Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Journal of Institute of Control, Robotics and Systems
Journal Basic Information
Journal DOI :
Institute of Control, Robotics and Systems
Editor in Chief :
Volume & Issues
Volume 10, Issue 12 - Dec 2004
Volume 10, Issue 11 - Nov 2004
Volume 10, Issue 10 - Oct 2004
Volume 10, Issue 9 - Sep 2004
Volume 10, Issue 8 - Aug 2004
Volume 10, Issue 7 - Jul 2004
Volume 10, Issue 6 - Jun 2004
Volume 10, Issue 5 - May 2004
Volume 10, Issue 4 - Apr 2004
Volume 10, Issue 3 - Mar 2004
Volume 10, Issue 2 - Feb 2004
Volume 10, Issue 1 - Jan 2004
Selecting the target year
Optimized Structured Treatment Interruption for HIV Therapy and Its Performance Analysis on Controllability
Ko Ji Hyun ; Kim Won Hee ; Chung Han Byul ; Chung Chung Choo ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1119~1126
DOI : 10.5302/J.ICROS.2004.10.12.1119
This paper presents optimized structured treatment interruption to reduce medication and establish long-term immune response against HIV-infection. Understanding HIV-related immune system control enables better HIV therapy without using fulltreatments. Discrete regimen and continuous regimen characteristics are compared. Controllability of HIV-related immune system is analyzed for better understanding of optimal control in HIV therapy. Using optimal control provides more effective therapy than the full treatment without interruption in terms of controllability analysis. Case studies indicates that the proposed therapy induces long-erm non-progression while preserving high CD4 T-helper cell count and low virus load in HIV-infected patients.
Ad hoc Network Multicasting Algorithm Based on An Ant System
Kim Joong Hang ; Chang Hyeong Soo ; Lee Se-young ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1127~1136
DOI : 10.5302/J.ICROS.2004.10.12.1127
This paper proposes a novel multicasting algorithm, called ANMAS (Ad hoc Network Multicasting with Ant System), for Mobile Ad hoc Network (MANET). The algorithm utilizes the indirect communication method of the ants via `pheromone` to effectively obtain dynamical topology change information, generating safer multicasting paths, and adapts the well-known CBT (Core Based Tree) multicasting algorithm into the ANMAS framework with proper modificiations to make `tolerable` multicasting group in the MANET environment. We show the efficiency and the effectiveness of ANMAS via simulation studies.
A Design of Adaptive Controller based on Immune System
Lee Kwon Soon ; Lee Young Jin ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1137~1147
DOI : 10.5302/J.ICROS.2004.10.12.1137
In this paper, we proposed two types of adaptive control mechanism which is named HIA(Humoral Immune Algorithm) PID and CMIA(Cell-Mediated Immune Algorithm) controller based on biological immune system under engineering point of view. The HIA PID which has real time control scheme is focused on the humoral immunity and the latter which has the self-tuning mechanism is focused on the T-cell regulated immune response. To verify the performance of the proposed controller, some experiments for the control of AGV which is used for the port automation to carry container without human are performed. The experimental results for the control of steering and speed of an AGV system illustrate the effectiveness of the proposed control scheme. Moreover, in that results, proposed controllers have better performance than other conventional PID controller and intelligent control method which is the NN(neural network) PID controller.
Gradual Reduction of Drug Dosage on an HIV Infection Model with Helper-independent CTL
Chang Hyeygjeon ; Jo Nam Hoon ; Shim Hyungbo ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1148~1154
DOI : 10.5302/J.ICROS.2004.10.12.1148
The goal of this paper is to verity that the gradual reduction of drug dose (GRDD), which has already been shown by authors to be effective for a simplified HIV infection model, still works for a more realistic model. While the simplified HIV infection model does not take into account an helper-independent CTL, the five state nonlinear model proposed by Wodarz describes the dynamics of both helper-dependent and helper-independent CTL in HIV infection. In this paper, it is shown that, by applying GRDD to Wodarz`s five state HIV infection model, the state of HIV infected patient converges to that of non-progressor whose immune response is excited so that his symptom would not be developed into AIDS. Roughly speaking, GRDD is `slow reduction of dose after the maximum dose for a certain period.` It turns out that an equilibrium representing non-progressor is locally asymptotically stable for the most values of drug dosage, which is required to hold in order to apply GRDD. Simulation results establish that GRDD is still considerably effective both for an AIDS patient and a patient who has been on HAART for a long time.
