检索结果-内蒙古大学图书馆

Sensor diagnosis system combining Immune Network and Learning Vector Quantization

ELECTRICAL engineering IN JAPAN 1996年第5期117卷 44-56页

作者： Kayama, M Sugita, Y Morooka, Y Hitachi Ltd. Received his Master's degree in 1984 from Osaka University. He joined the Hitachi Research Laboratory of Hitachi Ltd. in 1984. He was a Visiting Researcher at the University of California Los Angeles from 1990 to 1991. He is engaged in research on control of FA systems and control application of neural networks. He received a Paper Award from the I.E.E. Japan in 1995. Received his Master's degree in 1992 from Okayama University. He joined the Hitachi Research Laboratory of Hitachi Ltd. in 1992. He is engaged in research on system control of steel plants and control application of neural networks. Graduated in 1965 from the Department of Control Engineering Kyushu Institute of Technology. He received his Ph.D. later. He joined the Hitachi Research Laboratory of Hitachi Ltd. in 1965. He is currently a Supervising Researcher at the Laboratory. He is engaged in research on computer control systems. He is engaged mainly in development of multivariable control knowledge control and system engineering of steel plants. He received a Paper Award from the I.E.E. Japan in 1995. He is a member of the Society of Instrument and Control Engineers and the Information Processing Society of Japan.

A distributed diagnosis system combining Immune Network (IN) and Learning Vector Quantization (LVQ) for detecting fault sensors accurately in industrial plants is proposed. It has two execution modes, namely, its training mode where LVQ extracts correlation between each two sensors from their outputs when they work properly, and its diagnosis mode, where LVQ contributes to testing each two sensors using the extracted correlation, while IN contributes to determining fault sensors by integrating these local testing results obtained from LVQ. Discussed here is how to improve diagnosis capability of the developed system. It is shown that the thresholds can be determined effectively by the constraint that the hyperregion corresponding to the normal sensor outputs in each quantization vector space is a single region. Diagnosis capability of the developed system is evaluated using a prototype system for detecting fault sensors of a reheating furnace plant. With the proposed method, abnormal sensors, such as aged deteriorated ones, which have been difficult to be detected only by checking each output of sensor independently, are possible to be specified.

关键词： immune network vector quantization fault diagnosis sensor learning

来源：评论

学校读者我要写书评

暂无评论

Development of transient stability controller system (TSC) based on on-line stability calculation

引用

ELECTRICAL engineering IN JAPAN 1996年第4期117卷 61-79页

作者： Ota, H Inoue, T Ito, H Fukushima, N Omata, K Morita, K Kokai, Y Chubu Electric Power Co. Graduated in 1955 from the Department of Electrical Engineering of the Faculty of Engineering University of Tokyo and joined Chubu Electric Power Co. in the same year. He is engaged mainly in developing technology for construction planning as well as protection stabilization and automatic control of power systems. He is currently a Director and Vice President of the company. He received an OHM Technology Award in 1971 and an Achievement Award from the I.E.E. Japan in 1992. Graduated in 1962 from the Department of Electrical Engineering Shibaura Institute of Technology and joined Chubu Electric Power Co. in the same year. He is engaged in the development of technology for large-scale centralized control of power systems as well as the networking of control computers. He is currently a System Analysis Group Chief in the System Operation Division of the company. Graduated in 1985 from the Department of Electronics and Electrical Engineering of the Faculty of Engineering Tokyo Institute of Technology and joined Chubu Electric Power Co. in the same year. He is engaged mainly in the development of technology for power system protection and stabilization. He is currently working in the System Analysis Group of the System Operation Division of the company. Toshiba Corporation Graduated in 1967 from the Department of Electrical Engineering University of Tokyo and joined Toshiba Corporation in the same year and engaged in development of power system control systems in Japan and abroad. He is currently a Chief of System Technology in the Power System Technology Division of the company. He is a member of the Theses Subcommittee of the 1995 World Energy Conference. He is an Assistant Secretary of the Japanese Committee of CIGRE and a member of the Japanese Subcommittee of CIGRE SC35 and 39. He is a member of IEEE. Completed his Master's course at the Science and Engineering Research Division of the Graduate School Waseda University in 1980 and joined Toshiba Corporation in the same year. H

