Methods, apparatus, equipment and storage media for predicting drift bias

Abstract

This disclosure relates to a method, apparatus, device, and storage medium for predicting drift bias. The drift bias prediction model used in the method is obtained through the following steps: acquiring sample drift data, including the drift velocity value of a sample floating object and sample environmental parameters, the environmental parameters including at least the surface water flow velocity, flow direction, and wind direction; calculating an estimated wind-induced drift velocity based on the drift velocity value, flow velocity, and flow direction; determining the sample drift bias based on the estimated wind-induced drift velocity and wind direction; and training the drift bias prediction model based on the sample drift bias and sample environmental parameters. Because the drift bias prediction model implicitly incorporates the influence characteristics of environmental parameters on the drift bias of floating objects through training with sample drift data, the predicted drift bias obtained using the drift bias prediction model is more reasonable than the drift bias predicted randomly.

Description

Technical Field

[0001] This disclosure relates to the field of maritime technology, and more particularly to a method, apparatus, device, and storage medium for predicting drift bias. Background Technology

[0002] Maritime accidents can generate various types of floating debris. For example, an oil spill may produce oil slicks; while a ship collision may produce debris such as collision fragments, life rafts, and wrecked vessels.

[0003] To quickly salvage and clear various floating objects after a maritime accident, it is necessary to determine the approximate and accurate area where the objects are located, that is, to determine their drift path. Because floating objects are affected by wind, currents, and waves, accurately predicting their drift path requires accurately predicting the wind-induced drift speed, current-induced drift speed, and wave-induced drift speed at various times. In particular, predicting the wind-induced drift speed requires considering drift bias, that is, taking into account the bias of wind direction and wind-induced drift speed.

[0004] Traditional methods for predicting drift bias assume that wind-induced drift bias has an equal probability of left and right velocities, thus setting the probability of both left and right velocities for floating objects to 50%. However, experimental results have shown that this assumption is incorrect. Summary of the Invention

[0005] To solve the above-mentioned technical problems, or at least partially solve them, embodiments of this disclosure provide a training method for a drift bias prediction model, a method for predicting drift bias, an apparatus, a computing device, and a storage medium.

[0006] In a first aspect, embodiments of this disclosure provide a method for training a drift bias prediction model, comprising:

[0007] Acquire sample drift data, which includes the drift velocity value of the floating sample and sample environmental parameters, including at least the flow velocity, flow direction and wind direction of the surface water;

[0008] Calculate the estimated wind-induced drift velocity based on the drift velocity value, the flow velocity, and the flow direction;

[0009] The sample drift bias is determined based on the estimated wind-induced drift velocity and the wind direction.

[0010] The drift bias prediction model is trained based on the sample drift bias and the sample environment parameters.

[0011] Optionally, obtaining sample drift data includes: obtaining drift experiment data and using the drift experiment data as the sample drift data.

[0012] Optionally, acquiring sample drift data includes: acquiring drift experiment data;

[0013] A fluid-floating object drift coupling model is constructed based on the drift experiment data. This fluid-floating object drift coupling model is used to characterize the influence of wind, waves and current on the drift of sample floating objects.

[0014] The fluid-floating object drift coupling model was used for simulation to obtain multiple simulation data, including simulated drift velocity values ​​and simulated environmental parameters.

[0015] The simulation data is used as the sample drift data.

[0016] Optionally, constructing the fluid-floating object drift coupling model based on the drift experiment data includes:

[0017] A water flow model is constructed for the surface water flow on the floating sample, a wind effect model is constructed for the wind effect on the floating sample, and a second-order slow-drift force model of waves is constructed.

[0018] Based on the water flow model, the wind action model, and the second-order slow drift force model of the wave, a constant fluid-floating object drift coupling model for the sample floating object under the action of wind, waves, and current is constructed.

[0019] The drift experiment data was used to calibrate the fluid-floating object drift coupling model to be calibrated, resulting in a calibrated fluid-floating object drift coupling model.

