Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Real-time monitoring method and device for abnormal power performance of wind turbine generator

A technology for real-time monitoring of wind turbines, applied in the monitoring of wind turbines, wind power generation, wind turbines, etc., can solve inaccurate, inability to accurately represent the fluctuation and dispersion of wind power, and the incomplete power performance of wind turbines, etc. problem, to achieve the effect of improving the prediction accuracy

Active Publication Date: 2021-07-13
ZHEJIANG ZHENENG TECHN RES INST
View PDF16 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The wind power curve is an important index parameter to characterize the operating performance of the wind turbine. At present, most of the industry adopts the method of averaging the bien bin slices in the international standard IEC61400-12 to obtain the power curve. This method only represents the test unit during the evaluation period. Therefore, it is incomplete and inaccurate to quantitatively evaluate the power performance of wind turbines based on the wind power curve.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Real-time monitoring method and device for abnormal power performance of wind turbine generator
  • Real-time monitoring method and device for abnormal power performance of wind turbine generator
  • Real-time monitoring method and device for abnormal power performance of wind turbine generator

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] Such as figure 1 As shown, this embodiment proposes a working method of a real-time monitoring device for abnormal power performance of wind turbines as follows:

[0067] By obtaining a large number of historical operating data of wind turbines and historical data of wind measuring towers, based on the above historical operating data, the multi-dimensional feature quantity that characterizes the power generation performance of wind turbines is constructed to the greatest extent;

[0068] Continuously and fully learn historical data through machine learning algorithms, and establish a power regression prediction model of the wind turbine;

[0069] Use the power prediction model to predict the real-time power generation, and calculate the deviation between it and the actual power generation;

[0070] Finally, the principal component analysis method is used to calculate the T of the time-domain statistical characteristics of the power deviation 2 and SPE statistics, by m...

Embodiment 2

[0074] Such as figure 2 As shown, on the basis of Embodiment 1, the working method of the real-time monitoring device for abnormal power performance of the wind turbine is specifically:

[0075] Step 1. Obtain the historical operation data of the wind turbine to be monitored and the historical data of the anemometer tower of the wind farm in the same period through the big data cloud platform; the historical operation data of the wind turbine to be monitored includes temperature, humidity, wind direction of the nacelle, wind speed of the nacelle, and wind speed of the nacelle Location, generator speed, active power and pitch angle; the historical data of the wind tower in the wind farm in the same period includes the wind direction and wind speed of the wind tower.

[0076] Step 2. In order to improve the accuracy and convergence of the subsequent power prediction model, clean the historical operating data of the wind turbine to be monitored, eliminate invalid data, and retai...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a real-time monitoring method for abnormal power performance of a wind turbine generator. The method comprises the following steps: acquiring historical operation data of a to-be-monitored wind turbine generator and historical data of an anemometer tower of a wind power plant in the same period; cleaning historical operation data of the to-be-monitored wind turbine generator, removing invalid data and reserving data of the to-be-monitored wind turbine generator in the normal operation state; and constructing a multi-dimensional feature vector representing the power performance of the wind turbine generator, and dividing the multi-dimensional feature vector into a model learning group and a model verification group. The method has the advantages that quantitative evaluation of the power generation power is more accurate and effective, the operation data of the wind turbine generator and the data at the anemometer tower are considered when the prediction model is established, and the prediction precision of the model is remarkably improved. The purpose of monitoring the power generation performance of the wind turbine generator in real time can be achieved. The power performance change condition of the wind turbine generator can be monitored in real time.

Description

technical field [0001] The invention belongs to the technical field of wind power generation, and in particular relates to a real-time monitoring method and device for abnormal power performance of a wind turbine. Background technique [0002] As a recognized new type of clean energy, wind power is an indispensable and important part of energy structure adjustment and a key link in the process of my country's goal of carbon neutrality and carbon peaking. With the continuous increase of wind power installed capacity and the continuous increase of unit operation time, the industry pays more and more attention to the monitoring of the power generation performance of wind turbines. The performance of wind power generation power directly affects the economic benefits and safety production of wind farms. Therefore, it is of great significance to study a method that can monitor the power generation performance of wind turbines in real time to increase the power generation and prolo...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): F03D17/00F03D80/00G06Q50/06G06F30/20
CPCF03D17/00F03D80/00G06Q50/06G06F30/20Y04S10/50
Inventor 陆超吴伊雯何国栋寿春晖沈洋朱金奎
Owner ZHEJIANG ZHENENG TECHN RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products