A new transient stability controller system (TSC) based on on-line transient stability calculation has been developed. The TSC system prevents the power system from wide-area blackout by shedding generators optimally when a serious fault occurs. This system consists of a central processing unit (TSC-P), and four local units for fault detection (TSC-C), and seventeen units for generator shedding(TSC-T). The TSC-P selects optimal generators to be shed for stabilization based on on-line transient stability calculation for contingencies at 500 kV lines and buses every five minutes. The results are transmitted to the TSC-Cs periodically. Should any fault occur, only one TSC-C will detect the fault occurrence and send control signals to the TSC-Ts which actually generate shedding signals. To realize the TSC system, essential are fast stability evaluation methods for a large number of contingencies and effective selection methods of optimal generators to be shed for stabilization. This paper presents total algorithms applied in the TSC-P, the results of algorithm verification tests using a prototype system combined with a large-scale analog simulator, and the characteristics of the actual system.

关键词： power system stabilization generation shedding on-line stability calculation screening parallel calculation

来源：评论

学校读者我要写书评

暂无评论

Coordinated fuzzy logic control between SVC and PSS to enhance stability of power systems

引用

ELECTRICAL engineering IN JAPAN 1996年第1期116卷 43-54页

作者： Kihara, H Hiyama, T Miyauchi, H Ortmeyer, TH Kumamoto University B.E. and M.S. degrees in Electrical Engineering from Kumamoto University in 1986 and 1988 respectively and is currently in the doctoral program at the university. In 1988 he joined Kyushu Electric Power Co. and is working in the Research Division. B.E. M.S. and Ph.D. degrees in Electrical Engineering from Kyoto University Japan in 1969 1971 and 1980 respectively. He joined Kumamoto University in 1971 and he has been a Professor of Electrical Engineering and Computer Science since 1989. During the period of June 1985 through September 1986 he was at Clarkson University and was involved with power system harmonics research. His current interests include intelligent control of electric power systems using fuzzy logic control scheme and neural network measurement and real time control of photovoltaic systems and harmonic analysis in distribution systems. He is a senior member of IEEE SICE of Japan and Japan Solar Energy Society. B.E. M.S. and Ph.D. degrees in Electrical Engineering from Kyoto University in 1981 1983 and 1991 respectively. He joined Kyoto University in 1985. Since 1993 he has been at Kumamoto University and currently is an Associate Professor of Electrical Engineering and Computer Science. His current interests include stabilizing control of electric power system and applications of the Superconducting Magnetic Energy Storage (SMES) to electric power systems. He is a member of IEEE and Institute of Systems Control and Information Engineers of Japan. B.S.E.E. degree in 1972 his M.S.E.E. degree in 1977 and Ph.D. degree in 1980 all from Iowa State University. From 1972 to 1976 he worked in the Operational Analysis Department Commonwealth Edison Company Chicago Illinois. Since 1979 he has been at Clarkson University Potsdam N.Y. where he is a Professor of Electrical Engineering. During the period of July 1993 to June 1994 he was also a Visiting Professor at Kumamoto University Kumamoto Japan. His current interests include harmonic performance po

This paper presents a new switching control scheme for static var compensator (SVC) using fuzzy logic control rules to enhance the overall stability of electric power systems. In addition, the coordination with power system stabilizers (PSS) is also considered to achieve a wider stable region. An SVC is set on one of the busbars in the transmission system, where the real power flow signal is utilized at the location of the SVC to determine the firing angle of the thyristor switch. The switching control scheme is simple so as not to require heavy computation on the microcomputer based switching controller. The PSSs are also set on the generators in the study system. Simulation results show the effectiveness of the proposed fuzzy logic switching control scheme for the SVC. The coordination between SVC and PSS is also effective to enlarge the stable region.