Dynamical Analysis of Cellular Signal Transduction Pathways with Nonlinear Systems Perspectives
Kim Hyun-Woo ; Cho Kwang-Hyun ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1155~1163
DOI : 10.5302/J.ICROS.2004.10.12.1155
Extracellular signal-regulated kinase (ERK) signaling pathway is one of the mitogen-activated protein kinase (MAPK) signal transduction pathways. This pathway is known as pivotal in many signaling networks that govern proliferation, differentiation and cell survival. The ERK signaling pathway comprises positive and negative feedback loops, depending on whether the terminal kinase stimulates or inhibits the activation of the initial level. In this paper, we attempt to model the ERK pathway by considering both of the positive and negative feedback mechanisms based on Michaelis-Menten kinetics. In addition, we propose a fraction ratio model based on the mass action law. We first develop a mathematical model of the ERK pathway with fraction ratios. Secondly, we analyze the dynamical properties of the fraction ratio model based on simulation studies. Furthermore, we propose a concept of an inhibitor, catalyst, and substrate (ICS) controller which regulates the inhibitor, catalyst, and substrate concentrations of the ERK signal transduction pathway. The ICS controller can be designed through dynamical analysis of the ERK signaling transduction pathway within limited concentration ranges.
A Multi-scale Simulation Model of Circulation Combining Cardiovascular Hemodynamics with Cardiac Cell Mechanism
Ko Hyung Jong ; Leem Chae Hun ; Shim Eun Bo ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1164~1171
DOI : 10.5302/J.ICROS.2004.10.12.1164
A new multi-scale simulation model is proposed to analyze heart mechanics. Electrophysiology of a cardiac cell is numerically approximated using the previous model of human ventricular myocyte. The ion transports across cell membrane initiated by action potential induce an excitation-contraction mechanism in the cell via cross bridge dynamics. Negroni and Lascano model (NL model) is employed to calculate the tension of cross bridge which is closely related to the ion dynamics in cytoplasm. To convert the tension on cell level into contraction force of cardiac muscle, we introduce a simple geometric model of ventricle with a thin-walled hemispheric shape. It is assumed that cardiac tissue is composed of a set of cardiac myocytes and its orientation on the hemispheric surface of ventricle remains constant everywhere in the domain. Application of Laplace law to the ventricle model enables us to determine the ventricular pressure that induces blood circulation in a body. A lumped parameter model with 7 compartments is utilized to describe the systemic circulation interacting with the cardiac cell mechanism via NL model and Laplace law. Numerical simulation shows that the ion transports in cell level eventually generate blood hemodynamics on system level via cross bridge dynamics and Laplace law. Computational results using the present multi-scale model are well compared with the existing ones. Especially it is shown that the typical characteristics of heart mechanics, such as pressure volume relation, stroke volume and ejection fraction, can be generated by the present multi-scale cardiovascular model, covering from cardiac cells to circulation system.
Cancer-Subtype Classification Based on Gene Expression Data
Cho Ji-Hoon ; Lee Dongkwon ; Lee Min-Young ; Lee In-Beum ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1172~1180
DOI : 10.5302/J.ICROS.2004.10.12.1172
Recently, the gene expression data, product of high-throughput technology, appeared in earnest and the studies related with it (so-called bioinformatics) occupied an important position in the field of biological and medical research. The microarray is a revolutionary technology which enables us to monitor several thousands of genes simultaneously and thus to gain an insight into the phenomena in the human body (e.g. the mechanism of cancer progression) at the molecular level. To obtain useful information from such gene expression measurements, it is essential to analyze the data with appropriate techniques. However the high-dimensionality of the data can bring about some problems such as curse of dimensionality and singularity problem of matrix computation, and hence makes it difficult to apply conventional data analysis methods. Therefore, the development of method which can effectively treat the data becomes a challenging issue in the field of computational biology. This research focuses on the gene selection and classification for cancer subtype discrimination based on gene expression (microarray) data.
