Training method and device of wave-induced drift model, computing device and storage medium

Abstract

Embodiments of the present disclosure provide a training method and device of a wave-induced drift model, a computing device and a storage medium. The training method comprises: obtaining drift velocity observation values, surface current characteristic parameters, wind characteristic parameters and wave characteristic parameters; determining a current-induced drift coefficient, a wind-induced drift coefficient and a coefficient perturbation range based on the drift velocity observation values, the surface current characteristic parameters and the wind characteristic parameters; randomly determining a current-induced drift perturbation coefficient and a wind-induced drift perturbation coefficient within the coefficient perturbation range; calculating a wave-induced drift velocity estimation value based on the drift velocity observation values, the surface current characteristic parameters, the wind characteristic parameters, the current-induced drift coefficient, the wind-induced drift coefficient, the current-induced drift perturbation coefficient and the wind-induced drift perturbation coefficient; and training the wave-induced drift model using the wave-induced drift velocity estimation value and the wave characteristic parameters. The model training mines the implicit causal relationship between the wave-induced drift velocity and the wave characteristic parameters, without considering the theoretical model for constructing the wave-induced drift model.

Description

Technical Field

[0001] This disclosure relates to the field of maritime technology, and in particular to a training method, apparatus, computing device, and storage medium for a wave-induced drift model. Background Technology

[0002] Maritime accidents can generate various types of floating debris. For example, an oil spill may produce oil slicks. A collision may produce debris such as debris, life rafts, people who have fallen overboard, and other floating objects.

[0003] To quickly salvage and clear floating debris or conduct search and rescue operations after a maritime accident, it is necessary to determine the approximate sea area where the debris is located. Determining the approximate sea area requires predicting the drift path of the debris. Because floating debris is affected by wind, currents, and waves, accurately predicting its drift path presupposes accurately determining the wind-induced drift speed, current-induced drift speed, and wave-induced drift speed at various times.

[0004] Because there is no reasonable theoretical explanation for wave-induced drift, and the impact of wave-induced drift is relatively small compared to current-induced drift and wind-induced drift, the influence of ocean waves is generally not considered when predicting the drift path of floating objects at sea, that is, the wave-induced drift speed of floating objects at sea is not taken into account.

[0005] However, without considering wave-induced drift speed, the accuracy of predicting the drift path and actual location of floating objects at sea decreases, requiring a larger search area for floating objects during salvage, cleanup, or search and rescue operations. Summary of the Invention

[0006] To solve the above-mentioned technical problems, or at least partially solve them, this disclosure provides a training method, apparatus, computing device, and storage medium for a wave-induced drift model.

[0007] In a first aspect, embodiments of this disclosure provide a training method for a wave-induced drift model, comprising:

[0008] Acquire drift observation data collected from drift experiments. The drift observation data includes drift velocity observation values, as well as corresponding surface water flow characteristic parameters, wind characteristic parameters, and wave characteristic parameters.

[0009] Based on the observed drift velocity, the corresponding surface water flow characteristic parameters and wind characteristic parameters, the first flow-induced drift coefficient and the first wind-induced drift coefficient are determined, as well as the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient are determined.

[0010] The flow-induced drift coefficient is randomly determined within the perturbation range of the flow-induced drift coefficient, and the wind-induced drift coefficient is randomly determined within the perturbation range of the wind-induced drift coefficient.

[0011] Based on the observed drift velocity, the corresponding surface water flow characteristic parameters and wind characteristic parameters, as well as the first flow-induced drift coefficient, the first wind-induced drift coefficient, the flow-induced drift disturbance coefficient and the wind-induced drift disturbance coefficient, the wave-induced drift velocity estimate is calculated.

[0012] The wave-induced drift model is trained using the estimated wave-induced drift velocity and the corresponding wave characteristic parameters.

[0013] Optionally, before determining the first flow-induced drift coefficient and the first wind-induced drift coefficient based on drift velocity observations, corresponding surface water flow characteristic parameters, and wind characteristic parameters, and before determining the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient, the method further includes:

[0014] A sliding time window was used to perform sliding sampling on the drift observation data to obtain drift observation data for multiple sub-time periods;

[0015] Based on drift velocity observations, corresponding surface water flow characteristic parameters, and wind characteristic parameters, the first flow-induced drift coefficient and the first wind-induced drift coefficient are determined, including:

[0016] Based on the drift velocity observations, corresponding surface water flow characteristic parameters, and wind characteristic parameters in the drift observation data included in each sub-period, the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient are calculated respectively.

[0017] The first flow-induced drift coefficient is determined based on multiple second flow-induced drift coefficients, and the first wind-induced drift coefficient is determined based on multiple second wind-induced drift coefficients.

[0018] Optionally, a sliding time window is used to perform sliding sampling on the drift observation data to obtain drift observation data for multiple sub-time periods, including:

[0019] The drift observation data acquired in a continuous time period is sampled by sliding the first sliding window with the first sliding step size to obtain sample drift observation data for multiple sub-time periods, wherein the duration of the first sliding step size is less than the duration of the first sliding window.

[0020] Optionally, the first flow-induced drift coefficient is determined based on multiple second flow-induced drift coefficients, including:

[0021] Calculate the mean and standard deviation of multiple second-flow-induced drift coefficients;

[0022] Based on the mean and standard deviation of the second flow-induced drift coefficient, delete the second flow-induced drift coefficient that does not meet the first preset condition;

[0023] Repeat the aforementioned steps until all second flow-induced drift coefficients meet the first preset condition;

[0024] Calculate the mean value of the second flow-induced drift coefficient that meets the first preset condition, and use it as the first flow-induced drift coefficient;

[0025] The first wind-induced drift coefficient is determined based on multiple second wind-induced drift coefficients, including:

[0026] Calculate the mean and standard deviation of multiple second-wind-induced drift coefficients;

[0027] Based on the mean and standard deviation of the second wind-induced drift coefficient, delete the second wind-induced drift coefficient that does not meet the second preset condition;

[0028] Repeat the aforementioned steps until all the second wind-induced drift coefficients meet the second preset conditions;

[0029] Calculate the mean value of the second wind-induced drift coefficient that meets the second preset condition, and use it as the first wind-induced drift coefficient.