关键词： fuzzy logic control scheme real time control SVC PSS FACTS

来源：评论

学校读者我要写书评

暂无评论

Reliability evaluation of highly reliable computer control systems for energy generation, transmission and distribution

引用

EUROPEAN TRANSACTIONS ON ELECTRICAL POWER 1996年第2期6卷 111-118页

作者： Kochs, HD Dieterle, W Dittmar, E Prof. Dr.-Ing. Hans-Dieter Kochs (1943) VDE is head of the Department of Computer Science and Information Processing Systems at the Gerhard Mercator-University of Duisburgl Germany. He received the Dip1.-Ing. degree in Electrical Engineering and the Dr.-Ing. degree from the RWTH Aached Germany in 1972 and 1976 respectively. From 1979 to 1991 he was system engineer and division leader in the areas of R & D of highly-reliable large-scale control and information systems (AEGIDaimler FAG-Kugelfischer). Since 199 1 he has been Professor at the University of Duisburg. His current R & D areas are reliability safety and fault tolerance of technical systems especially automation systems and hybridknowledge based systems including fuzzy-logic and neural networks. (Gerhard-Menxitor-University-GH Duisburg FB 71FG 10 Lotharstr. 1 D-47048 Duisburg T +49203/379-2204 Fax +49203I379-2205) Dipl.-Ing. Werner Dieterle (1966). VDE received his degree in Electrical Engineering (Dip1.-Ing.) from the Technical University of Karlsruhd Germany in 1991. After having finished his studies he joined the scientific staff of the department of Computer Science and Information Processing Systems at the Gerhard-Mercator-University of Duisburgg Germany. His research interests include design of highly-reliable distributed computer control systems with particular focus on system communication. (Gerhard-Mercator-University -GH Duisburg FB 7/FG 10 Lothantr. 1 D-47048 Duisburg T +49203/3793483 Fax +49203/379-2205) Ing. (grad.) Ewald Dittmar (1943) received his degree in Electrical Engineering from the school of engineering in Mannheim/Germany. Since then he worked for different industrial companies and utilities. Since 1988 he has been with ABB/Germany where he cumntly is head of the strategy department of ABB Network Control and Rotection. He investigates new development strategies for modern control systems hardware and software architecture in the area of energy transmission and distribution. (ABB Netzleittechnik GmbH. Wallstadter S

The paper presents the results of an application-based reliability study of distributed computer control systems with very high reliability demand, e.g. for supervision and control of power plants and energy distribution systems. A reliability classification scheme is presented and typical redundant control system structures are evaluated and classified due to their system reliability Special focus is placed on assessing the influence of the communication system on total system reliability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Roles of neural and evolutionary computing in intelligent software systems

British Telecom technology journal

引用

British Telecom technology journal 1996年第4期14卷 46-54页

作者： Tsui, K.C. Azvine, B. Plumbley, M. Hong Kong Polytechnic University of Essex Kings College University of London BT Laboratories Manchester University Dynamics and Control Research Group Engineering Department Manchester University Contr. and Instrum. Research Group Staffordshire University Intelligent Systems Research Group Churchill College Cambridge United Kingdom Thorn-EMI Ctrl. Res. Laboratories Cambridge Univ. Eng. Department Centre for Neural Networks King's College London Department of Computer Science Electron. and Electrical Engineering King's College London United Kingdom European Neural Network Society

This paper describes two computing paradigms known as neural computing and evolutionary computing, and their potential contribution to building intelligent software systems. The paper begins by giving a brief introduction to the origins of each paradigm. Then two sections introduce the basic principles, and identify the role of each paradigm in intelligent system design. Each section ends with a number of applications that have been or are being investigated. These include connection admission control, modem communication, adaptive model-based control, face and handwriting recognition, frequency assignment, help-desk scheduling, financial time-series prediction, face recognition and evolving agent behavior. A section introduces the idea of using communications theory to design neural networks and the paper concludes with the authors' views on the future of neural and evolutionary computing for intelligent software systems.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Measuring the distance and orientation of a planar surface using nonstructured lighting

