Offshore wind power area identification method and system

Abstract

The present invention discloses a method and system for identifying offshore wind power areas. The method comprises: obtaining satellite image information of a target ocean area and sound information of multiple ocean locations; determining multiple noise anomaly locations corresponding to the target ocean area based on a noise propagation analysis model and the sound information; determining multiple wind power equipment locations corresponding to the target ocean area based on an image recognition algorithm and the satellite image information; and determining wind power areas within the target ocean area based on a probability algorithm based on the noise anomaly locations and the wind power equipment locations. This method can more efficiently and accurately identify offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data foundation for subsequent environmental assessments.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for identifying an offshore wind power area. Background Art

[0002] Offshore wind power utilizes stronger and more stable sea wind resources to promote the development of renewable energy, and is one of the important directions of the current mainstream energy transformation. However, since the establishment and operation of offshore wind farms and the changes in the waterways along the way have adverse effects on the natural ecology, it is necessary to conduct effective management and environmental assessment of offshore wind farms to determine their adjustment strategies. When evaluating offshore wind farms, the existing technology generally uses manual identification and analysis based on building records to determine the offshore wind power areas in the ocean area. It does not further consider the use of multiple sensor information to accurately identify offshore wind power areas. Therefore, its recognition efficiency is low, the recognition cost is high, and the recognition accuracy is not ideal. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for identifying offshore wind power areas, which can more efficiently and accurately identify offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for identifying an offshore wind power area, the method comprising:

[0005] Obtain satellite image information of the target ocean area and sound information of multiple ocean locations;

[0006] Determining multiple noise anomaly locations corresponding to the target ocean area based on a noise propagation analysis model and the sound information;

[0007] Determining the locations of multiple wind turbines corresponding to the target ocean area based on an image recognition algorithm and the satellite image information;

[0008] Based on the abnormal noise location and the wind power equipment location, and based on a probability algorithm, a wind power area in the target ocean area is determined.

[0009] As an optional embodiment, in the first aspect of the present invention, determining multiple noise anomaly locations corresponding to the target ocean area based on the noise propagation analysis model and the sound information includes:

[0010] Based on a preset continuous sound change rule, grouping all the ocean locations according to the sound information corresponding to each of the ocean locations to obtain a plurality of continuous sound location groups;

[0011] Inputting the sound information corresponding to all the ocean locations in each of the continuous sound location groups into a trained noise prediction neural network to obtain a noise prediction probability corresponding to each of the continuous sound location groups; the noise prediction neural network is trained using a training data set including multiple training sound groups and corresponding labels indicating whether they are wind turbine noise;

[0012] Screening out all the continuous sound position groups whose noise prediction probability is greater than a preset first probability threshold to obtain a plurality of high-risk position groups;

[0013] According to the multiple high-risk location groups, multiple noise anomaly locations corresponding to the target ocean area are determined.

[0014] As an optional embodiment, in the first aspect of the present invention, based on the preset continuous sound change rule, all the ocean locations are grouped according to the sound information corresponding to each ocean location to obtain a plurality of continuous sound location groups, including:

[0015] For any two adjacent ocean locations, calculating the distance between the two ocean locations;

[0016] Calculating a difference in sound parameters between the sound information corresponding to the two ocean locations;

[0017] Calculating the ratio between the sound parameter difference and the position distance to obtain the sound change parameters corresponding to the two ocean positions;

[0018] Based on a dynamic programming algorithm, all the ocean positions are grouped and iteratively calculated based on the sound change parameters to obtain multiple continuous sound position groups.

[0019] As an optional embodiment, in the first aspect of the present invention, the dynamic programming algorithm is used to perform grouping and iterative calculations on all the ocean locations based on the sound change parameters to obtain multiple continuous sound location groups, including:

[0020] Setting the objective function to maximize the total number of ocean locations in each continuous sound location group;

[0021] The restriction conditions include that the curvature of the lowest curvature line segment formed by connecting all the ocean positions included in each continuous sound position group is less than a preset curvature threshold, the sound change parameters of any two ocean positions in each continuous sound position group are greater than a first parameter threshold, and the sound propagation prediction probability corresponding to each continuous sound position group is greater than a preset second probability threshold; the sound propagation prediction probability is obtained by inputting a parameter sequence of the sound change parameters corresponding to all the ocean positions in the continuous sound position group, arranged in position order, into a trained sound propagation prediction neural network; the noise prediction neural network is trained using a training data set including multiple training sound change parameter sequences and corresponding labels of whether the sound is continuously propagated;

[0022] Based on a dynamic programming algorithm, according to the objective function and the constraint conditions, all the ocean positions are grouped and iteratively calculated until convergence, thereby obtaining a plurality of continuous sound position groups.

[0023] As an optional embodiment, in the first aspect of the present invention, determining, based on the multiple high-risk location groups, multiple noise anomaly locations corresponding to the target ocean area includes:

[0024] Connecting all the ocean locations included in each high-risk location group with the lowest curvature to obtain a high-risk line segment corresponding to each high-risk location group;

[0025] Calculating intersections of all the high-risk line segments to obtain multiple intersection points;

[0026] For each intersection point, calculate the number of line segments of the high-risk line segment where the intersection point is located;

[0027] Calculating the average number of ocean locations corresponding to the high-risk location group corresponding to all the high-risk line segments where the intersection point is located, to obtain a location quantity parameter corresponding to the intersection point;

[0028] Calculating a weighted average of the number of line segments and the number of positions to obtain an abnormality parameter corresponding to the intersection point;

[0029] All the intersections whose abnormal parameters are greater than the second parameter threshold are screened out to obtain multiple noise abnormality positions.

