Scheduled System Maintenance:
On May 6th, single article purchases and IEEE account management will be unavailable from 8:00 AM - 5:00 PM ET (12:00 - 21:00 UTC). We apologize for the inconvenience.
By Topic

Intelligent Control, 1990. Proceedings., 5th IEEE International Symposium on

Date 5-7 Sept. 1990

Filter Results

Displaying Results 1 - 25 of 194
  • Proceedings. 5th IEEE International Symposium on Intelligent Control 1990 (Cat. No.90TH0333-5)

    Publication Year: 1990
    Save to Project icon | Request Permissions | PDF file iconPDF (378 KB)  
    Freely Available from IEEE
  • Fuzzy sets and neurocomputations: knowledge representation and processing in intelligent controllers

    Publication Year: 1990 , Page(s): 626 - 630 vol.1
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (364 KB)  

    The problem of knowledge representation and processing for controllers for complex systems characterized by the availability of partial information is studied. Fundamental features of intelligent control are considered, and the role of fuzzy sets and neural nets is discussed. A new controller structure in which fuzzy sets and neural nets are used together is proposed, along with details of the associated design methodology. Learning processes in the resulting neural network are also clarified. All the formulas are given in detail View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robotics in intelligent manufacturing: IMPAQT activities

    Publication Year: 1990 , Page(s): 1205 - 1210 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (608 KB)  

    The Center for Intelligent Manufacturing, Processing, and Quality Technologies (IMPAQT) at Drexel University was established to integrate education, research, and technology transfer in technical and business fields which are associated with intelligent manufacturing and processing. A report on some of the Center's ongoing robotics activities is presented. Projects described are: (1) interpretation of redundant kinematic parameters in robotic manipulator calibration algorithms, (2) brushless motors for direct-drive robots and numerically controlled machines, (3) a robot control laboratory, (4) computer-based control and intelligent control systems and (5) a robot dynamics laboratory View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The analysis of fuzzy knowledge-based systems using cell-to-cell mapping

    Publication Year: 1990 , Page(s): 633 - 637 vol.1
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (368 KB)  

    A cell-to-cell mapping method is introduced and applied to the analysis of a fuzzy-knowledge-based mobile robot motion control system. The cell-to-cell mapping was originally used in nonlinear system analysis. This method is found to be very compatible with the fuzzy-knowledge-based system. By dividing the state space into cell state space, the multi-image fuzzy mapping is transformed to a fuzzy cell-to-cell mapping. The periodic solutions of the fuzzy dynamic system are located by using an algorithm. The global behavior of the fuzzy mapping is described by finding the domain of attraction of a periodic solution View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural-net based megawatt-frequency control

    Publication Year: 1990 , Page(s): 1231 - 1236 vol.2
    Cited by:  Papers (1)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (296 KB)  

    The design of a new adaptive control system is presented, and its performance in a computer simulation of the single-area megawatt-frequency control problem is demonstrated. The new design utilizes self-organization and predictive estimation capabilities of neural-net computing. Real-time adaptation is facilitated by the error-based online learning scheme implemented on a clusterwise segmented associative memory system. The use of the pattern recognition approach in power systems control is demonstrated. The role of feedback is emphasized in order to compensate for uncertainties and lack of information View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy associative memories: identification and control of complex systems

    Publication Year: 1990 , Page(s): 910 - 915 vol.2
    Cited by:  Papers (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (388 KB)  

    Fundamental properties of fuzzy associative memories (FAMs), which form a class of fuzzy neural networks, are examined. Fuzzy neural networks combine notions of conventional neural networks and fuzzy set theory, which has been proved suitable for coping with system uncertainty. Atomic and composite FAMs are defined, and their recall behavior is studied. The recall process is recognized as a reasoning process. An approximate FAM is defined on the basis of the l p-distance of two fuzzy subsets to provide a quantitative measure of the recall process. Fuzzy neural networks are applied to problems which possess high complexity and uncertainty. The FAM implementation issue is addressed in terms of three functional units: a min-net which performs fuzzy conjunction operations, a max-net which performs fuzzy disjunction operations, and a learning unit which adjusts the connection coefficients whenever necessary View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • AI research activities at Saint Joseph's University

    Publication Year: 1990 , Page(s): 1178 - 1179 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (124 KB)  

