Fault diagnosis method and device for wind turbine pitch bearing based on neural network

Abstract

The invention discloses a neural network-based fault diagnosis method and device for pitch bearings of wind power generators. The method includes: measuring the signal strengths of different azimuth angles of blades and different points of sensors, and determining the best measurement azimuth angles of blades and the arrangement of sensor points. Solution, fix the blades at the optimal azimuth angle to collect pitch vibration data, further process the collected vibration data into a data set, build a neural network model, use the collected data set to train the network, and deploy the trained network To the PLC for real-time dynamic monitoring of the fan; the device includes a vibration sensor, a data acquisition card and an editable logic controller (PLC). The invention applies the neural network algorithm to the fault diagnosis of the pitch bearing of the wind power generator, uses the historical vibration data to train the network, and then utilizes the trained network to perform fault diagnosis, thereby realizing fast, real-time and accurate monitoring of the health status of the pitch bearing.

Description

technical field [0001] The invention relates to the technical field of wind power generation and bearing fault diagnosis, in particular to a method and device for diagnosing faults of pitch bearings of wind turbines based on neural networks. Background technique [0002] During the operation of the wind turbine, the pitch bearing is an important supporting component for the adjustment angle of the wind turbine blade. The pitch bearing of wind turbine is an important part connecting the hub and blade of the wind turbine, and it is responsible for transmitting the load. When the pitch bearing of the wind turbine is in the working state, when the various components inside the pitch bearing are subjected to the extrusion force or the components wear each other, the working state of the pitch bearing is constantly changing, and the working state of this change will be largely affected. Causes the pitch bearing to fail. The pitch bearing of wind turbine has high precision, high ...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the shortcomings of the existing technology, in the fault diagnosis process, overcome the shortcomings of high requirements for prior knowledge, low analysis efficiency of a large amount of time-domain data, and low signal-to-noise ratio in the process of pitch change, and realize the goal of improving the accuracy of fault diagnosis and analysis. Purpose, the present invention adopts following technical scheme:

Images