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

Wind turbine generator bearing early warning method based on feature fusion

A generator bearing and feature fusion technology, applied in the testing of mechanical components, testing of machine/structural components, instruments, etc., can solve problems such as inaccurate fault judgment, weak generalization ability, and single fault identification method

Active Publication Date: 2021-02-02
ZHEJIANG WINDEY
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007]The present invention mainly solves the technical problems of the original technical solution, such as single fault identification method, weak generalization ability, and inaccurate fault judgment, and provides a feature fusion-based The wind turbine generator bearing early warning method uses the vibration data of the CMS condition monitoring system to analyze the failure mechanism of the generator bearing from the time domain characteristics, trend characteristics, frequency domain characteristics and envelope characteristics, and integrates the four characteristics to effectively extract The eigenvector representing the operating state of the generator is obtained, which greatly improves the sensitivity of the algorithm to identify the generator bearing fault of the unit. The limit gradient lifting method is used to realize the fault early warning, which has a higher accuracy rate.

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
  • Wind turbine generator bearing early warning method based on feature fusion
  • Wind turbine generator bearing early warning method based on feature fusion
  • Wind turbine generator bearing early warning method based on feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0086] Embodiment: A kind of wind turbine generator bearing early warning method based on feature fusion in this embodiment, such as figure 1 shown, including the following steps

[0087] Step 1: Feature Fusion. Preprocess the CMS data, screen the data of the stable operation of the generator, and eliminate the low-precision and unstable data to obtain the effective data of the unit operation. From the four dimensions of vibration trend, time-domain features, frequency-domain features, and envelope features, the characteristics of the generator's operating state can be characterized. A total of 25 features form a feature vector for fusion. Mark the eigenvectors according to the normal, generator bearing damage, and generator bearing loose running circles;

[0088] Step 2: Fault warning. The Extreme Gradient Boosting (XGBoost) algorithm is used to train the generator bearing case data to obtain the XGBoost early warning model. For the data collected online, the feature fusi...

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 discloses a wind turbine generator bearing early warning method based on feature fusion. The method comprises the following steps: preprocessing CMS data; obtaining a time domain characteristic index; obtaining trend characteristic indexes; obtaining a frequency domain characteristic index; obtaining envelope characteristic indexes; carrying out feature fusion; training an extreme gradient lifting model; training a function set in the classification model, and constructing a learning objective function of XGBoost; and calculating the learning objective function of the XGBoost. According to the technical scheme, the vibration data of the CMS state monitoring system is utilized, the generator bearing fault mechanism is analyzed from the time domain feature, the trend feature, the frequency domain feature and the envelope feature, the four features are fused, the feature vector representing the running state of the generator is effectively extracted, the method greatly improves the recognition sensitivity of the algorithm for the generator set bearing fault, achieves the fault early warning through employing a limit gradient lifting method, and is higher in accuracy.

Description

technical field [0001] The invention relates to the technical field of wind power generation, in particular to a feature fusion-based early warning method for generator bearings of wind turbines. Background technique [0002] According to data, in recent years, wind energy has become more and more prominent in my country's energy structure because of its clean and renewable characteristics. With the increase in the number of grid-connected units, a large number of units that have been in operation for 2-5 years have a greatly increased probability of failure due to the loss of continuous operation. The operating environment of generator bearings is complex and the working conditions are changeable, and they are prone to damage, looseness, etc. Faults, high maintenance costs and long downtime, resulting in huge economic losses, are a major problem in the operation and maintenance of wind turbines. Therefore, monitoring and early warning of generator operating status is the k...

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
IPC IPC(8): G01M13/045
CPCG01M13/045Y02E10/72
Inventor 陈棋朱朋成刘伟江王欣柴问奇郭鹏飞
Owner ZHEJIANG WINDEY
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