    Research activities in artificial intelligence at Saint Joseph's University are described. There has been significant progress in both basic research and system implementation in the last few years. The software developed pertains to search pruning for problem solving, learning from examples (similarity-based learning as it is often called), and explanation-based generalization and self-improving game-playing programs. The work on similarity-based learning can support the automatic formation of expert rules. All of this work is based on the basic research. Activities in the areas of the theory of problem solving, learning algorithms, and software development are described View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimation of dynamic system parameters by neural networks

    Publication Year: 1990 , Page(s): 541 - 545 vol.1
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (296 KB)  

    Identification of dynamic systems, operating under correlated noise, is conventionally performed by the generalized least squares algorithm. The Hopfield neural network has been used in connection with the generalized least squares technique to identify the system parameters. A theoretical comparison is made between the conventional generalized least squares and the neural-network-based generalized least squares techniques. This comparison is also supported by the simulated examples. It is shown that the Hopfield-based neural network can perform two fundamental steps of the generalized least squares algorithm in parallel fashion. These steps are the application of least squares routines View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy supervision of direct controllers

    Publication Year: 1990 , Page(s): 638 - 643 vol.1
    Cited by:  Papers (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (372 KB)  

    In closed-loop control systems, a supervision loop is sometimes needed in order to perform an operation task which usually consists of adjustments of set points and controller parameters. A fuzzy approach to the supervision of controller parameters in single-loop plants is described. The fuzzy supervision is performed over two different direct controllers: a PI (proportional-integral) and a fuzzy controller. The results of experiments conducted to test the supervision strategy with two different simulated systems and one scaled pilot plant are presented. In the fuzzy controller, the central values of the rules output membership functions are adjusted at the supervision sampling instants. For the PI controller, the adjusted parameters are the proportional and integral gains View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Active sensing at a microscopic scale

    Publication Year: 1990 , Page(s): 246 - 251 vol.1
    Cited by:  Papers (2)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (616 KB)  

    The possibilities afforded by the application of active sensing principles to microscopic scale systems are examined. Active point sensor systems consist of collections of simple sensing elements that have motor, computational, and communication capabilities. Depending on the laws of motion programmed into these elements, complex operations as diverse as nonlinear diffusion, shape from shading, and deformable template matching can be performed. Active point sensor systems represent an entirely new way of implementing sensing devices. In contrast to sensor arrays, active point sensor systems permit the integration of complex information processing on the same substrate as the sensing elements, and they can be adaptive, altering their processing on the basis of changes in the state of individual sensing elements. Their output is asynchronous and object oriented, reducing communication bandwidths and easing interfacing to other systems View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Airborne ultrasonic potential in intelligent control

    Publication Year: 1990 , Page(s): 1261 - 1265 vol.2
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (476 KB)  

    A brief review of some current efforts to fully understand ultrasonic wave propagation in air is presented, along with some miscellaneous items of value in an intelligent manufacturing environment. The use of an airborne ultrasonic sensor can be a valuable tool in an intelligent manufacturing environment as long as the physics of wave propagation is thoroughly understood. Beam divergence, attenuation, presence of side lobes, ability to control interference patterns, etc., and the ability to improve signal-to-noise ratio can add significantly to creative use of ultrasonic sensors in manufacturing. Dimensional checks of a product, position measurement of various system hardware, and product quality measurements are all possible with airborne ultrasonic sensors. Basic tools for accomplishing these sensing activities are discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural networks and fuzzy logic in intelligent control

    Publication Year: 1990 , Page(s): 916 - 920 vol.2
    Cited by:  Papers (3)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (368 KB)  

    An introduction to fuzzy controllers and neural network controllers is presented, and methods for merging their capabilities to design hybrid neurofuzzy controllers (NFCs) are discussed. NFCs provide the knowledge representation power of fuzzy controllers and the learning capabilities of artificial neural networks. Several examples are given to contrast the architecture of the NFCs with individual fuzzy controllers or neural network controllers. The major elements of neurocontrol, a term used to refer to the neural networks that serve as controllers, are reviewed, with special emphasis on the learning behavior of these networks. Recent research on integrating neural networks with fuzzy logic control is outlined. It is shown that both of these techniques can use interpolative reasoning, which enables them to go beyond the traditional true-false restriction of the artificial intelligence symbolic methods View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On estimation of noise variance in linear dynamic systems by multiple observers

