• 한국항해학회지
• /
• 제23권2호
• /
• pp.1-9
• /
• 1999

A trailer truck is a major equipment for transporting containers, and its driving is difficult due to two degrees of freedom which exist in the joint part between truck and trailer. Especially Backing a trailer truck to a parking home is a difficult exercise for all but the most skilled truck drivers. Normal driving instincts lead to erroneous movements. When watching a truck driver backing toward a parking home, one often observes the driver backing, going forward, backing again, going forward, etc., and finally backing to the desired position along the parking home. This paper discusses the design of the controller to control the steering of a trailer truck while only backing up to a parking home from an initial position. In this paper, we propose a backing up control system for a container trailer truck using fuzzy theory where the primitive fuzzy control rules are macroscopically designed using an expert's knowledge, and the control rules are regulated by LIBL(Linguistic Instruction Based Learning) to enable to back up successfully the trailer tuck to a parking home from arbitrary initial position. The validity of the proposed parking control system is shown by applying it to some initial positions on the simulator for container trailer truck.

• International Journal of Control, Automation, and Systems
• /
• 제1권3호
• /
• pp.289-300
• /
• 2003

In this paper, we introduce an identification method in Fuzzy Relation-based Fuzzy Neural Networks (FRFNN) through a hybrid identification algorithm. The proposed FRFNN modeling implement system structure and parameter identification in the efficient form of "If...., then... " statements, and exploit the theory of system optimization and fuzzy rules. The FRFNN modeling and identification environment realizes parameter identification through a synergistic usage of genetic optimization and complex search method. The hybrid identification algorithm is carried out by combining both genetic optimization and the improved complex method in order to guarantee both global optimization and local convergence. An aggregate objective function with a weighting factor is introduced to achieve a sound balance between approximation and generalization of the model. The proposed model is experimented with using two nonlinear data. The obtained experimental results reveal that the proposed networks exhibit high accuracy and generalization capabilities in comparison to other models.er models.

• 동력기계공학회지
• /
• 제2권3호
• /
• pp.21-26
• /
• 1998

Numerical simulations for various fluid flows require enormous computing time during iterations. In order to solve this problem, several techniques have been proposed. A SOR method is one of the effective methods for solving elliptic equations. However, it is very difficult to find the optimum relaxation factor, the value of this factor for practical problems used to be estimated on the basis of expertise. In this paper, the implication of the relaxation factor are translated into fuzzy control rules on the basis of the expertise of numerical analysers, and fuzzy controller incorporated into a numerical algorithm. From two cases of study, Poisson equation and cavity flow problem, we confirmed the possibility of computational acceleration with fuzzy logic and qualitative reasoning in numerical simulations. Numerical experiments with the fuzzy controller resulted in generating a good performance.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1994년도 Proceedings of the Korea Automatic Control Conference, 9th (KACC) ; Taejeon, Korea; 17-20 Oct. 1994
• /
• pp.263-266
• /
• 1994

Recently, complicated and dexterous tasks with two or more arms are needed in ninny robot manipulator applications which can not be accomplished with one manipulator. In general, when two arms manipulate an object, tile dynamics of the arms and the object should be considered simultaneously. In order to control the force of tile arms, we can use various control schemes based upon dynamic modeling. But, there are difficulties in solving inverse dynamics equations, and the environment where a manipulator performs various tasks is usually unknown, and we can not describe a model precisely, for instances, the effect of the joint flexibility, and the friction between the arm and the object. Therefore, in this paper, we suggest a new force control method employing fuzzy inference without solving dynamic equations. Fuzzy inference rules and parameters are designed and adjusted with the automatic fuzzy modeling method using the Hough transform and gradient descent method.

