Wiley E. Thompson

An advanced fuzzy controller

A methodology for the reduction of complexity of the fuzzy if-then rules for a robust controller system is presented. An analysis of the fuzzy if-then rules is performed by viewing the fuzzy sets in the rules as crisp sets. The knowledge of the analysis is used to reduce the number of variables and the number of fuzzy if-then rules. By applying fuzzy logic to the reduced linguistic if-then rules, a robust controller system based on fuzzy if-then rules is reconstructed. The simulation results show that the reconstructed controller is more efficient and performs as well as the original controller.

An intelligent controller design based on genetic algorithms

A methodology for designing digital controllers using genetic algorithms (GAs) is presented. A simulated digital proportional-integral-differential (PID) controller is designed, and the performance is compared to that obtained using a traditionally designed controller. The GA-based method does not require a mathematical model of the system and yields a controller that performs better than the traditional controller.<<ETX>>

Stability of a class of interconnected systems

Sufficient conditions are given for exponential stability of the equilibrium of systems of interconnected components taken from a class of nonlinear, time-varying, multi-terminal, differential, algebraic and mixed components. The analysis is based on the mathematical models of the unconstrained components and the linear constraints imposed by the interconnections between the components. A Liapunov function is constructed for the interconnected system from Liapunov functions for the individual components. A parameter vector appearing in the Liapunov function is selected in a prescribed optimal manner. The Liapunov function so constructed can be used to establish a lower bound on the rate of decay of the system. An example of a ninth-order, non-linear system is included to demonstrate the application to design.

A design methodology for fuzzy controllers and comparison with an optimal PD controller for a nonlinear control system

This paper presents a method for designing fuzzy logic controllers by using the experience of human operators and/or control engineers. This five-step method, involving a fuzzy logic controller, uses a modified fuzzy associative memory (FAM) approach. The Magnetic Ball Suspension Problem (a nonlinear system problem) is used for illustrative purposes. Comparisons with an optimal PD controller in the linearized and nonlinear cases are made with the result that not only is the fuzzy logic controller more robust than the optimal PD controller in the sense of stability, but it also provides better performance for a given performance index.<<ETX>>

Adaptive selection of sensors based on individual performances in a multisensor environment

An important issue in the fusion of multisensor data in the context of scene interpretation and multitarget tracking is the ability to evaluate and characterize sensor performance and establish confidence factors for the individual sensors. This paper presents a methodology for adaptively determining sensor confidence factors based upon sensor performance as measured by the degree of consensus among the various sensors. The fusion process is based upon evidential reasoning and statistical clustering which utilize the sensor confidence factors. The sensor confidence factors are based upon sensor characteristics, environmental conditions, and sensor performance. The individual sensor performance is derived in terms of the fusion results and the degree of consensus between the individual sensor data and the fusion data. Experimental results are presented to illustrate the technique and to demonstrate the effectiveness of the methodology in scene interpretation.

Methodology for designing an optimum fuzzy tracker using genetic algorithms

A methodology for designing an optimum fuzzy tracker is presented. The method uses genetic algorithms and is based upon minimizing a weighted combination of performance criteria. The resulting fuzzy tracker gives a performance that is superior to that of traditional trackers and shows a marked improvement over fuzzy trackers designed without the use of genetic algorithms. An application is provided to illustrate the effectiveness of the methodology.

Reduction of complexity for a robust fuzzy controller

A methodology for the reduction of complexity of fuzzy if-then rules for a robust controller is presented. An analysis of the fuzzy if-then rules is performed by viewing the fuzzy sets in the rules as crisp sets. The knowledge of the analysis is used to reduce the number of variables and the number of fuzzy if-then rules. By applying fuzzy logic to the reduced linguistic if-then rules, a robust controller based on fuzzy if-then rules was reconstructed. The simulation results show that the reconstructed controller is more efficient than and performs as well as the original controller.<<ETX>>

An improved method for designing fuzzy controllers for position control systems

The authors propose a simulation method for determining fuzzy rules in fuzzy control of tracking systems. The method is based upon minimizing the mean squared error for the combination of the rules in the original position control system. The resulting key rules for adjusting the gain yield a fuzzy controller which gives a performance that is superior to traditional controllers. It is shown that vagueness and uncertainty of this tracking system can be handled adequately by using a fuzzy controller.<<ETX>>

Application of the mathematical theory of evidence to the image cueing and image segmentation problem

In electronic vision systems, locating regions of interest-a process referred to as cueing-allows the computing power of the vision system to be focused on small regions rather than the entire scene. The purpose of this paper is to illustrate the ability of a new technique to locate regions that may contain objects of interest. This technique employs the mathematical theory of evidence to combine evidence received from disparate sources. Here the evidence consists of the images obtained from two sources: laser radar range and laser radar amplitude. The mean values of the super pixel gray levels for the two images are calculated and combined based on the Dempster-Shafer rule of combination.

Multiple-class identification algorithm using genetic neural networks

Multiple-class identification algorithm using genetic neural networks is presented. The algorithm uses a feedforward neural network so it is fast. The algorithm uses the Kohonen network to provide an unsupervised learning. The Kohonen network is used with Z-axis normalization. The weight initialization is done by genetic optimization to escape from local minima. The performance of the algorithm is evaluated using a confusion matrix method. The algorithm does not require the number of classes to be known a priori. It also provides a threshold selection method. An example is given to illustrate the application of the algorithm and to evaluate its performance.