Power plant early warning device and method employing multiple prediction model

Abstract

The present invention relates to a power plant early warning device and method which employ a multiple prediction model, and includes: a plurality of prediction models which receive information about the operation states of equipment in a power plant, and output prediction values and the reliabilities of the prediction values; a reliability analysis module which quantizes and analyzes the reliabilities output from the plurality of prediction models to determine the ranks of the plurality of prediction models, and calculates a final prediction value; a comparison module which compares the final prediction value with an actual measurement value, and outputs a residual; and a determination module which analyzes the residual to determine whether there are defects in the operating states of the equipment in the power plant.