[0030] As an optional embodiment, in the first aspect of the present invention, determining the locations of multiple wind turbines corresponding to the target ocean area based on an image recognition algorithm and the satellite image information includes:

[0031] Inputting the satellite image information into a trained wind turbine area segmentation algorithm model to obtain a plurality of wind turbine image portions corresponding to the satellite image information and corresponding image prediction probabilities; the wind turbine area segmentation algorithm model is trained using a training data set including a plurality of training satellite image information and corresponding wind turbine area annotations;

[0032] The actual coordinate position corresponding to the position of each wind turbine image portion in the satellite image information is determined as the corresponding wind turbine position.

[0033] As an optional embodiment, in the first aspect of the present invention, determining the wind power area in the target ocean area based on the abnormal noise location and the wind power equipment location and a probability algorithm includes:

[0034] For each wind turbine location, determine a circular area with a preset radius value with the wind turbine location as the center, and obtain an equipment range area corresponding to the wind turbine location;

[0035] Calculating the probability of a wind power area corresponding to the location of the wind power equipment according to the location of the abnormal noise within the range of the equipment;

[0036] The equipment range areas corresponding to the wind power equipment locations whose wind power area probabilities are greater than a third probability threshold are determined as wind power areas in the target ocean area.

[0037] As an optional embodiment, in the first aspect of the present invention, the calculating, based on the abnormal noise location within the equipment range, the probability of a wind power area corresponding to the wind power equipment location, includes:

[0038] Counting the number of the abnormal noise locations within the equipment range to obtain noise location parameters corresponding to the wind power equipment location;

[0039] Calculating an average value of the abnormal parameters corresponding to all the abnormal noise locations within the equipment range to obtain the abnormal noise parameter corresponding to the wind power equipment location;

[0040] The product of the image prediction probability corresponding to the portion of the wind power equipment image corresponding to the wind power equipment position, the noise position parameter, and the noise anomaly parameter is calculated to obtain the wind power area probability corresponding to the wind power equipment position.

[0041] A second aspect of an embodiment of the present invention discloses a system for identifying an offshore wind power area, the system comprising:

[0042] an acquisition module for acquiring satellite image information of a target ocean area and sound information of multiple ocean locations;

[0043] a first determination module, configured to determine a plurality of noise anomaly locations corresponding to the target ocean area based on a noise propagation analysis model and the sound information;

[0044] a second determination module, configured to determine locations of multiple wind turbines corresponding to the target ocean area based on an image recognition algorithm and the satellite image information;

[0045] The third determination module is configured to determine the wind power area in the target ocean area based on the abnormal noise location and the wind power equipment location and a probability algorithm.

[0046] As an optional embodiment, in the second aspect of the present invention, the first determination module determines the specific manner of the multiple noise anomaly locations corresponding to the target ocean area based on the noise propagation analysis model and the sound information, including:

[0047] Based on a preset continuous sound change rule, grouping all the ocean locations according to the sound information corresponding to each of the ocean locations to obtain a plurality of continuous sound location groups;

[0048] Inputting the sound information corresponding to all the ocean locations in each of the continuous sound location groups into a trained noise prediction neural network to obtain a noise prediction probability corresponding to each of the continuous sound location groups; the noise prediction neural network is trained using a training data set including multiple training sound groups and corresponding labels indicating whether they are wind turbine noise;

[0049] Screening out all the continuous sound position groups whose noise prediction probability is greater than a preset first probability threshold to obtain a plurality of high-risk position groups;

[0050] According to the multiple high-risk location groups, multiple noise anomaly locations corresponding to the target ocean area are determined.

[0051] As an optional embodiment, in the second aspect of the present invention, the first determination module groups all the ocean locations based on the preset continuous sound change rule and the sound information corresponding to each ocean location to obtain a plurality of continuous sound location groups, including:

[0052] For any two adjacent ocean locations, calculating the distance between the two ocean locations;

[0053] Calculating a difference in sound parameters between the sound information corresponding to the two ocean locations;

[0054] Calculating the ratio between the sound parameter difference and the position distance to obtain the sound change parameters corresponding to the two ocean positions;

[0055] Based on a dynamic programming algorithm, all the ocean positions are grouped and iteratively calculated based on the sound change parameters to obtain multiple continuous sound position groups.

