• 한국정밀공학회지
• /
• 제15권4호
• /
• pp.15-26
• /
• 1998

Full car model is needed for investigating as a entire dynamics of vehicle. In this study, 7DOF of full car model's dynamics is selected. This paper proposes the output feedback controller based on optimal control theory. Input data and output data from the optimal controller are used for neural network system identification of the suspension system. To do system identification, neural network which has robustness against nonlinearities and disturbances is adapted. This study uses back-propagation algorithm to train a multil-layer neural network. After obtaining a neural network model of a suspension system, a neuro-controller is designed. Neuro-controller controls suspension system with off-line learning method and multistep ahead prediction model based on the neural network model and a neuro-controller. The optimal controller and the neuro-controller are designed and then, both performances are compared through. For simulation, sinusoidal and rectangular virtual bumps are selected.

• Ecology and Resilient Infrastructure
• /
• 제3권2호
• /
• pp.117-125
• /
• 2016

도시 내 인구집중과 기후변화로 인해 다양한 형태의 도시 물 문제가 발생한다. 이에 대한 피해 예방과 사회적 손실 최소화를 위해 회복탄력적인 대안 수립이 필요하다. 본 연구는 도시 물 문제 저감을 위한 회복탄력적 사회기반시설 구축 전략 수립에 관한 기초연구로서, 대표적인 도시 물 문제 중 하나인 도시홍수를 사례로 하여 구조적 대안의 내구성을 평가하였다. 내구성 평가를 위한 지표로 내구성 지수 (robustness index, RI) 및 비용지수 (cost index, CI)를 결합한 내구성-비용지수 (robustness cost index, RCI)를 제안하고, 이를 강남역 상습침수구역에 적용하여 기존 기반시설과 구조적 대안 (하수관거 확충, 저류조 설치, 옥상녹화)을 평가하였다. 그 결과, 2~20년 빈도의 강우강도범위에서 저류조와 옥상녹화설치가 상대적으로 높은 RCI 값을 나타내었고 두 대안 중 RCI가 보다 높은 대안은 강우강도에 따라 달라지는 경향을 보였다. 30년 빈도 강우강도에 대하여는 저류조와 옥상녹화를 병용 설치하는 대안이 가장 높은 RCI 값을 나타내어 가장 회복탄력적인 대안으로 확인되었다. 최종적으로 재해의 계획규모에 따른 현행 사회기반시설의 내구성 평가 및 최적의 구조적 대안 선택 절차를 수립하여, 도시홍수 문제에 대한 회복탄력적 사회기반시설 구축 전략을 제시하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.548-551
• /
• 1997

Performance of force tracking impedance control of robot manipulators is degraded by the uncertainties in the robot and environment dynamic model. The purpose of this paper is to improve the controller robustness by applying neural network. Neural networks are designed to learn the uncertainties in robot and environment model for compensating the uncertainties. The proposed scheme is verified through the simulation of 20DOF robot manipulator.

• Journal of Information Processing Systems
• /
• 제5권4호
• /
• pp.221-228
• /
• 2009

Due to low cost, low-power, and scalability, ZigBee is considered an efficient wireless AMR infrastructure. However, these characteristics of ZigBee can make the devices more vulnerable to unexpected error environments. In this paper, a fault-tolerant wireless AMR network (FWAMR) is proposed, which is designed to improve the robustness of the conventional ZigBee-based AMR systems by coping well with dynamic error environments. The experimental results demonstrate that the FWAMR is considerably fault-tolerant compared with the conventional ZigBee-based AMR network.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 추계학술대회 학술발표 논문집
• /
• pp.263-266
• /
• 1997

In this paper we will develope the immnized recurrent neural network control system of a robot manipulator with high robustness in dynamically changing environment conditions. Immune system detects and eliminates the non-self materials called antigen such as virus, bacteria and so on which come from inside and outside of the living system, so plays an important role in maintaining its own system against dynamically changing environments. We apply this concept to a robot manipulator and evaluate the effectiveness of the above proposed system.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 추계학술대회 학술발표 논문집
• /
• pp.267-270
• /
• 1997

As an approach to develope a control system with robustness in changing control environment conditions, this paper will propose a robot manipulator control system using multilayer neural network and immune algorithm. The proposed immune algorithm which has the characteristics of immune system such as distributed and anomaly detection, probabilistic detection, learning and memory, consists of the innate immune algorithm and the adaptive immune algorithm. We will demonstrate the effectiveness of the proposed control system with simulations of a 2-link robot manipulator.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.161.4-161
• /
• 2001

This paper presents adaptive control of robot manipulator using neuro-fuzzy controller Fuzzy logic is control incorrect system without correct mathematical modeling. And, neural network has learning ability, error interpolation ability of information distributed data processing, robustness for distortion and adaptive ability. To reduce the number of fuzzy rules of the FLS(fuzzy logic system), we consider the properties of robot dynamic. In fuzzy logic, speciality and optimization of rule-base creation using learning ability of neural network. This paper presents control of robot manipulator using neuro-fuzzy controller. In proposed controller, fuzzy input is trajectory following error and trajectory following error differential ...

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.133.2-133
• /
• 2001

This paper focuses on the feasibility of fuzzy logic control for networked control systems. In order to evaluate its feasibility, a networked control system for motor speed control is implemented on a Profibus-DP network. The NCS consists of several independent, but interacting processes running on two separate stations. By using this NCS, the network delay is analyzed to find the cause of the delay. Furthermore, in order to prove the feasibility, the fuzzy logic controllers performance is compared with those of conventional PID controllers. Based on the experimental results, the fuzzy logic controller can be a viable choice for NCS due to its robustness against parameter uncertainty.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.224-229
• /
• 1992

We investigate a neural network as a dynamic system controller when system characteristics are abruptly changing. The shape of sigmoid functions are determined by autotuing method for the optimum sigmoid function of the neural networks. By using information stored in the identifying network a novel algorithm that can adapt the control action of the controller has been developed. Robustness can be seen from its ability to adjust large variations of parameters. The potential of the proposed method is demonstrated by simulations.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 하계학술대회 논문집 D
• /
• pp.2149-2151
• /
• 2002

In this paper, a novel speed estimation method of an induction motor using neural networks(NNs) is presented. The NN speed estimator is trained online by using the error backpropagation algorithm, and the training starts simultaneously with the induction motor working. The neural network based vector controller has the advantage of robustness against machine parameter variation. The simulation results using Matlab/Simulink verify the useful of the proposed method.