Artificial neural network-based wind measurement data interpolation method for offshore floating wind measurement device

Abstract

The invention discloses a wind measurement data interpolation method and device of an offshore floating wind measurement device based on an artificial neural network, an electronic product and a computer readable storage medium. According to the invention, the method achieves the interpolation of the wind measurement data of the offshore floating wind measurement device based on an artificial neural network through the correlation between the wind measurement data and the feature data of the water body near the motion posture data when the offshore floating wind measurement device measures the wind. The method solves the problem that an existing wind measurement data interpolation method cannot directly carry out wind measurement data interpolation of the offshore floating wind measurement device, guarantees the accuracy and reasonability of wind measurement data interpolation of the offshore floating wind measurement device, guarantees the evaluation precision of wind energy resources, and improves the operation safety and economic benefits of a wind power plant.

Description

Technical Field

[0001] The present invention belongs to the field of wind power technology, and specifically relates to a method, device, electronic product and computer-readable storage medium for interpolating wind data of an offshore floating wind measuring device based on an artificial neural network. Background Art

[0002] Compared with traditional fixed wind measuring devices, offshore floating wind measuring devices (such as offshore floating wind towers) have the advantages of good portability and low deployment cost. At present, they are increasingly used in offshore wind power, especially in offshore floating wind power projects. However, due to factors such as bad weather and instrument failure, the measured data of offshore floating wind measuring devices may be missing or invalid. The interpolation of wind measurement data has become the basic work of wind energy resource assessment. Reasonable wind measurement data interpolation methods are of great significance to improving the accuracy of wind energy resource assessment, ensuring the safe operation of wind farms, and improving their economic benefits.

[0003] The existing wind data interpolation method is mainly for fixed wind measuring devices, and can only consider the correlation between wind speed data. Moreover, when there is no other data source with high correlation for reference during the period of missing measurement, it may cause large errors in the interpolation of wind speed. When the existing wind data interpolation method is used for offshore floating wind measuring devices, it is easy to have no data source with high correlation. Therefore, it cannot be directly used for wind data interpolation of offshore floating wind measuring devices. Summary of the invention

[0004] The purpose of the present invention is to ensure the accuracy and rationality of wind data interpolation of an offshore floating wind measuring device, ensure the accuracy of wind energy resource assessment, improve the safety and economic benefits of wind farm operation, and solve the problems existing in the above-mentioned background technology.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a method for interpolating wind data of an offshore floating wind measuring device based on an artificial neural network, comprising:

[0006] Obtaining wind measurement related data for the time period to be interpolated and performing rationality checks to remove abnormal values, the wind measurement related data including a time series of local water body characteristic parameters and a time series of motion posture parameters when an offshore floating wind measurement device measures wind;

[0007] The wind measurement related data after rationality check and outliers are eliminated are input into a local artificial neural network interpolation model to obtain the wind measurement data for the time period to be interpolated; the local artificial neural network interpolation model is a model obtained by training and evaluating the artificial neural network, and then learning the correlation between the wind measurement related data and the wind measurement data. The model can calculate and output the wind measurement data for the time period to be interpolated based on the input wind measurement related data for the time period to be interpolated, and the wind measurement data includes a local offshore wind speed time series and a local offshore wind direction time series.

[0008] In some embodiments of the present invention, training and evaluating an artificial neural network includes:

[0009] The data required for training and evaluation are obtained and rationality tests are performed to remove abnormal values; wherein the data required for training and evaluation include a time series of local meteorological characteristic parameters, a time series of local water body characteristic parameters, and a time series of motion posture parameters during the same period of time when the offshore floating wind measuring device measures wind, and the time series of local meteorological characteristic parameters includes a time series of local offshore wind speed and a time series of local offshore wind direction;

[0010] Constructing a complete set of training and detection data; wherein the complete set of training and detection data includes a complete set of independent variable data and a complete set of dependent variable data in the same period, the complete set of independent variable data includes a time series of local water body characteristic parameters and a time series of motion posture parameters, and the complete set of dependent variable data includes a time series of meteorological characteristic parameters;

[0011] The entire set of training and testing data is divided into a training set and a testing set. The training set is used to train an artificial neural network. The testing set is used to evaluate the eligibility of the trained artificial neural network. After the evaluation is qualified, a local artificial neural network interpolation model is obtained.

