The invention relates to a method for monitoring yawing fault events of a yaw system of a wind turbine. The yaw system comprises one or more actuators for driving the yaw system and a holding system to resist yaw rotation. The yaw system is arranged to provide yaw rotation in response to a yaw control signal. According to the method, the monitored yaw angle is compared with the yaw control signal, and based on the comparison, a correlation between a monitored change in the yaw angle and the yaw control signal is determined. A yawing fault event is determined dependent on the determined correlation.

A method and system for early fault detection in a wind turbine generator (7) is provided. A vibration signal of noise produced by the generator is received. A periodic signal component related to the number of rotor bars of a rotor (11) of the generator (7) is identified in the vibration signal, and a potential fault in the stator of the generator is identified based at least in part on a change in characteristic of the periodic signal component over time.

Techniques are provided for monitoring blades of a wind turbine by actively promoting blade vibrations by imposing a pitch actuation signal. A method of operating a wind turbine is disclosed where for each blade of a wind turbine, vibrations of the blade are actively promoted by imposing a pitch actuation signal to the pitch actuator, and at least one parameter relating to the blade vibration is determined.

This application discloses a method, device, and apparatus for maintaining a wind turbine generator plant, which relates to the field of wind power generation. The method includes determining a failure of the wind turbine generator plant when the wind turbine generator plant enters a shutdown maintenance mode; determining a maintenance wind speed corresponding to the failure; adjusting one of blades of the wind turbine generator plant to reach a predetermined azimuth angle and lock an impeller of the wind turbine generator plant to maintain the wind turbine generator plant in a case where the failure belongs to a first type of failure and a real-time wind speed obtained is less than or equal to the maintenance wind speed corresponding to the failure, the first type of failure comprising a failure that requires to lock the impeller for maintenance and the predetermined azimuth angle being a different integral multiple of 30.

One example includes a wind turbine yaw control fault detection system. The system includes current monitors that are each configured to monitor a current amplitude of a respective one of a plurality of yaw motors of a wind turbine and to generate a current signal that is indicative of the respective current amplitude. The system further includes a processor to compare the current amplitude of each of the yaw motors relative to each other and relative to at least one threshold based on the current signal from each of the current monitors. The fault detection algorithm further determines a fault condition associated with at least one yaw mechanical drive component of the wind turbine based on the comparison of the current amplitude of each of the yaw motors relative to each other and relative to at least one threshold.

The invention provides a method and a device for fault diagnosis of a yaw system in a wind turbine, and relates to the technical field of wind turbines. The method comprises the following steps: acquiring monitoring data collected in a yaw system, inputting the monitoring data into a yaw fault diagnosis model, and outputting a fault diagnosis result, wherein the fault diagnosis model is obtained by training known fault diagnosis results and corresponding monitoring data, and the fault diagnosis result comprises at least one of the following: the position of a yaw sensor is shifted, the yaw sensor is damaged, the yaw contactor is stuck, the hardware of a yaw motor/reducer is damaged, and the yaw motor is braked, In the working process, the monitoring data collected by the yaw system can be input into the yaw fault diagnosis model in real time, and the yaw fault diagnosis model can be used to determine whether the yaw system has a fault and the specific fault diagnosis results when the fault occurs. In this way, the operation and maintenance personnel can be prevented from going to the aircraft seat for inspection, and the fault diagnosis efficiency of the yaw system can be improved.

Example systems and methods comprise receiving sensor measurements including time data from one or more wind turbines over time, aligning time domain data of the sensor measurements of a particular wind turbine with a rotation speed of the particular wind turbine, the particular wind turbine being at least one of the one or more wind turbines, transforming the aligned time domain data to obtain a cepstrum data, identifying one or more quefrency components of the cepstrum data that correspond to periodicities of interest, classifying at least one of the one or more quefrency components with future failure of at least one component of the particular wind turbine, and providing an alert to a user based on the classification to alert the user of a predicted failure of the particular wind turbine.

Techniques for operating a wind farm include setting an area of interest, a forecast interval, and a maximum lag time for using mesoscale forecasts. Mesoscale forecasts are collected for a training time interval TT at model grid locations. TT is at least ten times the maximum lag time. Fine-scale wind measurements are collected in the area during TT. Selected parameters of the mesoscale forecasts, and coefficients of an evolving ML forecast model are determined based on the mesoscale forecasts and the fine-scale wind measurements during the TT ending at the current time. Then, the coefficients and the mesoscale forecast for the selected parameters during the lag time produce a forecast wind at the wind turbines during the forecast interval. Operation of the wind farm is based on the forecast wind.