检索结果-内蒙古大学图书馆

An Integrated Diagnostic System using Analytical Redundancy and Artificial Intelligence for Coal-Fired Power Plants

IFAC Proceedings Volumes 1992年第1期25卷 193-198页

作者： Z. Fathi J. Korbicz W.F. Ramirez G. Gilliland Department of Chemical Engineering University of Colorado Boulder CO 80309 USA Department of Applied Mathematics and Computer Science Higher College of Engineering ul. Podgórna 50 65-246 Zielona Góra Poland Public Service Company of Colorado 1667 Cole Boulevard 80401 Golden CO USA

The increasing complexity of process plants and their reliability has encouraged industry to look for new approaches for detecting and diagnosing process abnormalities. One such approach is the use of knowledge-based system techniques. On the contrary to many recent attempts using this technology where diagnostic analysis is based solely on measurable and observable data, in this work we consider the adaptive inclusion of a state and/or parameter estimation module in the diagnostic reasoning loop, in addition to employing information based on measurable data. The design methodology is a new layered knowledge base that houses compiled/qualitative knowledge in the high-levels and process-general estimation knowledge in the low-levels of a hierarchical knowledge structure. The compiled knowledge is used to narrow the diagnostic search space and provide an effective way of employing estimation modules. The purpose of this paper is to present the failure detection issues for the deaerator control subsystem of a coal fired power plant. The main emphasis is placed upon the model-based redundancy methods which create the low-levels of the hierarchical knowledge base. Due to the highly-nonlinear and mixed-mode nature of the power plant dynamics, the modified extended Kalman filter is used in designing the local detection filters.

关键词： Power system control failure detection estimation Kalman filters artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Knowledge-Based System with Embedded Estimation Components for Fault Detection and Isolation in Process Plants

引用

IFAC Proceedings Volumes 1992年第4期25卷 43-48页

作者： Z. Fathi W.F. Ramirez A.P. Tavares G. Gilliland J. Korbicz Department of Chemical Engineering University of Colorado Boulder CO 80309 USA Public Service Company of Colorado 1667 Cole Boulevard Golden CO 80401 USA Department of Applied Mathematics and Computer Science Higher College of Engineering ul. Podgórna 50 65-246 Zielona Góra Poland

Fault diagnosis in the area of process operations is critical for modern production and is receiving increasing theoretical and practical attention. In spite of many research and practical attempts, process fault diagnosis remains a rather complex task. In this work, we present a diagnostic methodology in which the symbolic reasoning of knowledge-based systems techniques is integrated with quantitative analysis of analytical redundancy methods. The system first performs a diagnosis by means of a compiled knowledge structure, and then attempts to build a detailed explanation by using proper fault models (adaptive filters). It also performs various statistical analyses to determine the process condition and check the validity of models. This unified approach increases the completeness and reliability of the diagnostic system.

关键词： failure detection estimation Kalman filters expert systems hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

