An example method comprises receiving historical sensor data from sensors of components of wind turbines, training a set of models to predict faults for each component using the historical sensor data, each model of a set having different observation time windows and lead time windows, evaluating each model of a set using standardized metrics, comparing evaluations of each model of a set to select a model with preferred lead time and accuracy, receive current sensor data from the sensors of the components, apply the selected model(s) to the current sensor data to generate a component failure prediction, compare the component failure prediction to a threshold, and generate an alert and report based on the comparison to the threshold.

A simulation evaluation model of a high voltage ride through capability includes a wind turbine system aerodynamic model, a torque control model, a converter model, and a high voltage fault generating device model connected in sequence; the wind turbine system aerodynamic model is configured to calculate an airflow input power; the torque control model is configured to calculate a rotor electromagnetic torque according to the airflow input power; the high voltage fault generating device model is configured to simulate a high voltage fault and output a predetermined voltage on a low voltage side of a transformer; and the converter model is configured to calculate a stator reactive current, an active power and a reactive power of the wind turbine system during the high voltage fault according to the airflow input power, the rotor electromagnetic torque and the predetermined voltage on the low voltage side of the transformer.

A wind field dynamic downscaling method based on aerodynamic parameters of simplified terrain, the method comprises steps of: numerically simulating the simplified terrain based on computational fluid dynamics to obtain the aerodynamic parameters of the simplified terrain; redistributing the wind speed at the corner point of a mesoscale grid within the downscaling grid based on terrain elevation data, land use type data and the aerodynamic parameters, to implement the wind field downscaling calculation. It is based on the aerodynamic parameters of the two-dimensional simplified terrain, and a new wind field dynamic downscaling scheme is designated by adding the high-resolution terrain elevation data and the land use type data.

Disclosed are a virtual power plant operation risk analysis method and a device. The method comprises: establishing a multi-state model of wind turbine output, analyzing influence of wind speed on wind turbine failure rate based on the multi-state model of wind turbine output, and establishing a wind turbine failure model considering wind turbine time-varying failure rate; establishing a multi-state model of wind turbine output considering the wind speed and the wind turbine time-varying failure rate by an improved general generating function method based on the multi-state model of wind turbine output and the wind turbine failure model considering the wind turbine time-varying failure rate; establishing a multi-state output model of virtual power plant based on the multi-state model of wind turbine output considering wind speed and wind turbine time-varying failure rate; and calculating operation risk indicators of virtual power plant through the multi-state output model of virtual power plant.

The present invention relates to a method of determining the wind speed in the plane of a rotor (PR) of a wind turbine (1), by measuring (MES2) the rotational speed of the rotor, the angle of the blades and the generated power. The method according to the invention uses a wind turbine model (MOD) constructed from wind speed measurements (LID), and by use of measurement clustering (GRO) and regressions (REG).

A benchmark state space model construction method for an offshore wind turbine is provided. The benchmark state space model is constructed by the modal information of the first several orders of the high-order finite element model of the offshore wind turbine. Since the benchmark state space model is only established by the first several orders of the high-order finite element model, the time domain analysis of the offshore wind turbine using the benchmark state space model instead of the high-order finite element model can improve the calculation efficiency and reduce the calculation cost. The benchmark state space model construction method solves the problem of low computational efficiency and high computational cost of time domain analysis of offshore wind turbines using high-order finite element models due to the excessive number of high-order finite element units in existing technologies.

Correlated sets of historical meteorological data and terrain data are obtained for at least one geographical area. A data model is derived based on the basis of the correlated sets, by training the data model. The trained data model is adapted to identify coherence between meteorological data and terrain data relating to the same geographical area. Meteorological data and terrain data related to the renewable energy site are fed to the trained data model, the terrain data having a higher resolution than the meteorological data. Using the trained model, meteorological data related to the renewable energy site with increased resolution is estimated by downscaling the meteorological data. The estimated meteorological data with increased resolution for the renewable energy site is then used for planning a layout of the renewable energy site.

A method and an apparatus for arranging wind turbines based on a rapid assessment fluid model and a wake model. The method for arranging wind turbines includes: calculating, via a rapid assessment fluid model and based on an anemometry data of a predetermined area in a wind farm, a flow field data of the predetermined area in the wind farm; selecting a first wind-speed area from the predetermined area in the wind farm based on at least one of an occupied area limitation, a gradient limitation, a turbulence limitation or a wind speed limitation; and calculating, via a differential evolution algorithm, coordinates for arranging wind turbines that make annual power production of each wind turbine in the first wind-speed area highest. The annual power production of each wind turbine in the first wind-speed area is calculated based on the flow field data and the wake model.

A method and a device for calculating a power generation of a wind farm is provided. The method includes: determining whether a terrain complexity of a wind farm field exceeds a predetermined complexity; determining a representativeness of anemometer tower data in the wind farm field in a case where the terrain complexity exceeds the predetermined complexity; performing a mesoscale numerical simulation of a meteorological variable in the wind farm field in a case where the anemometer tower data is unrepresentative; extracting mesoscale numerical simulation data as virtual anemometer tower data; and calculating the power generation of the wind farm by using the virtual anemometer tower data.

A method is disclosed for determining an individual maximum power level for one or more wind turbines in a wind power plant. The method comprises storing a wind turbine type maximum power level for one or more types of the one or more wind turbines, storing one or more fatigue load values relating to a range of power levels for each of the one or more types wind turbine, and storing one or more parameters relating to site conditions at the wind power plant. The method further comprises determining, based on at least the stored one or more fatigue load values and the stored one or more parameters, the individual maximum power level for each wind turbine of at least a first type of the one or more types.