algorithm (GA) is used for optimization of the FLC. The main purpose of employing a GA is to determine appropriate fuzzy control rules as well to adjust parameters of the membership functions. To this end, a GA with a local improvement mechanism is applied. Neuro-fuzzy models are used to represent dynamic behavior of the MR damper and FPS. Effectiveness of the proposed method for optimal design of the FLC is judged based on computed responses to several historical earthquakes. It has been shown that the proposed method can find appropriate fuzzy rules and the GA-optimized FLC outperforms not only a passive control strategy but also a human-designed FLC and a conventional semi-active control algorithm.

• 전기학회논문지P
• /
• 제51권2호
• /
• pp.99-104
• /
• 2002

In this paper, we construct a hybrid intelligent controller based on a fusion scheme of GA(Genetic Algorithm) and FCM(Fuzzy C-Means) clustering-based ANFIS(Adaptive Neuro-Fuzzy Inference System). In the structure identification, a set of fuzzy rules are generated for a given criterion by FCM clustering algorithm. In the parameter identification, premise parameters are optimally searched by adaptive GA. On the other hand, consequent parameters are estimated by RLSE(Recursive Least Square Estimate) to reduce the search space. Finally, we applied the proposed method to the truck backer-upper control and obtained a better performance than previous works.