[0020] Optionally, the construction of the surface water flow model on the floating sample includes:

[0021] Construct a sub-model of the hydrodynamic effect and a sub-model of the hydrodynamic moment effect of the surface water flow on the floating sample;

[0022] The construction of the wind effect model on the sample floating objects includes:

[0023] Construct sub-models of wind force and wind moment action on the sample floating objects;

[0024] The construction of the second-order slow-drift force model of the wave includes: constructing the second-order slow-drift force model of the wave using the direct integration method of three-dimensional potential flow theory.

[0025] Optionally, calculating the estimated wind-induced drift velocity based on the drift velocity value, the flow velocity, and the flow direction includes:

[0026] Calculate the estimated flow-induced drift velocity based on the flow velocity and the flow direction;

[0027] The wind-induced drift velocity estimate is calculated using the drift velocity value and the flow-induced drift velocity estimate.

[0028] Optionally, the sample environmental parameters may also include at least one of wind speed, wave height, wave period, and wave direction.

[0029] Secondly, embodiments of this disclosure provide a method for predicting drift bias, including:

[0030] Obtain environmental parameters at the location of the floating object to be predicted;

[0031] The environmental parameters are input into the drift bias prediction model to obtain the predicted drift bias.

[0032] The drift bias prediction model is trained using the aforementioned training method for the drift bias prediction model.

[0033] Thirdly, embodiments of this disclosure provide a training apparatus for a drift bias prediction model, comprising:

[0034] The sample acquisition unit is used to acquire sample drift data, which includes the drift velocity value of the floating sample and the sample environment parameters of the surrounding environment. The sample environment parameters include at least the flow velocity, flow direction and wind direction of the surface water.

[0035] The wind-induced drift velocity estimation unit is used to calculate the wind-induced drift velocity estimate based on the drift velocity value, the flow velocity, and the flow direction.

[0036] A bias determination unit is used to determine the sample drift bias based on the wind-induced drift velocity estimate and the wind direction.

[0037] The model training unit is used to train the drift bias prediction model based on the sample drift bias and the sample environment parameters.

[0038] Fourthly, embodiments of this disclosure provide a device for predicting drift bias, comprising:

[0039] The environmental parameter acquisition unit is used to acquire the environmental parameters at the location of the floating object to be predicted.

[0040] A drift bias prediction unit is used to input the environmental parameters into a drift bias prediction model to obtain a predicted drift bias.

[0041] The drift bias prediction model is trained using the same method described above.

[0042] Fifthly, embodiments of this disclosure provide a computing device, including: a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the training method for the drift bias prediction model or the drift bias prediction method as described above.

[0043] Sixthly, embodiments of this disclosure provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the training method for the drift bias prediction model or the drift bias prediction method as described above.

[0044] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0045] The solution provided in this disclosure calculates wind-induced drift velocity estimates using sample drift data, determines sample drift bias based on the wind-induced drift velocity estimates and wind direction, and trains a drift bias prediction model based on the sample drift bias and sample environmental parameters. Subsequently, when predicting the drift bias of a floating object, the environmental parameters at the location of the floating object are directly input into the drift bias deep learning model to obtain the predicted drift bias. Since the drift bias model implicitly incorporates the influence characteristics of environmental parameters on the drift bias of floating objects through sample drift data training, the accuracy of the predicted drift bias obtained using the drift bias prediction model is higher. Attached Figure Description

[0046] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0047] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of the training method for the drift bias prediction model provided in this embodiment of the disclosure;

[0049] Figure 2 This is a flowchart of a method for obtaining sample drift data according to some embodiments of this disclosure;

[0050] Figure 3 This is a flowchart of the drift bias prediction method provided in the embodiments of this disclosure;

[0051] Figure 4This is a schematic diagram of the structure of the training device for the drift bias prediction model provided in the embodiments of this disclosure;

[0052] Figure 5 This is a schematic diagram of the structure of the drift bias prediction device provided in the embodiments of this disclosure;

[0053] Figure 6 This is a schematic diagram of the structure of a computing device provided in an embodiment of this disclosure. Detailed Implementation

[0054] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0055] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based 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". Definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc., used in this disclosure are only used to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0056] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0057] Figure 1 This is a flowchart illustrating the training method for the drift bias prediction model provided in this embodiment of the disclosure. Figure 1 As shown, the training method for the drift bias prediction model provided in this embodiment includes steps S110-S140.

