Web Based Automatic Classification of Power Quality Disturbances Using the S-transform and a Rule Based Expert System

摘要

The detection and classification of power quality problems are important issues for electronic systems. This paper deals with a new approach for the automatic detection and classification of power quality disturbances through the Internet by combining the S-transf'orm, a rule based expert system and a MATLAB web server. The S-transform is used to obtain the time frequency characteristics of power quality events under noisy conditions, and a set of features is extracted for pattern classification of power quality disturbances. A rule-based expert system is also developed in which the system classifies various power quality disturbances. Finally, a MATLAB web server is used to integrate the graphical and computational process with remote access through the internet. Our test results illustrate the effectiveness and robustness of the proposed method for automatic power quality disturbance classification through the Internet.