CN117195673A

CN117195673A - Method, device, equipment and storage medium for predicting drift velocity of floater

Info

Publication number: CN117195673A
Application number: CN202210699790.1A
Authority: CN
Inventors: 牟林; 王道胜; 李琰; 秦浩
Original assignee: Shenzhen Lightsun Technology Co ltd; Southern Marine Science and Engineering Guangdong Laboratory Guangzhou
Current assignee: Shenzhen Lightsun Technology Co ltd; Southern Marine Science and Engineering Guangdong Laboratory Guangzhou
Priority date: 2022-05-25
Filing date: 2022-06-20
Publication date: 2023-12-08
Also published as: CN117195675A; CN117195674A; CN117195672A

Abstract

The embodiment of the disclosure provides a method, a device, equipment and a storage medium for predicting drift velocity of a floater. The drift velocity prediction method of the floater comprises the following steps: inquiring unstructured grids used for sea state prediction according to the current position of the floater to be predicted, and determining a preset number of target grid points nearest to the current position; determining a predicted sea state parameter at the current position according to the current position, the position of the target grid point and the predicted sea state parameter; and determining the predicted drift speed of the floater to be predicted at the current position according to the predicted sea state parameter at the current position. After the predicted drift velocity of the to-be-predicted float is determined, the position of the to-be-predicted float at the future moment can be predicted, so that the drift path of the to-be-predicted float is determined, and the drift range of the to-be-predicted float is predicted based on the drift path. That is, based on the drift velocity prediction method for the floater provided by the embodiment of the present disclosure, the drift range of the floater to be predicted can be predicted more accurately.

Description

Method, device, equipment and storage medium for predicting drift velocity of floater

Technical Field

The embodiment of the disclosure relates to the technical field of maritime, in particular to a method, a device, equipment and a storage medium for predicting drift speed of a floater.

Background

Maritime accidents can create a variety of maritime floats. For example, in the event of an oil spill at sea, oil film floats may be generated; in the event of a marine vessel crash, floaters such as crash debris, life rafts, and crash ships may be generated.

In order to quickly perform salvage cleaning of various kinds of marine floaters after a marine accident, it is necessary to determine the approximate floating area where the marine floaters are located. The precondition of determining the approximate floating area of the sea-state floater is that the drift speed of the floater can be reasonably predicted. How to rapidly and accurately predict the drift velocity of a float is a technical problem to be solved.

Disclosure of Invention

In order to solve the above technical problems or at least partially solve the above technical problems, embodiments of the present disclosure provide a method, an apparatus, a device, and a storage medium for predicting drift velocity of a floater.

In a first aspect, embodiments of the present disclosure provide a drift velocity prediction method for a float, including,

inquiring unstructured grids used for sea state prediction according to the current position of a floater to be predicted, and determining a preset number of target grid points nearest to the current position;

Determining a predicted sea state parameter at the current position according to the current position, the position of the target grid point and the predicted sea state parameter, wherein the predicted sea state parameter at the target grid point is determined by numerical prediction according to an assimilated sea state simulation model;

and determining the predicted drift speed of the floater to be predicted at the current position according to the predicted sea state parameter at the current position.

Optionally, the querying the unstructured grid for sea state prediction according to the current position of the floater to be predicted, and determining a preset number of target grid points nearest to the current position, includes:

determining the regional square grid where the floater to be predicted is located according to the current position;

and inquiring unstructured grids used for sea state prediction in the regional square, and determining a preset number of target grid points nearest to the current position.

Optionally, the predicted sea state parameters include wave characteristic parameters, surface water flow characteristic parameters and wind characteristic parameters;

the determining the predicted drift speed of the floating object to be predicted at the current position according to the predicted sea state parameter at the current position comprises the following steps:

Inputting the wave characteristic parameters at the current position into a pre-trained wave-induced drift deep learning model to obtain a wave-induced drift speed, determining the wave-induced drift speed according to the surface water flow characteristic parameters at the current position, and determining the wind-induced drift speed according to the wind characteristic parameters at the current position;

determining the predicted drift velocity according to the flow-induced drift velocity, the wind-induced drift velocity and the wave-induced drift velocity;

the wave-induced drift deep learning model is trained based on first sample drift data, wherein the first sample drift data comprises a sample drift velocity observation value of a sample floater and corresponding sample surface water flow characteristic parameters, sample wind characteristic parameters and sample wave characteristic parameters.

Optionally, before calculating the wind-induced drift velocity according to the wind characteristic parameter at the current position, the method further comprises:

determining the predicted drift bias of the to-be-predicted floating object according to the predicted sea state parameter, wherein the predicted drift bias is the bias of the wind-induced drift direction of the to-be-predicted floating object relative to the wind direction;

the determining the wind-induced drift velocity according to the wind characteristic parameter at the current position comprises the following steps:

And calculating the wind-induced drift speed of the floater to be predicted according to the wind characteristic parameters and the predicted drift bias.

Optionally, the calculating the wind-induced drift velocity of the floater to be predicted according to the wind characteristic parameter and the predicted drift bias comprises:

selecting a corresponding wind-induced drift coefficient according to the wind-induced drift bias;

and calculating the wind-induced drift speed according to the wind characteristic parameter at the current position and the wind-induced drift coefficient.

Optionally, the determining the predicted drift bias of the to-be-predicted float according to the predicted sea state parameter includes:

inputting the predicted sea state parameters into a pre-trained bias deep learning model, and determining the predicted drift bias of the floater to be predicted;

the bias deep learning model is trained based on second sample drift data, wherein the second sample drift data comprises drift bias observations of sample floaters and corresponding sample sea state parameters.

Optionally, the determining the predicted drift speed of the floater to be predicted at the current position according to the predicted sea state parameter at the current position includes:

Adding random disturbance to the predicted sea state parameter at the current position to obtain a disturbed predicted sea state parameter;

and determining the predicted drift speed of the floater to be predicted at the current position according to the disturbed predicted sea state parameters.

