Techniques for controlling rotor speed of a wind turbine. One technique includes defining a system model describing resonance dynamics of a wind turbine component, such as a wind turbine tower, where the system model has a nonlinear input term, e.g. a periodic forcing term. A transform is applied to the system model to obtain a transformed model for response oscillation amplitude of the wind turbine component, where the transformed model has a linear input term. A wind turbine model describing dynamics of the wind turbine is then defined, and includes the transformed model. A model-based control algorithm, e.g. model predictive control, is applied using the wind turbine model to determine at least one control output, e.g. generator torque, and the control output is used to control rotor speed of the wind turbine.

A method for constrained control of a wind turbine includes receiving a plurality of operating parameters corresponding to the wind turbine. The plurality of operating parameters includes a wind preview parameter and a plurality of constraint parameters. The method further includes generating a constraint parameter estimate corresponding to a future time instant for at least one constraint parameter of the plurality of constraint parameters based on the plurality of operating parameters and a wind preview model. The method also includes predicting an extreme event corresponding to the at least one constraint parameter based on the constraint parameter estimate. The method includes determining a control parameter value corresponding to a wind turbine control parameter among a plurality of wind turbine control parameters. The method also includes operating the wind turbine using a feedforward control technique based on the control parameter value to circumvent the extreme event.

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 invention provides a hydraulic turbine cavitation acoustic signal identification method based on big data machine learning. According to the method, time sequence clustering based on multiple operating conditions under the multi-output condition of the hydraulic turbine set is performed by utilizing an neural network, characteristic quantities of the hydraulic turbine set under a steady condition in a healthy state is screened; a random forest algorithm is introduced to perform feature screening of multiple measuring points under steady-state operation of the hydraulic turbine set, optimal feature measuring points and optimal feature subsets are extracted, finally a health state prediction model is constructed by using gated recurrent units; whether incipient cavitation is present in the equipment is judged. The present invention can effectively identify the occurrence of incipient cavitation in the hydraulic turbine set, reducing unnecessary shutdown of the equipment and prolonging the service life.

A wind turbine is disclosed which comprises a control system configured to execute at least one ice removal routine which comprises a heating stage of at least one of the blades (3), and a mechanical removal ice stage. A wind turbine removing ice method is also disclosed which comprises a stage wherein the presence of ice is detected on at least one of the blades and, once said presence of ice is detected, comprises a stage wherein at least one ice removal routine is activated which comprises, in turn, a heating stage of at least one of the blades and a mechanical removing ice stage on at least said blade.

A device and a method of controlling blade instabilities of a wind turbine is provided. The method including the following steps: defining at least one preliminary overspeed threshold value; defining a fluttering rotor speed at and above which a predetermined fluttering of at least one of the blades occurs, the fluttering rotor speed is defined as a function of the pitch angle and/or as a function of the wind speed; setting a final overspeed threshold value to be equal to or smaller than a minimum rotor speed of the at least one preliminary overspeed threshold value and the fluttering rotor speed at the actual pitch angle and/or at the actual wind speed; and controlling the rotor speed to not exceed the final overspeed threshold value.

The invention relates to a method for identifying an asymmetrical extreme load which is caused by a gust of wind and acts on a wind power installation, wherein the wind power installation has a rotor having at least three rotor blades; the rotor blades are adjustable in terms of the blade angle thereof; and the rotor by way of the rotor blades thereof sweeps a rotor field; and the method comprises continuous detecting of a blade load for each rotor blade; ascertaining for at least one sector of the rotor field at least one temporal sector load profile from blade loads detected of different rotor blades with the same azimuth position, said sector load profile describing a temporal profile of a load on the rotor blades in the sector and containing a profile extrapolated for a future temporal period, wherein the blade loads are detected or taken into account at successive detection time points which are spaced apart by a partial period in which the rotor rotates further by one rotor blade, so that successive blade loads are detected or taken into account for the respective sector; and checking in terms of expecting an extreme load as a function of the at least one sector load profile.

The disclosure relates to a method for operating a wind turbine wherein the method includes: operating the wind turbine over an operating period in accordance with a control strategy, providing one or more input values representing a load acting on at least one component of the wind turbine and providing uncertainties of the input values, determining, based on the input values, an aggregated load value representing an aggregated load acting on the at least one component of the wind turbine over an aggregation period, determining, based on the uncertainties of the input values, an uncertainty of the aggregated load value, determining a statistical load aggregate from the aggregated load value and the uncertainty of the aggregated load value, adjusting the control strategy based on the statistical load aggregate. The disclosure further relates to a wind turbine and a wind farm configured to perform the above method.

The invention provides a method for controlling a wind turbine, including predicting behaviour of one or more wind turbine components such as a wind turbine tower over a prediction horizon using a wind turbine model that describes dynamics of the one or more wind turbine components or states. The method includes determining behavioural constraints associated with operation of the wind turbine, wherein the behavioural constraints are based on operational parameters of the wind turbine such as operating conditions, e.g. wind speed. The method includes using the predicted behaviour of the one or more wind turbine components in a cost function, and optimising the cost function subject to the determined behavioural constraints to determine at least one control output, such as blade pitch control or generator speed control, for controlling operation of the wind turbine.

Control of a multi-rotor wind turbine system. A local controller is arranged for each wind turbine module and implementing a local model predictive control (MPC) routine. A central controller is arranged to determine a set of operational constraints of the wind turbine modules. Based on a current operational state of the wind turbine module and the set of operational constraints, one or more predicted operational trajectories are calculated and used for controlling the wind turbine module.