Method for evaluating health state of wind turbine generator based on multi-dimensional SCADA data

Abstract

The invention discloses a method for evaluating the health state of a wind turbine generator based on multi-dimensional SCADA data, and aims at solving the problem of incomplete evaluation caused by single parameter used for evaluating the health state of the wind turbine generator in the traditional method, and extracting a plurality of characteristic parameters representing unit degradation information. According to the method, mutual information between parameters in the SCADA system is calculated through an empirical Copula function, and the magnitude of the mutual information can reflectthe degree of influence of the parameters on the performance of the fan. The parameters with large mutual information values are used as health assessment objects, and compared with a traditional method that a wind power curve is used as an assessment object, assessment of the health state of the wind turbine generator is more comprehensive and accurate. A method for dividing working conditions according to wind speed intervals is introduced into the model. And the method is combined with kernel principal component analysis to establish a wind turbine generator health state evaluation model based on adaptive KPCA. The diagnosis result shows that the wind turbine generator health evaluation result of the model is superior to the evaluation result of a traditional method.

Description

technical field [0001] The invention is a method applied in the field of health assessment of wind turbines, aiming at the harsh environment of wind turbines and high repair and maintenance costs, real-time evaluation and prediction can reduce maintenance costs and improve the use efficiency of wind turbines; it belongs to prediction and health management technology field. Background technique [0002] The high reliability of wind turbines is the fundamental requirement of wind power generation. However, the harsh operating environments such as humidity, corrosion, wind and sand, vibration, extreme cold and extreme heat, imperfect operation control strategies and design and installation defects lead to low overall reliability of wind power generation devices. Low. Low reliability leads to high operation and maintenance costs of wind farms. According to statistics, the operation and maintenance costs of offshore wind farms account for 30% to 35% of power generation costs, of...

AI Technical Summary

Problems solved by technology

[0008] Aiming at the problem that the single parameter used in the state evaluation method of wind turbines under complex working conditions leads to incomplete evaluation at the present stage, the present invention proposes a new wind turbine degradation evaluation method based on multi-dimensional SCADA parameters

This method is more accurate than traditional wind turbine health assessment methods

Images