[0012] In some embodiments of the present invention, the local water body characteristic parameter time series includes at least one of a local Euler flow velocity time series, a flow direction time series, a wave height time series and a wave direction time series.

[0013] In some embodiments of the present invention, the motion attitude parameter time series includes at least one of a latitude and longitude position time series, a moving speed time series, a moving direction time series and an attitude angle time series during local measurement of the offshore wind measuring device.

[0014] In some embodiments of the present invention, a stratified random sampling method is used to divide the entire set of training and detection data into a training set and a detection set.

[0015] In some embodiments of the present invention, the entire set of training test data is divided into a training set and a test set. Specifically, the entire set of training test data is divided into corresponding N training verification data subsets according to N wind speed levels, and data are extracted from the N training verification data subsets according to the test set data ratio α. The extracted data constitute the test set, and the remaining data of the N training verification data subsets constitute the training set, N≥2, 0<α≤0.5.

[0016] In some embodiments of the present invention, there are two wind speed levels, namely, a high wind speed level and a low wind speed level, wherein the high wind speed is a wind speed greater than or equal to 30 m / s, and the low wind speed is a wind speed less than 30 m / s.

[0017] In a second aspect, the present invention provides a device for interpolating wind data of an offshore floating wind measuring device based on an artificial neural network, comprising:

[0018] A wind measurement related data acquisition unit is used to acquire wind measurement related data of the time period to be interpolated and perform rationality check to remove abnormal values, wherein the wind measurement related data includes a time series of local water body characteristic parameters and a time series of motion posture parameters when the offshore floating wind measurement device measures wind;

[0019] The wind measurement data interpolation unit is used to input the wind measurement related data after rationality inspection and elimination of abnormal values ​​into the local artificial neural network interpolation model to obtain the wind measurement data of the time period to be interpolated. The local artificial neural network interpolation model is a model obtained by training and evaluating the artificial neural network and then learning the correlation between the wind measurement related data and the wind measurement data. It can calculate and output the wind measurement data of the time period to be interpolated according to the input wind measurement related data of the time period to be interpolated. The wind measurement data includes a local offshore wind speed time series and a local offshore wind direction time series. .

[0020] In a third aspect, the present invention provides an electronic product, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for interpolating wind measurement data of an offshore floating wind measurement device based on an artificial neural network.

[0021] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for interpolating wind measurement data of an offshore floating wind measurement device based on an artificial neural network.

[0022] Beneficial Effects

[0023] The present invention utilizes the correlation between wind measurement data and water body characteristic data near the motion posture data of the offshore floating wind measuring device when measuring wind, and realizes the interpolation of the wind measurement data of the offshore floating wind measuring device based on an artificial neural network, thereby solving the problem that the existing wind measurement data interpolation method cannot directly interpolate the wind measurement data of the offshore floating wind measuring device, ensuring the accuracy and rationality of the interpolation of the wind measurement data of the offshore floating wind measuring device, ensuring the accuracy of wind energy resource assessment, and improving the safety and economic benefits of wind farm operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 FIG. 4 is a flow chart of a method for interpolating wind data in one embodiment of the present invention.

[0025] Figure 2 FIG. 4 is a flow chart of an artificial neural network training evaluation according to an embodiment of the present invention.

[0026] Figure 3 The figure is a schematic diagram of the composition of a wind measurement data interpolation device in one embodiment of the present invention.

[0027] Figure 4 FIG. 4 is a schematic diagram of the composition of an electronic product in one embodiment of the present invention. DETAILED DESCRIPTION

[0028] Considering that the current offshore floating wind measuring devices (such as floating wind towers) can record their motion posture data in addition to measuring basic wind measurement data, and the water body characteristic data such as waves and currents recorded by the hydrological measuring instruments mounted on them, the correlation between their motion posture data, water body characteristic data and wind measurement data provides new possibilities for interpolation of wind measurement data of offshore floating wind towers. Therefore, based on the above-mentioned inventive concept, the present invention provides a method, device, electronic product and computer-readable storage medium for interpolation of wind measurement data of offshore floating wind measuring devices based on artificial neural networks, which solves the problem that the existing wind measurement data interpolation method cannot directly interpolate the wind measurement data of offshore floating wind measuring devices, ensures the accuracy and rationality of interpolation of wind measurement data of offshore floating wind measuring devices, ensures the accuracy of wind energy resource assessment, and improves the safety and economic benefits of wind farm operation.