[0058] It should be noted that the training method for the drift bias prediction model provided in this disclosure can be executed by a computing device. The computing device can be a terminal device such as a laptop or desktop computer, or a server; this disclosure does not impose any particular limitation.

[0059] Step S110: Obtain sample drift data.

[0060] Sample drift data characterizes the drift properties of floating objects and the characteristics of their surrounding environment. The aforementioned floating objects can be of various types, such as oil slicks, life rafts, people awaiting rescue, floating equipment awaiting salvage, and wrecked vessels awaiting rescue.

[0061] The sample drift data includes the drift velocity of the sample float and the sample environmental parameters, including at least the surface water flow velocity, flow direction, and wind direction.

[0062] In some embodiments of this disclosure, the sample drift data may be drift experiment data. Drift experiment data is data obtained based on drift experiments conducted on the sample float, including the drift velocity value of the sample float and environmental parameters at the location of the sample float.

[0063] Specifically, a floating object drift experiment can be conducted in a specific aquatic environment using sample floating objects. The drift trajectory of the floating object can be tracked using a tracking observation vessel and positioning buoys to obtain the drift velocity value of the sample floating object. At the same time, the environmental parameters at the location of the sample floating object can be monitored using environmental monitoring equipment carried on the tracking observation vessel.

[0064] Step S120: Calculate the estimated wind-induced drift velocity based on the drift velocity value, flow velocity, and flow direction.

[0065] The wind-induced drift speed estimate is an estimated speed value. In this embodiment of the disclosure, considering that the drift speed of the floating object is mainly affected by surface water flow and wind, and that waves have a relatively small impact on the drift speed of the floating object, the wave-induced drift speed caused by waves is ignored, and it is assumed that the drift speed value is only affected by surface water flow and wind.

[0066] In this embodiment of the present disclosure, the wind-induced drift velocity estimate is calculated based on the drift velocity value, flow velocity, and flow direction. The flow velocity of the surface water flow can be multiplied by a pre-set flow-induced drift coefficient to obtain the flow-induced drift velocity estimate, and the flow direction is used as the direction of the flow-induced drift velocity estimate. Then, the drift velocity value is subtracted from the flow-induced drift velocity estimate to obtain the wind-induced drift velocity estimate.

[0067] The aforementioned pre-set flow-induced drift coefficient can be determined through floating object experiments conducted under windless or very low wind conditions. Specifically, the flow-induced drift coefficient can be determined by dividing the drift velocity of the floating object by the corresponding surface water flow velocity under windless conditions.

[0068] Step S130: Determine the sample drift bias based on the estimated wind-induced drift velocity and wind direction.

[0069] Sample drift bias is the direction of wind-induced drift of a floating sample relative to the wind direction; specifically, it refers to the leftward or rightward deviation of the floating sample relative to the wind direction when subjected to wind.

[0070] In this embodiment of the disclosure, after obtaining the estimated wind-induced drift velocity, the estimated wind-induced drift velocity can be projected along the wind direction and perpendicular to the wind direction, and the sample drift bias can be determined based on the projection perpendicular to the wind direction.

[0071] For example, if the wind-induced drift direction of the sample floating object is from south to north and the wind direction is from west to east, then the sample drift bias is left-leaning.

[0072] Step S140: Train the drift bias prediction model based on the sample drift bias and sample environment parameters.

[0073] A drift bias prediction model is a model used to predict the influence of environmental parameters on the drift bias of floating objects. In this embodiment of the disclosure, the drift bias model can be various possible deep learning models, such as widely used deep learning models like the BP neural network model.

[0074] After obtaining sample drift data and determining the drift bias, the computing device can use the environmental parameters in the sample drift data and the determined drift bias to train a pre-designed drift bias prediction model, thereby obtaining a trained drift bias prediction model.

