12 results about "Wind component" patented technology

The invention discloses a wind field quality control method based on a single moment image structure, which comprises the following steps of: converting original wind direction and wind speed data into U and V wind components, and interpolating the U and V wind components and wind direction site observation data into regular grid data; adopting a curvelet decomposition method to decompose the grid-processed wind field data into two parts, namely a main term and a remainder term taking random change as a main term; for U and V wind speed and wind direction data, calculating a spatial gradient of a target grid point by using the main item data after curvelet analysis, and judging that the grid point with the gradient greater than a preset gradient threshold value is abnormal; performing progressive quality control for multiple times to identify discontinuous abnormal values in the main item; after main term curvelet analysis is completed, curvelet decomposition is carried out to obtain remainder term data, an abnormal threshold value is set, and a wind field area is divided into a weak rotating wind area and a strong rotating wind area; the quality control method is suitable for high-intensity weather system influence.

The invention relates to the field of wind power generation, in particular to a wind turbine generator yaw static error correction method and system based on a multi-beam laser radar. The method comprises the following steps: S1, scanning a wind field area in front of an impeller of a generator set through a multi-beam wind measurement laser radar mounted in a cabin of the wind turbine generator set to obtain parameter information of a plurality of spatial points; s2, performing fitting calculation on the parameter information system to obtain a fitting circle representing a horizontal wind vector of the wind field area, and solving the fitting circle to obtain a free flow wind direction; s3, the free flow wind direction is compared with the current cabin orientation, and a real-time static yaw error angle is obtained through calculation; generating a yaw control instruction according to a preset control strategy; s5, solving and calculating the fitting circle to obtain a transverse wind component, and correcting the yaw control instruction; according to the method, the control instruction is generated through the control strategy to drive the yaw system to perform dynamic compensation, so that the wind turbine generator can continuously maintain the optimal windward attitude, and the stability and long-term effectiveness of control are ensured.

The embodiment of the invention discloses a wind power prediction method and device in atmospheric sand and dust weather, and relates to the technical field of wind power generation, and the method comprises the steps: obtaining wind profile radar data, recognizing whether the current weather period is the atmospheric sand and dust weather or not based on the wind profile radar data, and generating a recognition result; if the weather is atmospheric sand and dust weather, predicting three-dimensional wind component prediction data in a target time period through a first prediction model based on historical three-dimensional wind component time sequence data calculated through historical wind profile radar data; and inputting the three-dimensional wind component prediction data into a second prediction model, and predicting a short-term power generation power prediction result of the wind power plant station in the target time period. The invention also provides a device for realizing the method. According to the method, the sand and dust weather is identified firstly, and then the special prediction process is started, so that the power prediction accuracy in special weather can be remarkably improved, the sensing ability to severe weather is enhanced, and the safety and economical efficiency of power grid operation are improved.

The present invention relates to a method for predicting wind power generation suitable for complex terrain, comprising: a weather information collection step for collecting weather information including forecasts for wind components predicted for a plurality of eta layers arranged vertically from the ground; a vertical characteristic integration step for deriving additional input characteristics using a characteristic extraction method that considers the physical characteristics of wind components for the wind components predicted for the plurality of eta layers; and a power generation prediction step for predicting power generation by applying the weather information and the additional input characteristics to a machine-learned algorithm for predicting power generation, wherein the algorithm is characterized by being learned using weather information for wind components, additional input characteristics derived using a characteristic extraction method that considers the physical characteristics of wind components for the wind components of the plurality of eta layers, and power generation. The present invention has the effect of improving the accuracy of wind power generation prediction for complex terrain by applying input characteristics derived by applying a characteristic extraction method that considers the physical characteristics of wind components predicted in a plurality of vertically arranged eta layers together with a conventional method for predicting wind power generation using weather information.

The application relates to a release evaluation method and equipment, wherein the method comprises the following steps: acquiring meteorological element data in multi-source live data in a target time domain; calculating temperature interpolation data, wind U component interpolation data and wind V component interpolation data of any position according to a bilinear interpolation algorithm on temperature data, wind U component data and wind V component data of CLDAS data; and / or calculating rainfall interpolation data of any position according to a distance reciprocal interpolation algorithm on rainfall data of QPE products in the CLDAS data and FY4A data; and / or calculating satellite-reversed one-hour rainfall interpolation data of any position according to a neighboring interpolation algorithm, wherein the satellite-reversed one-hour rainfall interpolation data is the mean value of estimated one-hour rainfall data of QPE reversal in all FY4A data in all neighboring positions corresponding to the any position. Through the technical scheme of the application, the automatic recognition capability of extreme weather can be improved, the precision of extreme weather monitoring can be improved, and the time of early warning information release can be advanced.

