A wave parameter inversion method and related components

Abstract

The present invention discloses a method for inverting ocean wave parameters and related components. In the scheme, an inverted ocean wave parameter model capable of inverting ocean wave parameters is pre-trained. By inputting the first wind data set, the first temperature and the first inertial navigation data set representing the ocean wave parameters of the sea area measured by an offshore floating wind laser radar within a first preset time period as input items into the pre-trained inverted ocean wave parameter model, the ocean wave parameters of the sea area within the first preset time period can be obtained. Compared with the prior art, the function of the ocean wave buoy sensor is integrated into the offshore floating wind laser radar, realizing the inversion of ocean wave parameters from the data measured by the offshore floating wind laser radar, reducing the cost, and being able to timely and accurately determine the ocean wave parameters at different times, making up for the data loss that is easy to occur when using the ocean wave buoy sensor in the prior art, which is beneficial to the subsequent construction of offshore wind farms.

Description

Technical Field

[0001] The invention relates to the field of ocean dynamics, and in particular to an ocean wave parameter inversion method and related components. Background Art

[0002] As a clean and renewable energy, wind resources are one of the alternatives to traditional fossil energy and have great application and development potential. Although my country's offshore wind farms have been developed for many years, there is still a lot of room for exploration in terms of wind resource utilization and power generation. The feasibility of offshore wind farm construction cannot be separated from the corresponding wind resource assessment and wave parameter investigation to ensure the maximum utilization of wind resources while reducing the difficulty of wind turbine construction and ensuring wind turbine safety.

[0003] For wind resource assessment, currently, floating wind measurement lidar installed on an offshore buoy platform is usually used to accurately measure offshore wind field information and obtain wind resource data.

[0004] The monitoring of wave parameters currently mainly uses wave buoy sensors to collect wave parameters within a set range. However, a single wave buoy sensor can only provide sea condition information within a small set range. As the waves surge, the wave buoy sensor is likely to float out of the set range, resulting in loss of measurement data. In addition, the cost of the buoy sensor is relatively high, and subsequent maintenance after deployment is difficult. It can be seen that this method is difficult to achieve long-term wave parameter monitoring in a large area of ​​sea.

[0005] A large number of studies have shown that as an important driving factor of the upper ocean, the sea level wind field is closely related to the ocean dynamic process, especially the wave parameters. Therefore, it is of great significance to combine and establish a connection between the data measured by the wind lidar and the wave parameters, and realize the application of the wind lidar data to the wave parameters. However, due to the differences in application performance and spatiotemporal resolution of the wave parameter monitoring methods, the existing technology has not yet achieved the quantitative inversion of wave parameters using the data measured by the wind lidar. Summary of the invention

[0006] The purpose of the present invention is to provide a wave parameter inversion method and related components, which integrates the function of a wave buoy sensor on an offshore floating wind measurement laser radar, realizes the inversion of wave parameters from data measured by the offshore floating wind measurement laser radar, can timely and accurately determine the wave parameters at different times, make up for the data loss that is prone to occur when using wave buoy sensors, and is beneficial to the subsequent construction of offshore wind farms.

[0007] In order to solve the above technical problems, the present invention provides a wave parameter inversion method, which is applied to a processor in an offshore floating wind laser radar, wherein the offshore floating wind laser radar is arranged on an offshore buoy platform;

[0008] The ocean wave parameter inversion method comprises:

[0009] Acquire a first wind data set, a first temperature, and a first inertial navigation data set of sea wave parameters characterizing the sea area measured by the offshore floating wind laser radar within a first preset time period;

[0010] Inputting the first wind data set, the first temperature and the first inertial navigation data set as input items into a pre-trained inversion wave parameter model;

[0011] Determine that the output item of the inversion wave parameter model is the wave parameter of the sea area within the first preset time length.

[0012] Preferably, the first wind data set includes the wind speed and wind direction at each first preset height measured by the offshore floating wind measurement lidar within a wind measurement height threshold, and the maximum value of all the first preset heights is the wind measurement height threshold set by the offshore floating wind measurement lidar.

[0013] Preferably, the first temperature includes the temperature of the sea level of the sea area measured by a temperature sensor in the offshore floating wind laser radar.

[0014] Preferably, the first inertial navigation data set includes radar pitch correction, roll correction and motion speed correction of the offshore buoy platform relative to the actual motion direction of the waves measured by the inertial navigation system in the offshore floating wind measurement laser radar.