[0056] As an optional embodiment, in the second aspect of the present invention, the first determination module performs grouping and iterative calculations on all the ocean locations based on the sound change parameters based on a dynamic programming algorithm to obtain a plurality of continuous sound location groups, including:

[0057] Setting the objective function to maximize the total number of ocean locations in each continuous sound location group;

[0058] The restriction conditions include that the curvature of the lowest curvature line segment formed by connecting all the ocean positions included in each continuous sound position group is less than a preset curvature threshold, the sound change parameters of any two ocean positions in each continuous sound position group are greater than a first parameter threshold, and the sound propagation prediction probability corresponding to each continuous sound position group is greater than a preset second probability threshold; the sound propagation prediction probability is obtained by inputting a parameter sequence of the sound change parameters corresponding to all the ocean positions in the continuous sound position group, arranged in position order, into a trained sound propagation prediction neural network; the noise prediction neural network is trained using a training data set including multiple training sound change parameter sequences and corresponding labels of whether the sound is continuously propagated;

[0059] Based on a dynamic programming algorithm, according to the objective function and the constraint conditions, all the ocean positions are grouped and iteratively calculated until convergence, thereby obtaining a plurality of continuous sound position groups.

[0060] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the first determination module determines the multiple noise anomaly locations corresponding to the target ocean area based on the multiple high-risk location groups includes:

[0061] Connecting all the ocean locations included in each high-risk location group with the lowest curvature to obtain a high-risk line segment corresponding to each high-risk location group;

[0062] Calculating intersections of all the high-risk line segments to obtain multiple intersection points;

[0063] For each intersection point, calculate the number of line segments of the high-risk line segment where the intersection point is located;

[0064] Calculating the average number of ocean locations corresponding to the high-risk location group corresponding to all the high-risk line segments where the intersection point is located, to obtain a location quantity parameter corresponding to the intersection point;

[0065] Calculating a weighted average of the number of line segments and the number of positions to obtain an abnormality parameter corresponding to the intersection point;

[0066] All the intersections whose abnormal parameters are greater than the second parameter threshold are screened out to obtain multiple noise abnormality positions.

[0067] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the second determination module determines the locations of the multiple wind turbines corresponding to the target ocean area based on the image recognition algorithm and the satellite image information includes:

[0068] Inputting the satellite image information into a trained wind turbine area segmentation algorithm model to obtain a plurality of wind turbine image portions corresponding to the satellite image information and corresponding image prediction probabilities; the wind turbine area segmentation algorithm model is trained using a training data set including a plurality of training satellite image information and corresponding wind turbine area annotations;

[0069] The actual coordinate position corresponding to the position of each wind turbine image portion in the satellite image information is determined as the corresponding wind turbine position.

[0070] As an optional embodiment, in the second aspect of the present invention, the third determination module determines the specific manner of the wind power area in the target ocean area based on the noise anomaly location and the wind power equipment location and a probability algorithm, including:

[0071] For each wind turbine location, determine a circular area with a preset radius value with the wind turbine location as the center, and obtain an equipment range area corresponding to the wind turbine location;

[0072] Calculating the probability of a wind power area corresponding to the location of the wind power equipment according to the location of the abnormal noise within the range of the equipment;

[0073] The equipment range areas corresponding to the wind power equipment locations whose wind power area probabilities are greater than a third probability threshold are determined as wind power areas in the target ocean area.

[0074] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the third determination module calculates the probability of a wind power area corresponding to the wind power equipment location based on the abnormal noise location being within the equipment range area includes:

[0075] Counting the number of the abnormal noise locations within the equipment range to obtain noise location parameters corresponding to the wind power equipment location;

[0076] Calculating an average value of the abnormal parameters corresponding to all the abnormal noise locations within the equipment range to obtain the abnormal noise parameter corresponding to the wind power equipment location;

[0077] The product of the image prediction probability corresponding to the portion of the wind power equipment image corresponding to the wind power equipment position, the noise position parameter, and the noise anomaly parameter is calculated to obtain the wind power area probability corresponding to the wind power equipment position.

[0078] A third aspect of the present invention discloses another offshore wind power area identification system, the system comprising:

[0079] a memory storing executable program code;

[0080] a processor coupled to the memory;

[0081] The processor calls the executable program code stored in the memory to execute part or all of the steps in the offshore wind power area identification method disclosed in the first aspect of the present invention.

[0082] A fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when called, are used to execute some or all of the steps in the offshore wind power area identification method disclosed in the first aspect of the present invention.

[0083] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0084] The present invention can determine the location of noise anomalies based on sound information and noise propagation analysis models, and then determine the location of wind power equipment based on satellite image information and image recognition algorithms, and more accurately and comprehensively determine wind power areas in ocean areas based on probabilistic algorithms, thereby being able to more efficiently and accurately identify offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0086] Figure 1This is a flow chart of a method for identifying an offshore wind power area disclosed in an embodiment of the present invention.

[0087] Figure 2 This is a structural diagram of an offshore wind power area identification system disclosed in an embodiment of the present invention.

[0088] Figure 3 It is a structural schematic diagram of another offshore wind power area identification system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0089] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0090] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or device.

[0091] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0092] This invention discloses a method and system for identifying offshore wind farm areas. These methods can determine the location of noise anomalies based on sound information and a noise propagation analysis model, then determine the location of wind farm equipment based on satellite imagery and an image recognition algorithm. Finally, a probabilistic algorithm is used to more accurately and comprehensively determine wind farm areas within the ocean. This method enables more efficient and accurate identification of offshore wind farm areas, reduces the cost and errors of manual identification, and provides a more accurate data foundation for subsequent environmental assessments. Each of these methods is described in detail below.