[0029] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0030] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0031] The present invention, in one embodiment, provides a method for interpolating wind data of an offshore floating wind measuring device based on an artificial neural network. Figure 1 As shown, the method includes:

[0032] The wind measurement related data of the time period to be interpolated are obtained and rationality check is performed to remove abnormal values, wherein the wind measurement related data include the time series of local water body characteristic parameters and the time series of motion posture parameters when the offshore floating wind measurement device measures wind.

[0033] The wind measurement related data after rationality check and outliers are eliminated are input into a local artificial neural network interpolation model to obtain the wind measurement data for the time period to be interpolated; the local artificial neural network interpolation model is a model obtained by training and evaluating the artificial neural network, and then learning the correlation between the wind measurement related data and the wind measurement data. The model can calculate and output the wind measurement data for the time period to be interpolated based on the input wind measurement related data for the time period to be interpolated, and the wind measurement data includes a local offshore wind speed time series and a local offshore wind direction time series.

[0034] In some embodiments of the present invention, Figure 2 As shown, the training evaluation of the artificial neural network includes:

[0035] The data required for training and evaluation are obtained and rationality checks are performed to remove outliers; wherein the data required for training and evaluation include a time series of local meteorological characteristic parameters, a time series of local water body characteristic parameters, and a time series of motion posture parameters during the same period of time when the offshore floating wind measuring device measures wind, and the time series of local meteorological characteristic parameters includes a time series of local offshore wind speed and a time series of local offshore wind direction.

[0036] Construct a complete set of training and detection data; wherein the complete set of training and detection data includes a complete set of independent variable data and a complete set of dependent variable data in the same time period, the complete set of independent variable data includes a local water body characteristic parameter time series and a motion posture parameter time series, the complete set of dependent variable data includes a meteorological characteristic parameter time series, and the local meteorological characteristic parameter time series includes a local offshore wind speed time series.

[0037] The entire set of training and testing data is divided into a training set and a testing set. The training set is used to train an artificial neural network. The testing set is used to evaluate the eligibility of the trained artificial neural network. After the evaluation is qualified, a local artificial neural network interpolation model is obtained.

[0038] In some preferred embodiments of the present invention, the local water body characteristic parameter time series includes at least one of a local Euler flow velocity time series, a flow direction time series, a wave height time series and a wave direction time series.

[0039] In some preferred embodiments of the present invention, the motion attitude parameter time series includes at least one of a latitude and longitude position time series, a moving speed time series, a moving direction time series and an attitude angle time series during local measurement of the offshore wind measuring device.

[0040] In some embodiments of the present invention, a stratified random sampling method is used to divide the entire set of training and detection data into a training set and a detection set.

[0041] In some embodiments of the present invention, the entire set of training test data is divided into a training set and a test set. Specifically, the entire set of training test data is divided into corresponding N training verification data subsets according to N wind speed levels, and data are extracted from the N training verification data subsets according to the test set data ratio α, and the extracted data constitute the test set, and the remaining data of the N training verification data subsets constitute the training set, N≥2, 0<α≤0.5. Preferably, there are two levels of wind speed level, namely high wind speed level and low wind speed level, high wind speed means wind speed greater than or equal to 30 meters / second, and low wind speed means wind speed less than 30 meters / second.

[0042] In some embodiments of the present invention, specifically, the offshore floating wind measuring device is an offshore floating wind measuring tower, and the offshore floating wind measuring tower is mounted with a hydrological measuring instrument, which can measure the time series of local water body characteristic parameters, and is also hung with a motion posture measurement device, such as GPS, which can measure the time series of motion posture parameters.

[0043] In some embodiments of the present invention, the artificial neural network is a BiGRU artificial neural network.

[0044] The present invention provides an artificial neural network-based wind data interpolation method for an offshore floating wind measuring device in one embodiment, which utilizes the correlation between the floating wind tower motion posture data, wind wave velocity data and wind measurement data, and adopts a matrix calculation method. The details are as follows:

[0045] Step 1: Obtain the data required for training and evaluation.