[0015] Preferably, after determining that the output item of the inversion wave parameter model is the wave parameter of the sea area within the first preset time period, the method further includes:

[0016] The display module is controlled to display the wave parameters.

[0017] Preferably, the pre-training process of the inversion wave parameter model includes:

[0018] S11: obtaining a first data set of sea wave parameters characterizing the sea area measured by the offshore floating wind laser radar within a second preset time period, wherein the first data set includes each third preset time period, a second wind data set corresponding to each third preset time period, a second temperature and a second inertial navigation data set, and the sum of all the third preset time periods is the second preset time period;

[0019] S12: Acquire a second data set measured by the wave buoy sensor within the second preset time period, wherein the second data set includes each of the third preset time periods and the wave parameters of the sea area corresponding to each of the third preset time periods;

[0020] S13: inputting the first data set as an input item into a neural network model;

[0021] S14: Inputting the second data set as an output item into the neural network model;

[0022] S15: performing a j-th learning using the neural network model, where j is an integer not less than 1;

[0023] S16: Determine whether the learning accuracy of the neural network model learned for the jth time meets a preset threshold, if so, proceed to S18; if not, proceed to S17;

[0024] S17: Set j=j+1 and return to S15;

[0025] S18: Stop learning and determine that the neural network model at this time is the inversion wave parameter model.

[0026] Preferably, the neural network model includes a combination of one or more of a BP neural network, a convolutional neural network, a recurrent neural network and a long short-term memory neural network.

[0027] In order to solve the above technical problems, the present invention also provides a wave parameter inversion system, comprising:

[0028] An acquisition unit, used to acquire a first wind data set, a first temperature and a first inertial navigation data set of sea wave parameters characterizing a sea area measured by the offshore floating wind laser radar within a first preset time period;

[0029] An input unit, configured to input the first wind data set, the first temperature and the first inertial navigation data set as input items into a pre-trained inversion wave parameter model;

[0030] An output determination unit is used to determine that the output item of the inversion wave parameter model is the wave parameter of the sea area within the first preset time length.

[0031] In order to solve the above technical problems, the present invention also provides a wave parameter inversion device, comprising:

[0032] Memory for storing computer programs;

[0033] A processor is used to implement the steps of the wave parameter inversion method as described above when executing the computer program.

[0034] In order to solve the above technical problems, the present invention also provides an offshore floating wind measurement laser radar, which is arranged on an offshore buoy platform and includes the wave parameter inversion device as described above.

[0035] The present invention provides a method for inverting sea wave parameters and related components. The solution is applied to a processor in an offshore floating wind laser radar set on an offshore buoy platform. An inverted sea wave parameter model capable of inverting sea wave parameters is pre-trained. Therefore, by inputting the first wind data set, the first temperature and the first inertial navigation data set that can characterize the sea wave parameters of the sea area measured by the offshore floating wind laser radar within a first preset time period as input items into the pre-trained inverted sea wave parameter model, the sea wave parameters of the sea area within the first preset time period can be obtained. Compared with the prior art, the function of the wave buoy sensor is integrated on the offshore floating wind laser radar, realizing the inversion of sea wave parameters from the data measured by the offshore floating wind laser radar, and reducing the cost. Furthermore, the offshore floating wind measuring lidar is not easy to damage, and because the offshore floating wind measuring lidar is installed on an offshore buoy platform, subsequent management is more convenient, and there will be no situation where the wave buoy sensor in the prior art drifts out of the preset range with the movement of the waves and causes data loss. The wave parameters at different times can be determined timely and accurately, making up for the data loss that is easy to occur in the prior art using wave buoy sensors, which is conducive to the subsequent construction of offshore wind farms. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the prior art and the drawings required for use in the embodiments are briefly introduced below. 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.

[0037] Figure 1 A flow chart of a method for inverting ocean wave parameters provided by the present invention;

[0038] Figure 2 A schematic diagram of the structure of a wave parameter inversion system provided by the present invention;

[0039] Figure 3 A schematic structural diagram of a wave parameter inversion device provided by the present invention. DETAILED DESCRIPTION

[0040] The core of the present invention is to provide a method for inverting wave parameters and related components. The function of a wave buoy sensor is integrated into an offshore floating wind laser radar, realizing the inversion of wave parameters from data measured by the offshore floating wind laser radar. The wave parameters at different times can be determined timely and accurately, making up for the data loss that is prone to occur when using wave buoy sensors, which is beneficial to the subsequent construction of offshore wind farms.