The embodiment of the invention discloses a wind power prediction method based on wind shear forecast data, and relates to the technical field of wind power generation, and the method comprises the steps: obtaining the wind regime data of a plurality of heights covering a wind sweeping region of a wind driven generator, and calculating the three-dimensional wind component data of the plurality of heights according to the wind regime data; on the basis of the historical three-dimensional wind component data, through a first prediction model, three-dimensional wind component forecast data at a future moment is obtained through prediction; on the basis of the three-dimensional wind component forecast data, wind shear data representing the change of a wind field in the vertical direction at future moments are obtained through calculation; and taking the wind shear data as an input feature, combining preset data, and utilizing a second prediction model to obtain a wind power prediction value. According to the method, through two-stage prediction, prospective wind shear prediction data is introduced into the model, the prediction accuracy and stability are remarkably improved, and the method can be used for wind shear early warning.

The invention provides a valley region bridge site wind speed prediction method based on a valley wind theory and a topographic feature decomposition technology. The method comprises the following steps: acquiring observed wind speed and wind direction data and meteorological element data; acquiring high-resolution terrain elevation data near the bridge site, and calculating terrain feature parameters; determining the canyon trend of the position of the observation station according to the coordinates of the observation station and the terrain elevation data; the observed wind speed and wind direction time sequence is decomposed according to the canyon trend, and axial wind along the canyon trend and normal wind perpendicular to the canyon trend are obtained respectively; respectively predicting an axial wind component and a normal wind component of the target station by using the axial wind prediction model and the normal wind prediction model, and performing projection synthesis on prediction results along the canyon trend to obtain final prediction results of the wind speed and the wind direction; according to the method, the problem that the full wind speed of bridge site wind in a complex mountainous area is difficult to accurately predict due to the influence of valley wind can be relieved, and the accuracy of valley full wind speed prediction is improved.

The invention discloses a wind speed and wind direction combined prediction method suitable for a bridge structure monitoring system, and the method comprises the steps: S1, collecting the time series data of the wind speed and wind direction in the bridge structure monitoring system, and carrying out the normalization processing; s2, calculating the prevailing wind direction of the bridge structure monitoring point according to the historical wind direction data, and decomposing the wind speed into a transverse wind component and a longitudinal wind component along the prevailing wind direction; s3, respectively establishing an LSTM neural network model for the transverse wind component and the longitudinal wind component, and performing training; s4, respectively predicting a transverse wind component and a longitudinal wind component by utilizing the trained LSTM model; and S5, combining the transverse wind component and the longitudinal wind component obtained by prediction to obtain wind speed and wind direction prediction results. The method can significantly improve the wind direction prediction precision, has real-time performance and engineering applicability, is suitable for strong wind monitoring and structure operation safety early warning in a bridge structure monitoring system, and is also applied to the disaster prevention safety field of high-rise buildings, railways and other infrastructures.

The invention belongs to the technical field of southwest vortex automatic identification, and particularly relates to a southwest vortex automatic identification method based on reanalysis data, which comprises the following steps: acquiring a weft wind component and a warp wind component of a 700hPa layer in ERA5 hour-by-hour reanalysis data, and calculating the wind speed of each grid point; traversing all the grid points by adopting a flooding filling method, and identifying a grid point group of which the wind speed is smaller than a threshold value V and which is spatially gathered as a potential vortex center area; 3 layers of grid points are expanded outwards for each potential vortex center area, an expansion area is constructed, and the proportion of the positive vortex grid points in the expansion area is calculated; if the proportion of the positive vorticity exceeds a preset threshold value, the anticlockwise rotation degree of the wind direction of the grid points in the expansion area is calculated; and if the anticlockwise rotation degree meets a set threshold value, judging that the corresponding system is an effective cyclone.

The application provides a weather radar and wind profile radar networking wind field inversion method, system and readable storage medium, wherein the method comprises: in a networking system composed of a plurality of weather radars and wind profile radars, synchronously collecting radial velocity and reflectivity factor data of the weather radars in the networking system, and horizontal wind component profile data and vertical wind component profile data of the wind profile radars, to form an original data set; interpolating the radial velocity, reflectivity factor data and vertical profile data into the same inversion grid to obtain model input data; constructing a double-branch fusion deep learning model for extraction of the model input data, the double-branch fusion deep learning model comprising a DenseNet network for extracting spatial features of the radial velocity and reflectivity factor, and a Transformer network for extracting vertical time sequence features of the wind profile data, and outputting a three-dimensional wind field vector after feature fusion of the extracted spatial features and vertical time sequence features.

This invention discloses a spatiotemporal synchronous wind speed prediction method based on CAEL-UNet. The method involves acquiring long-term global satellite remote sensing data related to meteorological and environmental elements from publicly available data sources, and extracting two sets of wind speed data: easterly wind component data and northerly wind component data. The easterly and northerly wind component data are preprocessed, normalized, and then stacked together at the same time and space to form a spatiotemporal data cube. The dataset is then divided into training and testing sets according to time order. This invention significantly reduces computational resource consumption. CAEL-UNet uses a convolutional autoencoder to perform nonlinear dimensionality reduction on the high-dimensional input data, compressing the data dimension while preserving key spatiotemporal features, greatly reducing the memory usage and training time for model training, and meeting the timeliness requirements of real-time wind farm scheduling.