In this paper, we discuss a new method for extracting fuzzy rules directly from numerical input-output data for pattern classification. Fuzzy rules with variable fuzzy regions are defined by activation hyperboxes which show the existence region of data for a class and inhibition hyperboxes which inhibit the existence of data for that class. These rules are extracted from numerical data by recursively resolving overlaps between two classes. Then, optimal input variables for the rules are determined using the number of extracted rules as a criterion. The method is compared with neural networks using the Fisher iris data and a license plate recognition system for various examples.<>

A new method for evaluating energy and capacity losses on a distribution feeder in a rigorous manner is presented. Typical daily load shapes are integrated with a load flow procedure to produce an energy model. The performance of a feeder is analyzed by a three-phase load flow program capable of modeling the different load component characteristics as well as imbalance in loading and system configuration. The system configuration can be any combination of single, two and three-phase circuits as required, up to the capacity of the program. The effects of neutral and ground return paths are included. The load flow program utilitizes a new approach to load modeling that recognizes the key load components and their voltage sensitive characteristics.

Power system voltage stability is characterized as being capable of maintaining load voltage magnitudes within specified operating limits under steady state conditions. In this paper, the first order delay model of a load admittance change is introduced. Then, using this model, a set of linearized dynamic equations is derived and stability conditions are obtained. An earlier result in the literature is shown to agree with that in this paper. The stability conditions are tested and verified in a 2-load, 2- power source system and a 13-node, 4-power source system.