[0030] Optionally, the perturbation ranges of the flow-induced drift coefficient and the wind-induced drift coefficient are determined, including:

[0031] The perturbation range of the flow-induced drift coefficient is determined based on the standard deviation of the second flow-induced drift coefficient that meets the first preset condition, and the perturbation range of the wind-induced drift coefficient is determined based on the standard deviation of the second wind-induced drift coefficient that meets the second preset condition.

[0032] Optionally, before calculating the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient based on the drift velocity observations, corresponding surface water flow characteristic parameters, and wind characteristic parameters included in the drift observation data of each sub-period, the method further includes:

[0033] Determine the drift bias corresponding to each drift observation data. Drift bias is the bias of the wind-induced drift direction of the sample floating object relative to the wind direction.

[0034] Based on the drift velocity observations, corresponding surface water flow characteristic parameters, wind characteristic parameters, and drift bias in the drift observation data of each sub-period, the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient are calculated respectively.

[0035] Optionally, based on the drift velocity observations, corresponding surface water flow characteristic parameters, wind characteristic parameters, and drift bias in the drift observation data for each sub-period, the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient are calculated, including:

[0036] Based on the wind characteristic parameters and corresponding drift bias in the drift observation data, a wind-induced drift velocity expression is constructed, which includes a second wind-induced drift coefficient to be determined.

[0037] Based on surface water flow characteristic parameters in drift observation data, a flow-induced drift velocity expression is constructed, which includes a second flow-induced drift coefficient to be determined.

[0038] Based on the expressions for wind-induced drift velocity, flow-induced drift velocity, and corresponding drift velocity observations, an approximate equation is constructed.

[0039] The parameters were fitted based on the approximate equations corresponding to the drift observation data contained in each sub-period, and the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient were calculated.

[0040] Secondly, embodiments of this disclosure provide a training apparatus for a wave-induced drift model, comprising:

[0041] The data acquisition unit is used to acquire drift observation data collected in the drift experiment. The drift observation data includes drift velocity observation values, as well as corresponding surface water flow characteristic parameters, wind characteristic parameters, and wave characteristic parameters.

[0042] The coefficient determination unit is used to determine the first flow-induced drift coefficient and the first wind-induced drift coefficient based on the drift velocity observation value, the corresponding surface water flow characteristic parameters and wind characteristic parameters, as well as to determine the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient.

[0043] The disturbance determination unit is used to randomly determine the flow-induced drift disturbance coefficient within the perturbation range of the flow-induced drift coefficient and to randomly determine the wind-induced drift disturbance coefficient within the perturbation range of the wind-induced drift coefficient.

[0044] The wave-induced drift velocity estimation unit is used to calculate the wave-induced drift velocity estimate based on the drift velocity observation value, the corresponding surface water flow characteristic parameters and wind characteristic parameters, as well as the first flow-induced drift coefficient, the first wind-induced drift coefficient, the flow-induced drift disturbance coefficient and the wind-induced drift disturbance coefficient.

[0045] The model training unit is used to train the wave-induced drift model using the estimated wave-induced drift velocity and the corresponding wave characteristic parameters.

[0046] Thirdly, embodiments of this disclosure provide a computing device including a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, can implement the method described in the first aspect.

[0047] Fourthly, embodiments of this disclosure provide a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the method described in the first aspect.

[0048] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0049] Using the scheme provided in this embodiment, a first flow-induced drift coefficient, a first wind-induced drift coefficient, a perturbation range of the flow-induced drift coefficient, and a perturbation range of the wind-induced drift coefficient are determined based on drift observation data collected through drift experiments. Within these perturbation ranges, the flow-induced drift perturbation coefficient and the wind-induced drift perturbation coefficient are randomly determined. Subsequently, the actual flow-induced drift coefficient and the actual wind-induced drift coefficient are determined based on the first flow-induced drift coefficient and the flow-induced drift perturbation coefficient. Based on the actual flow-induced drift coefficient and the wind-induced drift coefficient, the observed drift velocity, surface water flow characteristic parameters, and wind characteristic parameters, an estimated wave-induced drift velocity is determined. After determining the estimated wave-induced drift velocity, a wave-induced drift model is trained using the estimated wave-induced drift velocity and wave characteristic parameters. Model training uncovers the implicit causal relationship between the wave-induced drift velocity and the wave characteristic parameters, enabling the wave-induced drift model to predict the wave-induced drift velocity effectively.

[0050] By adopting the scheme provided in this embodiment, by introducing the flow-induced drift disturbance coefficient and the wind-induced drift disturbance coefficient, the calculated flow-induced drift velocity estimate and the flow-induced drift velocity estimate are randomized, which in turn makes the wave-induced drift velocity estimate randomized, thereby enabling the wave-induced drift model trained with random wave-induced drift velocity estimates to better reflect the actual situation. Attached Figure Description

[0051] 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.

[0052] 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.

[0053] Figure 1 This is a flowchart of the training method for the wave-induced drift model provided in this embodiment of the disclosure;

[0054] Figure 2This is a flowchart of a wave-induced drift model training method provided in some embodiments of this disclosure;

[0055] Figure 3 This is a schematic diagram of a training device for the wave-induced drift model provided in an embodiment of this disclosure;

[0056] Figure 4 This is a schematic diagram of the structure of the computing device provided in the embodiments of this disclosure. Detailed Implementation

[0057] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0058] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0059] 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.

[0060] 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".

[0061] This disclosure provides a training method for a wave-induced drift model, which is used to train the wave-induced drift model and thus reasonably predict the wave-induced drift speed.

[0062] Figure 1 This is a flowchart of the training method for the wave-induced drift model provided in this embodiment of the disclosure. Figure 1 As shown, the training method for the wave-induced drift model provided in this embodiment may include S110-S150.

[0063] It should be noted that the training method for the wave-induced drift model provided in this embodiment is executed by a computing device. The computing device can be a server dedicated to data processing, or a computing device such as a laptop computer, shipborne terminal, personal digital assistant (PDA), or wearable device for rescue personnel.

