Disclosed are a method and apparatus for detecting a fault, and a method and apparatus for training a model. The method includes: acquiring characteristic data and actual temperature of a first wind turbine among n wind turbines, wherein the characteristic data of the first wind turbine is intended to characterize a working state of the first wind turbine, and n is an integer greater than 1; acquiring a prediction temperature set by inputting the characteristic data of the first wind turbine into a temperature prediction model corresponding to each of the n wind turbines; and detecting, based on the predicted temperature set and the actual temperature of the first wind turbine, whether the first wind turbine encounters a fault. Compared with the related art which depends on the working experience of the staff, the technical solution according to the embodiments of the present disclosure can more accurately detect whether a wind turbine encounters a fault, and provide early warning in time, so as to reduce the failure rate of the wind turbine.

The present disclosure relates to a wind turbine comprising a wind turbine rotor with a plurality of blades, a generator operatively coupled to the wind turbine rotor for generating electrical power and a power electronic converter for converting electrical power generated by the generator to a converted AC power of predetermined frequency and voltage. The wind turbine further comprises a wind turbine controller configured to receive values of one or more operational parameters of the wind turbine from one or more sensors and further configured to temporarily increase a speed of the generator to above a nominal generator speed if the values of the operational parameters satisfy a potential trip criterion. The present disclosure also relates to methods for controlling wind turbines.

The system and method of the present disclosure is configured to monitor changes associated with an air gap by: (1) receiving one or more sensor signals from one or more sensors that are indicative of changes associated with the air gap; and (2) comparing the changes associated with the air gap to certain thresholds to determine if the air gap is in need of attention. The system includes at least one proximity sensor arranged adjacent to the air gap, to monitor the air gap, and a controller. The controller is configured to receive the sensor signal(s) indicative of the changes associated with the air gap. The controller also is configured to compare the changes associated with the air gap to one or more air gap thresholds, and to implement a control action based on this comparison.

The present invention relates to a method of controlling an electro-thermal heating system in a wind turbine blade, comprising measuring a supply voltage to the electro-thermal heating system, determining a duration of a variable time based enforced off period based on the measured supply voltage, and inserting the variable time based enforced off period between subsequent switching duty cycles that controls the electro-thermal heating system. The present invention also relates to a wind turbine that comprises one or more wind turbine blades wherein each wind turbine blade comprises an electro-thermal heating system and a processor adapted to perform the method.

A system and method are provided for controlling a wind turbine. Accordingly, a controller of the wind turbine determines a thermal gradient of the tower due to solar heating. The controller also determines a displacement of a reference point of the wind turbine from a nominal position resulting from a thermal expansion of a portion of the tower. The displacement includes a displacement magnitude and a displacement direction. The displacement direction is in a radial direction opposite of a maximal peak of the thermal gradient. Additionally, the controller determines a correction factor corresponding to the displacement and a setpoint for a component of the wind turbine based, at least in part, on the correction factor. Finally, an operating state of the wind turbine is established based, at least in part, on the setpoint.

A method for operating a wind turbine is disclosed, wherein said wind turbine comprises a rotor having at least one rotor blade with a rotor blade surface and an icing detection device for detecting an icing condition for the rotor blade and/or for detecting the presence of icing on the rotor blade. Further, a controller configured for controlling a rotational speed of the rotor can be provided. The method comprises the steps of monitoring, via the controller and/or via the icing detection device, whether an icing condition for the rotor blade is present and/or if icing on the surface of the wind turbine is present, thus, that ice has been generated on the surface. If an icing condition is detected, or if it is detected that ice has generated on the surface of the rotor blade, the wind turbine is operated further according to a de-rated icing-mode having a reduced rotational speed, in particular while maintaining a generation of electrical energy by a generator of the wind turbine.

A heating deicing system for a blade and a control method thereof, a blade and a wind turbine are provided according to the present disclosure. The heating deicing system for the blade includes an isolating device, which is arranged in a blade cavity and divides a part of the blade cavity close to a leading edge of the blade into multiple sub-cavities sequentially distributed along a length direction of the blade, and each of the sub-cavities is provided with a heating device. The heating deicing system for the blade includes a controller, which is configured to separately control opening and closing of each set of multiple sets of heating devices in each sub-cavity to heat the multiple sub-cavities in response to a blade deicing instruction.

A method for operating a generator of a wind turbine includes generating, via a controller, a time series of a plurality of operating signals of the generator. The method also includes applying at least one algorithm to the time series of the plurality of operating signals of the generator to generate a processed time series of the of the plurality of operating signals of the generator. Moreover, the method includes identifying, via the controller, patterns in the processed time series of the plurality of operating signals of the generator to identify one or more of at least one slip event occurring in the slip coupling or a surface health of the slip coupling. Further, the method includes implementing, via the controller, a control action when the at least one slip event occurring in the slip coupling is identified or the surface health of the slip coupling is indicative of degradation in the slip coupling.

An inspection method according to the present disclosure includes a step of mounting an ultrasonic probe, a step of mounting a pulser receiver, a step of causing the ultrasonic probe to transmit ultrasonic waves, a step of causing the ultrasonic probe to receive a reflected wave of the ultrasonic waves reflected by the wind turbine blade, a step of causing the pulser receiver to acquire reflected-wave data, a step of causing the pulser receiver to wirelessly transmit the reflected-wave data, a step of causing at least one of antennas to receive the wirelessly transmitted reflected-wave data, and a step of causing an information processing device electrically connected to the at least two antennas to perform information processing on the reflected-wave data.

The present disclosure relates to methods (300) to determine a duration of a period for warming up of a power converter (20) of a wind turbine (1). The method (300) comprises determining (301) a first indicator that is indicative of a time that the power converter (20) has been inactive. Further, the method (300) comprises determining (302) the period for warming up at least partially based on the first indicator. A power converter assembly is also disclosed.