In a second aspect, embodiments of the present disclosure provide a drift velocity prediction apparatus for a float, comprising,

a target grid point inquiring unit, configured to inquire unstructured grids used for sea state prediction according to a current position of a floater to be predicted, and determine a preset number of target grid points nearest to the current position;

a sea state parameter determining unit, configured to determine a predicted sea state parameter at the current position according to the position and the predicted sea state parameter of the target grid point, and the current position, where the predicted sea state parameter at the target grid point performs numerical prediction determination according to the assimilated sea state simulation model;

and the predicted drift speed determining unit is used for determining the predicted drift speed of the floater to be predicted at the current position according to the predicted sea state parameter at the current position.

In a third aspect, embodiments of the present disclosure provide a computing device comprising a memory and a processor, wherein the memory has stored therein a computer program which, when executed by the processor, implements a drift velocity method as previously described.

In a fourth aspect, embodiments of the present disclosure provide a computer readable storage medium having a computer program stored therein, which when executed by a processor, implements a drift velocity method as previously described.

Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:

according to the scheme provided by the embodiment of the disclosure, the adjacent target grid points in the unstructured grid used for sea state prediction are determined according to the current position of the floating object to be predicted, the predicted sea state parameters of the position of the floating object to be predicted are estimated by using the predicted sea state parameters of the adjacent target grid points, and the predicted drift speed of the floating object to be predicted is determined according to the predicted sea state parameters, so that the rapid prediction of the predicted drift speed is realized. After the predicted drift velocity of the to-be-predicted floating object is determined, the position of the to-be-predicted floating object at the future moment can be predicted, the drift path of the to-be-predicted floating object is further determined, and the drift range of the to-be-predicted floating object is accurately predicted based on the drift path. That is, based on the drift velocity prediction method for the floater provided by the embodiment of the present disclosure, the drift range of the floater to be predicted can be predicted more quickly and accurately.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.

In order to more clearly illustrate the embodiments of the present disclosure or the solutions in the prior art, the drawings that are required for use in the embodiments or the description of the prior art will be briefly described below, and it will be apparent to those skilled in the art that other drawings can be obtained based on these drawings without inventive faculty.

FIG. 1 is a flow chart of a drift velocity prediction method for a float provided by an embodiment of the present disclosure;

FIG. 2 is a flow chart of a method for determining a sea state simulation model using a cyclic three-dimensional variation assimilation method;

FIG. 3 is a flow chart of a method for determining a sea state simulation model using an efficient ensemble Kalman filtering assimilation method;

FIG. 4 is a flow chart of a method for determining a sea state simulation model using an adaptive optimal interpolation assimilation method;

FIG. 5 is a flowchart of a training method for a wave-induced drift deep learning model provided by an embodiment of the present disclosure;

FIG. 6 is a schematic structural diagram of a drift velocity prediction apparatus for floats provided by embodiments of the present disclosure;

Fig. 7 is a schematic structural diagram of a computing device provided in an embodiment of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below. It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

Fig. 1 is a flowchart of a drift velocity prediction method of a float provided in an embodiment of the present disclosure. As shown in fig. 1, the drift velocity prediction method of the float provided in the embodiment of the present disclosure may include S110 to S130.

It should be noted that the float drift path prediction method provided by the embodiments of the present disclosure is performed by a computing device. The computing device may be a server dedicated to data processing, or may be a computing device such as a notebook computer, an on-board terminal, a Personal Digital Assistant (PDA), a rescuer wearable device, or the like.

S110: and inquiring unstructured grids used for sea state prediction according to the current position of the floater to be predicted, and determining a preset number of target grid points nearest to the current position.

The current position of the floater to be predicted can be obtained by performing time integral calculation according to the historical drift speed of the floater to be predicted. The current position of the float to be predicted may be represented by latitude and longitude, or may be represented by other manners, and the embodiments of the present disclosure are not particularly limited. The aforementioned historical drift velocity is the drift velocity before the float to be predicted drifts to the current position.

The unstructured grid used for sea state prediction is a grid which is established in advance for predicting sea state parameters of various positions in the sea area to be predicted. The unstructured grid used for sea state prediction can be a triangular grid or a grid with other structures.

In the embodiment of the disclosure, the method for determining the target grid points according to unstructured grids used for inquiring sea state prediction according to the current position of the floater to be predicted is to determine the preset number of grid points nearest to the current position. For example, in the case where the sea state unstructured grid is a triangular grid, the target grid point is determined according to the current position of the float to be predicted, and three grid points closest to the current position are determined.

In the embodiment of the disclosure, the position coordinates (specifically, longitude and latitude information) of each grid point in the unstructured grid used for sea state prediction are stored in a memory of a computing device in advance. After obtaining the current position of the float to be predicted, the computing device may retrieve the stored position coordinates of each grid point based on the current position of the float to be predicted, and determine the target grid point and the position of the target grid point.

Alternatively, in some embodiments of the present disclosure, the locations of the various grid points in the sea state unstructured grid may be indexed in a quadtree fashion. After obtaining the location of the float to be predicted, the computing device may retrieve the quadtree to determine the target grid point and its location.

In a specific embodiment, because the sea-state unstructured grid has a large number of grid points, if the quadtree index is directly constructed by adopting the large number of grid points, the resource and time consumption in the retrieval process are overlarge. To avoid this problem, in some embodiments of the present disclosure, the computing device tessellates the target sea area such that the target sea area is divided into a plurality of regional tiles and constructs quadtree indexes for grid points within each regional tile, respectively. On this basis, the computing device may determine the target grid point using S111-S112 after acquiring the current position of the float to be predicted.

S111: and determining the regional square grid where the floater to be predicted is located according to the current position.

In the embodiment of the disclosure, each area square has a unique two-dimensional identifier, and the two-dimensional identifier comprises a longitude direction identifier x and a latitude direction identifier y. Longitude is identified as x= (X-X) ₀ ) A, latitude is marked asWherein X is the longitude coordinate of the longitude minimum point in the area square, Y is the latitude coordinate of the latitude minimum point in the area square, and X ₀ Longitude coordinate of longitude minimum point in all regional squares, Y ₀ And a is the side length of the regional square, which is the latitude coordinate of the latitude minimum point in all the regional squares.

