Journal of Intelligent & Fuzzy Systems - Volume 8, issue 2

Authors: Cho, Jae-Soo | Park, Dong-Jo

Article Type: Research Article

Abstract: In this paper a new method of fuzzy logic control based on possibly inconsistent if-then rules representing uncertain knowledge or imprecise data is studied. In most cases of practical applications adopting fuzzy if-then rule bases, inconsistent rules have been considered as ill-defined rules and, thus, not allowed to be in the same rule base. When it is hard to obtain consistent rule bases, we propose a fuzzy logic controller based on weighted rules depending on output performances using the neural network and we will derive a weight updating algorithm. To guarantee convergence of the weights, a learning rate is developed …by introducing a Lyapunov function. With the final weight change informations, we can make better decisions by taking into consideration conflicting rules. The proposed method is applied to simple problems and simulation results are included. And real application problems are also discussed. Show more

Citation: Journal of Intelligent and Fuzzy Systems, vol. 8, no. 2, pp. 99-110, 2000

Authors: Alata, M. | Jarrah, M. | Demirli, K. | Bulgak, A.

Article Type: Research Article

Abstract: This paper presents an interactive procedure for controller design for nonlinear system by integrating available classical as well as modern tools such as fuzzy logic, and neural networks. The proposed approach is based on quasi-linear dynamic models of the plant. Classical optimal controllers for each set of operating conditions were developed. These controllers are used to construct a single fuzzy-logic gain scheduling-like controller. Adaptive-neuro-fuzzy inference system was used to construct the rules for the fuzzy gain schedule. This will guarantee the continuos change in the gains as the system parameters change in time or space. This procedure is systematic and …can be used to design controllers for many nonlinear systems. Two degrees of freedom (dof) planar manipulator was chosen to show the effectiveness of the proposed approach. A robot manipulator is inherently unstable and displays a strong nonlinearity. The resulting system is stable for different reference trajectories. The system is also robust for wide range of driving frequencies of the input. This system is able to deal with slow as well as fast varying systems, which is a significant improvement on conventional gain scheduling. Show more

Citation: Journal of Intelligent and Fuzzy Systems, vol. 8, no. 2, pp. 111-120, 2000

Authors: Chen, Y.H.

Article Type: Research Article

Abstract: We suggest an input-output system point of view of the mechanism in generalized modus ponens (GMP). The antecedent and consequent in the premise are treated as an input-output pair. The other premise and the conclusion are treated as another pair. It is suggested that the two pairs are related to each other in the sense that they are generated by the same system. With the input-output system aspect, we propose to categorize the previous approximate reasoning mechanism to be either internal or external. More insights of the internal and external mechanism are explored. In addition, a new hybrid mechanism is …introduced for the GMP. We suggest a way to justify that one pair is reasoned based purely on the other. This is through the comparison of the truth values of the two pairs. The hybrid mechanism preempts that the truth value of one input-output pair, which also can be viewed as a fuzzy inference, should be identical to the other. This is coined as the Principle of Equal Truth Value (PETV). Some GMP performance, which people would often expect in a realistic GMP but is never rigorously guaranteed in other mechanism, is a natural consequence of the hybrid mechanism. Another interesting result of the hybrid mechanism is that it not only indicates what can be achieved, but also what can not be done in the reasoning. This appears to be more aligned with human experience: If the basis of reasoning (in the GMP, it is Premise 2) is too far away from the occurrence (i.e., Premise 1), then there is nothing one can say about the consequence (i.e., Conclusion) due to the occurrence. Show more

Citation: Journal of Intelligent and Fuzzy Systems, vol. 8, no. 2, pp. 121-133, 2000

Authors: Senjyu, Tomonobu | Yokoda, Satoru | Uezato, Katsumi

Article Type: Research Article

Abstract: This paper presents a speed control system for ultrasonic motors by PI (proportional and integral) control which has auto-tuning structure based on fuzzy reasoning realized by a neural network. Since the speed characteristics of ultrasonic motor vary with temperature and applied load torque, adjusting the control gains of PI controller is necessary in order to obtain fine speed control performance. The proposed control scheme can incorporate the operator's knowledge in speed controller using fuzzy reasoning, furthermore, it can compensate the speed characteristic variations of the motor by online learning. The usefulness and validity of the proposed control scheme is examined …by experiments. Show more

Citation: Journal of Intelligent and Fuzzy Systems, vol. 8, no. 2, pp. 135-146, 2000

Authors: Lowen, R. | Peeters, W.

Article Type: Research Article

Abstract: The purpose of this article is to describe a recognition system, used in the matching of patterns that are distorted by various kinds of noise. The proposed technique is more general than the one described in [12], but also makes fundamental use of the concept of semi-pseudometrics. It will be shown that in some cases, the chance of correctly recognizing an image increases when using these in a distance classifier.

Citation: Journal of Intelligent and Fuzzy Systems, vol. 8, no. 2, pp. 147-158, 2000