[0064] S110: Acquire drift observation data collected from the drift experiment. The drift observation data includes drift velocity observation values, as well as corresponding surface water flow characteristic parameters, wind characteristic parameters, and wave characteristic parameters.

[0065] Before performing step S110, a floating sample can be used to conduct a floating experiment in a specific aquatic environment to obtain drift observation data.

[0066] Drift observation data includes drift velocity observations. Drift velocity observations are numerical values ​​characterizing the drift speed of the sample floating object. In practice, the drift trajectory of the floating object can be tracked using tracking observation vessels, positioning buoys, etc., and then the drift velocity observation value of the sample floating object can be determined by differential calculation based on the drift trajectory.

[0067] The drift observation data also includes surface water flow characteristic parameters, wind characteristic parameters, and wave characteristic parameters at the locations corresponding to the determined drift velocity observation values.

[0068] Surface flow characteristic parameters are parameters that characterize the surface water flow characteristics of the water body through which the sample floating object passes. Surface flow characteristic parameters can include the velocity and direction of the surface water flow.

[0069] Wind characteristic parameters are parameters that characterize the wind characteristics above the water surface of the water body through which the floating sample object passes. Wind characteristic parameters can include wind speed and direction. In practical applications, wind characteristic parameters can be the wind speed and direction at a height of 10m above the water level. Wave characteristic parameters are parameters that characterize the wave characteristics of the water surface of the water body through which the floating sample object passes.

[0070] Wave characteristic parameters can include at least one of wave height, wave period, and wave direction. In practice, the corresponding sample surface water flow characteristic parameters, wind characteristic parameters, and wave characteristic parameters can be obtained using equipment such as acoustic Doppler current profilers, meteorological sensors, and wave sensors carried on the tracking and observation vessel.

[0071] S120: Based on the drift velocity observations, the corresponding surface water flow characteristic parameters and wind characteristic parameters, determine the first flow-induced drift coefficient and the first wind-induced drift coefficient, as well as determine the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient.

[0072] The first flow-induced drift coefficient is a parameter characterizing the influence of surface water flow on the drift velocity of a floating sample in a body of water. The first wind-induced drift coefficient is a parameter characterizing the influence of wind acting on the floating sample on its drift velocity in a body of water.

[0073] The perturbation range of the flow-induced drift coefficient is a reliable fluctuation range of the flow-induced drift coefficient determined based on mathematical statistics. The perturbation range of the wind-induced drift coefficient is a reliable fluctuation range of the wind-induced drift coefficient determined based on mathematical statistics.

[0074] After obtaining the drift velocity observation value, the corresponding surface water flow characteristic parameters and wind characteristic parameters from the drift observation data, the aforementioned observation value and characteristic parameters can be used to perform data fitting to determine the first flow-induced drift coefficient and the first wind-induced drift coefficient, as well as the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient.

[0075] In this embodiment of the disclosure, considering that the wave-induced drift velocity is smaller than the flow-induced drift velocity and the wind-induced drift velocity, and that the wave-induced drift velocity has a smaller impact on the first flow-induced drift coefficient and the first wind-induced drift coefficient, the drift velocity observation value can be used as an approximation of the sum of the flow-induced drift velocity and the wind-induced drift velocity to construct an approximate equation, and the approximate equation is used to fit the data to determine the aforementioned drift coefficient and coefficient perturbation range.

[0076] Based on the preceding description, an approximate equation V≈V can be constructed. F-surface-current +L, where V is the observed drift velocity, V F-surface-current Let L be the estimated velocity of the flow-induced drift, and L be the estimated velocity of the wind-induced drift.

[0077] Based on the relationship between flow-induced drift velocity and surface water flow characteristic parameters, formula V can be used. F-surface-current =λ c V c Determine V F-surface-current , where λ c V is the first-order flow-induced drift coefficient. c The velocity is a characteristic parameter of surface water flow.

[0078] Wind-induced drift velocity includes wind-induced drift velocity along the wind direction and wind-induced drift velocity perpendicular to the wind direction, which can be specifically expressed as L = L d +L c The wind-induced drift velocity, L, was calculated. d L represents the wind-induced drift velocity along the wind direction. c L represents the wind-induced drift velocity perpendicular to the wind direction. d =a d W 10mWind +b d L c =ac W 10mWind +b c a d b d a c and b c W is the first wind-induced drift coefficient. 10mWind The wind speed is 10m above the water surface.

[0079] Based on the above analysis, an approximate equation V≈λ can be constructed. c V c +a d W 10mWind +b d +a c W 10mWind +b c The drift velocity observations, corresponding surface water flow characteristic parameters, and wind characteristic parameters were used to adjust the first flow-induced drift coefficient λ in the aforementioned formula. c And the first wind-induced drift coefficient a d b d a c and b c Calculations are performed. The first flow-induced drift coefficient λ mentioned above is then calculated. c And the first wind-induced drift coefficient a d b d a c and b c At the same time, the perturbation range ε ​​of the flow-induced drift coefficient can be determined. σ And the range of wind-induced drift coefficient perturbation ε d and ε c It should be noted that ε d It is aimed at b d The defined disturbance range, ε c It is aimed at b c The defined range of disturbance.

[0080] Of course, in other embodiments of this disclosure, other methods may also be used to determine the aforementioned first flow-induced drift coefficient, first wind-induced drift coefficient, flow-induced drift coefficient disturbance range, and wind-induced drift coefficient disturbance range.

[0081] S130: Randomly determine the flow-induced drift disturbance coefficient within the range of the flow-induced drift coefficient disturbance, and randomly determine the wind-induced drift disturbance coefficient within the range of the wind-induced drift coefficient disturbance.

[0082] The flow-induced drift disturbance coefficient is a random disturbance coefficient determined by adding random disturbance to the first flow-induced drift coefficient, and the wind-induced drift disturbance coefficient is a random disturbance coefficient determined by adding random disturbance to the first wind-induced drift coefficient.