[0041] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] Please refer to Figure 1 , Figure 1 The present invention provides a flow chart of a method for inverting ocean wave parameters.

[0043] The wave parameter inversion method is applied to a processor in an offshore floating wind laser radar, which is arranged on an offshore buoy platform;

[0044] The wave parameter inversion method includes:

[0045] S21: Acquire a first wind data set, a first temperature, and a first inertial navigation data set representing sea wave parameters of a sea area measured by an offshore floating wind laser radar within a first preset time period;

[0046] S22: inputting the first wind data set, the first temperature and the first inertial navigation data set as input items into a pre-trained inversion wave parameter model;

[0047] S23: Determine that the output item of the inversion wave parameter model is the wave parameter of the sea area within the first preset time length.

[0048] In this embodiment, considering that sea waves are one of the characteristics of ocean dynamics, studying the generation, evolution mechanism and spatiotemporal distribution of sea waves and revealing their internal structure and external distribution characteristics have become an important research field in physical oceanography. It is of great significance to national defense, shipping, shipbuilding, ports, and the construction and safety of offshore oil platforms and offshore wind farms. In the prior art, the monitoring of sea wave parameters mainly uses sea wave buoy sensors to collect sea wave parameters within a set range, but the sea wave buoy sensors in this method can only measure the sea condition information within a set small range, and there are shortcomings such as missing measurement data, high cost and difficult maintenance. In order to solve the above technical problems, the present application provides a sea wave parameter inversion method, which is applied to the processor in the offshore floating wind measurement laser radar, and realizes the inversion of sea wave parameters from the data measured by the offshore floating wind measurement laser radar.

[0049] Specifically, considering that sea waves are a kind of wind-generated gravity waves, they are closely related to the sea surface wind field, and there is an inevitable connection between the inertial navigation data of the offshore floating laser radar and the sea waves. At the same time, sea waves are elements driven by the interaction between the sea and the air. The use of the offshore floating laser wind radar to invert sea waves has good application potential. Therefore, in this method, the first wind data set, the first temperature and the first inertial navigation data set that characterize the sea wave parameters of the sea area measured by the offshore floating wind laser radar within the first preset time length are first obtained. The first preset time length here is the time interval between the current return data time of the offshore floating wind laser radar and the last return data time, such as 10 minutes. This application is not particularly limited here, and it is determined according to the working performance of the specific offshore floating wind laser radar. Then, the first wind data set, the first temperature and the first inertial navigation data set are input as input items into the pre-trained inversion sea wave parameter model, so that the output item of the inversion sea wave parameter model is determined to be the sea wave parameters of the sea area within the first preset time length.

[0050] In summary, the present application provides a method for inverting ocean wave parameters, which is applied to a processor in an offshore floating wind laser radar arranged on an offshore buoy platform, and a pre-trained inversion ocean wave parameter model capable of inverting ocean wave parameters is pre-trained. Therefore, by inputting the first wind data set, the first temperature and the first inertial navigation data set that can characterize the ocean wave parameters of the sea area measured by the offshore floating wind laser radar within a first preset time period as input items into the pre-trained inversion ocean wave parameter model, the ocean wave parameters of the sea area within the first preset time period can be obtained. Compared with the prior art, the function of the wave buoy sensor is integrated into the offshore floating wind laser radar, realizing the inversion of ocean wave parameters from the data measured by the offshore floating wind laser radar, and reducing the cost. Furthermore, the offshore floating wind measuring lidar is not easy to damage, and because the offshore floating wind measuring lidar is installed on an offshore buoy platform, subsequent management is more convenient, and there will be no situation where the wave buoy sensor in the prior art drifts out of the preset range with the movement of the waves and causes data loss. The wave parameters at different times can be determined timely and accurately, making up for the data loss that is easy to occur in the prior art using wave buoy sensors, which is conducive to the subsequent construction of offshore wind farms.

[0051] Based on the above embodiments:

[0052] As a preferred embodiment, the first wind data set includes the wind speed and wind direction at each first preset height within a wind measurement height threshold measured by the offshore floating wind measurement lidar, and the maximum value of all the first preset heights is the wind measurement height threshold set by the offshore floating wind measurement lidar.

[0053] In the present application, the first data set may include the wind speed and wind direction at each first preset height measured by the offshore floating wind laser radar within the wind measurement height threshold, wherein the maximum value among all the first preset heights is the wind measurement height threshold set by the offshore floating wind laser radar. It can be seen that in this way, one of the input items for inputting the inversion wave parameter model can be simply and effectively obtained.