After the position coordinates (X ', Y') of the position of the floating object to be predicted are obtained, the position coordinates (X ', Y') can be used for obtaining (X ', Y'), whereinThe area square where the float to be predicted is located can then be determined using (x ', y').

S112: and inquiring unstructured grids used for sea state prediction in the regional square, and determining a preset number of target grid points nearest to the current position.

After the area square where the floating object to be predicted is located is obtained, the unstructured grid used for sea state prediction in the area square is queried, specifically, the quadtree index corresponding to the area square is queried, and the target grid point can be determined.

By adopting the above-mentioned S111-S112, the unstructured grid used for sea state prediction is divided into smaller area squares, indexes of grid points in each area square are constructed, after the current position of the floating object to be predicted is determined, the corresponding area square is determined according to the current position of the floating object to be predicted, and then the grid points of the unstructured grid used for sea state prediction corresponding to the area square are searched, so that the searched data volume can be reduced, and then the speed of acquiring the target grid points is increased.

S120: and determining the predicted sea state parameter at the current position according to the position of the target grid point and the predicted sea state parameter and the current position.

Because the target grid point is closer to the current position of the floater to be predicted, the sea state characteristic parameters of the target grid point can be used for well estimating the predicted sea state parameters of the position of the floater to be predicted.

In the embodiment of the disclosure, the predicted sea state parameters at the target grid points are determined by numerical prediction according to the assimilated sea state simulation model. Specifically, after determining the sea state simulation model, the computing device may perform numerical prediction according to the sea state parameters at the initial time, and determine predicted sea state parameters of each grid point in the sea state unstructured grid at each time of the period to be predicted.

It should be noted that the predicted sea state parameter at the current position refers to a sea state parameter at the time when the float to be predicted drifts to the current position, and the predicted sea state parameter of the corresponding target grid point is also a sea state parameter at the time when the float to be predicted drifts to the current position.

In some embodiments of the present disclosure, the sea state unstructured grid is a triangular grid, a target gridThe points are three adjacent grid points of the triangular grid. Assume that the longitude and latitude coordinates of the current position of the floater to be predicted are (x) ₀ ,y ₀ ) The longitude and latitude coordinates of the three target grid points are (x ₁ ,y ₁ )、(x ₂ ,y ₂ ) And (x) ₃ ,y ₃ ) The weighting coefficients of the three target grid points may be p, q, and s, respectively, whereThe predicted sea state parameter at the current position of the float to be predicted is z=p×z ₁ +q×z ₂ +s×z ₃ Wherein z is ₁ 、z ₂ And z ₃ Predicted sea state parameters for three adjacent target grid points, respectively.

The foregoing mentions that a sea state simulation model needs to be used for numerical prediction to determine the predicted sea state parameters of each grid point in the sea state unstructured grid. In the embodiment of the disclosure, the sea state simulation model can be obtained by adopting various data assimilation methods and assimilating data according to observed sea state parameters. For example, the computing device may assimilate the sea state observation parameters using a cyclic three-dimensional variation assimilation method, an efficient set kalman filter assimilation method, an adaptive optimal interpolation assimilation method, and the like, to obtain a sea state simulation model. In particular, how to adopt the assimilation method to determine the sea state simulation model and then analyze the sea state simulation model.

S130: and determining the predicted drift speed of the floater to be predicted at the current position according to the predicted sea state parameter at the current position.

Because the floating object to be predicted drifts at sea due to the action of wind wave current on the sea surface, the predicted sea condition parameter is a parameter representing the characteristic of the wind wave current at the position of the floating object to be predicted, and after the predicted sea condition parameter of the current position of the floating object to be predicted is determined, the predicted drift speed of the floating object to be predicted can be determined according to the predicted sea condition parameter at the current position.

By adopting the drift velocity prediction method for the floating object provided by the embodiment of the disclosure, the adjacent target grid points in the unstructured grid used for sea state prediction are determined according to the current position of the floating object to be predicted, the predicted sea state parameters of the position of the floating object to be predicted are predicted by using the predicted sea state parameters of the adjacent target grid points, and the predicted drift velocity of the floating object to be predicted is determined according to the predicted sea state parameters, so that the rapid prediction of the predicted drift velocity is realized. After the predicted drift velocity of the to-be-predicted floating object is determined, the current position of the to-be-predicted floating object at the future moment can be predicted, the drift path of the to-be-predicted floating object is further determined, and the drift range of the to-be-predicted floating object is accurately predicted based on the drift path. That is, based on the drift velocity prediction method for the floater provided by the embodiment of the present disclosure, the drift range of the floater to be predicted can be predicted more quickly and accurately.

As before, after determining the predicted sea state parameter at the current location, the predicted drift velocity of the float to be predicted at the current location may be determined from the predicted sea state parameter. Optionally, in some embodiments of the present disclosure, the predicted sea state parameters include wave characteristic parameters, surface current characteristic parameters, and wind characteristic parameters.

The wave characteristic parameter is a parameter for characterizing the wave characteristics of the surface of the body of water. The wave characteristic parameter may comprise at least one of wave height, wave period and wave direction of the wave.

The surface water flow characteristic parameter is a parameter representing the surface water flow mobility characteristic of the water body. The surface water flow characteristic parameters may include the flow rate and direction of the surface water flow.

The wind characteristic parameter is a parameter for characterizing the crosswind characteristic on the surface of the water body. The wind characteristic parameters may include a wind speed and a wind direction of the wind. In a specific application, the wind characteristic parameters may be wind speed and wind direction at a height of 10m above the water level.

Correspondingly, determining the predicted drift velocity of the float to be predicted at the current location according to the predicted sea state parameter at the current location may comprise S131-S134.

S131: and inputting the wave characteristic parameters at the current position into a pre-trained wave-induced drift deep learning model to obtain the wave-induced drift speed.

The wave induced drift velocity is the drift velocity obtained by the float to be predicted due to the action of the sea wave on the float to be predicted. In some embodiments of the present disclosure, the wave-induced drift velocity is calculated based on the wave characteristic parameters, which may be by inputting at least one of the estimated wave characteristic parameters into a pre-trained wave-induced drift deep learning model, resulting in a wave-induced drift velocity.