[0083] In some embodiments of this disclosure, when the perturbation range of the flow-induced drift coefficient is a range symmetrically distributed based on the first flow-induced drift coefficient and is determined using a boundary coefficient, the computing device can randomly determine a random number between [-1, 1] and multiply the aforementioned random number by the aforementioned boundary coefficient to determine the flow-induced drift perturbation coefficient. Similarly, when the perturbation range of the wind-induced drift coefficient is a range symmetrically distributed based on the first wind-induced drift coefficient and is determined using a boundary coefficient, the computing device can also randomly determine a random number between [-1, 1] and multiply the random number by the boundary coefficient to determine the wind-induced drift perturbation coefficient.

[0084] In other embodiments of this disclosure, when the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient are not symmetrically distributed relative to the corresponding first flow-induced drift coefficient and first wind-induced drift coefficient, the flow-induced drift perturbation coefficient can be directly determined within the aforementioned perturbation range of the flow-induced drift coefficient and the wind-induced drift perturbation coefficient within the perturbation range of the wind-induced drift coefficient by a random number generation algorithm.

[0085] S140: Calculate the wave-induced drift velocity estimate based on the drift velocity observation, the corresponding surface water flow characteristic parameters and wind characteristic parameters, as well as the first flow-induced drift coefficient, the first wind-induced drift coefficient, the flow-induced drift disturbance coefficient and the wind-induced drift disturbance coefficient.

[0086] Since the drift speed of the sample floating object on the water surface is formed by the combined effects of wind, waves and current, that is, the drift speed observation value is the sum of the estimated drift speed caused by current, the estimated drift speed caused by wind and the estimated drift speed caused by waves. Therefore, the estimated drift speed caused by waves can be obtained by subtracting the estimated drift speed caused by current and the estimated drift speed caused by wind from the drift speed observation value.

[0087] In this embodiment of the disclosure, the estimated value of the flow-induced drift velocity can be calculated using surface water flow characteristic parameters, a first flow-induced drift coefficient, and a flow-induced drift disturbance coefficient. Specifically, the actual flow-induced drift coefficient can be determined using the first flow-induced drift coefficient and the flow-induced drift disturbance coefficient, and then the estimated value of the flow-induced drift velocity can be calculated using the surface water flow characteristic parameters and the actual flow-induced drift coefficient.

[0088] In this embodiment of the disclosure, the wind-induced drift velocity estimate can be calculated using wind characteristic parameters, a first wind-induced drift coefficient, and a wind-induced drift disturbance coefficient. Specifically, the actual wind-induced drift coefficient can be determined using the first wind-induced drift coefficient and the wind-induced drift disturbance coefficient, and then the wind-induced drift velocity estimate can be calculated using the wind characteristic parameters and the actual wind-induced drift coefficient.

[0089] After calculating the estimated values ​​of the flow-induced drift velocity and the wind-induced drift velocity, the estimated value of the wave-induced drift velocity can be obtained by subtracting the estimated values ​​of the flow-induced drift velocity and the wind-induced drift velocity from the observed drift velocity values.

[0090] S150: The wave-induced drift model is trained using the estimated wave-induced drift velocity and the corresponding wave characteristic parameters.

[0091] The wave-induced drift model is a deep learning model used to estimate wave-induced drift velocity based on wave characteristic parameters. In this embodiment of the disclosure, the wave-induced drift model can be any of the various possible models known in the art, such as a BP neural network model, a recurrent neural network model, etc., and this embodiment of the disclosure does not impose any particular limitation.

[0092] Specifically, in order to train the final optimal wave-induced drift model, multiple deep learning models can be pre-built in this embodiment of the disclosure, and each deep learning model can be trained separately. The quality of the training results determines which model to sample as the final wave-induced drift model.

[0093] For example, a pre-built deep learning model can be a model that uses wave height from the sample wave feature parameters as model input, a model that uses wave height and wave period from the sample wave feature parameters as model input, or a model that uses wave height, wave period, and wave direction from the sample wave parameters as model input.

[0094] Using the wave-induced drift model training method provided in this embodiment, a first flow-induced drift coefficient, a first wind-induced drift coefficient, a perturbation range of the flow-induced drift coefficient, and a perturbation range of the wind-induced drift coefficient are determined based on drift observation data collected from drift experiments. Within the aforementioned perturbation ranges of the flow-induced and wind-induced drift coefficients, the flow-induced drift perturbation coefficient and the wind-induced drift perturbation coefficient are randomly determined. Subsequently, based on the first flow-induced drift coefficient and the flow-induced drift perturbation coefficient, the actual flow-induced drift coefficient is determined; based on the first wind-induced drift coefficient and the wind-induced drift perturbation coefficient, the actual wind-induced drift coefficient is determined; and based on the actual flow-induced drift coefficient and the wind-induced drift coefficient, the observed drift velocity, surface water flow characteristic parameters, and wind characteristic parameters, the estimated wave-induced drift velocity is determined. After determining the estimated wave-induced drift velocity, the wave-induced drift model is trained using the estimated wave-induced drift velocity and wave characteristic parameters. Through model training, the implicit causal relationship between the wave-induced drift velocity and wave characteristic parameters is explored, enabling the wave-induced drift model to predict the wave-induced drift velocity better.

[0095] Furthermore, the aforementioned wave-induced drift model training method introduces flow-induced drift and wind-induced drift disturbance coefficients, making the calculated flow-induced drift velocity estimates and wind-induced drift velocity estimates random, thus also making the wave-induced drift velocity estimates random. The wave-induced drift model trained using random wave-induced drift velocity estimates can better reflect the actual situation.

[0096] Figure 2 This is a flowchart of a wave-induced drift model training method provided in some embodiments of this disclosure. Figure 2 As shown, in some embodiments of this disclosure, the training method for the wave-induced drift model includes steps S210-S270.

[0097] S210: Acquire drift observation data collected from the drift experiment. The drift observation data includes drift velocity observation values, as well as corresponding surface water flow characteristic parameters, wind characteristic parameters, and wave characteristic parameters.

[0098] S220: A sliding time window is used to perform sliding sampling on the drift observation data to obtain drift observation data for multiple sub-time periods.

[0099] In practice, the drift observation data acquired in the drift experiment is drift observation data obtained over a relatively long continuous period. By using a sliding time window to perform sliding sampling on the drift observation data, the long continuous period can be divided into multiple smaller sub-periods, and each sub-period has a large amount of drift observation data.