SMALL SHIPS, ADVANCED TECHNOLOGY AND WARFIGHTING PERFORMANCE

引用

NAVAL ENGINEERS JOURNAL 1991年第3期103卷 30-45页

作者： SKOLNICK, DH SKOLNICK, A David H. Skolnickhas practiced naval engineering in both government and industry. He has supported the Military Sealift Command and the Naval Sea Systems Command Ship Design Group and Amphibious Ship Acquisition Program Office participating in the design and assessment of ship structure evaluation of intact and damaged stability and arrangements during design and construction phases of acquisition conversion and overhaul. He is currently involved in systems engineering and integration. Recent responsibilities have included requirements analyses and feasibility studies interface analyses and computer aided analyses. He received his B.S. in naval architecture and marine engineering from Webb Institute of Naval Architecture in 1982 (as an ASNE scholar) and is currently an M.S. candidate in systems engineering at the University of Virginia. Alfred Skolnickserved over 30 years as an engineering duty officer and retired from the Navy with the rank of captain in 1983. His early assignments included tactical missile engineering shipboard duty and Polaris submarine inertial navigation. He later served in the Deep Submergence Systems Project was project director surface effect ships (SES) David Taylor Model Basin director of technology Joint Navy-Commerce SES Program director combat systems Naval Sea Systems Command and project manager directed energy weapons. His awards include the Navy League's Parsons Award in 1979 for scientific and technical progress ASNE's Gold Medal in 1981 for high energy laser development the Navy Legion of Merit in 1983 National Capital Engineer of the Year in 1986 and the American Defense Preparedness Association Gold Medal in 1988 for contributions to strategic defense. He was president of ASNE from 1985–1989. He received his B.S. in mathematics from Queens College his M.A. in mathematics from Columbia University his M.S. in electrical engineering from U.S. Naval Postgraduate School and his Ph.D. in electrical engineering/applied mathematics from Polytechnic University. He w

Changing threat requirements and radical budget shifts imply that Navy operational needs will broaden and engineering solutions will face tougher constraints. Existing and emerging technology promise increased combat capability in smaller packages;space-based assets will allow operator orchestration of widely dispersed naval units via connectivity attributes previously unavailable. Tactical data relay by downlink may permit reallocation of responsibilities among several platforms, space, air, or seaborne, so ships can be outfitted for custom-use (sensing, unique data processing, high-firepower) and optimized to meet specific mission needs. These evolving capabilities demand a fresh look at ship concepts and prospective force structures consistent with global and fiscal realities. Warfighting performance formerly unknown in small ship design may offer a very effective solution to the intricate, interacting issues of falling defense budgets, diverse operational requirements and complex national priorities. Multimission ships which take advantage of new or current technology to reduce ship size, manning and cost could be affordable in sufficient numbers to meet our continuing worldwide obligations, complement our larger ships' force structure, and produce a balanced fleet. These same ships could satisfy U.S. maritime needs beyond the Navy and improve export trade through foreign military sales (FMS).

关键词： Naval Warfare

来源：评论

学校读者我要写书评

暂无评论

FUTURE NAVAL CONTINGENCY AND LIMITED WAR OPERATIONS

引用

NAVAL ENGINEERS JOURNAL 1991年第4期103卷 89-91页

作者： PACE, DK VLAHOS, M The Author The Author is a member of the Principal Professional Staff of The Johns Hopkins University Applied Physics Laboratory (APL). From 1987 to 1989 he was APL's resident liaison with the Naval War College where as an adjunct professor he developed an elective course on technology and naval warfare as well as serving as analytic lead for the Technology Initiative Games. He teaches in the graduate technical management curriculum of the Whiting School of Engineering at The Johns Hopkins University. As a specialist in operations research and systems analysis his professional responsibilities include leadership roles in the Military Operations Research Society the Summer Computer Simulation Conference the American Society of Engineering Management and membership on the ASNE JournalCommittee. His undergraduate studies were in mathematics and physics at the University of Chicago and his graduate studies in theology at several seminaries with a decade as a correctional chaplain.

The world has changed dramatically in the past few years. In large part, many of the changes have been driven by the emphasis now given to contingency and limited war operations. Navy leadership even coined a special term for them late in the 1980s: CALOW (Contingency and Limited Objective Warfare). As a result, naval planning has also changed, and with it so have the demands upon naval engineering. This paper addresses some of the factors that are now shaping naval planning. Characteristics of contingency and limited war operations are presented. Their implications for naval planning, for naval systems, for concepts of employment, and for naval force structure are examined. It is important that both Navy leadership and the naval engineering community understand these implications fully so that they may respond to them appropriately. The specific value of this paper lies in its synthesis of information so that the naval engineering community may appreciate the full impact of future contingency and limited war operations.

