The objective of the research is two fold. The first is to design and propose a stable and robust learning control algorithm. The controller is CMAC Learning Controller which consists of a model-based controller, such as LQR or PID, as a reference control and a CMAC. The second objective is to implement a reference control and CMAC at two different sampling rates. Generally, a conventional controller is designed based on a mathematical plant model. However, increasing complexity of the plant and accuracy requirement on mathematical models nearly prohibits the application of the conventional controller design approach. To avoid inherent complexity and unavoidable uncertainty in modeling, biology mimetic methods have been developed. One of such attempts is Cerebellar Model Articulation Computer(CMAC) developed by Albus. CMAC has two main disadvantages. The first disadvantage of CMAC is increasing memory requirement with increasing number of input variables and with increasing accuracy demand. The memory needs can be solved with cheap memories due to recent development of new memory technology. The second disadvantage is a demand for processing powers which could be an obstacle especially when CMAC should be implemented in real-time. To overcome the disadvantages of CMAC, we propose CMAC learning controller with multiple sampling rates. With this approach a conventional controller which is a reference to CMAC at high enough sampling rate but CMAC runs at the processor's unoccupied time. To show efficiency of the proposed method, an inverted pendulum controller is designed and implemented. We also demonstrate it's possibility as an industrial control solution and robustness against a modeling uncertainty.

This paper presents an intelligent PID control for stochastic systems with nonstationary nature. We optimally determine parameters of a PID controller through learning algorithm and propose an online PID control to compensate system errors possibly occurred in realtime implementations. A dynamic Bayesian network (DBN) model for system errors is additionally explored for making decision about whether an online control is carried out or not in practice. We apply our control approach to traffic control of Transmission Control Protocol (TCP) networks and demonstrate its superior performance comparing to a fixed PID from computer simulations.

This paper proposes a new width control system composed of an ANWC(Automatic Neural network based Width Control) and a fuzzy-PID controller in hot strip finishing mills which aims at obtaining the desirable width. The ANWC is designed using a neural network based width prediction model to minimize a width variation between the measured width and its target value. Input variables for the neural network model are chosen by using the hypothesis testing. The fuzzy-PlD control system is also designed to obtain the fast looper response and the high width control precision in the finishing mill. It is shown through the field test of the Pohang no. 1 hot strip mill of POSCO that the performance of the width margin is considerably improved by the proposed control schemes.

This paper deals with ANN(Artificial Neural Networks) and its application to automatic ship berthing. Due to the characteristic of ship's manoeuvre comparing with other moving objects on land, it has been known that the automatic control for ship's berthing cannot cope with various berthing situations such as various port shape and approaching directions. for these reasons. the study on automatic berthing using ANN usually have been carried out based on one port shape and predetermined approaching direction. In this paper, new algorithm with ANN controller was suggested to cope with these problems. Under newly suggested algorithm, the controller can select appropriate weights on the link of neural networks according to various situations. so the ship can maintain stable berthing operation even in different situations. Numerical simulations are carried out with this control system to find its improvement.

This paper presents an adaptive neural computation algorithm for multi-layered neural networks which are applied to identify the characteristic function of dynamic systems. The main feature of the proposed algorithm is that the initial learning rate for the employed neural network is assigned systematically, and also the assigned learning rate can be adjusted empirically for effective neural leaning. By employing the approach, enhanced modeling of dynamic systems is possible. The effectiveness of this approach is veri tied by simulations.

A technique to model plasma processes was presented. This was accomplished by combining the backpropagation neural network (BPNN) and genetic algorithm (GA). Particularly, the GA was used to optimize five training factor effects by balancing the training and test errors. The technique was evaluated with the plasma etch data, characterized by a face-centered Box Wilson experiment. The etch outputs modeled include Al etch rate, AI selectivity, DC bias, and silica profile angle. Scanning electron microscope was used to quantify the etch outputs. For comparison, the etch outputs were modeled in a conventional fashion. GABPNN models demonstrated a considerable improvement of more than 25% for all etch outputs only but he DC bias. About 40% improvements were even achieved for the profile angle and AI etch rate. The improvements demonstrate that the presented technique is effective to improving BPNN prediction performance.