[0046] The data required for training and evaluation include: (1) time series of meteorological parameters observed and recorded during the wind measurement period of the floating wind tower, including local wind speed and direction; (2) time series of water characteristics, including local Euler flow velocity, flow direction, wave height and wave direction; (3) time series of the motion attitude of the floating wind tower, including longitude and latitude position, moving speed, moving direction and attitude angle data.

[0047] Step 2: Perform a rationality check on the collected data and remove outliers.

[0048] Specifically, the reasonable range of wind speed is between 0 and 40m / s; the reasonable range of flow velocity is between 0 and 10m / s; the reasonable range of wave height is between 0 and 10m; the reasonable range of the moving speed of the floating wind measurement tower is between 0 and 20m / s; the wind direction, flow direction and wave direction are between 0 and 360°; the standard deviation of each variable shall not be 0 for 2 consecutive hours, otherwise the instrument measuring the variable is deemed to be frozen or damaged.

[0049] Step 3: Reconstruct the data after rationality verification into the full set of training and evaluation data.

[0050] Specifically, in this embodiment, matrices are used to organize and store data and perform data operations.

[0051] The water body characteristic time series (including local Euler flow velocity, flow direction, wave height and wave direction) and the floating wind tower state time series (including moving speed, moving direction and attitude angle data) together constitute the independent variable matrix X.

[0052]

[0053] Among them, x i,j is a valid data value, i represents the position in the time series, j represents the corresponding variable, and can be a null value NaN, considering that different data are eliminated after rationality checks.

[0054] The meteorological parameter time series (wind speed and wind direction) constitutes the dependent variable (target variable) matrix Y,

[0055]

[0056] Among them, y i,1 represents the wind speed time series, y i,2 represents the wind direction time series, i represents the position in the time series, and to ensure the reliability of the model, the wind speed data at any time point i0 Cannot be the null value NaN.

[0057] Step 4: By performing stratified random sampling on the entire set of training and evaluation data, we can obtain the sample data matrix required for training and evaluation, namely the training set and the test set.

[0058] Specifically, according to the wind speed vector y in the dependent variable matrix Y i,1 The size of the independent variable data matrix X and Y are divided into two categories: low wind speed (wind speed less than 30m / s) and high wind speed (wind speed greater than or equal to 30m / s), denoted as X n , X e With Y n , Y e , where subscript n represents low wind speed category, subscript e represents high wind speed category; n With X e Simple random sampling is performed, and the number of samples is 10% of the total number of each, denoted as and The remaining 90% of the data that was not sampled in the entire training and evaluation data set is recorded as and According to the sampling results of the independent variable matrix X, the corresponding four matrices are obtained from the dependent variable matrix Y, which are recorded as Will and Merge into independent variable test data matrix X c ,Will and Merge into the dependent variable test data matrix Y c ,Right now

[0059]

[0060]

[0061] Similarly, obtain the independent variable training data matrix X t With dependent variable training data matrix Y t ,Right now

[0062]

[0063]

[0064] Step 5: Train the BiGRU artificial neural network model using the training set.

[0065] Specifically, the training data matrix X obtained by stratified random sampling is reorganized t As feature data, its corresponding Y t As the target variable, it is provided to the BiGRU (Bidirectional Gated Recurrent Units) artificial neural network model for supervised learning; BiGRU consists of forward GRU and reverse GRU, and the formula is:

[0066]

[0067]

[0068]

[0069] in, is the forward output, For reverse output, is the model result, It is a bitwise addition.

[0070] BiGRU fills in missing information by bidirectionally connecting the past and future states. Considering that GRU uses technologies such as update gate and reset gate to achieve information protection and gradient retention, its operation speed is faster and easier to deploy. In this embodiment, the BiGRU model selects a 3-layer network, and the number of neurons in the 3 layers is 128, 64, and 32 respectively, and the recurrent activation function of each layer selects sigmoid. During the training process, mse is selected as the cost function and adam is selected as the optimizer. The end point of model training is determined by setting the error threshold ε. In this embodiment, the threshold ε=0.0002.

[0071] Step 6: Use the cross-validation method to use the test set X c With Y c Evaluate supervised learning models.