[0054] It should be noted that the measurement height threshold here is the maximum distance at which the offshore floating wind measuring laser radar can measure data, such as 350 meters. The present application does not make any special limitation on the specific value of the measurement height threshold, which is determined according to the working performance of the specific offshore floating wind measuring laser radar; the first preset heights here are the heights corresponding to the data measured by the offshore floating wind measuring laser radar at various heights above the sea level within the wind measurement height threshold range. The present application does not make any special limitation here, which is still determined according to the working performance of the specific offshore floating wind measuring laser radar.

[0055] As a preferred embodiment, the first temperature includes the temperature of the sea surface of the sea area measured by a temperature sensor in an offshore floating wind laser radar.

[0056] In the present application, it is considered that the offshore floating wind laser radar includes a temperature sensor, through which the sea surface temperature of the sea area to be measured can be accurately and reliably obtained, and the temperature is one of the input items for inputting the inversion wave parameter model.

[0057] As a preferred embodiment, the first inertial navigation data set includes radar pitch correction, roll correction and motion speed correction of the offshore buoy platform relative to the actual motion direction of the waves measured by the inertial navigation system in the offshore floating wind measurement laser radar.

[0058] In the present application, taking into account that the offshore floating wind measurement lidar includes an inertial navigation system, the inertial navigation system can accurately and reliably obtain a first inertial navigation data set that is closely related to the wave parameters, including the radar pitch correction, roll correction and the motion speed correction of the offshore buoy platform relative to the actual motion direction of the waves. The inertial navigation system does not rely on external information and does not radiate energy to the outside, and can simply and effectively obtain one of the input items for inputting the inversion wave parameter model.

[0059] As a preferred embodiment, after determining that the output item of the inversion wave parameter model is the wave parameter of the sea area within the first preset time length, it also includes:

[0060] The control display module displays the wave parameters.

[0061] In this embodiment, in order to more intuitively display the wave parameters obtained through inversion, in this application, after determining that the output item of the inversion wave parameter model is the wave parameter of the sea area within the first preset time length, the processor will also control the display module to display the wave parameter.

[0062] It can be seen that this method can display the output results of the inversion wave parameter model, namely the wave parameters, to the developers in a more intuitive way, which is convenient for the developers to record and process later.

[0063] As a preferred embodiment, the pre-training process of the inversion wave parameter model includes:

[0064] S11: obtaining a first data set of sea wave parameters characterizing the sea area measured by an offshore floating wind laser radar within a second preset time period, wherein the first data set includes each third preset time period, a second wind data set corresponding to each third preset time period, a second temperature, and a second inertial navigation data set, and the sum of all the third preset time periods is the second preset time period;

[0065] S12: Acquire a second data set measured by the wave buoy sensor within a second preset time period, the second data set including each third preset time period and the wave parameters of the sea area corresponding to each third preset time period;

[0066] S13: Inputting the first data set as an input item into the neural network model;

[0067] S14: inputting the second data set as an output item into the neural network model;

[0068] S15: performing a j-th learning using the neural network model, where j is an integer not less than 1;

[0069] S16: Determine whether the learning accuracy of the neural network model learned for the jth time meets the preset threshold, if so, proceed to S18; if not, proceed to S17;

[0070] S17: Set j=j+1 and return to S15;

[0071] S18: Stop learning and determine that the neural network model at this time is an inversion wave parameter model.

[0072] In this application, a neural network model is used to implement the pre-training process of the inversion wave parameter model.

[0073] Specifically, a first data set of wave parameters characterizing the sea area measured by an offshore floating wind measurement lidar within a second preset time period is obtained, wherein the first data set includes each third preset time period, a second wind data set corresponding to each third preset time period, a second temperature and a second inertial navigation data set, and the sum of all the third preset time periods is the second preset time period. It should be noted that the second wind data set here may include the wind speed and wind direction at each second preset height measured by the offshore floating wind measuring laser radar within the wind measurement height threshold within each third preset time period, the sum of all the second preset heights is the wind measurement height threshold and each second preset height is the height corresponding to the data measured by the offshore floating wind measuring laser radar at each height from the sea level within the wind measurement height threshold range; the second temperature here may include the sea level temperature of the sea area measured by the temperature sensor in the offshore floating wind measuring laser radar within each third preset time period; the second inertial navigation data set here may include the radar pitch correction, roll correction and movement speed correction of the offshore buoy platform relative to the actual movement direction of the waves measured by the inertial navigation system in the offshore floating wind measuring laser radar within each third preset time period; the third preset time period here may be the time interval between the current return data time of the offshore floating wind measuring laser radar and the last return data time, such as 10 minutes, which is not specifically limited in this application and is determined according to the working performance of the specific offshore floating wind measuring laser radar.