[0075] The drift bias model training method provided in this disclosure calculates wind-induced drift velocity estimates using sample drift data, determines sample drift bias based on the wind-induced drift velocity estimates and wind direction, and trains a drift bias prediction model based on the sample drift bias and sample environmental parameters. Because the drift bias model implicitly incorporates the influence characteristics of environmental parameters on the drift bias of floating objects through sample drift data training, the predicted drift bias obtained using the drift bias prediction model is more accurate than the drift bias predicted randomly.

[0076] As previously described, some embodiments of this disclosure use drift experiment data as sample drift data. In other embodiments of this disclosure, other methods may be used to obtain sample drift data.

[0077] Figure 2 This is a flowchart illustrating a method for obtaining sample drift data according to some embodiments of this disclosure. Figure 2 As shown, in some embodiments of this disclosure, the method for obtaining sample drift data includes steps S210-S240.

[0078] Step S210: Obtain drift experiment data.

[0079] As mentioned earlier, the drift experiment data is based on data obtained from drift experiments on sample floating objects, including the drift velocity value of the sample floating objects and the environmental parameters of the sample floating objects' location.

[0080] Step S220: Construct a fluid-floating object drift coupling model based on drift experiment data.

[0081] The fluid-floating object drift coupling model is used to characterize the influence of wind, waves and current on the drift of sample floating objects.

[0082] In some embodiments of this disclosure, the fluid-floating object drift coupling model may include a water flow interaction model, a wind interaction model, and a second-order slow-drift force model of waves. The water flow interaction model is used to characterize the effect of surface water flow on the floating sample. The wind interaction model is used to characterize the effect of wind on the floating sample. The second-order slow-drift force model of waves characterizes the effect of waves on the floating sample. Constructing the fluid-floating object drift coupling model based on drift experiment data may include steps S221-S223.

[0083] Step S221: Construct a water flow model of the surface water flow on the floating sample, a wind effect model of the wind on the floating sample, and a second-order slow-drift force model of waves.

[0084] The effects of water flow on floating samples include the force pushing the floating objects and the torque rotation effect. Therefore, constructing a water flow effect model on floating samples can include constructing a hydrodynamic sub-model and a hydrodynamic torque sub-model.

[0085] The forces exerted by the water flow on the sample float include the longitudinal flow force F acting along the longitudinal direction of the float. xc and the lateral flow force F in the lateral direction yc The pitching torque of the water flow on the floating sample is M. xyc F xc F yc and M xyc It can be represented by the following expression (that is, by the following water flow action model).

[0086]

[0087] Among them, V cR Let ρ be the relative velocity between the floating object and the water flow. c C is the density of seawater. xc C yc C xyc These are the longitudinal flow coefficient, the transverse flow coefficient, and the bow roll moment, respectively. pp Let T be the length between the two columns of the floating object, and T be the average draft of the floating object.

[0088] The effect of wind on floating sample objects includes the force pushing the floating objects and the torque rotation effect. Therefore, constructing a wind effect model on floating sample objects can include constructing a wind force effect sub-model and a wind torque effect sub-model.

[0089] The force exerted by wind on the part of the floating object above the water surface includes the longitudinal wind force F along the longitudinal direction of the floating object. xw And the lateral wind force F along the lateral direction of the sample float yw The wind torque acting on the part of the floating object above the water surface is M. xyw F xw F yw and M xyw It can be represented by the following expression (that is, by the following wind action model).

[0090]

[0091] Where, ρ w C is the density of air. xw C yw C xyw These are the longitudinal wind force coefficient, the lateral wind force coefficient, and the initial sway moment coefficient, respectively. A T A is the area receiving the wind in the first direction. L L represents the lateral wind-receiving area. pp V is the length between the two columns. wR The relative wind speed is 10m above sea level.

[0092] In some embodiments of this disclosure, the second-order slow-drift force model of waves can be constructed using the direct integration method of three-dimensional potential flow theory, for example, it can be calculated using the following formula.

