检索结果-内蒙古大学图书馆

IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks (CoEN)

作者： G.G. Yen Haiming Lu Intelligent Systems and Control Laboratory School of Electrical and Computer Engineering Oklahoma State University Stillwater OK USA

In this paper, we propose a novel genetic algorithm based design procedure for multi-layer feedforward neural network. Hierarchical genetic algorithm is used to evolve both neural network topology and parameters. Compared with traditional genetic algorithm based designs for neural network, the proposed hierarchical approach addressed several deficiencies highlighted in literature. A multi-objective function is used herein to optimize the performance and topology of the evolved neural network. Two benchmark problems are successfully verified and the proposed algorithm proves to be competitive or even superior to the traditional back-propagation network in Mackey-Glass chaotic time series prediction.

关键词： Neural networks Biological neural networks Algorithm design and analysis Genetic algorithms Neurons Feedforward neural networks Network topology Multi-layer neural network Training data Force measurement

来源：评论

学校读者我要写书评

暂无评论

Winner take all experts network for sensor validation

Winner take all experts network for sensor validation

引用

IEEE Conference on control Technology and Applications (CCTA)

作者： G.G. Yen Wei Feng Intelligent Systems and Control Laboratory School of Electrical and Computer Engineering Oklahoma State University Stillwater OK USA

The validation of sensor measurements has become an integral part of the operation and control of modern industrial equipment. The sensor under a harsh environment must be shown to consistently provide the correct measurements. Analysis of the validation hardware or software should trigger an alarm when the sensor signals deviate appreciably from the correct values. Neural network based models can be used to estimate critical sensor values when neighboring sensor measurements are used as inputs. The discrepancy between the measured and predicted sensor values may then be used as an indicator for sensor health. The proposed winner take all experts (WTAE) network is based on a 'divide and conquer' strategy. It employs a growing fuzzy clustering algorithm to divide a complicated problem into a series of simpler sub-problems and assigns an expert to each of them locally. After the sensor approximation, the outputs from the estimator and the real sensor value are compared both in the time domain and the frequency domain. Three fault indicators are used to provide analytical redundancy to detect the sensor failure. In the decision stage, the intersection of three fuzzy sets accomplishes a decision level fusion, which indicates the confidence level of the sensor health. Two data sets, the Spectra Quest Machinery Fault Simulator data set and the Westland vibration data set, were used in simulations to demonstrate the performance of the proposed WTAE network. The simulation results show the proposed WTAE is competitive with or even superior to the existing approaches.

关键词： Industrial control Signal analysis Hardware Neural networks Clustering algorithms Frequency estimation Frequency domain analysis Failure analysis Redundancy Fault detection

来源：评论

学校读者我要写书评

暂无评论

Intelligent fault tolerant control using artificial neural networks

Intelligent fault tolerant control using artificial neural n...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： G.G. Yen Liang-Wei Ho Intelligent Systems and Control Laboratory School of Electrical and Computer Engineering Oklahoma State University Stillwater OK USA

As dynamic systems become more complex, experience more rapidly changing environments, and encounter a greater variety of unexpected component failures, solving the control problems of such systems is a grand challenge for control engineers. We investigate the fault tolerant control problem and propose an intelligent sliding mode control strategy using artificial neural networks to handle the desired trajectories tracking problem for systems suffering from catastrophic faults or incipient failures. The approach is to continuously monitor the system performance and identify what the system's current state is by using a fault detection method based upon our best knowledge of the nominal system and nominal controller. Once a fault is detected, the proposed intelligent controller will adjust its control signal by adding a robust term to confine the system performance within a boundary layer. At the same time, an artificial neural network is initialized and compensates for the unknown fault dynamics online. Once the online learning process converges, the control input is tuned again by using the output of the identification model and a new least upper bound for the remaining uncertainty is estimated to further reduce the tracking error. The simulation results show a significant improvement in trajectory following performance based upon the proposed intelligent control strategy.

关键词： Artificial intelligence Intelligent control Intelligent networks Fault tolerance Artificial neural networks control systems Sliding mode control System performance Fault detection Fault tolerant systems

来源：评论

学校读者我要写书评

暂无评论

Distributed modular computer-integrated surgical robotic systems: Implementation using modular software and networked systems 3rd

Distributed modular computer-integrated surgical robotic sys...

