Development of a Comprehensive System for Assessing the Generating Equipment Technical Condition Using Neural Network Modeling

Abstract

The article proposes an approach to solving the problem of implementing a neural network model for assessing the technical condition of a hydro generator. A set of universal indicators assessed without the need to shut down the equipment, which characterize its technical state, is proposed. Approaches to the formation of training and validation templates that provide high-quality neural network training are described. Functional evaluation system algorithms are proposed, and universal representation of relations between the objects of the mathematical model for determining the generating equipment remaining service life is formed. The obtained scientific research results open the possibility to apply the proposed system for comprehensively assessing the generating equipment technical condition with using neural network modeling to estimate the current remaining service life of generating equipment on the basis of available diagnostic data.