A Method for Assessing the Health Status of Wind Turbine Based on Gru Neural Network

Abstract

The invention discloses a method for assessing the health state of a wind turbine based on a GRU neural network, which includes the following steps: based on the CLIQUE clustering method, the division of the operating conditions of the wind turbine is completed; the characteristic parameters representing the operation status of important components of the wind turbine are selected as an evaluation index set; For each operating condition subspace, a wind turbine health status assessment model based on GRU neural network is established to predict the changes of each assessment index parameter in real time; the input parameters of the assessment model are determined by the feature selection method based on partial mutual information; The prediction error is weighted and analyzed to obtain the wind turbine operation health index, and the wind turbine operation health status is evaluated according to the health index. Compared with the current evaluation methods that mostly focus on a certain key component, the present invention can more comprehensively and accurately evaluate the operating health status of wind turbines, and can provide strong support for formulating maintenance plans for wind turbines, thereby reducing the operation and maintenance costs of wind turbines.

Description

Technical field [0001] The present invention relates to the field of wind power technology, and more particularly to a fan health status assessment method based on a GRU neural network. Background technique [0002] In recent years, my country's wind power industry has developed rapidly, while the installed location is also more far away while the installed capacity of the wind turbine is continuous. The wind turbines operate in harsh conditions all year round, and every year, the operation and maintenance costs caused by fan failure are high. Therefore, the health status assessment of the wind turbine is carried out. According to the assessment results, the health status and development trend of the fan is pre-determined, and the stability, reliable operation of the fan, wind farm, there is important to reduce fan operation and maintenance costs. [0003] Since the actual operating state of the wind turbine changes with the change of operation conditions, the traditional method ...

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