Substation data analysis with rough sets

The paper describes how a computational intelligence technique is applied to extract useful information from the large amount of data available in a substation control system. The technique groups objects of interest into classes that are indiscernible with respect to some or all of their features. It enhances the content of information by reducing the redundant. arid superfluous data in the database. The reduction in the data dimension not only improves the performance of diagnosis but also helps speed-up the knowledge acquisition process.