This paper presents a stiffness modeling of a low-DOF parallel robot, which takes into account of elastic deformations of joints and links, A low-DOF parallel robot is defined as a spatial parallel robot which has less than six degrees of freedom. Differently from serial chains in a full 6-DOF parallel robot, some of those in a low-DOF parallel robot may be subject to constraint forces as well as actuation forces. The reaction forces due to actuations and constraints in each serial chain can be determined by making use of the theory of reciprocal screws. It is shown that the stiffness of an F-DOF parallel robot can be modeled such that the moving platform is supported by 6 springs related to the reciprocal screws of actuations (F) and constraints (6-F). A general $6{\times}6$ stiffness matrix is derived, which is the sum of the stiffness matrices of actuations and constraints, The compliance of each spring can be precisely determined by modeling the compliance of joints and links in a serial chain as follows; a link is modeled as an Euler beam and the compliance matrix of rotational or prismatic joint is modeled as a $6{\times}6$ diagonal matrix, where one diagonal element about the rotation axis or along the sliding direction is infinite. By summing joint and link compliance matrices with respect to a reference frame and applying unit reciprocal screw to the resulting compliance matrix of a serial chain, the compliance of a spring is determined by the resulting infinitesimal displacement. In order to illustrate this methodology, the stiffness of a Tricept parallel robot has been analyzed. Finally, a numerical example of the optimal design to maximize stiffness in a specified box-shape workspace is presented.

This paper deals with self-tuning of fuzzy control systems. The fuzzy logic controller(FLC) has parameters that an: input and output scaling factors to effect control output. Tuning method is proposed for the scaling factor. In this paper. it is studied to control and to monitor the remote system statues using SOAP for communicate between the server part and the client part. The remote control system is controlled by using a web browser or a application program. The server part is waiting for the request of client part that uses internet network for communication each other and then the request is reached. the server part saves client data to the database and send a command set to the client part and then the client part sends command to controller in a cool chamber. The administrator can control and monitor the remote system just using a web browser. The effects of membership functions, defuzzification methods and scaling factors are investigated in the FLC system.

This paper deals with the method to estimate the friction in a system. We study a nonlinear friction model to estimate the friction in an inverted pendulum and approximate the friction model using fuzzy basis functions expansion. To demonstrate the friction observer using FBFs, we derive a update rule based on the error term that is formed by the output from a real system and observer output with a friction estimate. And two compensation algorithms to improve the response of an inverted pendulum are proposed. The first method that a observer parameter is updated in on-line and the friction is compensated at the same time. The second method is to compensate the friction with observer parameter estimated priori. The two methods is compared through the experimental results.

In this paper, we propose an approach to design multi-fuzzy controllers for the superheat and the low pressure that have an influence on energy efficiency and stabilization of air conditioning system with multi-evaporators. Air conditioning system with multi-evaporators is composed of compressor, condenser, several evaporators and several expansion valves. It is quite difficult to control the air conditioning system because the change of the refrigerant condition give an impact on the overall air conditioning system. In order to solve the drawback, we design multi-fuzzy controllers which control simultaneously both three expansion valve and one compressor for the superheat and the low pressure of air conditioning system. The proposed multi fuzzy controllers are given as a kinds of controller types such as a simplified fuzzy inference type. Here the scaling factors of each fuzzy controller are efficiently adjusted by Hierarchical Fair Competition-based Genetic Algorithms. The values of performance index of the simulation results of the A company type compare with simulation results of simplified inference type.