[0093]

[0094] Among them, F f For the second-order slow drift force of the wave, P ij (ω i ,ω j ) and Q ij (ω i ,ω j These represent the synchronous and asynchronous parts of the time-independent transfer function, respectively. i and ξ j These are the amplitudes of the regular wave components in the i and j directions, respectively, ω. i and ω j The sum is the wave frequency, representing the wave period, ε i and ε j is the phase angle, representing the wave direction, and N is the number of spectral divisions.

[0095] Step S222: Construct a fluid-floating object drift coupling model for the sample floating object under the action of wind, waves and current based on the water flow model, wind action model and second-order slow drift force model of waves.

[0096] Step S223: Use sample drift data to calibrate the fluid-floating object drift coupling model to be calibrated, and obtain the calibrated fluid-floating object drift coupling model.

[0097] Based on the water flow model, wind model, and second-order slow-drift force model of waves, a fluid-floating object drift coupling model to be calibrated is constructed. The aforementioned formulas can be integrated to obtain a comprehensive expression for force and torque.

[0098] Based on force analysis, the equation of motion for a floating object in the horizontal direction is:

[0099]

[0100] Where F Kw For wind force component, F Kc For the fluid force component, F Kf M represents the wave drift force component. Kj Let m be the mass matrix. Kj The mass matrix is ​​added. The forces acting on the sample floating object can be represented by the aforementioned fluid-floating object drift coupling model. Therefore, the parameters in the aforementioned fluid-floating object drift coupling model can be calibrated using sample drift data to obtain the calibrated fluid-floating object drift coupling model.

[0101] Step S230: Simulation is performed using a fluid-floating object drift coupling model to obtain multiple simulation data, including the drift velocity values ​​of the sample floating object and simulation environment parameters.

[0102] A fluid-floating object drift coupling model was used for simulation to obtain multiple simulation data points. These environmental parameters were then input into the fluid-floating object drift coupling model to obtain the forces and torques acting on the floating sample. Based on these forces and torques, the velocity of the floating sample was calculated to determine the simulated drift velocity. The sample drift data also included the aforementioned environmental parameters. It should be noted that the simulation data could be obtained from continuous simulations over a given time period.

[0103] Step S240: Determine sample drift data based on simulation data.

[0104] In some embodiments of this disclosure, determining sample drift data based on simulation data can be achieved by calculating wind-induced drift velocity estimates based on simulated drift velocity values ​​in the simulation data and flow velocity and direction parameters in the environmental parameters. Subsequently, the wind-induced drift velocity estimates and wind direction are used to determine the drift bias corresponding to the simulation data. Specifically, a method similar to step S130 can be used to determine the drift bias corresponding to the simulation data. Finally, the drift bias corresponding to the simulation data is used as the sample drift bias, and the simulated environmental parameters in the simulation data are used as the sample's environmental parameters, thereby determining the sample drift data.

[0105] In practical applications, due to limitations in experimental costs and actual environmental conditions, it may be impossible to obtain a sufficient number of training samples for training the drift bias model. For example, in practical applications, it may be impossible to obtain a large number of experimental samples under strong typhoon sea conditions or tropical storm conditions. The method provided in this disclosure, by obtaining a fluid-floating object drift coupling model, obtaining simulation data based on the coupling model, and obtaining simulated training samples based on the simulation data, can increase the number of training samples and the richness of features, thereby improving the accuracy of the trained drift bias model.

[0106] Of course, in some embodiments of this disclosure, the aforementioned drift experimental data and simulation data can also be used simultaneously as sample drift data for calculating wind-induced drift velocity estimates, determining sample drift bias, and training drift bias prediction models.

[0107] In the preceding embodiments, the sample environment characteristic parameters include the surface water flow velocity, flow direction, and wind direction. In other embodiments, the sample environment parameters may also include at least one of wind speed, wave height, wave period, and wave direction. More preferably, the sample environment parameters include all of wind speed, wave height, wave period, and wave direction.

[0108] In addition to providing the aforementioned training method for the drift bias prediction model, this disclosure also provides a method for predicting drift bias. Figure 3 This is a flowchart of the drift bias prediction method provided in the embodiments of this disclosure, as follows: Figure 3 As shown, the method for predicting drift bias includes steps S310-S320.