The wave-induced drift deep learning model is a deep learning model for predicting the wave-induced drift speed according to wave characteristic parameters. In an embodiment of the disclosure, the wave-induced drift deep learning model is trained based on first sample drift data. The first sample drift data includes a sample drift velocity observation of the sample float and corresponding sample surface water flow characteristic parameters, sample wind characteristic parameters, and sample wave characteristic parameters. And particularly how to train to obtain the wave-induced drift deep learning model based on the first sample drift data, and then analyze the model.

S132: and determining the flow-induced drift speed according to the surface water flow characteristic parameters at the current position.

The drift velocity caused by the flow is the drift velocity obtained by the float to be predicted due to the surface water flow acting on the float to be predicted. The direction of the flow-induced drift velocity is the same as that of the surface water flow, and the magnitude of the flow-induced drift velocity is in direct proportion to the flow velocity of the surface water flow.

The calculating device can calculate the flow-induced drift velocity by adopting a preset flow-induced drift coefficient and the flow velocity of the surface water flow. Specifically, V can be used _{F-surface-current} ＝λ _c ·V _c Calculating to obtain the flow-induced drift velocity V _{F-surface-current} Wherein lambda is _c For the flow-induced drift coefficient, V _c Indicating the velocity of the surface water flow. In practical applications, in order to make the calculated flow-induced drift velocity have a certain randomness, random disturbance may be added when calculating the flow-induced drift velocity. Specifically, V can be adopted _{F-surface-current} ＝(λ _c +λ _c ′)·V _c Calculating a flow induced drift velocity, wherein lambda _c ' is the random disturbance factor added.

S133: and determining the wind-induced drift speed according to the wind characteristic parameters at the current position.

The wind-induced drift velocity is the drift velocity obtained by the float to be predicted due to the wind acting on the float to be predicted. The wind-induced drift velocity includes a wind-induced drift velocity along a wind direction and a wind-induced drift velocity perpendicular to the wind direction. In an embodiment of the present disclosure, determining the wind-induced drift velocity from the wind characteristic parameter at the current location includes determining a wind-induced drift velocity along the wind direction and a wind-induced drift velocity perpendicular to the wind direction.

The wind-induced drift velocity can be calculated according to the wind-induced drift coefficient and the wind characteristic parameter. Specifically, L can be used _d ＝a _d W _10mwind +b _d The wind-induced drift velocity along the wind direction is calculated by L _c ＝a _c W _10mwind +b _c Calculated wind-induced drift velocity perpendicular to the wind direction, in particular wherein W _10mwind Is wind characteristic parameter L _d For wind-induced drift velocity in wind direction, L _c A is the wind-induced drift velocity perpendicular to the wind direction _d And b _d A is the wind-induced drift coefficient along the wind direction _c And b _c Is the wind-induced drift coefficient perpendicular to the wind direction; in practical application, in order to make the calculated wind-induced drift velocity have a certain randomness, random disturbance can be added when the wind-induced drift velocity is calculated. Specifically, L can be used _d ＝a _d W _10mwind +b _d +ε _d ' and L _c ＝a _c W _10mwind +b _c +ε _c ' calculating a windage drift velocity along a wind direction and a windage drift velocity perpendicular to the wind direction, wherein ε _d ' and ε _c ' is the random disturbance factor added.

S134: and determining the predicted drift velocity according to the wave-induced drift velocity, the flow-induced drift velocity and the wind-induced drift velocity.

After the wave-induced drift velocity, the flow-induced drift velocity and the wind-induced drift velocity are calculated, the three velocities are added to obtain the predicted drift velocity of the floater to be predicted.

According to the method provided by the embodiment of the disclosure, the wave-induced drift velocity is calculated by adopting the wave-induced drift deep learning model, and the final prediction drift velocity is calculated according to the wave-induced drift velocity, the flow-induced drift velocity and the wind-induced drift velocity, so that the finally calculated prediction drift velocity is more in line with the actual situation. The predicted drift range of the floater calculated based on the predicted drift speed is also more accurate.

In other embodiments of the present disclosure, considering that the drift velocity effect of the wave on the float is small relative to the drift velocity effect of the surface water flow, wind on the float, the predicted drift velocity may also be calculated based on the flow-induced drift velocity and the wind-induced drift velocity alone, without considering the wave-induced drift velocity, i.e. without calculating the wave-induced drift velocity based on the wave characteristic parameters.

As before, the wind induced drift velocity includes a wind induced drift velocity perpendicular to the wind direction. Through experimental tests, the correlation exists between the direction of the wind-induced drift velocity perpendicular to the wind direction and the predicted sea state parameters. In order to be able to predict the wind-induced drift velocity more accurately perpendicular to the wind direction, the method provided by the embodiment of the present disclosure may further include S135 before performing S133 of determining the wind-induced drift velocity according to the wind characteristic parameter at the current position.

S135: and determining the predicted drift bias of the floater to be predicted according to the predicted sea state parameters.

The predicted drift bias is the bias of the predicted wind induced drift direction of the float to be predicted relative to the wind direction,

in some embodiments of the present disclosure, the predicted drift bias is determined from predicted sea state parameters, which may be input to a pre-trained bias deep learning model to determine the predicted drift bias of the float to be predicted. The bias deep learning model is trained based on second sample drift data, wherein the second sample drift data comprises drift bias observations of sample floats and corresponding sample sea state parameters.

In a specific embodiment, a sample floating object can be sampled to carry out a floating object drifting experiment under a specific water area environment, the drifting track of the floating object is tracked and determined by utilizing a tracking observation ship, a positioning buoy and the like, and corresponding sample sea state parameters and drifting speed are obtained by utilizing equipment such as an acoustic Doppler flow velocity profiler, a meteorological sensor, a wave sensor and the like carried in the tracking observation ship. After enough sample drift experimental data is obtained, the sample drift velocity observation value of the sample drift can be used for subtracting the flow velocity of the sample surface water flow to obtain the wind-induced drift velocity approximately. And then determining a drift bias observation value of the sample floater by adopting the wind-induced drift velocity direction and the wind direction. The drift bias observations of the sample float, and corresponding sample sea state parameters, may then be used to construct second sample drift data.