引用

3rd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2000

作者： Bzostek, Andrew Kumar, Rajesh Hata, Nobuhiko Schorr, Oliver Kikinis, Ron Taylor, Russell H. Department of Computer Science Johns Hopkins University BaltimoreMD United States Surgical Planning Laboratory Brigham and Women’s Hospital and Harvard Medical School BostonMA United States Institute of Process Control and Robotics University of Karlsruhe Germany Engineering Research Center for Computer Integrated Surgical Systems and Technology Germany

ISBN: (纸本)3540411895

We seek to build CIS research systems within a flexible, open architecture. In this paper, we outline our solutions to the problems of system design, construction, and integration in this environment: building distributed, modular systems for sensing, control, and processing. Based on our experience building these systems, we utilize distributed network architectures, modular software components, and intelligent object distribution to maximize flexibility while complying with the particular needs and interfaces of specific components. While a work in progress, these approaches have been integrated into several systems in development and have demonstrated significant utility, based on construction time and system flexibility. This paper will discuss the first two aspects: modular software and basic network architectures, while intelligent object distribution is presented in a companion paper. Based on the applications we have targeted and technologies we have used, this paper introduces our architecture and its components. It then presents the system’s current state and finally, discusses plans for future improvements and extensions. © Springer-Verlag Berlin Heidelberg 2000.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Validating executable controller specifications through formal model checking

Validating executable controller specifications through form...

引用

IEEE International Symposium on computer Aided control System Design (CACSD)

作者： J.J. Scillieri K.R. Butts J.S. Freudenberg Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI USA Powertrain Control Systems Department Ford Research Laboratory Dearborn MI USA

ISBN: (纸本)0780365666

In many embedded control system applications, the control algorithm includes both logical and data flow portions. We apply formal methods of system verification to discrete-state algorithms. Specifically, we make use of a formal model checking tool to prove or disprove various properties of the algorithm. Questions pertaining to the achievability of states and paths and proper variable assignment are cast as logical assertions in computation tree logic (CTL), and evaluated using the model checker. In addition, we describe an approach for generating scenarios; that is, a sequence of inputs and parameters that will take a discrete-state system model through a given sequence. We present several examples illustrating various questions that the designer may wish to pose, and an appropriate CTL assertion for each.

关键词： Mathematical model System testing Power system modeling control system synthesis Logic Design engineering computer science Mechanical power transmission Laboratories Application software

来源：评论

学校读者我要写书评

暂无评论

C4ISR architectures: I. Developing a process for C4ISR architecture design

引用

systems engineering 2000年第4期3卷 225-247页

作者： Levis, Alexander H. Wagenhals, Lee W. System Architectures Laboratory C3I Center MSN 4D2 George Mason University Fairfax VA 22030 United States Department of Electrical Computer and Systems Engineering C3I Center System Architectures Laboratory United States Institute of Electrical and Electronic Engineers (IEEE) Advancement of Science (AAAS) United States Center of Excellence Command Control Communications and Intelligence George Mason University Fairfax VA United States System Architectures Laboratory United States

The C4ISR Architecture Framework document issued by the Department of Defense specifies three views of an information architecture and defines a set of products that describe each view. These architecture views are to serve as the basis for C4ISR system development and acquisition. The Framework does not provide a process for architecture design. In this paper, information architectures are described in the context of Structured Analysis, and then the architecture views of the Framework and the related products are interpreted in that context. A methodology for architecture design is developed that is then implemented using Structured Analysis and object orientation in two companion papers. © 2000 John Wiley & Sons, Inc.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Factorization method for multiple perspective views via iterative depth estimation

引用

systems and computers in Japan 2000年第13期31卷 87-95页

作者： Ueshiba, Toshio Tomita, Fumiaki Electrotechnical Laboratory Tsukuba 305-8568 Japan Department of Electrical Engineering University of Tokyo Electrotechnical Laboratory Min. of Intl. Trade and Industry Intelligent Systems Division Canada Nat. Inf. Eng. Lab. Information Processing Society Robotics Society of Japan Soc. of Instrum. Control Engineers Department of Control Engineering Osaka University CMU Department of Computer Science Information Processing Society Robotics Society of Japan