Systemic Simulation Models for the Theoretical Analysis of Human Cardiovascular System
Ko Hyung Jong ; Youn Chan Hyun ; Shim Eun Bo ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1181~1188
DOI : 10.5302/J.ICROS.2004.10.12.1181
This paper reviews the main aspects of cardiovascular system dynamics with emphasis on modeling hemodynamic characteristics using a lumped parameter approach. Methodological and physiological aspects of the circulation dynamics are summarized with the help of existing mathematical models: The main characteristics of the hemodynamic elements, such as the heart and arterial and venous systems, are first described. Lumped models of micro-circulation and pulmonary circulation are introduced. We also discuss the feedback control of cardiovascular system. The control pathways that participate in feedback mechanisms (baroreceptors and cardiopulmonary receptors) are described to explain the interaction between hemodynamics and autonomic nerve control in the circulation. Based on a set-point model, the computational aspects of reflex control are explained. In final chapter we present the present research trend in this field and discuss the future studies of cardiovascular system modeling.
Construction of Gene Interaction Networks from Gene Expression Data Based on Evolutionary Computation
Jung Sung Hoon ; Cho Kwang-Hyun ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1189~1195
DOI : 10.5302/J.ICROS.2004.10.12.1189
This paper investigates construction of gene (interaction) networks from gene expression time-series data based on evolutionary computation. To illustrate the proposed approach in a comprehensive way, we first assume an artificial gene network and then compare it with the reconstructed network from the gene expression time-series data generated by the artificial network. Next, we employ real gene expression time-series data (Spellman`s yeast data) to construct a gene network by applying the proposed approach. From these experiments, we find that the proposed approach can be used as a useful tool for discovering the structure of a gene network as well as the corresponding relations among genes. The constructed gene network can further provide biologists with information to generate/test new hypotheses and ultimately to unravel the gene functions.
controller Design for Networked Contorl Systems with Time-Varying Delay
Lee Hong Hee ; Ro Young Shick ; Kang Hee Jun ; Suh Young Soo ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1196~1201
DOI : 10.5302/J.ICROS.2004.10.12.1196
H₂ controller is proposed for networked control systems with time-varying delay. The time-varying network delay is assumed to be unknown, but its lower and upper bounds are assumed to be known. The time-varying delay is treated like a parameter variation and robust control technique is used to deal with the time-varying delay. The proposed controller can be computed by solving linear matrix inequalities. Through numerical simulations, the proposed controller is verified.
Center Compensation Servo and Eccentric Compensation Control for High Speed CD-RW Drive System
Kim Dongwon ; Park Gwi-Tae ; Seo Sam-Jun ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1202~1209
DOI : 10.5302/J.ICROS.2004.10.12.1202
This paper presents a design methodology of a Digital Servo Signal Processor for high speed CD-RW drive systems. The proposed Digital Servo Signal Processor enables us to develop CD-related systems for the very high speed applications and is one of the key components of the CD-RW systems. The proposed center compensation servo control is newly built for an actuator shaking due to the fast response of a step motor when it jumps to a long distance. A control method compensating for eccentricity of a disc is implemented for operating robustly at a higher rotational speed. This servo mechanism is more size efficient and less power consumed because it is implemented using a ARM7 embedded processor and hardware digital filters. Furthermore, it is convenient to upgrade firmware for the future required functions. From experimental results, we can see that the performance of the control system is improved greatly. The proposed servo algorithm shows a shorter setting time including a pull-in time and a faster access time. It can be applied easily to the DVD-ROM and the DVD-RAM which have the same optical structure.
A Gait Implementation of a Biped Robot Based on Intelligent Algorithm
Kang Chan-Soo ; Kim Jin-Geol ; Noh Kyung-Kon ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1210~1216
DOI : 10.5302/J.ICROS.2004.10.12.1210
This paper deals with a human-like gait generation of a biped robot with a balancing weight of an inverted pendulum type by using genetic algorithm. The ZMP (Zero Moment Point) is the most important index in a biped robot`s dynamic walking stability. To perform a stable walking of a biped robot, a balancing motion is required according to legs` trajectories and a desired ZMP trajectory. A dynamic equation of the balancing motion is nonlinear due to an inverted pendulum type`s balancing weight. To solve the nonlinear equation by the FDM (Finite Difference Method), a linearized model of equation is proposed. And GA (Genetic Algorithm) is applied to optimize a human-like balancing motion of a biped robot. By genetic algorithm, the index of the balancing motion is efficiently optimized, and a dynamic walking stability is verified by the ZMP verification equation. These balancing motion are simulated and experimented with a real biped robot IWR-IV. This human-like gait generation will be applied to a humanoid robot, at future work.