[0072] Specifically, we select the best hyperparameter tuning and trained dataset matrix (X t With Y t ) The trained BiGRU artificial neural network model is reorganized into a test data matrix X obtained by stratified random sampling c And the optimal hyperparameters are input into the BiGRU neural network model for simulation testing to obtain the simulation result matrix Compare it with the test dataset matrix Y c For comparison, the simulation effects of the model on wind speed and wind direction were evaluated respectively. The evaluation parameters were selected as the model skill score (SS) and root mean square error (RMSE). The formula is:

[0073]

[0074]

[0075] in, is the simulation result (wind speed or wind direction) of the BiGRU artificial neural network model, Y i cis the real observation data (wind speed or wind direction) of the test data set, and N is the amount of data.

[0076] In this embodiment, the standard for the model to be qualified is that SS is greater than 0.6, the RMSE of wind speed is less than 0.5 m / s, and the RMSE of wind direction is less than 10°.

[0077] Step 7: Use the verified BiGRU artificial neural network model to simulate and interpolate the wind measurement data during the interpolation period.

[0078] Specifically, the local Euler flow velocity, flow direction, wave height and wave direction data recorded by the floating wind tower during the interpolation period, as well as the latitude and longitude position, moving speed, moving direction and attitude angle data of the floating wind tower are collected, and invalid data are eliminated after the rationality test described in step 2 to form the independent variable matrix X to be interpolated. * , X * Input the verified BiGRU artificial neural network model for simulation to obtain the dependent variable matrix Y * , which is the wind measurement data after interpolation.

[0079] like Figure 3 As shown, in one embodiment of the present invention, a wind data interpolation device for an offshore floating wind measuring device based on an artificial neural network comprises:

[0080] A wind measurement related data acquisition unit is used to acquire wind measurement related data of the time period to be interpolated and perform rationality check to remove abnormal values, wherein the wind measurement related data includes a time series of local water body characteristic parameters and a time series of motion posture parameters when the offshore floating wind measurement device measures wind;

[0081] The wind measurement data interpolation unit is used to input the wind measurement related data after rationality inspection and elimination of abnormal values ​​into the local artificial neural network interpolation model to obtain the wind measurement data of the time period to be interpolated. The local artificial neural network interpolation model is a model obtained by training and evaluating the artificial neural network and then learning the correlation between the wind measurement related data and the wind measurement data. It can calculate and output the wind measurement data of the time period to be interpolated according to the input wind measurement related data of the time period to be interpolated. The wind measurement data includes a local offshore wind speed time series and a local offshore wind direction time series. .

[0082] In one embodiment, the present invention provides an electronic product, such as Figure 4 As shown, the electronic device includes at least one processor and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned method for interpolating wind measurement data of an offshore floating wind measurement device based on an artificial neural network.

[0083] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits through interfaces, which are all well known in the art. The interface provides an interface between the bus and the transceiver, such as a communication interface and a user interface. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium through an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0084] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0085] In one embodiment, the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the embodiment of the method for interpolating wind data of an offshore floating wind measuring device based on an artificial neural network is implemented.

[0086] Those skilled in the art can understand from the above description that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions for making a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes but is not limited to various media that can store program codes, such as USB flash drives, mobile hard disks, magnetic storage devices, and optical storage devices.

[0087] The present invention utilizes the correlation between wind measurement data and water body characteristic data near the motion posture data of the offshore floating wind measuring device when measuring wind, and realizes the interpolation of the wind measurement data of the offshore floating wind measuring device based on an artificial neural network, thereby solving the problem that the existing wind measurement data interpolation method cannot directly interpolate the wind measurement data of the offshore floating wind measuring device, ensuring the accuracy and rationality of the interpolation of the wind measurement data of the offshore floating wind measuring device, ensuring the accuracy of wind energy resource assessment, and improving the safety and economic benefits of wind farm operation.

[0088] In the several embodiments provided in the present application, it should be understood that the disclosed system, device or method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules or units, which can be electrical, mechanical or other forms.

