Journal of Intelligent & Fuzzy Systems - Volume 5, issue 3

Authors: Theocharis, John | Vachtsevanos, George

Article Type: Research Article

Abstract: In recent years, recurrent neural network models have found extensive applications in the identification and control of complex dynamical systems. A wide class of dynamic learning algorithms have been applied to train such models. The objective of this work is to apply concepts and techniques developed in the neural network arena to the fuzzy neural network field. A recurrent fuzzy neural network model is proposed that is called the dynamical-adaptive fuzzy neural network (D-AFNN), which is employed to identify dynamic nonlinear plants. Thefuzzy model is based upon the Takagi-Sugeno inference method with polynomial consequent functions. Training of the recurrent models …is performed by means of the epochwise backpropagation through time (BPTT) scheme and the on-line BPTT. The mathematical background of the learning algorithms is presented and the computational procedure providing the error gradients is thoroughly discussed. We present also the rule base adaptation mechanism performing the fuzzy system structure learning. The rule base is constructed via training and a membership insertion mechanism. Simulation results are employed to illustrate the effectiveness of the proposed methodology. Show more

DOI: 10.3233/IFS-1997-5301

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 3, pp. 167-191, 1997

Authors: Pan, Yin | Klir, George J.

Article Type: Research Article

Abstract: Although Bayesian inference has been successful in many applications, its serious limitation is the requirement that exact prior probabilities be available. It has increasingly been recognized that this requirement is often not realistic. To overcome this limitation of classical Bayesian inference, we investigate a generalized Bayesian inference, in which prior probabilities as well as likelihoods are interval-valued. Employing the tools of interval analysis and the theory of imprecise probabilities, we develop a method for exact calculation of interval-valued posterior probabilities for given interval-valued prior probabilities and precise or interval-valued likelihoods. This method is further generalized for fuzzy likelihood and fuzzy …probabilities later. The classical Bayesian inference is a special case of our method. Show more

DOI: 10.3233/IFS-1997-5302

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 3, pp. 193-203, 1997

Authors: Alwan, Majd | Cheung, Peter Y.K.

Article Type: Research Article

Abstract: This paper introduces a method for modelling a Mobile Robot's environment, with its in-built uncertainties, in the Configuration Space using sonar range finders. The sonar uncertainties are modelled using a possibilistic, rather than probabilistic, measure and are represented by Fuzzy Membership grades. The Resistive Grid path planning method, that maps the Fuzzy Configuration Space Map into a grid of resistors and models goals as voltage sources, is used for planning a path. The near-optimal planned path takes into consideration position and modelling uncertainties, kinematic constraints of the vehicle as well as the uncertainty of the goal. The path is produced …incrementally, giving inherent interleaving between planning and execution, thus the method is particularly suited for real time applications. Show more

DOI: 10.3233/IFS-1997-5303

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 3, pp. 205-217, 1997

Authors: Feng, G. | Cao, S.G. | Rees, N.W. | Ma, J.

Article Type: Research Article

Abstract: This paper considers control of fuzzy dynamic systems. New controller design methods using output feedback are proposed based on quadratic stability theory. A number of necessary and sufficient conditions are derived for quadratic stabilizability of the fuzzy control system concerned. An example is also given to demonstrate the performance of the proposed controller design methods.

DOI: 10.3233/IFS-1997-5304

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 3, pp. 219-227, 1997

Authors: Mo, John P.T. | Wang, Hongbing | Chen, Nelson

Article Type: Research Article

Abstract: A class of programmable pneumatic axes has been constructed from a series of 3/2 way on-off solenoid valves and standard commercial components. To compensate for the deficiencies of the stock items, afuzzy logic control scheme has been designed based on a component oriented modelling approach by which the physical system was logically decomposed into components. The basic proportional-derivative control algorithm was then extended with three fuzzy logic control algorithms by considering the effects of individual components on the accuracy of the servomechanism. Tests were performed on two different pneumatic axes. The test results showed that the axes were stable dynamically …in all test conditions and could achieve the desired positions accurately. It was concluded that the component oriented modelling methodology provided a robust fuzzy logic control scheme which could be applied to both axes and achieved the same high degree of accuracy even without adjustment to its parameters. Show more

DOI: 10.3233/IFS-1997-5305

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 3, pp. 229-243, 1997

Authors: Chen, Guanrong | Ying, Hao

Article Type: Research Article

Abstract: In this paper, we analyze in detail the bounded-input/bounded-output (BIBO) stability of the nonlinear fuzzy proportional-integral (PI) control systems developed in Ying, Siler, and Buckley (1990). In this investigation, the “small gain theorem” is employed to obtain a simple sufficient condition on the global BIBO stability for general (stable and unstable) nonlinear control systems that possess finite gains and under the control of this type of fuzzy PI controlers. The derived sufficient condition provides a useful criterion for the design of such fuzzy PI control systems. In addition, we prove that in a conventional PI control system, if the linear …PI controller is replaced by the nonlinear fuzzy PI controller, the stability of the resulting control system remains unchanged. This is true no matter the given process is linear or not. We will also derive some simple and explicit formulas for computing the fuzzy PI controller parameters, using only the proportional and integral gains of the corresponding conventional linear PI controller. This result makes the new sufficient condition very practical, because using these formulas one can always replace a conventional linear PI controller by a nonlinear fuzzy PI controller without altering the system stability, to obtain better control performance. Show more