引用

systems AND computerS IN JAPAN 1996年第8期27卷 83-92页

作者： Tsukiyama, T Member Electrotechnical Laboratory Tsukuba Japan 305 Tosbifumi Tsukiyama:graduated in 1972 from the Biological Engineering Department Osaka University where he also received his Dr. of Eng. degree. He joined Electrotechnical Laboratory Ministry of Tread and Industry (Japan) in 1972. At present he is Senior Researcher at Computer Vision Section Intelligent Systems Division ETL. He was a Visiting Researcher at University of Illinois during 1984–1985. He has been interested in vision system for mobile robots and image processing architectures. He is a member of the Society of Instrumental and Control Engineers Japan Robotics Society of Japan and Information Processing Society of Japan.

This paper proposes a method of 3-dimensional measurement of a planar surface by using two fixed light sources and a TV camera. A set of two images is recorded by the camera switching on each light alternately. The peak of the luminance distribution in each image is detected, and the orientation and distance of the planar surface are calculated. The position of the peak of a luminance distribution can be estimated accurately by using an image processing. The light sources can be conventional apparatus with no particular structure. The method is simple and suitable for a vision system on an indoor mobile robot.

关键词： distance to surface orientation of planar surface point light source luminance distribution ring light

来源：评论

学校读者我要写书评

暂无评论

Application of running quantities for control of an adaptive hybrid compensator

引用

EUROPEAN TRANSACTIONS ON ELECTRICAL POWER 1996年第5期6卷 337-344页

作者： Czarnecki, LS Chen, G Staroszczyk, Z Guangda Chen (1953) received the B.S. and M.S. degrees from the Wuhan University of Hydraulic and Electrical Engineering China in 1977 and 1988 respectively. Since 1993 he worked for three years at the Department of Electrical and Computer Engineering Louisiana State University Baton Rouge USA as a Visiting Research Associate. Presently he is with Wuhan University of Hydraulic and Electrical Engineering China. His research interests include control systems powerquality improvement and power electronics. (University of Hydraulic and Electrical Engineering Wuhan. Hubei 430072 P.R. China T+8627/78822 12 ext. 3634) Dr. Zbigniew Staroszczyk (1952) received the M.Sc. and Ph.D. degrees in Telecommunications and Electrical Engineering from Warsaw University of Technology Poland in 1974 and 1984. respectively. He is an Assistant Professor at the Electrical Engineering Department of Warsaw University offechnology. His current research interests include digital signal processing oriented to high accuracy spectral analysis and digital filtering. He develops intelligent measuring instrumentation in that field. (Warsaw University of Technology Institute of the Theory of Electrical Engineering and Electrical Measurements Koszykowa 75 PL-00-66 I Warsaw/Poland T+482/6210070-7484 Fax+48 221292962)

A control algorithm for a hybrid compensator based on a concept of running complex RMS values of the fundamental harmonic of voltages and currents is presented in the paper. The hybrid compensator is composed of an adaptive passive balancing compensator controlled in the frequency-domain, and a current source, controlled in the time-domain. The algorithm used for the compensator control is rooted in a new approach to the power theory of electrical systems with quasi-periodic waveforms. it is based on the concept of running quantities and a forward extrapolation of the power properties of a time-variant load. Experimental results obtained using such an algorithm for controlling a laboratory prototype of the hybrid compensator are presented in the paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Linear-programming-based method for optimum schedule of reactive power sources in power systems