Systemic Development of Tele-Robotic Interface for the Hot-Line Maintenance
Kim Min-Soeng ; Lee Ju-Jang ; Kim Chang-Hyun ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1217~1222
DOI : 10.5302/J.ICROS.2004.10.12.1217
This paper describes the development of tele-robotic interface for the hot-line maintenance robot system. One of main issues in designing human-robot interface for the hot-line maintenance robot system is to plan the control procedure for each part of the robotic system. Another issue is that the actual degree of freedom (DOF) in the hot-line maintenance robot system is much greater than that of available control devices such as joysticks and gloves in the remote-cabin. For this purpose, a virtual simulator, which includes the virtual hot-line maintenance robot system and the environment, is developed in the 3D environment using CAD data. It is assumed that the control operation is done in the remote cabin and the overall work process is observed using the main-camera with 2 DOFs. For the input device, two joysticks, one pedal, two data gloves, and a Head Mounted Display (HMD) with tracker sensor were used. The interface is developed for each control mode. Designed human-interface system is operated using high-level control commands which are intuitive and easy to understand without any special training.
Implementation of Real-Time Fuzzy Controller for SCARA Type Dual-Arm Robot
Kim Hong-Rae ; Han Sung-Hyun ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1223~1232
DOI : 10.5302/J.ICROS.2004.10.12.1223
We present a new technique to the design and real-time implementation of fuzzy control system basedon digital signal processors in order to improve the precision and robustness for system of industrial robot in this paper. The need to meet demanding control requirement in increasingly complex dynamical control systems under significant uncertainties, leads toward design of intelligent manipulation robots. The TMS320C80 is used in implementing real time fuzzy control to provide an enhanced motion control for robot manipulators. In this paper, a Self-Organizing Fuzzy Controller for the industrial robot manipulator with a actuator located at the base is studied. A fuzzy logic composed of linguistic conditional statements is employed by defining the relations of input-output variables of the controller. In the synthesis of a Fuzzy Logic Controller, one of the most difficult problems is the determination of linguistic control rules from the human operators. To overcome this difficult Self-Organizing Fuzzy Controller is proposed for a hierarchical control structure consisting of basic and high levels that modify control rules. The proposed Self-Organizing Fuzzy Controller scheme is simple in structure, fast in computation, and suitable for implementation of real-time control. Performance of the SOFC is illustrated by simulation and experimental results for a Dual-Arm robot with eight joints.
A Motion Planning Algorithm for Synchronizing Spatial Trajectories of Multi-Robots
Jeong Young-Do ; Kim Sung-Rak ; Lee Choong-Dong ; Lim Hyun-Kyu ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1233~1240
DOI : 10.5302/J.ICROS.2004.10.12.1233
Recently the need for cooperative control among robots is increasing in a variety of industrial robot applications. Such a control framework enhances the efficiency of the real robotic assembly environment along with extending the robot application. In this paper, an ethernet-based cooperative control framework was proposed. The cooperative control of robots can multiply the handling capacity of robot system, and make it possible to implement jigless cooperation, due to realization of trajectory-synchronized movement between a master robot and slave robots. Coordinate transformation was used to relate among robots in a common coordinate. An optimized ethernet protocol of HiNet was developed to maximize the speed of communication and to minimize the error of synchronous movement. The proposed algorithm and optimization of network protocol was tested in several class of robots.
A Design of Fuzzy-Neural Network Controller of Wheeled-Mobile Robot for Path-Tracking
Park Chongkug ; Kim Sangwon ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1241~1248
DOI : 10.5302/J.ICROS.2004.10.12.1241
A controller of wheeled mobile robot(WMR) based on Lyapunov theory is designed and a Fuzzy-Neural Network algorithm is applied to this system to adjust controller gain. In conventional controller of WMR that adopts fixed controller gain, controller can not pursuit trajectory perfectly when initial condition of system is changed. Moreover, acquisition of optimal value of controller gain due to variation of initial condition is not easy because it can be get through lots of try and error process. To solve such problem, a Fuzzy-Neural Network algorithm is proposed. The Fuzzy logic adjusts gains to act up to position error and position error rate. And, the Neural Network algorithm optimizes gains according to initial position and initial direction. Computer simulation shows that the proposed Fuzzy-Neural Network controller is effective.