DOI: 10.3233/IFS-1997-5306

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 3, pp. 245-256, 1997

Authors: Marimin, | Umano, Motohide | Hatono, Itsuo | Tamura, Hiroyuki

Article Type: Research Article

Abstract: In this article, we propose a non-numeric method for pairwise group-decision analysis based on fuzzy preference relations. The proposed method expresses and processes the preference relations non-nwnerically. The computation processes are relatively simple and fast. We apply our method for selecting the most prospective new agro-industries to be implemented by a multi-corporate company. Moreover, in the application we develop a procedure consisting of 4 stages: (1) a brain-storming process for alternatives and criteria identifications, (2) a pre-selection of the prospective alternatives using a modification of fuzzy Delphi method, (3) a pre-selection of the significant criteria using a non-nwneric independent evaluation …method, and (4) a final alternatives selection based on all significant criteria by using the non-numeric pairwise fuzzy group-decision analysis. The final results are compared with results obtained by a semi-numeric method. The proposed method is suitable for group-decision making cases in which a full consensus is the most important role in selecting the alternatives. Show more

DOI: 10.3233/IFS-1997-5307

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 3, pp. 257-269, 1997

Authors: Jang, Dae-Sik | Choi, Hyung-Il

Article Type: Research Article

Abstract: Afuzzy rule-based system, widely used in the areas of control and pattern recognition, is mostly structured into inference mechanism and fuzzy rules expressed in terms of fuzzy sets. In this paper, we provide a general framework for fuzzy inference, which consists of a learning part and an inferring part. The learning part analyzes histograms of learning data to generate fuzzy sets and correlation matrix. The inferring part processes test data and draws conclusions with the model built up in the learning part. To confirm the effectiveness, we applied the suggested system to a pattern recognition problem with the iris data. …We believe that the suggested system can also be used in control problems. Show more

DOI: 10.3233/IFS-1997-5308

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 3, pp. 271-284, 1997

Authors: Arciszewski, Tomasz

Article Type: Research Article

Abstract: This paper proposes an engineering semantic evaluation method of a collection of decision rules, acquired automatically or manually. The method is intended to complement the available decision rule evaluation methods which are based on the use of various empirical error rates. These methods are often criticized as evaluating only the “predictive power” of decision rules without any indication of how appropriate these rules are in the context of a given domain. The proposed method directly addresses the issue of the domain relevance of decision rules, and it measures their “semantic power.” In the proposed method, the evaluation is conducted …using Background Knowledge in the form of a Concept library containing both primary and complex concepts which are acquired from/or provided by the domain experts. Primary Concepts represent the basic notions from a given domain which are directly related to the problem described by the collection of decision rules to be evaluated. Complex Concepts are those defined by a combination of at least two primary concepts and they are classified into several categories considering their complexity measured by the number of primary concepts used for their definition. All basic assumptions and the procedure of the method are provided. Also, a concept of an evaluation system based on the method is described. The method was used to evaluate two collections of decision rules which are equivalent in terms of their “predictive power.” Surprisingly, a significant difference in their “semantic power” was discovered, as shown by the numerical results and by the semantic learning curves constructed. The performed experiments demonstrated feasibility of the proposed method and that it can produce results which may provide an additional, yet unknown, understanding of decision rules and eventually of the symbolic learning systems which produced those rules. Show more

DOI: 10.3233/IFS-1997-5309

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 3, pp. 285-295, 1997

Authors: Chung, Byeong-Mook

Article Type: Research Article

Abstract: A learning method that can acquire the control rules in the multi-input multi-output system is presented. Generally, in the control of a multivariable system, the error of the outputs must be transformed into the corrections of the inputs to get the control rules. If we do not know the mathematical modeling equation of the system, we cannot find out the Jacobian matrix to show the output variance with respect to the input variance. However, because it is not necessary to use the exact variable matrix in the learning of the fuzzy rules, this article introduces a method to get a …representative constant Jacobian matrix that assures the convergence. Using this constant matrix, the fuzzy rules are successfully obtained. In particular, because many fuzzy subsets must be used in the case of a multivariable system, the optimization technique to minimize the fuzzy rule structure is also applied. Show more

DOI: 10.3233/IFS-1997-5310

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 3, pp. 297-310, 1997