[0100] In some embodiments of this disclosure, a first sliding step size can be used to slide a first sliding time window to perform sliding sampling on drift observation data acquired over a continuous time period, resulting in sample drift observation data for multiple sub-time periods. The duration of the first sliding step size is less than the duration of the first sliding time window. In other words, when the first sliding step size is used to slide the first sliding time window, two adjacent sub-time periods have a temporal intersection, which means they have an intersection of drift observation data.

[0101] S230: Based on the drift velocity observations, corresponding surface water flow characteristic parameters, and wind characteristic parameters included in the drift observation data of each sub-period, calculate the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient respectively.

[0102] In this embodiment of the disclosure, the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient can be calculated using the drift velocity observation values, surface water flow characteristic parameters, and wind characteristic parameters included in the drift observation data of each sub-time period, as described in S120 above. This will not be repeated here. It should be noted that when calculating the second flow-induced drift coefficient and the second wind-induced drift coefficient using the method described above, it is not necessary to calculate the corresponding perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient.

[0103] S240: Determine the first flow-induced drift coefficient based on multiple second flow-induced drift coefficients, determine the first wind-induced drift coefficient based on multiple second wind-induced drift coefficients; and determine the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient.

[0104] In some embodiments of this disclosure, the average of multiple second flow-induced drift coefficients can be calculated, and the average value can be used as the first flow-induced drift coefficient. Similarly, the average of multiple second wind-induced drift coefficients can be calculated, and the average value can be used as the first wind-induced drift coefficient.

[0105] In some embodiments of this disclosure, the perturbation range of the flow-induced drift coefficient can be determined based on the standard deviation calculated from multiple second flow-induced drift coefficients. Similarly, the perturbation range of the wind-induced drift coefficient can be determined based on the standard deviation calculated from multiple second wind-induced drift coefficients.

[0106] In other embodiments of this disclosure, the computing device may determine the first flow-induced drift coefficient based on the second flow-induced drift coefficient using the following steps S241-S244.

[0107] S241: Calculate the mean and standard deviation of multiple second flow-induced drift coefficients.

[0108] For example, if the second flow-induced drift coefficients are λ c1 ,λ c2 ,L,λ cn The corresponding mean is λ. c =(λ c1 +λ c2 +L+λ cn ) / n, standard deviation is

[0109] Step S242: Based on the mean and standard deviation of the second flow-induced drift coefficients, determine whether the distribution characteristics of multiple second flow-induced drift coefficients meet the first preset condition. If they meet the condition, proceed to step S243; otherwise, proceed to step S244.

[0110] The first preset condition is determined by the mean and standard deviation of the second flow-induced drift coefficient. For example, the first preset condition could be the possible range of the flow-induced drift coefficient, centered at the mean of the second flow-induced drift coefficient and defined by m times the standard deviation. In a specific application, m could be set to 3.

[0111] Step S243: Take the average of multiple second flow-induced drift coefficients as the first flow-induced drift coefficient.

[0112] Step S244: Delete the second flow-induced drift coefficient that does not meet the first preset condition, and re-execute S241-S242 until the distribution characteristics of the remaining second flow-induced drift velocity meet the first preset condition.

[0113] If the distribution characteristics of the second flow-induced drift coefficients do not meet the first preset condition, then the second flow-induced drift coefficients that do not meet the first preset condition can be deleted. Subsequently, the mean and standard deviation of the filtered second flow-induced drift coefficients are recalculated according to the aforementioned method until the distribution characteristics of the remaining second flow-induced drift coefficients meet the second preset condition.

[0114] When calculating the first flow-induced drift coefficient using the aforementioned steps S241-S244, the perturbation range of the flow-induced drift coefficient can be determined based on the standard deviation of the remaining first flow-induced drift coefficient. For example, three times the standard deviation can be used to determine the perturbation range of the flow-induced drift coefficient.

[0115] Similar to the aforementioned method for calculating the first flow-induced drift coefficient, in some embodiments of this disclosure, the computing device may use the following steps S245-S248 to determine the first wind-induced drift coefficient based on the second wind-induced drift coefficient.

[0116] Step S245: Calculate the mean and standard deviation of the second wind-induced drift coefficient.

[0117] In this embodiment of the disclosure, the mean and standard deviation of each second wind-induced drift coefficient can be calculated separately.

[0118] Step S246: Based on the mean and standard deviation of the second wind-induced drift coefficient, determine whether the distribution characteristics of multiple second wind-induced drift coefficients meet the second preset conditions; if they meet the conditions, proceed to step S247; if they do not meet the conditions, proceed to step S248.

[0119] Step S247: The average of multiple second wind-induced drift coefficients is used as the first wind-induced drift coefficient.

[0120] Step S248: Delete the second wind-induced drift coefficient that does not meet the second preset condition, and repeat steps S245-S246 until the distribution characteristics of the second wind-induced drift velocity after screening meet the second preset condition.

[0121] When calculating the first wind-induced drift coefficient using the aforementioned steps S245-S248, the perturbation range of the wind-induced drift coefficient can be determined based on the standard deviation of the remaining first wind-induced drift coefficient. For example, three times the standard deviation can be used to determine the perturbation range of the wind-induced drift coefficient.

[0122] S250: Randomly determine the flow-induced drift disturbance coefficient within the range of the flow-induced drift coefficient disturbance, and randomly determine the wind-induced drift disturbance coefficient within the range of the wind-induced drift coefficient disturbance.

[0123] S260: Based on the observed drift velocity, the corresponding surface water flow characteristic parameters and wind characteristic parameters, as well as the first flow-induced drift coefficient, the first wind-induced drift coefficient, the flow-induced drift disturbance coefficient and the wind-induced drift disturbance coefficient, the wave-induced drift velocity estimate is calculated.

[0124] S270: The wave-induced drift model is trained using the estimated wave-induced drift velocity and the corresponding wave characteristic parameters.

[0125] The specific implementation process of S250-S270 is as described in the previous embodiments and will not be repeated here.