[0109] Step S310: Obtain environmental parameters at the location of the floating object to be predicted.

[0110] The location of the floating object to be predicted can be its actual location or a possible location predicted based on historical data.

[0111] For example, in the event of an oil spill from an offshore drilling platform, the location of the floating debris could be the location of the drilling platform itself. As another example, if the debris has drifted away from the accident area and its actual location cannot be accurately determined, its location could be predicted based on historical data.

[0112] The environmental parameters at the location of the floating object to be predicted can be the actual environmental parameters at its location, or environmental parameters predicted based on historical data and actual meteorological and oceanographic forecast data.

[0113] For example, if the floating debris is located in a nearshore area with numerous offshore floating observation stations and other monitoring equipment, the environmental characteristic parameters can be the actual observed data. Alternatively, the environmental characteristic parameters can also be relatively accurate predicted data obtained through simulations of meteorological and oceanographic environmental characteristics.

[0114] In this embodiment of the disclosure, the environmental parameters for predicting the location of the floating object should include at least the environmental parameters required for training the drift bias prediction model. In one specific embodiment, the environmental parameters include the velocity and direction of surface water flow, the wind speed and direction, and the wave height, wave period, and wave direction.

[0115] Step 320: Input the environmental feature parameters into the pre-trained drift bias prediction model to obtain the drift bias of the floating object.

[0116] In this embodiment, the drift bias prediction model is the model trained using sample drift data in the previous embodiments. Because the drift bias model implicitly incorporates the influence characteristics of environmental parameters on the drift bias of floating objects through sample drift data training, the predicted drift bias obtained using the drift bias prediction model is more reasonable than the drift bias predicted randomly.

[0117] This disclosure also provides a training device 400 for a drift bias prediction model. Figure 4 This is a schematic diagram of the structure of the training device 400 for the drift bias prediction model provided in this embodiment of the disclosure. Figure 4 As shown, the training device 400 for the drift bias prediction model provided in this embodiment includes a sample acquisition unit 401, a wind-induced drift velocity estimation unit 402, a bias determination unit 403, and a model training unit 404.

[0118] The sample acquisition unit 401 is used to acquire sample drift data, which includes the drift velocity value of the sample floating object and the sample environment parameters of the environment in which it is located. The sample environment parameters include at least the flow velocity, flow direction and wind direction of the surface water flow.

[0119] The wind-induced drift velocity estimation unit 402 is used to calculate the wind-induced drift velocity estimate based on the drift velocity value, flow velocity, and flow direction.

[0120] The bias determination unit 403 is used to determine the sample drift bias based on the wind-induced drift velocity estimate and wind direction.

[0121] The model training unit 404 is used to train the drift bias prediction model based on the sample drift bias and sample environment parameters.

[0122] In some embodiments of this disclosure, the sample acquisition unit 401 acquires drift experiment data and uses the drift experiment data as sample drift data.

[0123] In some embodiments of this disclosure, the sample acquisition unit 401 includes an experimental data acquisition subunit, a coupled model construction subunit, a simulation subunit, and a sample data determination subunit.

[0124] The experimental data acquisition subunit is used to acquire drift experimental data. The coupled model construction subunit is used to construct a fluid-floating object drift coupled model based on the drift experimental data. The fluid-floating object drift coupled model is used to characterize the influence of wind, waves, and currents on the drift of the sample floating object. The simulation subunit is used to perform simulations using the fluid-floating object drift coupled model, obtaining multiple simulation data, including the drift velocity values ​​of the sample floating object and simulation environment parameters. The sample data determination subunit is used to use the simulation data as sample drift data.

[0125] In some embodiments of this disclosure, the coupling model construction subunit includes a sub-model construction module, a coupling model construction module, and a model calibration module. The sub-model construction module is used to construct a water flow interaction model of the surface water flow on the floating sample, a wind interaction model of the wind on the floating sample, and a second-order slow-drift force model of waves. The coupling model construction module is used to construct a fluid-floating object drift coupling model to be calibrated under the action of wind, waves, and current, based on the water flow interaction model, the wind interaction model, and the second-order slow-drift force model of waves. The model calibration module is used to calibrate the fluid-floating object drift coupling model to be calibrated using drift experiment data, obtaining a calibrated fluid-floating object drift coupling model.