This paper proposes a factorization method that reconstructs camera motion and scene shape based on the matching of multiple images under the condition that the camera captures a perspective view. Starting from the affine projection camera model, the projection depth is iteratively estimated until the measurement matrix has rank 4. Then, the obtained measurement matrix is factorized to restore the three-dimensional information of the scene in the projection space. This approach eliminates noise sensitive processes, such as the calculation of the fundamental matrix, that are required in the factorization for the conventional perspective projection image, and a stable reconstruction is realized. Furthermore, the metric constraint in the conventional affine model is extended, and the metric constraint in the perspective projection condition is derived. It is shown that the reconstruction in Euclidean space is realized if the internal parameters of the camera are given.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Application of a genetic algorithm in triangulation of a 3-D object surface

引用

International Journal of computers and Applications 2000年第2期22卷 73-77页

作者： Zhenyu, Chen Mbede, J.B. Yan, Zhou Dehua, Li Hanping, Hu State Commn. Res. Open Lab. Image P. Inst. Pattern Recog. Artif. Intell. Huazhong Univ. of Sci. and Technol. 430074 Wuhan China Intelligent Contr. and Robotics Lab. Dept. of Contr. Sci. and Engineering Huazhong Univ. of Sci. and Technol. 430074 Wuhan China Second Artillery Institute Huazhong Univ. of Sci. and Technol. Inst. Pattern Recog. Artif. Intell. Huazhong Univ. of Sci. and Technol. Second Artillery Institute China Wuhan University China Artificial Intelligence Department University of Edinburgh Inst. of AI and Pattern Recognition Huazhong Univ. of Sci. and Technol. China Cogn. Sci. Natl. Key Found. Res. P. Douala University Cameroon Tübingen University Germany Automatic Control Laboratory Darmstadt University Department of Service Cameroon Min. of National Education Robotics Laboratory Huazhong Univ. of Sci. and Technol. Wuhan China Assoc. Connectionnistes These-ACTH Rennes France IEEE Soc. of Robotics and Automation IEEE Society of Control Systems IASTED Assoc. Jeunes Chercheurs Robotique France Navy University of Engineering China Huazhong Univ. of Sci. and Technol. China Department of Computer Science Airforce Radar Acad. of Engineering China Inst. of P.R and AI Huazhong Univ. of Sci. and Technol.

This paper proposes a genetic-based algorithm for surface reconstruction of three-dimension (3-D) objects from a group of contours representing its section plane lines. The algorithm can optimize the triangulation of the surface of 3-D objects with a multi-objective optimization function to meet the needs of a wide range of applications. Further, a new crossover operator for triangulation and a new 3-D quadrilateral mutation operator are also introduced.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Constrained feedback control of discrete-time systems decribed by ARMA models

Constrained feedback control of discrete-time systems decrib...

引用

1999 European control Conference, ECC 1999

作者： Vassilaki, M. Bitsoris, G. Control Systems Laboratory Department of Electrical and Computer Engineering University of Patras Patras26 500 Greece

ISBN: (纸本)9783952417355

In this paper the problem of determination of bounded output-feedback control laws which stabilize multivariable discrete-time systems described by ARMA models is investigated. The proposed approach is based upon the properties of polyhedral positively invariant sets with respect to this class of systems. In the first part of the paper, necessary and sufficient conditions for the positive invariance of polyhedral sets are established. Then, conditions guaranteeing the existence of a solution to the constrained control problem are developed. Finally, it is shown that a solution to this problem can been obtained by solving a linear programming problem. © 1999 EUCA.

关键词： Feedback control

来源：评论

学校读者我要写书评

暂无评论

Design of a neural network observer to control a FED-batch bioprocess

Design of a neural network observer to control a FED-batch b...

引用

1999 European control Conference, ECC 1999

作者： Boutalis, Y.S. Kosmidou, O.I. Automatic Control Systems Laboratory Department of Electrical and Computer Engineering Democritus University of Thrace XanthiGR-67100 Greece

ISBN: (纸本)9783952417355

The present paper deals with the production of Saccharomyces cerevisiae, described by a sixth order nonlinear state space model. The control objective is to ensure the process stability and desirable specifications in the presence of disturbances and lack of reliable state measurements. First, the model of the process and its properties are presented. Next the ability of multi-layer Neural Networks to act as reliable emulators of the system dynamics is tested by simulation results and a training strategy is proposed to improve their performance. Finally, a non-linear adaptive observer is designed by means of artificial neural networks. © 1999 EUCA.

关键词： Neural networks

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：