[0126] The wave-induced drift model training method provided in this disclosure calculates a second flow-induced drift coefficient and a second wind-induced drift coefficient using first sample drift data included in each sub-time period. Multiple second flow-induced drift coefficients and second wind-induced drift coefficients are then used to calculate a first flow-induced drift coefficient, a first wind-induced drift coefficient, a flow-induced drift coefficient perturbation range, and a wind-induced drift coefficient perturbation range. Based on these parameters, the subsequently calculated wind-induced drift velocity estimates, flow-induced drift velocity estimates, and wave-induced drift velocity estimates are more accurate. This allows the data from the subsequently trained wave-induced drift model to more accurately reflect the actual situation, thereby making the wave-induced drift model more precise in its estimation of wave-induced drift velocity.

[0127] Optionally, in some embodiments of this disclosure, S280 may also be executed before S250.

[0128] S280: Determine the drift bias corresponding to each drift observation data.

[0129] Drift bias is the bias of the wind-induced drift direction of a sample floating object relative to the wind direction.

[0130] In this embodiment of the disclosure, the magnitude and direction of the wind-induced drift velocity estimate can be obtained by subtracting the flow-induced drift velocity estimate from the drift velocity observation value in the drift observation data, and the wind-induced drift velocity estimate and the wind direction in the wind characteristic parameters are used to determine the bias of the wind-induced drift direction of the sample floating object relative to the wind direction.

[0131] Building upon S280, S230 may specifically include: calculating the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient based on the drift velocity observations, corresponding surface water flow characteristic parameters, wind characteristic parameters, and drift bias in the drift observation data for each sub-period. In a specific embodiment, S230 may include S231-S234.

[0132] S231: Based on the wind characteristic parameters and corresponding drift bias in the drift observation data, construct a wind-induced drift velocity expression, which includes a second wind-induced drift coefficient to be determined.

[0133] In this embodiment of the disclosure, different wind-induced drift directions correspond to different second wind-induced drift coefficients. For example, when the drift bias is leftward, the corresponding second wind-induced drift coefficient includes a. c+ and b c+ When the drift bias is rightward, the corresponding second wind-induced drift coefficient includes a. c- and b c- .

[0134] In this embodiment of the disclosure, the following methods can be used: Determine the second wind-induced drift coefficient, where δ is determined based on the drift bias. δ is 1 when the drift bias is left and 0 when the drift bias is right.

[0135] S232: Based on the surface water flow characteristic parameters in the drift observation data, construct a flow-induced drift velocity expression, which includes a second flow-induced drift coefficient to be determined.

[0136] The execution process of S232 is as described in S120 above, and will not be repeated here.

[0137] S233: Based on the expressions for wind-induced drift velocity, flow-induced drift velocity, and the corresponding drift velocity observations, an approximate equation is constructed.

[0138] S234: Based on the approximate equations corresponding to the drift observation data contained in each sub-period, the parameters are fitted to calculate the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient.

[0139] It should be noted that when using the aforementioned method to determine the second wind drift coefficient corresponding to different wind-induced offset directionalities, it is necessary to determine the perturbation range of the wind drift coefficient corresponding to the first wind drift coefficient.

[0140] Based on the aforementioned S231-S234, the corresponding second wind-induced drift coefficient to be fitted is selected by drift bias and fitted, thereby making the final determined first flow-induced drift coefficient and first wind-induced drift coefficient more in line with the actual situation, so that the data of the wave-induced drift model obtained by subsequent training more accurately reflects the actual situation, and thus makes the wave-induced drift model more accurate in its wave-induced drift speed.

[0141] In addition to providing the aforementioned training method for the wave-induced drift model, this disclosure also provides a training device 300 for the wave-induced drift model. Figure 3 This is a schematic diagram of a training device for the wave-induced drift model provided in an embodiment of this disclosure. Figure 3 As shown, the wave-induced drift model training device 300 provided in this embodiment includes a data acquisition unit 301, a coefficient determination unit 302, a disturbance determination unit 303, a wave-induced drift velocity estimation calculation unit 304, and a model training unit 305.

[0142] The data acquisition unit 301 is used to acquire drift observation data collected in the drift experiment. The drift observation data includes drift velocity observation values, as well as corresponding surface water flow characteristic parameters, wind characteristic parameters, and wave characteristic parameters.

[0143] The coefficient determination unit 302 is used to determine the first flow-induced drift coefficient and the first wind-induced drift coefficient based on the drift velocity observation value, the corresponding surface water flow characteristic parameters and wind characteristic parameters, as well as to determine the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient.

[0144] The disturbance determination unit 303 is used to randomly determine the flow-induced drift disturbance coefficient within the range of the flow-induced drift coefficient disturbance, and to randomly determine the wind-induced drift disturbance coefficient within the range of the wind-induced drift coefficient disturbance.

[0145] The wave-induced drift velocity estimation unit 304 is used to calculate the wave-induced drift velocity estimate based on the drift velocity observation value, the corresponding surface water flow characteristic parameters and wind characteristic parameters, as well as the first flow-induced drift coefficient, the first wind-induced drift coefficient, the flow-induced drift disturbance coefficient and the wind-induced drift disturbance coefficient.

[0146] The model training unit 305 is used to train the wave-induced drift model using the estimated wave-induced drift velocity and the corresponding wave characteristic parameters.

[0147] Optionally, in some embodiments of this disclosure, the training device 300 for the wave-induced drift model further includes a sliding sampling unit. The sliding sampling unit is used to perform sliding sampling on the drift observation data using a sliding time window to obtain drift observation data for multiple sub-periods. When the training device 300 for the wave-induced drift model includes a sliding sampling unit, the coefficient determination unit 302 includes a first coefficient determination subunit and a second coefficient determination subunit. The first coefficient determination subunit is used to calculate the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient based on the drift velocity observation values, corresponding surface water flow characteristic parameters, and wind characteristic parameters included in the drift observation data for each sub-period; the second coefficient determination subunit determines the first flow-induced drift coefficient based on multiple second flow-induced drift coefficients, and determines the first wind-induced drift coefficient based on multiple second wind-induced drift coefficients.