• 대한기계학회논문집
• /
• 제18권8호
• /
• pp.2088-2100
• /
• 1994

Considerable attention has been given to controller designs that utilize the variable structure system theory in order to achieve robust tracking performance of robotic manipulators subjected to parameter variations and extraneous disturbances. However, the theory has not had wide spread acceptance in practical control engineering community due mainly to the worry of chattering which is inherently ever-existing in the variable structure system. This paper presents a novel type of fuzzy-sliding mode controller to alleviate the chattering problem. A sliding mode controller for robust robot control is firstly synthesized with an assumption that the imposed system uncertainties satisfy matching conditions so that certain deterministic performances can parameters and control rules are obtained from a relation between predetermined sliding surfaces and representative points in the error state space. A two degree-of-freedom robotic manipulator subjected to a variable payload and a torque disturbance is considered in order to demonstrate superior tracking performance accrued from the proposed methodology.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.993-996
• /
• 1993

This paper addresses the structure and its associated learning algorithms of a feedforward multi-layered connectionist network, which has distributed learning abilities, for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed neural-network-based fuzzy logic control system (NN-FLCS) can be contrasted with the traditional fuzzy logic control system in their network structure and learning ability. An on-line supervised structure/parameter learning algorithm dynamic learning algorithm can find proper fuzzy logic rules, membership functions, and the size of output fuzzy partitions simultaneously. Next, a Reinforcement Neural-Network-Based Fuzzy Logic Control System (RNN-FLCS) is proposed which consists of two closely integrated Neural-Network-Based Fuzzy Logic Controllers (NN-FLCS) for solving various reinforcement learning problems in fuzzy logic systems. One NN-FLC functions as a fuzzy predictor and the other as a fuzzy controller. As ociated with the proposed RNN-FLCS is the reinforcement structure/parameter learning algorithm which dynamically determines the proper network size, connections, and parameters of the RNN-FLCS through an external reinforcement signal. Furthermore, learning can proceed even in the period without any external reinforcement feedback.

• 산업기술연구
• /
• 제16권
• /
• pp.231-237
• /
• 1996

In this paper, the nonlinear I/O characteristic of fuzzy logic controller is analyzed by using cell concept. Sources of the nonlinearity in a fuzzy logic controller include the fuzzification, the fuzzy reasoning and the defuzzification. A closed form expression for the defuzzified output is derived in case of a fuzzy logic controller with two inputs, triangular memberships, MacVicar-Whelan type linguistic rules, and direct fuzzy reasoning. As a result, it is shown that fuzzy logic controller is a nonlinear controller. Also its nonlinearity is analyzed with respect to the conventional PID control and the sliding mode control.

• 한국지능시스템학회논문지
• /
• 제10권3호
• /
• pp.260-269
• /
• 2000

The fuzzy and state-feedback control systems have been applied in various areas from non-linear to linear systems. A Fuzzy controller is endowed with control rules and membership function that are constructed on the knowledge of expert, as like intuition and experience. but It is very difficult to obtain the exact values which are the membership function and consequent parameters. though apply back-propagation algorithm to the system, the convergence time a much. Besides, the state-feedback system is most widely used in industry due to its simple control structure and easily able to design the controller. but it is weak in complex system of higher degree and non-linear. In this paper presents the design of a fuzzy switching mode, it these two controllers work at different operation conditions, the advantages of both controller can be retained and the disadvantages can be removed. Between the Fuzzy and the State-feedback controlles, the good outputs are selected by the switching mode. Moreover it is powerful in complex system of higher degree and non-linear. In these sense compared with the state-feedback controller, the performance of the proposed controller was improvedin the section of linearization.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1024-1026
• /
• 1996

Sources of nonlinearity In a fuzzy logic controller Include the fuzzification, the fuzzy reasoning and the defuzzification. In this paper, a closed form expression for the defuzzified output is derived in case of a fuzzy logic controller with two Inputs, triangular memberships, MacVicar-Whelan type linguistic rules, and direct fuzzy reasoning. As a result, it is shown that fuzzy logic controller is a nonlinear controller. Also its nonlinearity Is analyzed with respect to the conventional PID control and the sliding mode control.

• 제어로봇시스템학회논문지
• /
• 제7권6호
• /
• pp.494-501
• /
• 2001

In this paper an ANFIS(Adativo Neuro-Fuzzy Inference System)- based fault detection and diagnosis for a closed loop control system is proposed. The proposed diagnostic system contains two ANFIS. One is run as a parallel model within the model in closed loop control(MCL) and the other is run as a series-parallel model within the process in closed loop(PCL) for the generation of relevant symptoms for fault diagnosis. These symptoms are further processed by another classification logic with simple rules and neural network for process and controller fault diagnosis. Experimental results for a DC shunt motor control system illustrate the effectiveness of the proposed diagnostic scheme.