    Publication Year: 1990 , Page(s): 1237 - 1239 vol.2
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (248 KB)  

    The use of multiple observers as a practical solution to the problem of determining the variances of the noise that excite a dynamic process or are present in observing it is discussed. The method is relatively easy to implement and does not require extraordinary computer resources, and at least in several examples studied by simulation, it can give acceptable performance. The method was tested on data obtained from real gyros. Since the true value of the parameters were, of course, unknown in these cases, it was not possible to determine how well the method works for real data; it was determined, however, that the results obtained by this method were in reasonably good agreement with the results obtained by the standard algorithm embodied in the test equipment. This is further favorable evidence that the method is practical View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Merging AI and game theory in multiagent planning

    Publication Year: 1990 , Page(s): 853 - 857 vol.2
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (312 KB)  

    An approach to reasoning about the actions that other agents are likely to pursue is outlined. This approach is based on the idea that many attempts to reason about another agent's beliefs and actions are based on an ability to self-reflect on one's own reasoning process and then to extrapolate to the other agent (`If I were she. . .'). It is shown how to combine knowledge-based option enumeration procedures with game-theoretic models for calculating a minimum (maximum) probability that an agent will identify and execute a specified course of action. In addition, it is shown how this approach addresses, in part, the outguessing problem in game theory View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The formalist manifesto [artificial intelligence]

    Publication Year: 1990 , Page(s): 1152 - 1155 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (260 KB)  

    A categorical model of problem solving is introduced. The concept is that domain-dependent knowledge can also take the form of structural knowledge about the domain and, more specifically, that the decomposition methods that have proved to be so effective in mathematical reasoning can also be applied in the case of artificial intelligence systems. The fact that such knowledge is superficially more arcane because of its abstract nature does not automatically indict it as being necessarily weak. It is shown that a number of algebraic approaches to problem solving can be incorporated into the viewpoint View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Control of the flexible automation of metal forming

    Publication Year: 1990 , Page(s): 1071 - 1073 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (204 KB)  

    Pressbrake bending and multibending are two metal-forming processes that can produce a wide variety of parts with fixed tooling. An overview of the technology for producing such parts emphasizing the control issues is presented. Closed-loop control of these processes is essential to maintaining accuracy and to minimizing the setup time for a new part. Moreover, the control algorithms used must incorporate physically sound models of the process. Some recent research aimed at better controls for pressbrake bending and multibending is outlined View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Task and resource coordination in human teams

    Publication Year: 1990 , Page(s): 113 - 119 vol.1
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (784 KB)  

    Distributed decision making and coordination in multiperson teams are studied. The problems of resource allocation, in which a team shares a limited pool of resources to process a mix of tasks under various overlaps in team responsibility, are addressed. The modeling approach is to blend normative mathematical theories for team decision making with descriptive facets that capture known and observed human cognitive limitations and biases. Three modeling efforts in resource allocation and task sequencing are described: the first is for a dyad, the second for a three-person flat organization, and the third for a three-person team plus a leader. The resulting normative descriptive models show an excellent ability to replicate individual and team data across a wide range of independent variables and provide insight into the process of human decision making in distributed organizations View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Organizing engineering designs and design techniques

    Publication Year: 1990 , Page(s): 977 - 984 vol.2
    Cited by:  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (628 KB)  

    The authors present an approach to organizing engineering designs and design techniques in a database system. This database system stores existing designs and provides a mechanism for capturing the design process in the database. The authors develop the notions of assembly objects and component objects, define the idea of design dependencies among objects and explain dependencies in terms of constraints. They also develop a representation of design techniques, show a representation of design objects, techniques, and dependencies, and present a scenario for performing designs. Dependencies between objects are recognized and treated uniformly as objects in a database. It is pointed out how this environment may be used for conducting the design process by selection of components View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive frequency divers filtering techniques for ultrasonic analysis

    Publication Year: 1990 , Page(s): 1266 - 1270 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (364 KB)  