[0074] The second data set measured by the wave buoy sensor within the second preset time length is obtained, and the second data set includes each third preset time length and the wave parameters of the sea area corresponding to each third preset time length, and then the first data set is input into the neural network model as the input item of the neural network model, and the second data set is input into the neural network model as the output item of the neural network model, thereby establishing the input-output correspondence relationship under each third preset time length so that the neural network model can perform corresponding learning. It should be noted that since the input-output relationship under each third preset time length is established, if there is only the first data set input for a certain third preset time length and there is no corresponding second data set due to the lack of measurement data of the wave buoy sensor, the neural network model will not perform learning for the third preset time length.

[0075] Then the neural network model is used for the jth learning, and it is determined whether the learning accuracy of the neural network model learned for the jth time meets the preset threshold. If so, it means that the training requirements are met, the learning is stopped and the neural network model at this time is determined to be the inversion wave parameter model; if not, it means that the training requirements are not met, and j=j+1 is set and the learning continues. It should be noted that the preset threshold here is set according to the learning accuracy that the actual neural network model training ultimately needs to achieve, and this application does not make any special restrictions here.

[0076] It should also be noted that in order to ensure the effect of training, the second preset time length here needs to be long enough to ensure that the amount of data used for training is sufficient. Therefore, the second preset time length is much longer than the third preset time length. For example, it can be 3 months. The present application does not make any special restrictions here. In addition, what is considered here is that the time interval required for the wave buoy sensor and the offshore floating wind measurement laser radar to return data is the same, that is, the third preset time length. If the time intervals for the subsequent return of data are different, it is only necessary to process the data accordingly, such as taking the time interval for the return of data from the wave buoy sensor as a benchmark, and calculating the average value of each data returned by the offshore floating wind measurement laser radar within this time interval so that the time intervals between the two can match. The present application does not make any special restrictions here.

[0077] It can be seen that this method can reliably and accurately establish an inversion model of wave parameters, realizing the inversion of wave parameters from data measured by the offshore floating wind lidar.

[0078] As a preferred embodiment, the neural network model includes a combination of one or more of a BP neural network, a convolutional neural network, a recurrent neural network, and a long short-term memory neural network.

[0079] In this embodiment, the neural network model used to obtain the inversion wave parameter model may include one of a BP neural network, a convolutional neural network, a recurrent neural network and a long short-term memory neural network. Alternatively, according to actual application needs, the neural network model may also include a combination of multiple BP neural networks, convolutional neural networks, recurrent neural networks and long short-term memory neural networks.

[0080] It should be noted that only BP neural network, convolutional neural network, recurrent neural network and long short-term memory neural network are listed here. Other neural networks can also be used in actual use. This application does not make any special limitations here and it depends on actual needs.

[0081] It can be seen that the inversion wave parameter model for wave inversion can be obtained simply and reliably in this way, and the accuracy and reliability of the model are high.

[0082] Please refer to Figure 2 , Figure 2 A schematic structural diagram of a wave parameter inversion system provided by the present invention.

[0083] The wave parameter inversion system includes:

[0084] An acquisition unit 31 is used to acquire a first wind data set, a first temperature and a first inertial navigation data set representing sea wave parameters of a sea area measured by an offshore floating wind laser radar within a first preset time period;

[0085] An input unit 32, used for inputting the first wind data set, the first temperature and the first inertial navigation data set as input items into a pre-trained inversion wave parameter model;

[0086] The output determination unit 33 is used to determine that the output item of the inversion wave parameter model is the wave parameter of the sea area within the first preset time length.

[0087] For an introduction to the ocean wave parameter inversion system provided in the present invention, please refer to the above-mentioned embodiments of the ocean wave parameter inversion method, which will not be described in detail here.

[0088] Please refer to Figure 3 , Figure 3 A schematic structural diagram of a wave parameter inversion device provided by the present invention.

[0089] The wave parameter inversion device comprises:

[0090] A memory 41, used for storing computer programs;

[0091] The processor 42 is used to implement the steps of the above-mentioned wave parameter inversion method when executing the computer program.