[0126] In some embodiments of this disclosure, the sub-model building module constructs a flow action model by building a flow force action sub-model and a flow torque action sub-model on the surface water flow to the sample floating object, and then constructs a water flow action model by combining the flow force action sub-model and the flow torque action sub-model.

[0127] In some embodiments of this disclosure, the sub-model building module constructs a wind force action sub-model and a wind moment action sub-model on the sample floating object, and uses the wind force action sub-model and the wind moment action sub-model as the wind action model.

[0128] In some embodiments of this disclosure, the sub-model building module uses the direct integration method of three-dimensional potential flow theory to construct a second-order slow-drift force model of waves.

[0129] In some embodiments of this disclosure, the wind-induced drift velocity estimation unit 402 includes a flow-induced drift velocity calculation subunit and a wind-induced drift velocity calculation subunit. The flow-induced drift velocity calculation subunit is used to calculate a flow-induced drift velocity estimate based on the flow velocity, and the wind-induced drift velocity calculation subunit is used to calculate a wind-induced drift velocity estimate using the drift velocity value and the flow-induced drift velocity estimate.

[0130] In some embodiments of this disclosure, the sample environmental parameters include, in addition to the aforementioned surface water flow velocity, flow direction and orientation, at least one of wind speed, wave height, wave period and wave direction.

[0131] The training device 400 for the drift bias prediction model provided in this embodiment can perform the above-mentioned tasks. Figure 1 Figure 2 The methods in any of the embodiments are similar in execution and beneficial effects, and will not be described again here.

[0132] This disclosure also provides a drift bias prediction device 500. Figure 5 This is a schematic diagram of the drift bias prediction device 500 provided in an embodiment of this disclosure. Figure 5 As shown, the drift bias prediction device 500 provided in this embodiment includes an environmental parameter acquisition unit 501 and a drift bias prediction unit 502.

[0133] The environmental parameter acquisition unit 501 is used to acquire environmental parameters at the location of the floating object to be predicted. The drift bias prediction unit 502 is used to input the environmental parameters into the drift bias prediction model to obtain the predicted drift bias. The drift bias prediction model is trained using the training method provided in the previous embodiment.

[0134] This disclosure also provides a computing device, which includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it can perform the above-described functions. Figures 1-3 The method of any of the embodiments.

[0135] Example, Figure 6 This is a schematic diagram of the structure of a computing device provided in an embodiment of this disclosure. Figure 6As shown, computing device 600 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from storage device 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of computing device 600. Processing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0136] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 608 including, for example, magnetic tape, hard disk, etc.; and communication devices 609. Communication device 609 allows computing device 600 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 A computing device 600 with various devices is shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0137] In particular, based on embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 609, or installed from storage device 608, or installed from ROM 602. When the computer program is executed by processing device 601, it performs the functions defined in the methods of embodiments of this disclosure.

[0138] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0139] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0140] The aforementioned computer-readable medium may be included in the aforementioned computing device; or it may exist independently and not assembled into the computing device.

[0141] The aforementioned computer-readable medium carries one or more programs that, when executed by the computing device, cause the computing device to: acquire sample drift data, including the drift velocity values ​​of sample floating objects and sample environmental parameters, the sample environmental parameters including at least the surface water flow velocity, flow direction, and wind direction; calculate a wind-induced drift velocity estimate based on the drift velocity values, flow velocity, and flow direction; determine the sample drift bias based on the wind-induced drift velocity estimate and wind direction; and train a drift bias prediction model based on the sample drift bias and sample environmental parameters. Alternatively: acquire environmental parameters at the location of the floating object to be predicted; input the environmental parameters into the drift bias prediction model to obtain the predicted drift bias.

[0142] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0143] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0144] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0145] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0146] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0147] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can perform the above-described functions. Figures 1-3 The methods in any of the embodiments are similar in execution and beneficial effects, and will not be described again here.