[0089] The modules / units described as separate components may or may not be physically separated, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, the functional modules / units in the various embodiments of the present application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0090] Those of ordinary skill in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0091] The descriptions of the processes or structures corresponding to the above-mentioned figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0092] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A method for interpolating wind data of an offshore floating wind measuring device based on an artificial neural network, characterized in that: Obtaining wind measurement related data for the time period to be interpolated and performing rationality checks to remove abnormal values, the wind measurement related data including a time series of local water body characteristic parameters and a time series of motion posture parameters when an offshore floating wind measurement device measures wind; The wind measurement related data after rationality check and outliers are eliminated are input into a local artificial neural network interpolation model to obtain the wind measurement data for the time period to be interpolated; the local artificial neural network interpolation model is a model obtained by training and evaluating the artificial neural network and then learning the correlation between the wind measurement related data and the wind measurement data, and can calculate and output the wind measurement data for the time period to be interpolated based on the input wind measurement related data for the time period to be interpolated, and the wind measurement data includes a local offshore wind speed time series and a local offshore wind direction time series.

2. The wind measurement data interpolation method according to claim 1, characterized in that: The training evaluation of the artificial neural network comprises: The data required for training and evaluation are obtained and rationality tests are performed to remove abnormal values; wherein the data required for training and evaluation include a time series of local meteorological characteristic parameters, a time series of local water body characteristic parameters, and a time series of motion posture parameters during the same period of time when the offshore floating wind measuring device measures wind, and the time series of local meteorological characteristic parameters includes a time series of local offshore wind speed and a time series of local offshore wind direction; Constructing a complete set of training and detection data; wherein the complete set of training and detection data includes a complete set of independent variable data and a complete set of dependent variable data in the same period, the complete set of independent variable data includes a time series of local water body characteristic parameters and a time series of motion posture parameters, and the complete set of dependent variable data includes a time series of meteorological characteristic parameters; The entire set of training and testing data is divided into a training set and a testing set. The training set is used to train an artificial neural network. The testing set is used to evaluate the eligibility of the trained artificial neural network. After the evaluation is qualified, a local artificial neural network interpolation model is obtained.

3. The wind measurement data interpolation method according to claim 2, characterized in that: The local water body characteristic parameter time series includes at least one of a local Euler flow velocity time series, a flow direction time series, a wave height time series and a wave direction time series.

4. The wind measurement data interpolation method according to claim 2, characterized in that: The motion attitude parameter time series includes at least one of a latitude and longitude position time series, a moving speed time series, a moving direction time series and an attitude angle time series during local measurement by the offshore wind measuring device.

5. The wind measurement data interpolation method according to claim 1, characterized in that: The stratified random sampling method is used to divide the entire set of training and testing data into a training set and a testing set.

6. The wind measurement data interpolation method according to claim 5, characterized in that: The entire set of training and test data is divided into a training set and a test set. Specifically, according to N wind speed levels, the entire set of training and test data is divided into corresponding N training and verification data subsets. Data are extracted from the N training and verification data subsets according to the test set data ratio α. The extracted data constitute the test set, and the remaining data of the N training and verification data subsets constitute the training set, N≥2, 0<α≤0.

5.

7. The wind measurement data interpolation method according to claim 6, characterized in that: There are two levels of wind speed: high wind speed level and low wind speed level. High wind speed means the wind speed is greater than or equal to 30 meters / second, and low wind speed means the wind speed is less than 30 meters / second.

8. A wind data interpolation device for an offshore floating wind measuring device based on an artificial neural network, comprising: A wind measurement related data acquisition unit is used to acquire wind measurement related data of the time period to be interpolated and perform rationality check to remove abnormal values, wherein the wind measurement related data includes a time series of local water body characteristic parameters and a time series of motion posture parameters when the offshore floating wind measurement device measures wind; The wind measurement data interpolation unit is used to input the wind measurement related data after rationality inspection and elimination of abnormal values ​​into the local artificial neural network interpolation model to obtain the wind measurement data of the time period to be interpolated. The local artificial neural network interpolation model is a model obtained by training and evaluating the artificial neural network and then learning the correlation between the wind measurement related data and the wind measurement data. It can calculate and output the wind measurement data of the time period to be interpolated according to the input wind measurement related data of the time period to be interpolated. The wind measurement data includes a local offshore wind speed time series and a local offshore wind direction time series. .

9. An electronic product comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the wind measurement data interpolation method for an offshore floating wind measurement device based on an artificial neural network as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, wherein: When the computer program is executed by a processor, the method for interpolating wind measurement data of an offshore floating wind measurement device based on an artificial neural network as described in any one of claims 1 to 7 is implemented.

Images