Fan health state evaluation method based on GRU neural network

Abstract

The invention discloses a fan health state evaluation method based on a GRU neural network, and the method comprises the following steps: completing the division of fan operation conditions based on aCLIQUE clustering method; selecting characteristic parameters representing the operation conditions of important parts of the fan as an evaluation index set; for each operation condition subspace, establishing a GRU neural network-based fan health state evaluation model to predict the change condition of each evaluation index parameter in real time; determining input parameters of the evaluationmodel by adopting a feature selection method based on partial mutual information; and performing weighted analysis on the prediction error through a variable weight evaluation method to obtain a fan operation health degree index, and evaluating the fan operation health state according to the health degree index. Compared with an evaluation method mostly concentrated on a certain key component at present, the method can evaluate the operation health state of the fan more comprehensively and accurately, and can provide powerful support for making a maintenance plan of the wind turbine generator,so that the operation and maintenance cost of the wind turbine generator is reduced.

Description

technical field [0001] The invention relates to the technical field of wind power, in particular to a method for evaluating the health state of a wind turbine based on a GRU neural network. Background technique [0002] In recent years, my country's wind power industry has developed rapidly. While the installed capacity of wind turbines has continued to grow, the installed locations have also become more remote. Wind turbines operate under harsh working conditions all year round, and the operation and maintenance costs due to fan failures remain high every year. Therefore, it is of great significance to carry out the health status assessment of wind turbines and pre-judge the health status and development trend of wind turbines based on the assessment results to ensure the stable and reliable operation of wind turbines and wind farms, thereby reducing the operation and maintenance costs of wind turbines. [0003] Since the actual operating state of wind turbines will change...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for evaluating the health status of wind turbines based on the GRU neural network to solve the problem that the existing technology cannot accurately and effectively realize the evaluation of the health status and development trend of equipment operation, and to realize real-time monitoring of the health status of wind turbine operation and evaluation, which can provide strong support for the staff to formulate maintenance plans for wind turbines, thereby reducing the operation and maintenance costs of wind turbines

Images