[0092] For an introduction to the ocean wave parameter inversion device provided in the present invention, please refer to the above-mentioned embodiment of the ocean wave parameter inversion method, which will not be described in detail here.

[0093] The present invention also provides an offshore floating wind measurement laser radar, which is arranged on an offshore buoy platform and includes the above-mentioned wave parameter inversion device.

[0094] For an introduction to the offshore floating wind measurement laser radar provided in the present invention, please refer to the above-mentioned embodiment of the wave parameter inversion method, which will not be described in detail here.

[0095] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0096] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0097] Professionals may 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. Professionals and technicians may 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 the present invention.

[0098] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for inverting ocean wave parameters, characterized in that: A processor used in an offshore floating wind laser radar, wherein the offshore floating wind laser radar is arranged on an offshore buoy platform; The ocean wave parameter inversion method comprises: Acquire a first wind data set, a first temperature, and a first inertial navigation data set of sea wave parameters characterizing the sea area measured by the offshore floating wind laser radar within a first preset time period; Inputting the first wind data set, the first temperature and the first inertial navigation data set as input items into a pre-trained inversion wave parameter model; Determining that the output item of the inversion wave parameter model is the wave parameter of the sea area within the first preset time length; Wherein, the first temperature includes the temperature of the sea surface of the sea area measured by the temperature sensor in the offshore floating wind laser radar; Among them, the first inertial navigation data set includes the radar pitch correction, roll correction and movement speed correction of the offshore buoy platform relative to the actual movement direction of the waves measured by the inertial navigation system in the offshore floating wind measurement laser radar.

2. The method for inverting ocean wave parameters according to claim 1, characterized in that: The first wind data set includes the wind speed and wind direction at each first preset height measured by the offshore floating wind measurement laser radar within the wind measurement height threshold, and the maximum value of all the first preset heights is the wind measurement height threshold set by the offshore floating wind measurement laser radar.

3. The method for inverting ocean wave parameters according to claim 1, characterized in that: After determining that the output item of the inversion wave parameter model is the wave parameter of the sea area within the first preset time period, the method further includes: The display module is controlled to display the wave parameters.

4. The method for inverting ocean wave parameters according to any one of claims 1 to 3, characterized in that: The pre-training process of the inversion wave parameter model includes: S11: obtaining a first data set of sea wave parameters characterizing the sea area measured by the offshore floating wind laser radar within a second preset time period, wherein the first data set includes each third preset time period, a second wind data set corresponding to each third preset time period, a second temperature and a second inertial navigation data set, and the sum of all the third preset time periods is the second preset time period; S12: Acquire a second data set measured by the wave buoy sensor within the second preset time period, wherein the second data set includes each of the third preset time periods and the wave parameters of the sea area corresponding to each of the third preset time periods; S13: inputting the first data set as an input item into a neural network model; S14: inputting the second data set as an output item into the neural network model; S15: performing a j-th learning using the neural network model, where j is an integer not less than 1; S16: Determine whether the learning accuracy of the neural network model learned for the jth time meets a preset threshold, if so, proceed to S18; if not, proceed to S17; S17: Set j=j+1 and return to S15; S18: Stop learning and determine that the neural network model at this time is the inversion wave parameter model.

5. The method for inverting ocean wave parameters according to claim 4, characterized in that: The neural network model includes one or more combinations of BP neural network, convolutional neural network, recurrent neural network and long short-term memory neural network.

6. A wave parameter inversion system, characterized in that: include: An acquisition unit, used to acquire a first wind data set, a first temperature, and a first inertial navigation data set representing sea wave parameters of a sea area measured by an offshore floating wind measurement laser radar within a first preset time period; An input unit, configured to input the first wind data set, the first temperature and the first inertial navigation data set as input items into a pre-trained inversion wave parameter model; An output determination unit, used to determine that the output item of the inversion wave parameter model is the wave parameter of the sea area within the first preset time length; Wherein, the first temperature includes the temperature of the sea surface of the sea area measured by the temperature sensor in the offshore floating wind laser radar; Among them, the first inertial navigation data set includes the radar pitch correction, roll correction and motion speed correction of the offshore buoy platform relative to the actual motion direction of the waves measured by the inertial navigation system in the offshore floating wind measurement laser radar.

7. A wave parameter inversion device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the ocean wave parameter inversion method as claimed in any one of claims 1 to 5 when executing the computer program.

8. An offshore floating wind laser radar, characterized in that: It is arranged on an offshore buoy platform and comprises the wave parameter inversion device as claimed in claim 7.

Images