[0148] Optionally, in some embodiments of this disclosure, the sliding sampling unit uses a first sliding step size to slide a first sliding time window to perform sliding sampling on drift observation data acquired in continuous time periods, thereby obtaining sample drift observation data for multiple sub-time periods, wherein the duration of the first sliding step size is less than the duration of the first sliding time window.

[0149] Optionally, in some embodiments of this disclosure, the second coefficient determining subunit determines the first flow-induced drift coefficient using the following method: calculating the mean and standard deviation of a plurality of second flow-induced drift coefficients; based on the mean and standard deviation of the second flow-induced drift coefficients, determining whether the distribution characteristics of the plurality of second flow-induced drift coefficients meet a first preset condition; if the distribution characteristics of the plurality of second flow-induced drift coefficients do not meet the first preset condition, deleting the second flow-induced drift coefficients that do not meet the first preset condition, and re-executing the aforementioned steps; if the distribution characteristics of the plurality of second flow-induced drift coefficients meet the first preset condition, calculating the mean of the second flow-induced drift coefficients that meet the first preset condition, and using it as the first flow-induced drift coefficient.

[0150] Optionally, in some embodiments of this disclosure, the second coefficient determining subunit determines the first wind-induced drift coefficient using the following method: calculating the mean and standard deviation of multiple second wind-induced drift coefficients; based on the mean and standard deviation of the second wind-induced drift coefficients, determining whether the distribution characteristics of the multiple second wind-induced drift coefficients meet a second preset condition; if the distribution characteristics of the multiple second wind-induced drift coefficients do not meet the second preset condition, deleting the second wind-induced drift coefficients that do not meet the second preset condition and re-executing the aforementioned steps; if the distribution characteristics of the multiple second wind-induced drift coefficients meet the second preset condition, calculating the mean of the second wind-induced drift coefficients that meet the second preset condition, and using it as the first wind-induced drift coefficient.

[0151] Optionally, in some embodiments of this disclosure, the coefficient determination unit 302 determines the perturbation range of the flow-induced drift coefficient based on the standard deviation of the second flow-induced drift coefficient that meets the first preset condition, and determines the perturbation range of the wind-induced drift coefficient based on the standard deviation of the second wind-induced drift coefficient that meets the second preset condition.

[0152] Optionally, in some embodiments of this disclosure, the training apparatus 300 for the wave-induced drift model may further include a bias determination unit. The bias determination unit determines the drift bias corresponding to each drift observation data point, whereby the drift bias is the deviation of the wind-induced drift direction of the sample floating object relative to the wind direction. Correspondingly, the first coefficient determination subunit calculates the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient based on the drift velocity observation values, corresponding surface water flow characteristic parameters, wind characteristic parameters, and drift bias in the drift observation data for each sub-period.

[0153] Optionally, in some embodiments of this disclosure, the first coefficient determination subunit includes a wind-induced drift expression construction module, a flow-induced drift expression construction module, an approximate equation construction module, and a drift coefficient construction module. The wind-induced drift expression construction module is used to construct a wind-induced drift velocity expression based on wind characteristic parameters and corresponding drift biases in drift observation data. The wind-induced drift velocity expression includes a second wind-induced drift coefficient to be determined. The flow-induced drift expression construction module is used to construct a flow-induced drift velocity expression based on surface water flow characteristic parameters in drift observation data. The flow-induced drift velocity expression includes a second flow-induced drift coefficient to be determined. The approximate equation construction module is used to construct an approximate equation based on the wind-induced drift velocity expression, the flow-induced drift velocity expression, and the corresponding drift velocity observation values. The drift coefficient construction module is used to perform parameter fitting based on the approximate equations corresponding to the drift observation data contained in each sub-period, respectively, to calculate the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient.

[0154] This disclosure also provides a computing device including a processor and a memory, wherein the memory stores a computer program that, when executed by the processor, can implement the methods of any of the above embodiments.

[0155] Figure 4 This is a schematic diagram of the structure of the computing device provided in the embodiments of this disclosure. For example... Figure 4 As shown, the computing device 400 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the computing device 400. The processing unit 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0156] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows computing device 400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 A computing device 400 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.

[0157] 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 409, or installed from storage device 408, or installed from ROM 402. When the computer program is executed by processing device 401, it performs the functions defined in the methods of embodiments of this disclosure.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] The aforementioned computer-readable medium carries one or more programs, which, when executed by the computing device, cause the computing device to: acquire drift observation data collected from drift experiments, the drift observation data including drift velocity observation values, and corresponding surface water flow characteristic parameters, wind characteristic parameters, and wave characteristic parameters; determine a first flow-induced drift coefficient and a first wind-induced drift coefficient, and determine the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient, based on the drift velocity observation values, the corresponding surface water flow characteristic parameters, and the wind characteristic parameters; randomly determine the flow-induced drift perturbation coefficient within the perturbation range of the flow-induced drift coefficient, and randomly determine the wind-induced drift perturbation coefficient within the perturbation range of the wind-induced drift coefficient; calculate the wave-induced drift velocity estimate based on the drift velocity observation values, the corresponding surface water flow characteristic parameters, the wind characteristic parameters, the first flow-induced drift coefficient, the first wind-induced drift coefficient, the flow-induced drift perturbation coefficient, and the wind-induced drift perturbation coefficient; and train the wave-induced drift model using the wave-induced drift velocity estimate and the corresponding wave characteristic parameters.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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 1-4The methods in any of the embodiments are similar in execution and beneficial effects, and will not be described again here.

[0168] 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. Unless otherwise specified, 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 the element.