[0093] Example 1

[0094] See also Figure 1 , Figure 1 This is a flow chart of a method for identifying an offshore wind power area disclosed in an embodiment of the present invention. Figure 1 The offshore wind power area identification method described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the offshore wind power area identification method may include the following operations:

[0095] 101. Obtain satellite image information of the target ocean area and sound information of multiple ocean locations.

[0096] 102. Based on the noise propagation analysis model and sound information, multiple noise anomaly locations corresponding to the target ocean area are determined.

[0097] 103. Based on image recognition algorithms and satellite image information, determine the locations of multiple wind turbines corresponding to the target ocean area.

[0098] 104. Based on the location of the noise anomaly and the location of the wind power equipment, the wind power area in the target ocean area is determined based on a probability algorithm.

[0099] It can be seen that the above-mentioned embodiments of the invention can determine the location of noise anomalies based on sound information and noise propagation analysis models, and then determine the location of wind power equipment based on satellite image information and image recognition algorithms, and more accurately and comprehensively determine the wind power areas in the ocean area based on probabilistic algorithms, thereby being able to more efficiently and accurately identify offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0100] As an optional embodiment, in the above step, determining multiple noise anomaly locations corresponding to the target ocean area based on the noise propagation analysis model and sound information includes:

[0101] Based on the preset continuous sound change rules, all ocean locations are grouped according to the sound information corresponding to each ocean location to obtain multiple continuous sound location groups;

[0102] Inputting the sound information corresponding to all ocean locations in each continuous sound location group into a trained noise prediction neural network to obtain a noise prediction probability corresponding to each continuous sound location group; optionally, the noise prediction neural network is trained using a training data set including multiple training sound groups and corresponding labels indicating whether they are wind turbine noise;

[0103] Screening out all continuous sound location groups whose noise prediction probability is greater than a preset first probability threshold to obtain multiple high-risk location groups;

[0104] Based on multiple high-risk location groups, multiple noise anomaly locations corresponding to the target ocean area are determined.

[0105] It can be seen that through the above optional embodiments, ocean locations can be grouped based on continuous sound change rules, and then the noise probability of each location group can be predicted based on a neural network to screen out high-risk location groups, so as to comprehensively and accurately determine the locations of noise anomalies, assist in more efficient and accurate identification of offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0106] As an optional embodiment, in the above steps, based on the preset continuous sound change rule, all ocean locations are grouped according to the sound information corresponding to each ocean location to obtain multiple continuous sound location groups, including:

[0107] For any two adjacent ocean locations, calculate the location distance between the two ocean locations;

[0108] Calculating the difference in sound parameters between the sound information corresponding to the two ocean locations;

[0109] Calculating the ratio between the difference in sound parameters and the distance between locations to obtain the sound change parameters corresponding to the two ocean locations;

[0110] Based on the dynamic programming algorithm, all ocean locations are grouped and iteratively calculated based on the sound change parameters to obtain multiple continuous sound location groups.

[0111] Optionally, the sound parameter difference can be the difference between sound decibel values, the difference between sound characteristic values, or the difference between sound change rates. Other characteristic values ​​that can effectively characterize the difference between sound information should also be considered to fall within the scope of protection of the present invention.

[0112] It can be seen that through the above-mentioned optional embodiments, multiple continuous sound position groups can be obtained based on the calculation of sound change parameters between ocean positions and the iterative grouping of the dynamic programming algorithm, so as to comprehensively and accurately determine the abnormal noise location in the subsequent period, assist in more efficient and accurate identification of offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0113] As an optional embodiment, in the above steps, based on the dynamic programming algorithm, all ocean positions are grouped and iteratively calculated based on the sound change parameters to obtain multiple continuous sound position groups, including:

[0114] The objective function is set to maximize the total number of ocean locations in each continuous sound location group;

[0115] The restriction conditions include that the curvature of the lowest curvature line segment connecting all ocean positions included in each continuous sound position group is less than a preset curvature threshold, the sound change parameters of any two ocean positions in each continuous sound position group are greater than a first parameter threshold, and the sound propagation prediction probability corresponding to each continuous sound position group is greater than a preset second probability threshold; optionally, the sound propagation prediction probability is obtained by inputting a parameter sequence of sound change parameters corresponding to all ocean positions in the continuous sound position group arranged in position order into a trained sound propagation prediction neural network; the noise prediction neural network is obtained by a training data set including a plurality of training sound change parameter sequences and corresponding labels of whether the sound is continuously propagated;

[0116] Based on the dynamic programming algorithm, all ocean positions are grouped and iteratively calculated according to the objective function and constraints until convergence, and multiple continuous sound position groups are obtained.

[0117] Optionally, the dynamic programming algorithm may adopt a particle swarm evolution algorithm or a spatial search algorithm, or other dynamic programming algorithms capable of iterative calculation.