After the second sample drift data is obtained, training a pre-constructed bias deep learning model by adopting the second sample drift data to obtain a trained bias deep learning model. In an application of the embodiment of the present disclosure, the bias deep learning model may be various possible models, for example, may be a neural network model that has been widely used, such as a BP neural network model.

In the case of performing the foregoing S135, S133 may specifically be S1331, which calculates the wind-induced drift velocity according to the wind characteristic parameter at the current position.

S1331: and calculating the wind-induced drift speed of the floater to be predicted according to the wind characteristic parameters and the predicted drift bias.

In an embodiment of the present disclosure, the different prediction drift biases include different wind-induced drift coefficients, in particular different wind-induced drift coefficients perpendicular to the wind direction. To calculate the wind induced drift velocity, the computing device may select a corresponding wind induced drift coefficient perpendicular to the wind direction according to the predicted drift bias. For example, the wind-induced drift coefficient perpendicular to the wind direction selected when the predicted drift bias is left bias is a _c+ And b _c+ And the wind-induced drift coefficient perpendicular to the wind direction selected when the predicted drift bias is right bias is a _c- And b _c- . Of course, the computing device also obtains the wind-induced drift coefficient a along the wind direction _d And b _d 。

After determining the wind induced drift coefficient, the wind induced drift velocity may then be calculated from the wind induced drift coefficient and the wind induced characteristic parameter at the current position, in particular according to the calculation formula above.

In some embodiments of the present disclosure, in order to enable a predicted drift velocity to be predicted with a randomness that is consistent with reality, in some embodiments of the present disclosure. The aforementioned S130 determining the predicted drift velocity of the float to be predicted at the current location according to the predicted sea state parameter at the current location may include S131-S132.

S131: and adding random disturbance to the predicted sea state parameters at the current position to obtain the disturbed predicted sea state parameters.

In embodiments of the present disclosure, the computing device may have a disturbance parameter fluctuation range stored in advance. When the predicted sea state parameters are randomly disturbed, the computing equipment randomly selects one disturbance parameter in the fluctuation range of the disturbance parameter, and obtains the predicted sea state parameters after disturbance based on the disturbance parameter and the preset sea state parameters before disturbance.

For example, in some embodiments, the foregoing disturbance parameter fluctuation range may be a proportional range obtained by probability analysis based on the predicted sea state and the actual sea state. For example, between [0.95,1.05 ]. In this case, after the disturbance parameter is selected in the proportion range, the disturbance parameter is multiplied by the predicted sea state parameter before disturbance to obtain the predicted sea state parameter after disturbance.

For another example, in some embodiments, after the predicted sea state parameters are calculated, the corresponding disturbance parameter ranges may be found based on the predicted sea state parameters. And then adding the predicted sea state parameter and the disturbance parameter randomly selected in the disturbance parameter range to obtain the predicted sea state parameter after disturbance.

And S132, determining the predicted drift speed of the floater to be predicted at the current position according to the predicted sea state parameters after disturbance.

S131-S132 are methods for adding random disturbance to predicted sea state parameters to enable the obtained predicted drift speed to have certain randomness. In other embodiments of the present disclosure, the predicted drift velocity may also be made to have some randomness by adding a perturbation method to the flow induced drift coefficient and the wind induced drift coefficient.

In the foregoing, the computing device may assimilate the sea state observation parameters by using a cyclic three-dimensional variation assimilation method, an efficient set kalman filter assimilation method, an adaptive optimal interpolation assimilation method, and the like, to obtain a sea state simulation model.

FIG. 2 is a flow chart of a method for determining a sea state simulation model using a cyclic three-dimensional variational assimilation method. As shown in FIG. 2, the method for determining the sea state simulation model by the computing device through adopting the cyclic three-dimensional variation assimilation method comprises S210-S250.

S210: dividing the time window to be assimilated to obtain N sub-assimilation time windows, wherein each sub-assimilation time window comprises sea state observation parameters.

In some embodiments of the present disclosure, the computing device may slide window divide the assimilation window based on a predetermined sub-assimilation time window, resulting in N sub-assimilation time windows. Among the N sub-assimilation time windows, two adjacent sub-assimilation time windows may or may not have time overlap, and the embodiment of the present disclosure is not particularly limited.

In other embodiments of the present disclosure, the computing device may also divide the assimilation window into N sub-assimilation time windows using a random partitioning method.

It should be noted that each sub-assimilation time window should comprise sea state observation parameters. In practical application, if a certain sub-assimilation time window obtained by dividing does not have sea state observation parameters, the sub-assimilation time window and an adjacent sub-assimilation time window can be combined.

S220: and carrying out data assimilation on the sea state observation parameters of the ith sub-assimilation time window by adopting a three-dimensional variation assimilation method to obtain a sea state simulation state of the ith sub-assimilation time window at the initial moment.

In the disclosed embodiments, i=0, 1,2, … …, N-1. In the specific implementation process, the computing device firstly sets i to 0, that is, adopts a three-dimensional variation assimilation method to data assimilate the sea state observation parameters included in the 0 th sub-assimilation time window to obtain the sea state simulation state at the initial moment of the 0 th sub-assimilation time window.

And similarly, for each subsequent sub-assimilation time window, assimilating the sea state observation parameters included in the sub-assimilation time window by adopting the same three-dimensional variation assimilation method to obtain a sea state simulation state of each sub-assimilation time window at the initial moment.

When three-dimensional variation assimilation is carried out on a certain sub-assimilation time window, the computing equipment carries out minimization treatment by solving an objective function corresponding to the sub-assimilation time window, and further corrects the sea state simulation model to obtain a corrected model. Wherein the objective function is j=j _B +J _O ，J _B ＝(x _b -x) ^T B ^-1 (x _b -x)/2，J _o ＝[H(x)-y _o ] ^T O ^-1 [H(x)-y _o ]/2. Wherein x is a prediction parameter matrix constructed according to sea state prediction parameters determined by the sea state simulation model before correction, x _b For the background parameter matrix constructed according to sea state prediction parameters, B is background error covariance matrix, O is observation error covariance matrix, y _o The observation parameter matrix is constructed according to sea state observation parameters, and H is an observation operator.

