Journal of Intelligent & Fuzzy Systems - Volume 1, issue 2

Authors: Pin, François G. | Watanabe, Yutaka

Article Type: Research Article

Abstract: Because outdoor environments are typically dynamic and not fully predictable, real-time vehicle control in such environments requires many calculational and reasoning schemes to operate on the basis of incomplete, unreliable, and/or imprecise information. For such systems, in which all the uncertainties cannot be engineered away, approximate reasoning may provide an alternative to the complexity and computational requirements of conventional uncertainty analysis and propagation techniques. Two types of computer boards including custom-designed VLSI fuzzy inferencing chips have been developed to add an approximate reasoning capability to real-time control systems. All inferencing rules on a chip are processed in parallel, allowing execution …of the entire rule base in about 30 μs (i.e., at rates much faster than typical sensor sampling rates) and therefore making control of “reflex-type” motions envisionable. The use of these boards and a proposed approach using superposition of sensor-based fuzzy behaviors for the development of qualitative reasoning schemes are first discussed. We then describe how a fuzzy behavior-based navigation scheme emulating human-like navigation in a priori unknown environments was implemented on one of the fuzzy inferencing boards and installed on a test-bed platform to investigate two control modes for driving a car on the basis of sparse and imprecise sensor data. In the first mode, the car navigates fully autonomously, while in the second mode the system acts as a driver's aid, providing the driver with linguistic-type (fuzzy) commands to turn left or right and speed up, slow down, or back up depending upon the obstacles perceived by the sensors. Experiments with both modes of control are described in which the system uses only three acoustic-range (sonar) sensor channels to perceive the environment. Simulation results as well as indoor and outdoor experiments are presented and discussed to illustrate the feasibility and robustness of the proposed approach for sensor-based functions such as autonomous navigation and/or safety-enhancing driver's aid. Show more

DOI: 10.3233/IFS-1993-1201

Citation: Journal of Intelligent and Fuzzy Systems, vol. 1, no. 2, pp. 95-107, 1993

Authors: Hellendoorn, Hans | Thomas, Christoph

Article Type: Research Article

Abstract: An important subject in fuzzy control theory is tuning of a fuzzy controller. If one wants to tune a fuzzy controller, one can focus on the choice of rules, membership functions, number of input and output fuzzy sets and their degree of overlapping, implication, and connection operations, and defuzzification method. All these choices are closely related and in no way independent of each other. We describe six important defuzzification methods and their respective merits and shortcomings, dependent on the rules, domains, etc. Further, we give an alternative approach for the case in which the output fuzzy sets have different shapes …or are asymmetrical. We illustrate this by several examples. Show more

DOI: 10.3233/IFS-1993-1202

Citation: Journal of Intelligent and Fuzzy Systems, vol. 1, no. 2, pp. 109-123, 1993

Authors: Kim, Jong-Hwan | Park, Jong-Hwan | Lee, Seon-Woo | Chong, Edwin K.P.

Article Type: Research Article

Abstract: Simple conventional control methods, such as PD and PID controllers, are widely used in industrial applications. Such controllers exhibit poor performance when applied to systems containing nonlinearities arising from unknown deadzones. In this article, we propose a novel fuzzy logic-based precompensation approach for controlling systems with deadzones. The control structure consists of a fuzzy logic-based precompensator followed by a conventional PD controller. Our proposed control scheme shows superior transient and steady-state performance compared to conventional PD and PID controllers. In addition, the scheme is robust to variations in deadzone nonlinearities, as well as the steady-state gain of the plant. We …illustrate the effectiveness of our scheme using computer simulation examples. Show more

DOI: 10.3233/IFS-1993-1203

Citation: Journal of Intelligent and Fuzzy Systems, vol. 1, no. 2, pp. 125-133, 1993

Authors: Ross, T.J. | Hasselman, T.K. | Chrostowski, J.D. | Verzi, S.J.

Article Type: Research Article

Abstract: Aerospace institutions such as NASA and the U.S. Air Force have long been interested in the development of methods for evaluating the predictive accuracy of structural dynamic models. This interest is due to the fact that mathematical models are used to evaluate the structural integrity of all aircraft and spacecraft prior to flight. Space structures are often too large and too weak to be tested fully assembled in a ground test laboratory. The predictive accuracy of a model depends on the nature and extent of its experimental verification. The further the test conditions depart from in-service conditions, the less accurate …the model is likely be. The best method for quantitatively evaluating the predictive accuracy of a model is to make direct measurements under simulated service conditions. Unfortunately, this method is expensive and fraught with problems in achieving service conditions on earth. This article presents progress made in the combined use of several methods to evaluate the accuracy of dynamic models of large space structures using numerical simulation. Some of these methods involve the theory of fuzzy sets. The fuzzy set methods are shown to be effective and computationally efficient as tools for bounding the range of possible responses, segregating important modal responses from those having less effect on predicted response, reduction of uncertainty in plant models in a control-structure interaction context, and providing the only plausible means of uncertainty prediction at the poles and zeros of the frequency response spectra. The article illustrates these notions with some numerical examples. Show more

DOI: 10.3233/IFS-1993-1204

Citation: Journal of Intelligent and Fuzzy Systems, vol. 1, no. 2, pp. 135-155, 1993

Authors: Sekii, Katsumi | Hadipriono, Fabian C.

Article Type: Research Article

Abstract: An erector's experience plays an important role in successfully erecting a precast, prestressed, concrete girder bridge. Commonly, the experienced erector establishes the method and sequence of the erection process heuristically, based on educated guesses, experiential judgment, and assumptions. This motivated the authors to develop EXPERECT, a knowledge-based expert system for erecting precast, prestressed, concrete girder bridges in the Kanto area of Japan. EXPERECT has been successfully tested on a limited basis. It introduces itself, its scope and limitations, and furnishes the user with substantial help statements; it informs the user as to why and how a particular erection method was …chosen; and it furnishes the user with step-by-step recommendations to reach interim and final conclusions. In addition, EXPERECT presents the user with an animation of each erection method. Show more

DOI: 10.3233/IFS-1993-1205

Citation: Journal of Intelligent and Fuzzy Systems, vol. 1, no. 2, pp. 157-170, 1993

Authors: Vadiee, Nader | Jamshidi, Mohammad

Article Type: Research Article

Abstract: In this article, the general problems of system identification and control system design are formulated and the concept of control or decision surface is described. The article shows that a collection of fuzzy conditional restrictive rules can be used to model complex or ill-defined processes (fuzzy systems), and some simple canonical formats for the production rule sets are given. It is shown that a system of fuzzy relational equations could be obtained from a set of IF-THEN production rules. A fuzzy system transfer relation based on a system of fuzzy relational equations is defined. The article also shows how a …variety of fuzzy implication relations or Zadeh's extension principle might be used to derive the fuzzy relational equations. Various methods for obtaining the solution of these equations are studied based on a number of composition of relations techniques. Finally, two of the most commonly used solution techniques in fuzzy control applications, that is, Max-Min and Max-Product methods, are described. Show more

DOI: 10.3233/IFS-1993-1206

Citation: Journal of Intelligent and Fuzzy Systems, vol. 1, no. 2, pp. 171-188, 1993