[0118] It can be seen that through the above optional embodiments, multiple continuous sound position groups can be obtained based on the preset objective function and constraints and the iterative calculation grouping of the dynamic programming algorithm, so as to comprehensively and accurately determine the abnormal noise location in the subsequent process, assist in more efficient and accurate identification of offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0119] As an optional embodiment, in the above step, determining multiple noise anomaly locations corresponding to the target ocean area based on multiple high-risk location groups includes:

[0120] Connect all ocean locations included in each high-risk location group with the lowest curvature to obtain the high-risk line segment corresponding to each high-risk location group;

[0121] Calculate the intersections of all high-risk line segments to obtain multiple intersection points;

[0122] For each intersection point, calculate the number of high-risk line segments where the intersection point is located;

[0123] Calculate the average number of ocean locations corresponding to the high-risk location groups corresponding to all high-risk line segments where the intersection point is located, and obtain the location quantity parameter corresponding to the intersection point;

[0124] Calculate the weighted sum average of the number of line segments and the number of positions to obtain the anomaly parameter corresponding to the intersection;

[0125] All intersection points where the abnormal parameters are greater than the second parameter threshold are screened out to obtain multiple noise abnormality locations.

[0126] It can be seen that through the above optional embodiments, the location of noise anomaly can be accurately determined based on the intersection calculation of the connecting line segments corresponding to multiple high-risk location groups, as well as the calculation and screening of multiple parameters corresponding to the intersection, to assist in more efficient and accurate identification of offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0127] As an optional embodiment, in the above step, determining the locations of multiple wind turbines corresponding to the target ocean area based on an image recognition algorithm and satellite image information includes:

[0128] Inputting the satellite image information into a trained wind turbine area segmentation algorithm model to obtain a plurality of wind turbine image portions corresponding to the satellite image information and corresponding image prediction probabilities; optionally, the wind turbine area segmentation algorithm model is trained using a training data set including a plurality of training satellite image information and corresponding wind turbine area annotations;

[0129] The actual coordinate position corresponding to the position of each wind turbine image portion in the satellite image information is determined as the corresponding wind turbine position.

[0130] It can be seen that through the above optional embodiments, the locations of multiple wind power equipment can be accurately determined from satellite image information based on the trained wind power equipment area segmentation algorithm model, so as to facilitate the subsequent precise offshore wind power area, assist in more efficient and accurate identification of offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0131] As an optional embodiment, in the above step, determining the wind power area in the target ocean area based on the noise anomaly location and the wind power equipment location based on a probability algorithm includes:

[0132] For each wind turbine location, determine a circular area with a preset radius value with the wind turbine location as the center, and obtain an equipment range area corresponding to the wind turbine location;

[0133] Calculate the probability of a wind power area corresponding to the location of the wind power equipment based on the location of the noise anomaly within the equipment range;

[0134] The equipment range areas corresponding to the wind power equipment locations with all wind power area probabilities greater than the third probability threshold are determined as wind power areas in the target ocean area.

[0135] It can be seen that through the above optional embodiments, the probability of each wind power equipment location belonging to a wind power area can be calculated based on the noise anomaly position within the range area corresponding to the location, and the wind power areas in the ocean area can be accurately screened out by combining noise factors and image factors, thereby achieving more efficient and accurate identification of offshore wind power areas, reducing the cost and errors of manual identification, and providing a more accurate data basis for subsequent environmental assessment work.

[0136] As an optional embodiment, in the above step, calculating the probability of a wind power area corresponding to the location of the wind power equipment according to the location of the abnormal noise within the equipment range includes:

[0137] Counting the number of abnormal noise locations within the equipment range to obtain noise location parameters corresponding to the wind turbine equipment location;

[0138] Calculate the average value of abnormal parameters corresponding to all noise abnormality locations within the equipment range to obtain the noise abnormality parameter corresponding to the wind turbine equipment location;

[0139] The image prediction probability corresponding to the portion of the wind turbine image corresponding to the wind turbine location and the product of the noise location parameter and the noise anomaly parameter are calculated to obtain the probability of the wind power area corresponding to the wind turbine location.

[0140] It can be seen that through the above optional embodiments, the probability of belonging to a wind power area can be accurately calculated based on the number of locations and abnormality levels corresponding to the noise abnormality locations within the range area corresponding to each wind power equipment location, as well as the image prediction probability of the wind power equipment location, so as to accurately screen out wind power areas in the ocean area based on this in the future, achieve more efficient and accurate identification of offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0141] Example 2

[0142] See also Figure 2 , Figure 2 This is a schematic diagram of the structure of an offshore wind power area identification system disclosed in an embodiment of the present invention. Figure 2 The offshore wind power area identification system described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the offshore wind power area identification system may include:

[0143] The acquisition module 201 is used to acquire satellite image information of a target ocean area and sound information of multiple ocean locations.

[0144] The first determination module 202 is configured to determine a plurality of noise anomaly locations corresponding to a target ocean area based on a noise propagation analysis model and sound information.

[0145] The second determination module 203 is configured to determine the locations of multiple wind turbines corresponding to the target ocean area based on an image recognition algorithm and satellite image information.

[0146] The third determination module 204 is configured to determine the wind power area in the target ocean area based on the abnormal noise location and the wind power equipment location and a probability algorithm.