S230: and carrying out numerical simulation according to the sea state simulation state at the initial moment of the ith sub-assimilation time window to obtain the sea state simulation state at the starting moment of the (i+1) th sub-assimilation time window.

After the sea state simulation state at the initial time of the ith sub assimilation time window is obtained, numerical simulation is performed according to the sea state simulation state at the initial time, and the sea state simulation state at the starting time of the (i+1) th sub assimilation time window can be obtained.

In a specific application, if the ith sub-assimilation time window and the (i+1) th sub-assimilation time window are overlapped, numerical simulation is performed until the overlapping starting time, and a sea state simulation state of the (i+1) th sub-assimilation time window starting time can be obtained.

If the ith sub-assimilation time window is not overlapped with the (i+1) th sub-assimilation time window, the sea state simulation state of the (i+1) th sub-assimilation time window at the starting time of the (i+1) th sub-assimilation time window can be obtained after the numerical simulation of the ith sub-assimilation time window is completed.

S240: judging whether i is smaller than N-1; if not, executing S250; if yes, let i=i+1, re-execute S220-S230.

S250: and calculating the sea state simulation state at the ending time of the N-1 th sub-assimilation time window based on the sea state simulation state at the starting time of the N-1 th sub-assimilation time window, and determining an assimilated sea state simulation model based on the sea state simulation state at the ending time of the N-1 th sub-assimilation time window.

By adopting the steps S210-S250, N sub-assimilation time windows are obtained by dividing the time windows to be assimilated, and the sea state simulation model is corrected based on sea state observation parameters in the N sub-assimilation time windows, so that the sea state simulation model is corrected step by step. The sea state simulation model is gradually corrected by adopting the N sub-assimilation time windows, so that the corrected simulation model in each sub-assimilation time window is more in line with sea state observation parameter characteristics, and the finally obtained corrected sea state simulation model is more accurate. In addition, the spin-up phenomenon can be effectively eliminated by adopting the assimilation method provided by the embodiment of the disclosure.

FIG. 3 is a flow chart of a method for determining a sea state simulation model using an efficient ensemble Kalman filter assimilation method. As shown in fig. 3, in some embodiments of the present disclosure, data assimilating the sea state observation parameters of the time window to be assimilated using the efficient set kalman filter assimilation method may include S310-S340.

S310: and randomly determining sea state simulation states of a plurality of time points randomly selected in the current assimilation window based on the sea state simulation model before assimilation, and acquiring sea state climate state states of the corresponding time points.

In the embodiment of the disclosure, the current assimilation time window isAfter determining the current assimilation time window, randomly selecting N time points within the current assimilation time window, which are respectively t ₁ ,t ₂ ,L,t _N . Subsequently, based on the current assimilation time window initial moment, i.e. +.>The simulated sea state at each moment is subjected to numerical simulation, and the simulated sea state corresponding to each moment can be obtained to be M ₁ ,M ₂ ,L,M _N 。

At the same time, sea state and climate state C corresponding to each moment point can be obtained ₁ ,C ₂ ,L,C _N .

S320: and determining a corresponding disturbance matrix based on the plurality of time points, the corresponding simulated sea state and the sea state climate state.

In some embodiments of the present disclosure, determining a corresponding disturbance matrix based on the plurality of time points, the corresponding simulated sea state and the sea state climate state may include S321-S322.

S321: and calculating the time interval from each time point to the initial time of the current assimilation time window, and simulating the state difference between the sea state and the sea state climate state at each time point.

Specifically, the time interval from each time point to the initial time of the current assimilation window is calculated by adoptingAnd (5) calculating to obtain the product.

Calculating the difference between the simulated sea state and the sea state and climate state at each time point, and adopting DeltaM _n ＝M _n -C _n ,n＝1,2,L,N。

S322: and determining a weighted average matrix of the state differences according to the time intervals, the corresponding state differences and the time length of the current assimilation time window.

In embodiments of the present disclosure, may employDetermining a weighted average matrix of state differences

S322: and determining a corresponding disturbance matrix according to the weighted average matrix and each state difference.

In embodiments of the present disclosure, in determining a weighted average matrixAfterwards, use can be made of +.>And determining a disturbance matrix corresponding to each state difference, wherein K is a weight coefficient.

S330: and determining the sea state simulation state at the ending time of the current assimilation time window based on the simulated sea state model before assimilation, and acquiring the observed sea state parameters and the observed error covariance matrix at the ending time of the current assimilation time window.

S340: and determining a filtered sea state simulation state according to the sea state simulation state at the end time of the current assimilation time window, the disturbance matrix and the observed sea state parameter observation error covariance matrix at the end time of the current assimilation time window, and determining an assimilation sea state simulation model based on the filtered sea state simulation state.

Determining that the sea state simulation state at the end time of the current assimilation time window is A based on the simulation of the simulated sea state before assimilation _j+1,n . The observed sea condition parameter at the end time of the current assimilation window is O _j+1 The covariance matrix of the observation error is R _j+1 Determining the sea state simulation state at the end time of the current assimilation time window after filtering asWherein->Is the sea state simulation state after filtering, H is the observation conversionAnd (5) matrix replacement.

By adopting the assimilation method provided by the embodiment of the disclosure, the data assimilation can be carried out by taking the aggregate state vector of the estimated background error covariance from the single sea state simulation numerical simulation result and the sea state climate state as the background error, the data processing amount can be reduced, and the better simulation result is ensured.

FIG. 4 is a flow chart of a method for determining a sea state simulation model using an adaptive optimal interpolation assimilation method. As shown in fig. 4, the method for data assimilating sea state observation parameters in a time window to be assimilated by adopting the adaptive optimal interpolation assimilation method comprises S410-S470.

S410: and calculating sea state prediction parameters of each to-be-predicted point at the j-th observation time in the to-be-assimilated time window, wherein j=1, 2, … …, M and M are the number of the observation time points included in the to-be-assimilated time window.

S420: and acquiring the sea state observation parameters of the observation points at the j-th observation time in the time window to be assimilated, and determining the sea state observation parameters of the preset number of the observation points nearest to the point to be assimilated.

