Data modeling based wearing monitoring and early-warning method for variable pitch bearing of wind turbine

Abstract

The invention relates to a data modeling based wearing monitoring and early-warning method for a variable pitch bearing of a wind turbine. The method includes the following steps: (1) data collection;(2) data pre-processing; (3) sample marking; (4) feature construction; (5) model construction; (6) algorithm verification; (7) model deployment. The method of the invention is high in effectiveness and accuracy, realizes a wearing monitoring and early-warning function for a variable pitch bearing of a wind turbine through modeling and predication by means of common sensor data, such as wind speed, power, rotational speed, pitch angle and pitch motor current, recorded by an SCADA system of the wind turbine, and has the characteristics of low cost, high efficiency, strong interpretation and thelike.

Description

technical field [0001] The invention relates to a data modeling-based method for monitoring and early warning of wind turbine pitch bearing wear. Background technique [0002] Pitch bearings are mainly used in variable pitch wind turbines, and are installed between the blades and the hub in the form of inner and outer rings. The pitch control system gives action instructions to the pitch motor according to the change in the speed and torque of the wind rotor caused by the wind speed, and converts it into a suitable speed and torque through the pitch variable speed gearbox to drive the relative angle of the inner and outer rings of the pitch bearing to adjust the blade. The pitch angle controls the efficiency of the blades to absorb wind energy, so that the wind turbine can maintain a stable power output above the rated wind speed. [0003] The pitch bearing is a load-bearing component with relatively complex forces in the wind turbine, and it has been working for a long tim...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the existing pitch bearing wear fault monitoring methods and the high cost of special monitoring equipment, the present invention uses common sensors such as wind speed, power, rotational speed, pitch angle, and pitch motor current recorded by the SCADA system of the wind turbine Data, providing a data modeling method for monitoring the wear of pitch bearings. After a large amount of historical data research of the unit, the effectiveness and accuracy of this method have been verified, and it has the characteristics of low cost, high efficiency, and strong interpretability.

Images