Integrated learning based mountain wind generation set behavior predicating model

Abstract

The invention discloses an integrated learning based mountain wind generation set behavior predicating model which comprises the following steps: 1, adopting a self-adaptive threshold value method todetermine a wind speed power sub-interval data density threshold value to clear abnormal data; 2, defining a sample matrix, and adopting a self-adaptive comprehensive over-sampling method to generatea new sample matrix for uniformly distributing different wind conditions; 3, performing Hilbert-Huang transform on data generated in the step 2 to obtain decomposition amount of input amount of the mountain wind generator set model; 4, according to the data of the step 4, determining input and output of the mountain wind generator set model, selecting a component learner and adopting a fusion strategy of integrated learning of stacking, and training and integrating to obtain the mountain wind generation set behavior predicating model; 5, adopting a grid search method to determine optimal parameters of the model; and 6, operating and testing the mountain wind generation set behavior predicating model. The integrated learning based mountain wind generation set behavior predicating model canprovide service for wind generation set predicating control, so that maintenance staff can normally operate a maintaining unit more efficiently better.

Description

technical field [0001] The invention relates to the modeling field of designing wind turbines, in particular to a behavior prediction model of mountain wind turbines based on integrated learning. Background technique [0002] With the increasingly prominent energy problems, wind energy, as a renewable energy source, has the characteristics of cleanness and environmental protection, and has attracted the attention of countries all over the world. At present, because inland mountainous areas also have extremely rich wind energy resources, the utilization of wind energy resources has become a new issue of concern to many scholars. However, compared with traditional offshore wind farms, the wind in mountainous wind farms is affected by the terrain and has greater wind fluctuations. Factors such as wind speed, wind direction, 5-second yaw, and pitch angle will affect the model of mountain wind turbines. accuracy. [0003] As the number of installed wind turbines in mountainous ...

AI Technical Summary

Problems solved by technology

[0004] (1) The mechanism model does not consider the actual operating environment of mountain wind turbines, and the accuracy of the model is low;

[0005] (2) Due to the large wind fluctuations in mountainous areas, the state quantities of wind turbines will also change drastically, and the state quantities of wind turbines at different frequencies will affect the output of the wind turbine model, thereby affecting the prediction accuracy of the model;

[0006] (3) The distribution of data is uneven under different wind conditions, and the data under extreme wind conditions is less, the model trained by the majority data is prone to overfitting, while the model trained by the minority data will be underfitting Phenomenon

Images