    Ultrasonic nondestructive testing of large grained materials is limited by the ability of the detection process to distinguish the flaw signals from the backscattered grain noise. This noise often masks the flaw signal, leading to difficulties in its detection and identification. Similar problems exist in other applications such as radar and sonar, where clutter interferes with the detection of targets. In order to enhance the flaw visibility, the frequency diverse statistic filter has been developed. In the past, considerable success has been reported in signal-to-noise ratio (SNR) enhancement using this technique. However, the frequency diverse statistic filter is fairly sensitive to the filtering parameters which may cause the processing to be very intolerant. In the paper, two adaptive techniques for the frequency diverse statistic filtering are discussed. Ultrasonic flaw detection experiments are presented to demonstrate the performance of these techniques View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy adaptation and control of a class of dynamic systems

    Publication Year: 1990 , Page(s): 304 - 309 vol.1
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (300 KB)  

    The use of fuzzy adaptation in tuning some types of control systems is examined. An analytical framework is outlined for fuzzy tuning, and a parallelism between fuzzy tuning and conventional parameter-adaptive control is highlighted. A numerical example is given to demonstrate the capability of a fuzzy tuner in tuning the parameters of a proportional-integral-derivative controller View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nonstationary noise identification with the interacting multiple model algorithm

    Publication Year: 1990 , Page(s): 585 - 589 vol.1
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (224 KB)  

    The interacting multiple-model state estimation algorithm has been shown to be one of the most cost-effective schemes for estimating the state of hybrid systems. Such systems, which have continuous and discrete uncertainties, are represented by a finite set of noisy state equations, each pertaining to a certain mode. The system can switch from one mode to another according to an assumed underlying Markov chain. This framework is described and used here to estimate the time-varying intensity of the noise processes in a dynamic system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Faster than real time robot simulation with real time feedback

    Publication Year: 1990 , Page(s): 932 - 935 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (464 KB)  

    The integration of operational sensory feedback with the sensed world model database is discussed, with the focus on the development of a database model of the environment which has the following three characteristics: a basic level of intelligence whereby information about individual objects, as well as repair and maintenance steps, is readily accessible; a degree of accuracy which allows for autonomous offline path planning or time-accelerated interactive path planning; and a means of comparing feedback sensor information with the information stored in the database. A rapid comparison is needed so that objects not modeled in the database can be identified in real time. Compatibility between the preplanned model environment and the as-encountered plant environment will significantly aid in the interpretation of sensor data View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Model-based architecture concepts for autonomous systems

    Publication Year: 1990 , Page(s): 27 - 32 vol.1
    Cited by:  Papers (8)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (496 KB)  

    It is argued that autonomy, as a design goal, offer an arena in which both control and artificial intelligence (AI) paradigms must be applied. Architectures in which AI and control paradigms can be integrated within a model-based approach are discussed. The ability of knowledge-model-based tools (SES/MB framework and DEVS scheme) to support the model-based design of high-autonomy systems is extended through the ability to generate families of planning alternatives and build a hierarchical event-based control structure. Concepts are illustrated by a robot-managed spaceborne laboratory environment View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparison of some neural network models of classical conditioning

    Publication Year: 1990 , Page(s): 1163 - 1168 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (412 KB)  

    Classical conditioning is a form of temporal learning that may be useful in intelligent control. Three neural network models of classical conditioning are compared: the Sutton-Barto model, the Klopf model, and the Grossberg-Schmajuk model. All are based on Hebbian learning, but they differ in how events are remembered. Although these models can learn to associate two events occurring at different times, they also show behaviors that may not be satisfactory in an intelligent control system. It is concluded that these models of classical conditioning fall far short of being good learners of temporal associations View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An expert system for monitoring the status of control systems

    Publication Year: 1990 , Page(s): 457 - 462 vol.1
    Cited by:  Papers (3)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (476 KB)  

    A real-time expert system, consisting of a knowledge base, an inference engine, and a linear predictive coding algorithm (LPCA), is proposed for monitoring the status of the control system. The ARMA (autoregressive moving average) model estimates are used to compute the performance and stability measures, predict overload, and detect faults. The control system is asserted to be in (1) normal state if the performance and stability measures are within the threshold limits, (2) alert state if the performance and/or stability measures violate the limits, and (3) emergency state if the error signal is unbounded. The LPCA is broken into a number of tasks. The expert system controls the execution of these tasks and validates the assertions using heuristic, contextual, and control-theoretic reasoning. The status information is displayed in the order of decreasing importance such that essentials are known earlier with the complete picture emerging later. The proposed scheme is implemented on a commercially available expert system shell View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.