This paper deals with modeling method and application of Fuzzy Discrete Event System(FDES). FDES have characteristics which Crisp Discrete Event System(CDES) can't deals with and is constituted with the events that is determined by vague and uncertain judgement like biomedical or traffic control. We proposed Real-time Fuzzy Temporal Logic Framework(RFTLF) to model Fuzzy Discrete Event System. It combines Temporal Logic Framework with Fuzzy Theory. We represented the model of traffic signal systems for intersection to have the property of Fuzzy Discrete Event System with Real-time Fuzzy Temporal Logic Framework and designed a traffic signal controller for smooth traffic flow. Moreover, we proposed the method to find the minimum-time route to reach the desired destination with information obtained in each intersection. In order to evaluate the performance of Real-time Fuzzy Temporal Logic Framework model proposed in this paper, we simulated unit-time extension traffic signal controller model of the latest signal control method on the same condition.

Intelligent walking modeling of humanoid robot using learning based neuro-fuzzy system is presented in this paper. Walking pattern, trajectory of the zero moment point (ZMP) in a humanoid robot is used as an important criterion for the balance of the walking robots but its complex dynamics makes robot control difficult. In addition, it is difficult to generate stable and natural walking motion for a robot. To handle these difficulties and explain empirical laws of the humanoid robot, we are modeling practical humanoid robot using neuro-fuzzy system based on the two types of natural motions which are walking trajectories on a t1at floor and on an ascent. Learning based neuro-fuzzy system employed has good learning capability and computational performance. The results from neuro-fuzzy system are compared with previous approach.

This paper studies an automation problem of a heating, a ventilating, and an air conditioning (HVAC) for the development of smart space. The HVAC system is described by the fuzzy system for the stability analysis and the controller design. The linear matrix inequalities (LMIs) conditions are derived for the stabilization problem of the closed-loop system under the analog control. Also, it is required to digitally redesign the pre-designed the analog HVAC control system in order to accomplish the remote control via web. It is shown the this digital redesign problem can be converted to the convex optimization problem with the LMI constraints. An example is provided to show the effectiveness of the proposed method.

This paper presents an emotion recognition and its expression system of an intelligent robot like a home robot or a service robot. Emotion recognition method in the robot is used by a facial image. We use a motion and a position of many facial features. apply a tracking algorithm to recognize a moving user in the mobile robot and eliminate a skin color of a hand and a background without a facial region by using the facial region detecting algorithm in objecting user image. After normalizer operations are the image enlarge or reduction by distance of the detecting facial region and the image revolution transformation by an angel of a face, the mobile robot can object the facial image of a fixing size. And materialize a multi feature selection algorithm to enable robot to recognize an emotion of user. In this paper, used a multi layer perceptron of Artificial Neural Network(ANN) as a pattern recognition art, and a Back Propagation(BP) algorithm as a learning algorithm. Emotion of user that robot recognized is expressed as a graphic LCD. At this time, change two coordinates as the number of times of emotion expressed in ANN, and change a parameter of facial elements(eyes, eyebrows, mouth) as the change of two coordinates. By materializing the system, expressed the complex emotion of human as the avatar of LCD.

This paper studies on the relation between linearization methods and controller gains in the looper ILQ(lnverse Linear Quadratic optimal control) system for hot strip finishing mills. Firstly, two linear models arc respectively derived by a linearization method using Taylor's series expansion and a static state feedback linearization method, respectively, and the linear models are compared with the nonlinear model. Secondly, the looper servo controllers are respectively designed on the basis of two linearization models. Finally, the relation between the performances of two ILQ servo controllers and the linearization methods, and the structures and control gains of two controllers are evaluated by a computer simulation.

A class D digital audio amplifier with small size, low cost, and high quality is positively necessary in the multimedia era. Since the digital audio amplifier is based on the PWM signal processing, it is improper to analyze the principle of signal generation using linear system theories. In this paper, a class D digital audio amplifier based ADSM (Advanced Delta-Sigma Modulation) is considered. We first model the digital audio amplifier and then explain the operation principle using variable structure control algorithm. Moreover, the ripple signal generated by the hysteresis in the comparator has a significant effect on the system performance. Thus, we present a method to find the magnitude and the frequency of the ripple signal using describing function. Finally, simulations and experiments are provided to show the validity of the proposed methods.