引用

EUROPEAN TRANSACTIONS ON ELECTRICAL POWER 1996年第1期6卷 31-37页

作者： AbdelSalam, MM ElSadek, MZ Hussein, AI Hussein, AA Mazen Abdel-Salam (1946) received the B.Sc. degree in 1967 The M.SC. degree in 1970 and the Ph.D. degree in 1973 all in Electrical Engineering from the University of Cairo Egypt. In 1967 he was with the Academy of Science and Technology Cairo as a Research Assistant. In 1973 he joined the faculty of Electrical Engineering at Assiut University Egypt as an Assistant Professor and in October 1977 he became an Associate Professor. During the academic years of 1977 to 1979 he was an Alexander-von-Humboldt Fellow in the Electrical Engineering Department TU Munic/Germany and the Electrical Engineering Department University of Liverpoo YGB. In September 1979 he began work as a Researcher with General Electric Co. Pittsfield MANSA. In January 1982 he rejoined Assiut University as a Professor of Electrical Power Engineering. During the academic years of 1982 to 1984 he was Professor in the Department of Electrical Engineering University of Jordad Amman. During the academic years of 1982 to 1984 he was a visiting Full Professor in the Department of Electrical Engineering Michigan Technological University Houghton NSA. From 1990 to 1994 he was a Professor of Electrical Power Engineering in the Department of Electrical Engineering at King Fahd University of Petroleum & Minerals Dhahran/Saudi Arabia. He had obtained Research Fellowships at the Military Technical University of Hamburg Eemany in 1984 at the University of Leedd GB in 1988 at Kaiserslautern University/Germany in 1989 and at Michigan Technological University in 1990. He is currently a Professor of Electrical Power Engineering Assiut University. His research activities include corona studies digital calculation of electric fields investigations of high-voltage phenomena low-voltage distribution networks and control of electrical machines. He is a fellow of the Institution of Electrical Engineers Londod GB and of the Institute of Electrical and Electronic Engineers New York AJSA. (Assiut University Electrical Engineering Departmen

This paper proposes a linear-programming optimization-based method for reactive power scheduling using generator terminal voltages and reactive outputs, transformer tap-settings and switchable reactive power sources as control variables. Dual linear programming is applied to minimize a composite objective function consisting of the cost of the adjusted control variables and the system transmission losses. The proposed composite objective function is more economical than that of the minimum total adjustment of the control variables and calls for less adjustments of var sources to meet the desired voltage limits. The proposed method is applicable to practical transmission and distribution networks, 500 kV to 11 kV of small and large sizes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visibility analysis on a massively data-parallel computer

引用

Concurrency and Computation: Practice and Experience 1996年第6期8卷

作者： Daniel Germain Denis Laurendeau Guy Vézina Computer Vision and Systems Laboratory Electrical Engineering Department Université Laval Ste-Foy Québec Canada G1K 7P4 Command and Control and Information Sytems Division Defence Research Establishment Valcartier PO Box 8800 Courcelette Québec Canada G0A 1R0

Visibility analysis algorithms use digital elevation models (DEMs), which represent terrain topography, to determine visibility at each point on the terrain from a given location in space. This analysis can be computationally very demanding, particularly when manipulating high resolution DEMs accurately at interactive response rates. Massively data-parallel computers offer high computing capabilities and are very well-suited to handling and processing large regular spatial data structures. In the paper, the authors present a new scanline-based data-parallel algorithm for visibility analysis. Results from an implementation onto a MasPar massively data-parallel SIMD computer are also presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LEARNING OF MODULAR STRUCTURED NETWORKS

引用

ARTIFICIAL INTELLIGENCE 1995年第1期75卷 51-62页

作者： ISHIKAWA, M Department of Control Engineering and Science Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Fukuoka 820 Japan

Learning of large-scale neural networks suffers from computational cost and the local minima problem. One solution to these difficulties is the use of modular structured networks. Proposed here is the learning of modular networks using structural learning with forgetting. It enables the formation of modules. It also enables automatic utilization of appropriate modules from among the previously learned ones. This not only achieves efficient learning, but also makes the resulting network understandable due to its modular character. In the learning of a Boolean function, the present module acquires information from its subtask module without any supervision. In the parity problem, a previously learned lower-order parity problem is automatically used. The geometrical transformation of figures can be realized by a sequence of elementary transformations. This sequence can also be discovered by the learning of multi-layer modular networks. These examples well demonstrate the effectiveness of modular structured networks constructed by structural learning with forgetting.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：