A Performance Improvement for Tracking Controller of a Mobile Robot Using Neural Networks
Park Jae-Hwae ; Lee Man-Hyung ; Lee JangMyung ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1249~1255
DOI : 10.5302/J.ICROS.2004.10.12.1249
A new parameter adaptation scheme for RBF Neural Network (NN) has been developed in this paper. Even though the RBF Neural Network (NN) based controllers are robust against both un-modeled dynamics and external disturbances, the performance is not satisfactory for a fast and precise mobile robot. To improve the tracking performance as well as robustness, all the parameters of RBF NN are updated in real time. The stability of this control law is rigorously proved by following the Lyapunov stability theory and shown by the experimental simulations. The fact that all of the weighting factors, width and center of RBF NN have been updated implies that this scheme utilizes all the possibilities in RBF NN to make the controller robust and precise while the mobile robot is following un-known trajectories. The performance of this new algorithm has been compared to the conventional RBF NN controller where some of the parameters are adjusted for robustness.
Dynamic Output Feedback Passivation of Nonlinear Systems with Application to Flexible Joint Robots
Son Young-Ik ; Lim Seungchul ; Kim Kab-Il ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1256~1263
DOI : 10.5302/J.ICROS.2004.10.12.1256
Output feedback passivation problem is studied when the given system is not minimum-phase or does not have relative degree one. Using a parallel connection with an additional dynamics, the authors provide a dynamic output feedback control law which renders the composite system passive. Sufficient conditions are presented under which the composite system is output feedback passive. As an application of the dynamic passivation scheme, a point-to-point control law for a flexible joint robot is presented when only the position measurements are available. This provides an alternative way of replacing the role of the velocity measurements for the proportional-derivative (PD) feedback law. The performance of the proposed control law is illustrated in the simulation studies of a manipulator with three revolute elastic joints.
Development of Software Architecture for Modular Personal Robot
Kim Hong-Seok ; Yang Kwang-Woong ; Choi Moo-Sung ; Won Dae-Heui ; Lee Ho-Gil ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1264~1270
DOI : 10.5302/J.ICROS.2004.10.12.1264
In this paper, a standard robot design methodology is suggested and a software architecture for modular robot is introduced. The robot is modularized by several functions, and the module is produced according to a standard proposal. Each module requires standard interface for communicate in distributed environments. Software architecture was developed to support distributed component environment, and application development support tools are developed for user convenience. Many robot softwares are developed in a library form so that, they are being used widely robot application software development. Also a device driver was developed for the mostly used sensor and actuator. It is verified that the modular robot can be applied in various fields through guide, errand and guard scenario.
Biomimetic Actuator Based on Dielectric Polymer
Jung Kwangmok ; Ryew Sungmoo ; Koo Igmo ; Jeon Jaewook ; Koo Jachoon ; Nam Jaedo ; Lee Youngkwan ; Choi Hyoukryeol ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1271~1279
DOI : 10.5302/J.ICROS.2004.10.12.1271
A new bio-mimetic actuator is proposed. The actuator realizes bidirectional actuation since it is with a stretched film antagonistically configured with compliant electrodes. Also, it is distinguished from existing actuators with respect to the controllability of its compliance. Bidirectional actuation and compliance controllability are important characteristics for the artificial muscle actuator and the proposed one accomplishes these requirements without any mechanical substitute or complicated algorithms. In this paper its basic concepts and working principles are introduced with static and dynamic analysis. Control strategies for displacement as well as stiffness are introduced and experimental results are given to confirm the effectiveness of the proposed methods. In addition, an example of robotic actuating devices is given to confirm the usefulness of the proposed actuator.