[0147] It can be seen that the above-mentioned embodiments of the invention can determine the location of noise anomalies based on sound information and noise propagation analysis models, and then determine the location of wind power equipment based on satellite image information and image recognition algorithms, and more accurately and comprehensively determine the wind power areas in the ocean area based on probabilistic algorithms, thereby being able to more efficiently and accurately identify offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0148] As an optional embodiment, the first determination module determines the specific manner of determining multiple noise anomaly locations corresponding to the target ocean area based on the noise propagation analysis model and the sound information, including:

[0149] Based on the preset continuous sound change rules, all ocean locations are grouped according to the sound information corresponding to each ocean location to obtain multiple continuous sound location groups;

[0150] Inputting the sound information corresponding to all ocean locations in each continuous sound location group into a trained noise prediction neural network to obtain a noise prediction probability corresponding to each continuous sound location group; optionally, the noise prediction neural network is trained using a training data set including multiple training sound groups and corresponding labels indicating whether they are wind turbine noise;

[0151] Screening out all continuous sound location groups whose noise prediction probability is greater than a preset first probability threshold to obtain multiple high-risk location groups;

[0152] Based on multiple high-risk location groups, multiple noise anomaly locations corresponding to the target ocean area are determined.

[0153] It can be seen that through the above optional embodiments, ocean locations can be grouped based on continuous sound change rules, and then the noise probability of each location group can be predicted based on a neural network to screen out high-risk location groups, so as to comprehensively and accurately determine the locations of noise anomalies, assist in more efficient and accurate identification of offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0154] As an optional embodiment, the first determination module groups all ocean locations based on preset continuous sound change rules and sound information corresponding to each ocean location to obtain multiple continuous sound location groups in a specific manner including:

[0155] For any two adjacent ocean locations, calculate the location distance between the two ocean locations;

[0156] Calculating the difference in sound parameters between the sound information corresponding to the two ocean locations;

[0157] Calculating the ratio between the difference in sound parameters and the distance between locations to obtain the sound change parameters corresponding to the two ocean locations;

[0158] Based on the dynamic programming algorithm, all ocean locations are grouped and iteratively calculated based on the sound change parameters to obtain multiple continuous sound location groups.

[0159] It can be seen that through the above-mentioned optional embodiments, multiple continuous sound position groups can be obtained based on the calculation of sound change parameters between ocean positions and the iterative grouping of the dynamic programming algorithm, so as to comprehensively and accurately determine the abnormal noise location in the subsequent period, assist in more efficient and accurate identification of offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0160] As an optional embodiment, the first determination module performs iterative calculations on all ocean locations based on the sound change parameters based on a dynamic programming algorithm to obtain a plurality of continuous sound location groups in a specific manner, including:

[0161] The objective function is set to maximize the total number of ocean locations in each continuous sound location group;

[0162] The restriction conditions include that the curvature of the lowest curvature line segment connecting all ocean positions included in each continuous sound position group is less than a preset curvature threshold, the sound change parameters of any two ocean positions in each continuous sound position group are greater than a first parameter threshold, and the sound propagation prediction probability corresponding to each continuous sound position group is greater than a preset second probability threshold; optionally, the sound propagation prediction probability is obtained by inputting a parameter sequence of sound change parameters corresponding to all ocean positions in the continuous sound position group arranged in position order into a trained sound propagation prediction neural network; the noise prediction neural network is obtained by a training data set including a plurality of training sound change parameter sequences and corresponding labels of whether the sound is continuously propagated;

[0163] Based on the dynamic programming algorithm, all ocean positions are grouped and iteratively calculated according to the objective function and constraints until convergence, and multiple continuous sound position groups are obtained.

[0164] It can be seen that through the above optional embodiments, multiple continuous sound position groups can be obtained based on the preset objective function and constraints and the iterative calculation grouping of the dynamic programming algorithm, so as to comprehensively and accurately determine the abnormal noise location in the subsequent process, assist in more efficient and accurate identification of offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0165] As an optional embodiment, the specific manner in which the first determining module determines the multiple noise anomaly locations corresponding to the target ocean area based on the multiple high-risk location groups includes:

[0166] Connect all ocean locations included in each high-risk location group with the lowest curvature to obtain the high-risk line segment corresponding to each high-risk location group;

[0167] Calculate the intersections of all high-risk line segments to obtain multiple intersection points;

[0168] For each intersection point, calculate the number of high-risk line segments where the intersection point is located;

[0169] Calculate the average number of ocean locations corresponding to the high-risk location groups corresponding to all high-risk line segments where the intersection point is located, and obtain the location quantity parameter corresponding to the intersection point;

[0170] Calculate the weighted sum average of the number of line segments and the number of positions to obtain the anomaly parameter corresponding to the intersection;

[0171] All intersection points where the abnormal parameters are greater than the second parameter threshold are screened out to obtain multiple noise abnormality locations.

[0172] It can be seen that through the above optional embodiments, the location of noise anomaly can be accurately determined based on the intersection calculation of the connecting line segments corresponding to multiple high-risk location groups, as well as the calculation and screening of multiple parameters corresponding to the intersection, to assist in more efficient and accurate identification of offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0173] As an optional embodiment, the second determination module determines the locations of multiple wind turbines corresponding to the target ocean area based on an image recognition algorithm and satellite image information in a specific manner including:

[0174] Inputting the satellite image information into a trained wind turbine area segmentation algorithm model to obtain a plurality of wind turbine image portions corresponding to the satellite image information and corresponding image prediction probabilities; optionally, the wind turbine area segmentation algorithm model is trained using a training data set including a plurality of training satellite image information and corresponding wind turbine area annotations;

[0175] The actual coordinate position corresponding to the position of each wind turbine image portion in the satellite image information is determined as the corresponding wind turbine position.