In the embodiment of the disclosure, the computing device may determine a preset number of nearest observation points by adopting an adaptive query method, and obtain sea condition observation parameters of the preset number of observation points at corresponding moments. Specifically, the computing device may determine the nearest preset number of grid points by setting a virtual circle, expanding the radius of the virtual circle gradually, and searching.

S430: and calculating a prediction error covariance matrix and an observation error covariance matrix according to the sea state prediction parameters of each point to be predicted and the sea state observation parameters of the latest preset number of observation points.

S440: and calculating a weight matrix according to the forecast error covariance matrix and the observation error covariance matrix.

S450: and calculating the sea state simulation state corrected at the j-th observation moment by adopting the sea state prediction parameter, the sea state observation parameter and the weight matrix.

In the embodiment of the disclosure, the prediction error covariance matrix adopts P ^b R is the observed error co-prescriptionThe difference matrix and the analysis error covariance matrix adopt P ^a Representation, P ^a ＝P ^b -KHP ^b 。

Employing P in obtaining a prediction error covariance matrix ^b And the observed error covariance matrix R, a weight matrix K=P can be obtained ^b H ^T (HP ^b H ^T +R) ^-1 . X can then be obtained ^a -X ^b ＝K(Y ^o -HX ^b ) Wherein X is ^a And the corrected sea state simulation state corresponding to the ith moment.

S460: it is determined whether j is less than M, if so, such that j=j+1, and S420 is re-executed. If not, S470 is performed.

S470: and constructing an assimilated sea state simulation model based on the sea state simulation state obtained at the last observation time.

By adopting the steps of S410-S470, the simulated sea state model is corrected based on the sea state observation parameters of the preset number of adjacent observation points, so that the sea state simulation model is ensured to better simulate the actual sea state, and the prediction accuracy is ensured.

The wave-induced drift velocity is calculated based on the wave-induced drift deep learning model. Fig. 5 is a flowchart of a training method of a wave-induced drift deep learning model provided by an embodiment of the present disclosure. As shown in FIG. 5, the training method of the wave-induced drift deep learning model comprises S510-S550.

S510: and obtaining a flow-induced drift coefficient and a wind-induced drift coefficient.

In some embodiments of the present disclosure, the computing device may directly employ the flow-induced drift coefficients and wind-induced drift coefficients provided by other various technical literature or related software products as the flow-induced drift coefficients and wind-induced drift coefficients.

S520: and calculating a corresponding sample flow induced drift velocity estimated value based on the sample surface water flow characteristic parameter and the flow induced drift coefficient.

S530: and calculating a corresponding sample wind-induced drift velocity estimated value based on the sample wind characteristic parameter and the wind-induced drift coefficient.

S540: based on the sample drift velocity observations, corresponding sample flow induced drift velocity estimates and sample wind induced drift velocity estimates are calculated.

After the sample flow induced drift velocity estimation value and the sample wind induced drift velocity estimation value are obtained, subtracting the sample flow induced drift velocity estimation value and the sample wind induced drift velocity estimation value from the sample drift velocity observation value to obtain the sample wave induced drift velocity estimation value.

S550: and training a wave-induced drift deep learning model by adopting the sample wave characteristic parameters and the corresponding sample wave-induced drift velocity estimated values.

After the estimated value of the wave-induced drift velocity of the sample is obtained, the wave-induced drift velocity of the sample is trained by using the sample wave parameters and the estimated value of the wave-induced drift velocity of the sample as training samples, and then the wave-induced drift deep learning model can be obtained.

The wave-induced drift deep learning model may be various possible models known in the art, for example, may be a BP neural network model, a recurrent neural network model, etc., and the embodiments of the present disclosure are not particularly limited.

In the foregoing embodiments, the wind-induced drift coefficients and the flow-induced drift coefficients are directly employed as coefficients provided by other various technical literature or related software products. In some embodiments of the present disclosure, the wind induced drift coefficients and the flow induced drift coefficients may also be determined in training a wave induced drift deep learning model. And determining the wind-induced drift coefficient and the flow-induced drift coefficient in the training wave-induced drift deep learning model, wherein the sample drift velocity observation value is used as an approximate value of the sum of the flow-induced drift velocity and the wind-induced drift velocity, and fitting the flow-induced drift coefficient and the wind-induced drift coefficient.

In particular, a formula can be constructedAn approximate relationship of the sum of the sample drift velocity observation, the flow induced drift velocity, and the wind induced drift velocity is established. Wherein V is _ox-s And V _oy-s The components of the sample drift velocity observations in the x and y directions, respectively (x-axis may be latitude and y-axis may be longitudeDirection), V _{F-surface-current-sx} And V _{F-surface-current-sy} L is the component of the flow induced drift velocity of the sample float in the x-axis and y-axis _sx And L _sy Is the component of the sample float's wind induced drift velocity in the x-axis and y-axis.

According to the relation between the drift velocity and the characteristic parameters of the surface water flow, a formula can be adoptedDetermining V _{F-surface-current-sx} And V _{F-surface-current-sy} Wherein V is _csx And V _csy The components of the superficial flow velocity in the x-axis and y-axis, respectively.

Based on the relation between the wind-induced drift velocity and the wind characteristic parameters, a formula can be adoptedCalculation and determination of L _sx And L _sy Wherein L is _d ＝a _d W _10mwind-s +b _d ，/>Wherein W is _10mwind S is the sample wind speed, L _d For wind-induced drift velocity in wind direction, L _c />For a wind-induced drift velocity perpendicular to the wind direction, a value of 1 indicates that the drift bias is left-biased perpendicular to the wind direction, i.e., L is used when the drift bias is left-biased _c+ ＝a _c+ W _10mwind-s +b _c+ Fitting calculation a _c+ 、b _c+ The method comprises the steps of carrying out a first treatment on the surface of the And when delta is 0, the drift bias is perpendicular to wind and rightFitting calculation a _c- 、b _c- 。

The random disturbance range of the drift coefficient can be determined simultaneously with the calculation of the drift information signature, so as to determine the random disturbance coefficient in the random disturbance range.