关键词： Naval Warfare

来源：评论

学校读者我要写书评

暂无评论

NAVAL engineering ANALYSIS

引用

NAVAL ENGINEERS JOURNAL 1988年第3期100卷 306-316页

作者： PACE, DK HUNT, RJ Dale K. Pace:is a member of the Principal Professional Staff of The Johns Hopkins University Applied Physics Laboratory (APL). He currently serves as the APL liaison with the Hopkins School of Advanced International Studies and with the Naval War College. His professional responsibilities have included various leadership roles in the Military Operations Research Society chairmanship of the Physical and Engineering Sciences Group for the Summer Computer Simulation Conference and chairmanship of the ASNEJournalCommittee. Richard J. Hunt:is head of the Naval Warfare Analysis Department of The Johns Hopkins University Applied Physics Laboratory (APL). A graduate of the Loyola College in Baltimore (B.S. in mathematics) in the 1950s Mr. Hunt was involved with development and use of the first digital computer simulation of Navy AAW. Since then he has played major roles in all aspects of analyses of surface ship AAW and of many other naval warfare topics. Currently he is a member of the FOSAD the Federation of Systems Analysis Directors for Navy R&D Centers and APL.

Analysis pervades all aspects of naval engineering. It is used to determine requirements for new or upgraded systems and to explore concepts for their employment. It is used to evaluate performance. It is used to establish design characteristics. And it comes in many varieties. This paper addresses use and misuse of analysis in naval engineering. The paper is oriented toward managers of analytic endeavors rather than the practitioners of analysis. It does not deal in depth with how to perform particular analytic techniques. Instead it discusses general principles that should guide both the selection and application of analytic techniques. The paper identifies problems which are frequently encountered in analyses related to naval engineering and suggests ways to ameliorate their deleterious effects. These problems are addressed from both the perspective of the manager of analysis and that of the user or consumer of results from the analysis. Some of the challenges that face naval engineering analyses as a consequence of hardware and software improvements and of more sophisticated systems are also discussed.

关键词： NAVAL ARCHITECTURE

来源：评论

学校读者我要写书评

暂无评论

THE VIRTUAL PROTOCOL MACHINE

引用

AT&T BELL LABORATORIES TECHNICAL JOURNAL 1984年第8期63卷 1859-1876页

作者： FITTON, MJ HARKNESS, CJ KELLEMAN, KA LONG, PF MEE, C AT&T Bell Laboratories. Michael J. Fitton: B.S. (Computer Science) 1981 Rutgers University M.S. (Computer Science) 1983 Stevens Institute of Technology AT&T Bell Laboratories 1977—. Carol J. Harkness: B.A. (Mathematics) 1969 University of Wisconsin M.S. (Computer Science) 1970 Purdue University AT&T Bell Laboratories 1969—. Keith A. Kelleman: B.S. (Electrical Engineering) 1979 Lafayette College M.S. (Computer Science) 1981 Stevens Institute of Technology AT&T Bell Laboratories 1979—. Paul F. Long: B.S. (Engineering Mathematics) 1960 M.S. (Applied Mathematics) 1963 North Carolina State University Bellcomm Inc. 1965–1972 AT&T Bell Laboratories 1972—. Carl Mee III: B.S. (Mathematics) 1957 The University of the South M.A. (Mathematics) 1964 The University of Virginia U.S. Air Force 1958–1962 Bellcomm Inc. 1964–1966 1968–1972 Informatics Inc. 1966–1968

The UNIX ™ operating system Virtual Protocol Machine (VPM) is a package of software tools that allows a wide variety of link-level data communications protocols to be implemented efficiently in a high-level language. The resulting protocol implementations are independent of the particular communications hardware, the host machine architecture, and the host operating system, and therefore can be ported easily from one hardware/software environment to another. An extension to VPM, the Common Synchronous Interface (CSI), provides similar benefits for the higher-level protocol software that runs in the UNIX system host. The implementations of VPM use Programmable Communications Devices (PCDs) to off load the link-level communications processing from the host CPU. A high-level language protocol description is translated by a protocol compiler that runs on the host machine. The resulting module is then loaded into the PCD and executed. The other components of VPM are a transparent protocol driver that allows user processes to interact directly with a link-level protocol implementation, a realtime trace capability to facilitate debugging, and several utility programs. VPM has been implemented on several different PCDs and several types of host computers. VPM-based protocol implementations can be ported with little or no change from one VPM implementation to another. VPM and CSI greatly reduce host system overhead while producing maximum communications throughput. A number of different higher-level protocols and their link-level counterparts have been implemented in the UNIX system using CSI and VPM; among them are X.25, 3270 emulation, a synchronous terminal interface, and a facility for remote job entry to IBM hosts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

