Hydroelectric generating set degradation prediction method and system

Abstract

The embodiment of the invention provides a hydroelectric generating set degradation prediction method and system, and the method comprises the steps of completing the training of health state models with different swing degrees according to the collected working condition parameters and swing degree data of a hydroelectric generating set under a steady-state working condition; calculating swing degree degradation sequences of different unit components, and fusing the swing degree degradation sequences of the different unit components to obtain a fused degradation sequence; and predicting the fusion swing degradation sequence to obtain a degradation trend. According to the hydroelectric generating set degradation prediction method and system provided by the embodiment of the invention, thehealth state models are established for the swing degrees of the different components respectively, and the fusion degradation degrees of the different components are obtained through calculation, sothat the states of the different components can be reflected, and the overall degradation degree of the set can be comprehensively reflected; and the prediction precision of the model is higher by using the advantage of the gating cycle unit neural network in time sequence data feature extraction and the stronger learning ability of the deep neural network than a shallow network.

Description

technical field [0001] The invention relates to the technical field of operation safety maintenance of hydroelectric units, in particular to a method and system for predicting degradation of hydroelectric units. Background technique [0002] Hydropower units play an important role in power generation, frequency regulation, peak shaving and valley filling. As the running time increases, the unit will gradually deteriorate and even fail. Obtaining the degradation sequence of the hydropower unit through the health state model, and predicting the degradation sequence of the hydropower unit to obtain the deterioration trend will help to improve the understanding of the operation and degradation rules of the unit equipment, improve the management and operation and maintenance level of the power plant equipment, and thus generate huge benefits. The economic, social and environmental benefits have important theoretical significance and engineering application value. [0003] Exist...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present invention provides a method and system for predicting the deterioration of hydroelectric units, which are used to solve the defects of simple model structure and low prediction accuracy in existing methods such as artificial neural network or gray prediction for predicting the deterioration trend of hydroelectric units

Images