In addition to providing the aforementioned drift velocity prediction method for a drift, embodiments of the present disclosure also provide a drift velocity prediction apparatus 600 for a drift. Fig. 6 is a schematic structural diagram of a drift velocity prediction apparatus for a float according to an embodiment of the present disclosure. The drift velocity prediction apparatus 600 of the float as shown in fig. 6 includes a target grid point query unit 601, a sea state parameter determination unit 602, and a predicted drift velocity determination unit 603.

The target grid point query unit 601 is configured to query the unstructured grid of sea conditions for prediction according to the current position of the floater to be predicted, and determine a preset number of target grid points nearest to the current position.

The sea state parameter determining unit 602 is configured to determine a predicted sea state parameter at a current location according to the location and the predicted sea state parameter of the target grid point, and the current location, where the predicted sea state parameter at the target grid point is determined by numerical prediction according to the assimilated sea state simulation model.

The predicted drift velocity determination unit 603 is configured to determine a predicted drift velocity of the float to be predicted at the current position according to the predicted sea state parameter at the current position.

Optionally, in some embodiments of the present disclosure the target grid point querying unit 601 includes a region grid determining subunit and a target grid point determining subunit. The regional square grid determining subunit is used for determining the regional square grid where the floater to be predicted is located according to the current position. The target grid point determining subunit is used for querying the unstructured sea state grid used for prediction in the regional grid and determining a preset number of target grid points nearest to the current position.

Optionally, the predicted sea state parameters include wave characteristic parameters, surface water flow characteristic parameters and wind characteristic parameters. The predicted drift velocity determining unit 603 firstly inputs the wave characteristic parameters at the current position to a pre-trained wave-induced drift deep learning model to obtain a wave-induced drift velocity, determines the flow-induced drift velocity according to the surface water flow characteristic parameters at the current position, and determines the wind-induced drift velocity according to the wind characteristic parameters at the current position; then, determining a predicted drift velocity according to the flow-induced drift velocity, the wind-induced drift velocity and the wave-induced drift velocity; the wave-induced drift deep learning model is trained based on first sample drift data, wherein the first sample drift data comprises a sample drift velocity observation value of a sample floater and corresponding sample surface water flow characteristic parameters, sample wind characteristic parameters and sample wave characteristic parameters.

Optionally, in some embodiments of the present disclosure, the drift velocity prediction apparatus 600 of the float further comprises a bias determination unit. The bias determination unit is used for determining the predicted drift bias of the floater to be predicted according to the predicted sea state parameters, wherein the predicted drift bias is the bias of the wind-induced drift direction of the floater to be predicted relative to the wind direction. The predicted drift velocity determination unit 603 calculates the wind-induced drift velocity of the float to be predicted from the wind characteristic parameter and the predicted drift bias.

In some embodiments of the present disclosure, the predicted drift velocity determination unit 603 selects a corresponding wind-induced drift coefficient according to the wind-induced drift bias, and then calculates the wind-induced drift velocity according to the wind characteristic parameter and the wind-induced drift coefficient at the current position.

In some embodiments of the present disclosure, the bias determination unit inputs the predicted sea state parameters to a pre-trained bias deep learning model, determining a predicted drift bias of the float to be predicted; the bias deep learning model is trained based on second sample drift data, wherein the second sample drift data comprises drift bias observations of sample floaters and corresponding sample sea state parameters.

In some embodiments of the present disclosure, the predicted drift velocity determination unit 603 adds random disturbance to the predicted sea state parameter at the current location, resulting in a disturbed predicted sea state parameter, and then determines the predicted drift velocity of the float to be predicted at the current location from the disturbed predicted sea state parameter.

Fig. 7 is a schematic structural diagram of a computing device provided in an embodiment of the present disclosure. As shown in fig. 7, a computing device 700 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 701, which may perform various suitable actions and processes based on programs stored in a Read Only Memory (ROM) 702 or programs loaded from a storage 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the computing device 700 are also stored. The processing device 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

In general, the following devices may be connected to the I/O interface 705: input devices 706 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, and the like; an output device 707 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 708 including, for example, magnetic tape, hard disk, etc.; and a communication device 709. The communication means 709 may allow the computing device 700 to communicate wirelessly or by wire with other devices to exchange data. While fig. 7 illustrates a computing device 700 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.

In particular, the processes described above with reference to flowcharts may be implemented as computer software programs, based on embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via communication device 709, or installed from storage 708, or installed from ROM 702. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 701.

It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be embodied in the computing device; or may exist alone without being assembled into the computing device.

Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including, but not limited to, an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The embodiments of the present disclosure further provide a computer readable storage medium, where a computer program is stored, where the computer program, when executed by a processor, may implement the method of any of the embodiments of fig. 1 to fig. 4, and the implementation manner and the beneficial effects are similar, and are not repeated herein.

It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.

The above is merely a specific embodiment of the disclosure to enable one skilled in the art to understand or practice the disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A drift velocity prediction method for a float is characterized by comprising the steps of,

2. The method of claim 1, wherein the querying the unstructured grid for sea state prediction based on the current location of the float to be predicted, determining a preset number of target grid points nearest to the current location, comprises:

3. The method of claim 1, wherein the predicted sea state parameters include wave characteristic parameters, surface current characteristic parameters, and wind characteristic parameters;

4. A method according to claim 3, wherein before calculating the wind induced drift velocity from the wind characteristic parameter at the current location, the method further comprises:

5. The method of claim 4, wherein said calculating a wind induced drift velocity of said float to be predicted based on said wind characteristic parameter and said predicted drift bias comprises:

6. The method of claim 4, wherein said determining a predicted drift bias of the float to be predicted based on the predicted sea state parameter comprises:

7. The method of claim 1, wherein said determining a predicted drift velocity of the float to be predicted at the current location based on the predicted sea state parameter at the current location comprises:

8. A drift velocity prediction device for a float is characterized by comprising,

9. A computing device, comprising:

a memory and a processor, wherein the memory has stored therein a computer program which, when executed by the processor, implements the method of any of claims 1-7.

10. A computer readable storage medium, characterized in that the storage medium has stored therein a computer program which, when executed by a processor, implements the method according to any of claims 1-7.