APPLICATION OF FORRESTER MODEL TO HARRIS-COUNTY, TEXAS

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS 1972年第2期SMC2卷 180-&页

作者： PORTER, HR HENLEY, EJ Urban Systems Laboratory University of Houston Houston TX USA Department of Applied Mathematics and Computer Science University of Louisville Louisville KY USA College of Engineering University of Houston Houston TX USA

The generalized Urban Dynamics model of Forrester was applied to Harris County, Tex. The 40 variables changed were those considered to be "region dependent." The model was initialized with data froni the year 1950. Statistical data for 1960 and 1970 were used to check the validity of the model. The statistical data used were obtained from the 1950, 1960, and 1970 censuses and from various county and city agencies. The results revealed that the model could be used as a planning tool for a specific region, as the final model appeared closely tuned to the county's major statistical variables. The lack of variables in the model which could be directly correlated with statistical data was thought to be the reason for deviations in the subvariables. Sensitivity of the model to a large number of variables was determined.

关键词： Cities and towns Business Delay Urban areas Testing Demography Laboratories mathematics computer science

来源：评论

学校读者我要写书评

暂无评论

Information System Design: Communication Networks and IoT 1

引用

丛书名： Lecture Notes in Networks and Systems

1000年

作者： Vikrant Bhateja Jinshan Tang Dilip Kumar Sharma Zdzislaw Polkowski Afaq Ahmad

来源：评论

学校读者我要写书评

暂无评论

Simulation-based Algorithms for Markov Decision Processes 1

引用

丛书名： Communications and Control engineering

1000年

作者： Hyeong Soo Chang Jiaqiao Hu Michael C. Fu Steven I. Marcus

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Sparse Nonlinear Modeling and Control

引用

Control, Robotics, and Autonomous Systems 1000年第1期8卷 127-152页

作者： Steven L. Brunton Nicholas Zolman J. Nathan Kutz Urban Fasel 3Department of Applied Mathematics University of Washington Seattle Washington USA 2AI Institute in Dynamic Systems University of Washington Seattle Washington USA 1Department of Mechanical Engineering University of Washington Seattle Washington USA email: sbrunton@uw.edu 4Department of Electrical and Computer Engineering University of Washington Seattle Washington USA 5Department of Aeronautics Imperial College London London United Kingdom

Machine learning is rapidly advancing nearly every field of science and engineering, and control theory is no exception. In particular, it has shown incredible promise for handling several of the main challenges facing modern dynamics and control, including complexity, unmodeled dynamics, strong nonlinearity, and hidden variables. However, machine learning models are often expensive to train and deploy, fail to generalize beyond the training data, and suffer from a lack of explainability, interpretability, and guarantees, all of which limit their use in real-world and safety-critical control applications. Sparse nonlinear modeling and control techniques are a powerful class of machine learning that promote parsimony through sparse optimization, providing data-efficient models that are more interpretable and generalizable and have proven effective for control. In this review, we explore the use of sparse optimization in the context of machine learning to develop compact models and controllers that are easy to train, require significantly less data, and make low-latency predictions. In particular, we focus on applications in model predictive control and reinforcement learning, two of the foundational algorithms in control theory.

关键词： machine learning sparse regression system identification model reduction observability uncertainty quantification reinforcement learning model predictive control nonlinear dynamics

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：