[0148] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0149] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily 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 this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A training method for a drift bias prediction model, characterized in that, include: Acquire sample drift data, which includes the drift velocity value of the floating sample and sample environmental parameters, including at least the flow velocity, flow direction and wind direction of the surface water; Calculate the estimated wind-induced drift velocity based on the drift velocity value, the flow velocity, and the flow direction; The sample drift bias is determined based on the estimated wind-induced drift velocity and the wind direction. The drift bias prediction model is trained based on the sample drift bias and the sample environment parameters. The acquisition of sample drift data includes: Obtain drift experiment data; A fluid-floating object drift coupling model is constructed based on the drift experiment data. This fluid-floating object drift coupling model is used to characterize the influence of wind, waves and currents on the drift of floating objects. The fluid-floating object drift coupling model was used for simulation to obtain multiple simulation data, including simulated drift velocity values ​​and simulated environmental parameters. The simulation data is used as the sample drift data.

2. The method according to claim 1, characterized in that, The construction of the fluid-floating object drift coupling model based on the drift experiment data includes: A water flow model is constructed for the surface water flow on the floating sample, a wind effect model is constructed for the wind effect on the floating sample, and a second-order slow-drift force model of waves is constructed. Based on the water flow model, the wind action model, and the second-order slow drift force model of the wave, a constant fluid-floating object drift coupling model for the sample floating object under the action of wind, waves, and current is constructed. The drift experiment data was used to calibrate the fluid-floating object drift coupling model to be calibrated, resulting in a calibrated fluid-floating object drift coupling model.

3. The method according to claim 2, characterized in that, The construction of the surface water flow model on the floating sample includes: Construct a sub-model of the hydrodynamic effect and a sub-model of the hydrodynamic moment effect of the surface water flow on the floating sample; The construction of the wind effect model on the sample floating objects includes: Construct sub-models of wind force and wind moment action on the sample floating objects; The construction of the second-order slow-drift force model of the wave includes: constructing the second-order slow-drift force model of the wave using the direct integration method of three-dimensional potential flow theory.

4. A method for predicting drift bias, characterized in that, include: Obtain environmental parameters at the location of the floating object to be predicted; The environmental parameters are input into the drift bias prediction model to obtain the predicted drift bias. The drift bias prediction model is trained using the training method for the drift bias prediction model as described in any one of claims 1-3.

5. A training device for a drift bias prediction model, characterized in that, include: The sample acquisition unit is used to acquire sample drift data, which includes the drift velocity value of the floating sample and the sample environment parameters of the surrounding environment. The sample environment parameters include at least the flow velocity, flow direction and wind direction of the surface water. The wind-induced drift velocity estimation unit is used to calculate the wind-induced drift velocity estimate based on the drift velocity value, the flow velocity, and the flow direction. A bias determination unit is used to determine the sample drift bias based on the wind-induced drift velocity estimate and the wind direction. The model training unit is used to train the drift bias prediction model based on the sample drift bias and the sample environment parameters. The sample acquisition unit includes: The experimental data acquisition subunit is used to acquire drift experimental data; The coupling model construction subunit is used to construct a fluid-floating object drift coupling model based on the drift experiment data. The fluid-floating object drift coupling model is used to characterize the influence of wind, waves and currents on the drift of floating objects. The simulation subunit is used to perform simulation using the fluid-floating object drift coupling model to obtain multiple simulation data, including simulated drift velocity values ​​and simulated environmental parameters. The sample data determination subunit is used to use the simulation data as the sample drift data.

6. A device for predicting drift bias, characterized in that, include: The environmental parameter acquisition unit is used to acquire the environmental parameters at the location of the floating object to be predicted. A drift bias prediction unit is used to input the environmental parameters into a drift bias prediction model to obtain a predicted drift bias. The drift bias prediction model is trained using the training method for the drift bias prediction model as described in any one of claims 1-3.

7. A computing device, characterized in that, include: A memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements the method as described in any one of claims 1-4.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1-4.

Images