Sequential Loop Closing Identification of Hammerstein Models for Multiple-Input Multiple-Output Processes
Park Ho Cheol ; Koo Doe Gyoon ; Lee Moon Yong ; Lee Jietae ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1280~1286
DOI : 10.5302/J.ICROS.2004.10.12.1280
A lot of industrial chemical processes contain certain input nonlinearities even though they are controlled by several linear controllers. Here we investigate a sequential loop closing identification method for MIMO Hammerstein nonlinear processes with diagonal nonlinearities. The proposed method separates the identification of the nonlinear static function from that of the linear subsystem by using a relay feedback test and a triangular type signal test. From 2 n activations for n n MIMO nonlinear processes, we sequentially identify the whole range of the nonlinear static function as well as the transfer function matrix of the linear subsystem.
Anti-Sway System for Container Transfer Crane for Automated Container Terminal: Part Ⅱ - Model Crane Implementation and Verification
Park ChanHun ; Kim DooHyung ; Shin YoungJae ; Park KyoungTaik ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1287~1294
DOI : 10.5302/J.ICROS.2004.10.12.1287
Automated container terminals have been being developed over the world for recent years and many countries are interested in it because the amount of containers exported or imported is rapidly increasing. The conventional container terminals were not designed to control this kind of heavily many containers. They would face many structural problems soon or later, although they have managed to do well so far. One of the most important things in developing automated container terminal is to develop the equipment able to handle many containers efficiently. Those are maybe automated transfer cranes, automatic guided vehicles, and automated quay-side cranes. The word `automated` means the equipment is operated without drivers and those equipments are able to work without any interruption in working schedule. Through the researches on the conventional transfer cranes, we decided that the structure of the conventional transfer cranes is not efficient in automated container terminal and it`s not possible to handle so many containers in limited time. Therefore we have been studying on the proper structure of the automated container crane for past several years and a new type of transfer crane has been developed. Design concept and control method of a new type of transfer crane had been presented in the previous paper: Part Ⅰ. Experimental features will be presented with a model transfer crane in this paper: Part Ⅱ.
A Study on the Bayesian Recurrent Neural Network for Time Series Prediction
Hong Chan-Young ; Park Jung-Hoon ; Yoon Tae-Sung ; Park Jin-Bae ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1295~1304
DOI : 10.5302/J.ICROS.2004.10.12.1295
In this paper, the Bayesian recurrent neural network is proposed to predict time series data. A neural network predictor requests proper learning strategy to adjust the network weights, and one needs to prepare for non-linear and non-stationary evolution of network weights. The Bayesian neural network in this paper estimates not the single set of weights but the probability distributions of weights. In other words, the weights vector is set as a state vector of state space method, and its probability distributions are estimated in accordance with the particle filtering process. This approach makes it possible to obtain more exact estimation of the weights. In the aspect of network architecture, it is known that the recurrent feedback structure is superior to the feedforward structure for the problem of time series prediction. Therefore, the recurrent neural network with Bayesian inference, what we call Bayesian recurrent neural network (BRNN), is expected to show higher performance than the normal neural network. To verify the proposed method, the time series data are numerically generated and various kinds of neural network predictor are applied on it in order to be compared. As a result, feedback structure and Bayesian learning are better than feedforward structure and backpropagation learning, respectively. Consequently, it is verified that the Bayesian reccurent neural network shows better a prediction result than the common Bayesian neural network.
Observer Design of an Injector for Fuel Control in DI Diesel Engines with an Electronically Controlled Injector
Kim Sunwoo ; Lee Kangyoon ; Chung Namhoon ; Sunwoo Myoungho ;
Journal of Institute of Control, Robotics and Systems, volume 10, issue 12, 2004, Pages 1305~1311
DOI : 10.5302/J.ICROS.2004.10.12.1305
This study presents a mathematical model and a sliding mode observer of the injection system for common rail diesel engines. The injector model consists of three subsystems: the actuator subsystem, the mechanical subsystem, and the hydraulic subsystem. In the actuator subsystem, the constitutive relations of piezoelectricity are used to model the actuator made up of piezoelectric material. Based on the proposed model, the observer estimates the injection rate and injection timing, and can play a vital role of sensorless control of fuel injection in the near future. The sliding mode theory is applied to the observer design in order to overcome model uncertainties. The injector model and observer are evaluated through the injector experiments. The simulation results of the injector model are in good agreement with the experimental data. The sliding mode observer can effectively estimate the injection timing and the injection rate of the injector.