Wind generation set impeller imbalance detection method based on stator current envelope spectrum

Abstract

The invention discloses a wind generation set impeller imbalance detection method based on a stator current envelope spectrum. The wind generation set impeller imbalance detection method comprises thefollowing steps that a stator current signal is collected; the collected electric generator stator current signal is processed; a sample database is constructed; a neural network model is built; a detection database is constructed; sample data are transmitted, and recognition judgment is conducted; and results are output. Through the convolutional neural network model and a Hilbert demodulation method, stator current envelope spectrum data extraction and fault feature learning are conducted in the operating of a wind power unit, fault features can be adaptively captured from the signal, uncertainty interference caused by environmental noise, fluctuations and manual judgment errors is avoided, and high recognition accuracy is achieved; and meanwhile, an additional sensor does not need to be mounted for data acquisition, thus the testing cost is lowered, data acquisition is little in environmental impact and high in accuracy, troubles caused by natural environment factors to model judgment can be effectively avoided, and the wind generation set impeller imbalance detection method is suitable for the conditions such as the complex operating situation of the wind power unit.

Description

technical field [0001] The invention relates to the field of wind turbines, in particular to a method for detecting the unbalance of a wind turbine impeller based on a stator current envelope spectrum. Background technique [0002] Wind turbines have been operating in the field for a long time, and the outdoor operating environment is usually relatively harsh. Therefore, this environment has caused a high failure rate of wind turbines, and the reasons for the failures are various. For example, the blades will cause the mass imbalance of the impeller due to wind and sand, icing and uneven mass distribution. In addition, the blades will also have cracks due to fatigue stress during long-term operation, resulting in the problem of aerodynamic imbalance of the impeller. [0003] In recent years, my country's wind power industry has developed rapidly, and the grid-connected capacity of wind turbines has continued to increase. In particular, the planning of offshore wind turbines ...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome that in the prior art, the signal of the unbalance detection and analysis of the impeller of the wind turbine is very easily disturbed by noise, and the fault information is easily submerged to cause judgment errors, and the stability and detection accuracy of the detection results are seriously affected by human factors. To solve the technical problems that easily lead to inaccurate detection, a wind turbine impeller unbalance detection method based on the stator current envelope spectrum is provided. In the case of complex operating conditions of the wind turbine, serious environmental noise interference, and high data acquisition costs, the method Methods Through the convolutional neural network model, the Hilbert demodulation method is used to extract the stator current envelope spectrum data and learn the fault characteristics during the operation of the wind turbine, which can adaptively capture the fault characteristics from the signal and avoid the environment Uncertainty interference caused by noise, fluctuation and human judgment error has high recognition accuracy and speed; at the same time, data collection does not need to install additional sensors, which greatly reduces the test cost, and the accuracy of data collection is affected by the environment. High, can effectively avoid natural environmental factors from causing troubles to model judgment

Images