[0176] It can be seen that through the above optional embodiments, the locations of multiple wind power equipment can be accurately determined from satellite image information based on the trained wind power equipment area segmentation algorithm model, so as to facilitate the subsequent precise offshore wind power area, assist in more efficient and accurate identification of offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0177] As an optional embodiment, the third determination module determines the specific manner of the wind power area in the target ocean area based on the noise anomaly location and the wind power equipment location and a probability algorithm, including:

[0178] For each wind turbine location, determine a circular area with a preset radius value with the wind turbine location as the center, and obtain an equipment range area corresponding to the wind turbine location;

[0179] Calculate the probability of a wind power area corresponding to the location of the wind power equipment based on the location of the noise anomaly within the equipment range;

[0180] The equipment range areas corresponding to the wind power equipment locations with all wind power area probabilities greater than the third probability threshold are determined as wind power areas in the target ocean area.

[0181] It can be seen that through the above optional embodiments, the probability of each wind power equipment location belonging to a wind power area can be calculated based on the noise anomaly position within the range area corresponding to the location, and the wind power areas in the ocean area can be accurately screened out by combining noise factors and image factors, thereby achieving more efficient and accurate identification of offshore wind power areas, reducing the cost and errors of manual identification, and providing a more accurate data basis for subsequent environmental assessment work.

[0182] As an optional embodiment, the third determination module calculates the probability of a wind power area corresponding to the wind power equipment location according to the abnormal noise location within the equipment range, including:

[0183] Counting the number of abnormal noise locations within the equipment range to obtain noise location parameters corresponding to the wind turbine equipment location;

[0184] Calculate the average value of abnormal parameters corresponding to all noise abnormality locations within the equipment range to obtain the noise abnormality parameter corresponding to the wind turbine equipment location;

[0185] The image prediction probability corresponding to the portion of the wind turbine image corresponding to the wind turbine location and the product of the noise location parameter and the noise anomaly parameter are calculated to obtain the probability of the wind power area corresponding to the wind turbine location.

[0186] It can be seen that through the above optional embodiments, the probability of belonging to a wind power area can be accurately calculated based on the number of locations and abnormality levels corresponding to the noise abnormality locations within the range area corresponding to each wind power equipment location, as well as the image prediction probability of the wind power equipment location, so as to accurately screen out wind power areas in the ocean area based on this in the future, achieve more efficient and accurate identification of offshore wind power areas, reduce the cost and errors of manual identification, and provide a more accurate data basis for subsequent environmental assessment work.

[0187] Example 3

[0188] See also Figure 3 , Figure 3 This is another offshore wind power area identification system disclosed in an embodiment of the present invention. Figure 3 The offshore wind power area identification system described is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the offshore wind power area identification system may include:

[0189] A memory 301 storing executable program code;

[0190] a processor 302 coupled to the memory 301;

[0191] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the offshore wind power area identification method described in the first embodiment.

[0192] Example 4

[0193] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the offshore wind power area identification method described in the first embodiment.

[0194] Example 5

[0195] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the offshore wind power area identification method described in Example 1.

[0196] The foregoing description of specific embodiments of the present disclosure is intended to illustrate a method for performing a multi-tasking process. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0197] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0198] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0199] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0200] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0201] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0202] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0203] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0204] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0205] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0206] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0207] This specification may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0208] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0209] Finally, it should be noted that the method and system for identifying offshore wind power areas disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for identifying an offshore wind power area, characterized in that: The method comprises: Obtain satellite image information of the target ocean area and sound information of multiple ocean locations; Based on the noise propagation analysis model and the sound information, multiple noise anomaly locations corresponding to the target ocean area are determined, including: Based on a preset continuous sound change rule, grouping all the ocean locations according to the sound information corresponding to each of the ocean locations to obtain a plurality of continuous sound location groups; Inputting the sound information corresponding to all the ocean locations in each of the continuous sound location groups into a trained noise prediction neural network to obtain a noise prediction probability corresponding to each of the continuous sound location groups; the noise prediction neural network is trained using a training data set including multiple training sound groups and corresponding labels indicating whether they are wind turbine noise; Screening out all the continuous sound position groups whose noise prediction probability is greater than a preset first probability threshold to obtain a plurality of high-risk position groups; Determining, based on the multiple high-risk location groups, multiple noise anomaly locations corresponding to the target ocean area; Determining the locations of multiple wind turbines corresponding to the target ocean area based on an image recognition algorithm and the satellite image information; Based on the abnormal noise location and the wind power equipment location, and based on a probability algorithm, a wind power area in the target ocean area is determined.

2. The offshore wind power area identification method according to claim 1, characterized in that: The method further comprises grouping all the ocean locations based on the preset continuous sound change rule according to the sound information corresponding to each ocean location to obtain a plurality of continuous sound location groups, including: For any two adjacent ocean locations, calculating the distance between the two ocean locations; Calculating a difference in sound parameters between the sound information corresponding to the two ocean locations; Calculating the ratio between the sound parameter difference and the position distance to obtain the sound change parameters corresponding to the two ocean positions; Based on a dynamic programming algorithm, all the ocean positions are grouped and iteratively calculated based on the sound change parameters to obtain multiple continuous sound position groups.

3. The method for identifying an offshore wind power area according to claim 2, characterized in that: The dynamic programming algorithm is used to perform grouping and iterative calculations on all the ocean locations based on the sound change parameters to obtain multiple continuous sound location groups, including: Setting the objective function to maximize the total number of ocean locations in each continuous sound location group; The restriction conditions include that the curvature of the lowest curvature line segment formed by connecting all the ocean positions included in each continuous sound position group is less than a preset curvature threshold, the sound change parameters of any two ocean positions in each continuous sound position group are greater than a first parameter threshold, and the sound propagation prediction probability corresponding to each continuous sound position group is greater than a preset second probability threshold; the sound propagation prediction probability is obtained by inputting a parameter sequence of the sound change parameters corresponding to all the ocean positions in the continuous sound position group, arranged in position order, into a trained sound propagation prediction neural network; the noise prediction neural network is trained using a training data set including multiple training sound change parameter sequences and corresponding labels of whether the sound is continuously propagated; Based on a dynamic programming algorithm, according to the objective function and the constraint conditions, all the ocean positions are grouped and iteratively calculated until convergence, thereby obtaining a plurality of continuous sound position groups.

4. The offshore wind power area identification method according to claim 1, characterized in that: Determining, based on the multiple high-risk location groups, multiple noise anomaly locations corresponding to the target ocean area includes: Connecting all the ocean locations included in each high-risk location group with the lowest curvature to obtain a high-risk line segment corresponding to each high-risk location group; Calculating intersections of all the high-risk line segments to obtain multiple intersection points; For each intersection point, calculate the number of line segments of the high-risk line segment where the intersection point is located; Calculating the average number of ocean locations corresponding to the high-risk location group corresponding to all the high-risk line segments where the intersection point is located, to obtain a location quantity parameter corresponding to the intersection point; Calculating a weighted average of the number of line segments and the number of positions to obtain an abnormality parameter corresponding to the intersection point; All the intersections whose abnormal parameters are greater than the second parameter threshold are screened out to obtain multiple noise abnormality positions.

5. The offshore wind power area identification method according to claim 4, characterized in that: The determining of the locations of multiple wind turbines corresponding to the target ocean area based on the image recognition algorithm and the satellite image information includes: Inputting the satellite image information into a trained wind turbine area segmentation algorithm model to obtain a plurality of wind turbine image portions corresponding to the satellite image information and corresponding image prediction probabilities; the wind turbine area segmentation algorithm model is trained using a training data set including a plurality of training satellite image information and corresponding wind turbine area annotations; The actual coordinate position corresponding to the position of each wind turbine image portion in the satellite image information is determined as the corresponding wind turbine position.

6. The offshore wind power area identification method according to claim 5, characterized in that: The determining of the wind power area in the target ocean area based on the abnormal noise location and the wind power equipment location and a probability algorithm includes: For each wind turbine location, determine a circular area with a preset radius value with the wind turbine location as the center, and obtain an equipment range area corresponding to the wind turbine location; Calculating the probability of a wind power area corresponding to the location of the wind power equipment according to the location of the abnormal noise within the range of the equipment; The equipment range areas corresponding to the wind power equipment locations whose wind power area probabilities are greater than a third probability threshold are determined as wind power areas in the target ocean area.

7. The method for identifying an offshore wind power area according to claim 6, characterized in that: The calculating, based on the abnormal noise location being within the equipment range, a probability of a wind power area corresponding to the wind power equipment location, includes: Counting the number of the abnormal noise locations within the equipment range to obtain noise location parameters corresponding to the wind power equipment location; Calculating an average value of the abnormal parameters corresponding to all the abnormal noise locations within the equipment range to obtain the abnormal noise parameter corresponding to the wind power equipment location; The product of the image prediction probability corresponding to the portion of the wind power equipment image corresponding to the wind power equipment position, the noise position parameter, and the noise anomaly parameter is calculated to obtain the wind power area probability corresponding to the wind power equipment position.

8. An offshore wind power area identification system, characterized in that: The system comprises: an acquisition module for acquiring satellite image information of a target ocean area and sound information of multiple ocean locations; The first determination module is configured to determine a plurality of noise anomaly locations corresponding to the target ocean area based on a noise propagation analysis model and the sound information, including: Based on a preset continuous sound change rule, grouping all the ocean locations according to the sound information corresponding to each of the ocean locations to obtain a plurality of continuous sound location groups; Inputting the sound information corresponding to all the ocean locations in each of the continuous sound location groups into a trained noise prediction neural network to obtain a noise prediction probability corresponding to each of the continuous sound location groups; the noise prediction neural network is trained using a training data set including multiple training sound groups and corresponding labels indicating whether they are wind turbine noise; Screening out all the continuous sound position groups whose noise prediction probability is greater than a preset first probability threshold to obtain a plurality of high-risk position groups; Determining, based on the multiple high-risk location groups, multiple noise anomaly locations corresponding to the target ocean area; a second determination module, configured to determine locations of multiple wind turbines corresponding to the target ocean area based on an image recognition algorithm and the satellite image information; The third determination module is configured to determine the wind power area in the target ocean area based on the abnormal noise location and the wind power equipment location and a probability algorithm.

9. An offshore wind power area identification system, characterized in that: The system comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the offshore wind power area identification method according to any one of claims 1 to 7.

Images