[0169] The above are merely specific embodiments of this disclosure, enabling those skilled in the art to understand or implement this disclosure. 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 these embodiments, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A training method for a wave-induced drift model, characterized in that, include: Acquire drift observation data collected from drift experiments, including drift velocity observation values, as well as corresponding surface water flow characteristic parameters, wind characteristic parameters, and wave characteristic parameters; Based on the observed drift velocity, the corresponding surface water flow characteristic parameters, and the wind characteristic parameters, a first flow-induced drift coefficient and a first wind-induced drift coefficient are determined, as well as the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient are determined. The perturbation range of the flow-induced drift coefficient is determined based on the standard deviation of the second flow-induced drift coefficient that meets a first preset condition, and the perturbation range of the wind-induced drift coefficient is determined based on the standard deviation of the second wind-induced drift coefficient that meets a second preset condition. The flow-induced drift coefficient is randomly determined within the perturbation range of the flow-induced drift coefficient, and the wind-induced drift coefficient is randomly determined within the perturbation range of the wind-induced drift coefficient. The perturbation range of the flow-induced drift coefficient is a reliable fluctuation range of the flow-induced drift coefficient determined based on mathematical statistics, and the perturbation range of the wind-induced drift coefficient is a reliable fluctuation range of the wind-induced drift coefficient determined based on mathematical statistics. Based on the observed drift velocity, the corresponding surface water flow characteristic parameters and wind characteristic parameters, as well as the first flow-induced drift coefficient, the first wind-induced drift coefficient, the flow-induced drift disturbance coefficient and the wind-induced drift disturbance coefficient, the wave-induced drift velocity estimate is calculated. The wave-induced drift velocity estimate and the corresponding wave characteristic parameters are used to train the wave-induced drift model; The process of determining the first flow-induced drift coefficient and the first wind-induced drift coefficient based on the observed drift velocity values, corresponding surface water flow characteristic parameters, and wind characteristic parameters, as well as determining the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient, includes: The observed drift velocity values, corresponding surface water flow characteristic parameters, and wind characteristic parameters are fitted to determine the first flow-induced drift coefficient and the first wind-induced drift coefficient, as well as the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient.

2. The method according to claim 1, characterized in that, Before determining the first flow-induced drift coefficient and the first wind-induced drift coefficient based on the drift velocity observations, corresponding surface water flow characteristic parameters, and wind characteristic parameters, and before determining the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient, the method further includes: The drift observation data is sampled using a sliding time window to obtain drift observation data for multiple sub-time periods; The determination of the first flow-induced drift coefficient and the first wind-induced drift coefficient based on the observed drift velocity, the corresponding surface water flow characteristic parameters, and the wind characteristic parameters includes: Based on the drift velocity observations, corresponding surface water flow characteristic parameters, and wind characteristic parameters included in each of the sub-time periods, the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient are calculated respectively. The first flow-induced drift coefficient is determined based on a plurality of second flow-induced drift coefficients, and the first wind-induced drift coefficient is determined based on a plurality of second wind-induced drift coefficients.

3. The method according to claim 2, characterized in that, The drift observation data is sampled using a sliding time window to obtain drift observation data for multiple sub-time periods, including: The drift observation data acquired in a continuous time period is sampled by sliding a first sliding window with a first sliding step size to obtain sample drift observation data for multiple sub-time periods, wherein the duration of the first sliding step size is less than the duration of the first sliding window.

4. The method according to claim 2, characterized in that, Determining the first flow-induced drift coefficient based on multiple second flow-induced drift coefficients includes: Calculate the mean and standard deviation of multiple second flow-induced drift coefficients; Based on the mean and standard deviation of the second flow-induced drift coefficient, determine whether the distribution characteristics of multiple second flow-induced drift coefficients meet the first preset condition; If the distribution characteristics of the plurality of second flow-induced drift coefficients do not meet the first preset condition, delete the second flow-induced drift coefficients that do not meet the first preset condition and repeat the aforementioned steps; If the distribution characteristics of the plurality of second flow-induced drift coefficients meet the first preset condition, the mean value of the second flow-induced drift coefficients that meet the first preset condition is calculated and used as the first flow-induced drift coefficient. The determination of the first wind-induced drift coefficient based on multiple second wind-induced drift coefficients includes: Calculate the mean and standard deviation of multiple second wind-induced drift coefficients; Based on the mean and standard deviation of the second wind-induced drift coefficient, determine whether the distribution characteristics of multiple second wind-induced drift coefficients meet the second preset conditions; If the distribution characteristics of the plurality of second wind-induced drift coefficients do not meet the second preset conditions, delete the second wind-induced drift coefficients that do not meet the second preset conditions and repeat the aforementioned steps; If the distribution characteristics of the plurality of second wind-induced drift coefficients meet the second preset conditions, the mean value of the second wind-induced drift coefficients that meet the second preset conditions is calculated and used as the first wind-induced drift coefficient.

5. The method according to claim 2, characterized in that, Before calculating the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient based on the drift velocity observations, corresponding surface water flow characteristic parameters, and wind characteristic parameters included in each of the sub-time periods, the method further includes: Determine the drift bias corresponding to each drift observation data, wherein the drift bias is the bias of the wind-induced drift direction of the sample floating object relative to the wind direction; The calculation of the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient based on the drift velocity observations, corresponding surface water flow characteristic parameters, and wind characteristic parameters included in each of the sub-time periods, includes: Based on the drift velocity observations, corresponding surface water flow characteristic parameters, wind characteristic parameters, and drift bias in the drift observation data of each sub-period, the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient are calculated respectively.

6. The method according to claim 5, characterized in that, The calculation of the second flow-induced drift coefficient and the second wind-induced drift coefficient based on the drift velocity observations, corresponding surface water flow characteristic parameters, wind characteristic parameters, and drift bias in the drift observation data of each sub-time period includes: Based on the wind characteristic parameters and corresponding drift bias in the drift observation data, a wind-induced drift velocity expression is constructed, which includes the second wind-induced drift coefficient to be determined. Based on the surface water flow characteristic parameters in the drift observation data, a flow-induced drift velocity expression is constructed, which includes the second flow-induced drift coefficient to be determined. Based on the wind-induced drift velocity expression, the flow-induced drift velocity expression, and the corresponding drift velocity observations, an approximate equation is constructed; The parameters are fitted based on the approximate equations corresponding to the drift observation data contained in each of the sub-time periods, and the corresponding second flow-induced drift coefficient and second wind-induced drift coefficient are calculated.

7. A training device for a wave-induced drift model, characterized in that, include: The data acquisition unit is used to acquire drift observation data collected in the drift experiment. The drift observation data includes drift velocity observation values, as well as corresponding surface water flow characteristic parameters, wind characteristic parameters, and wave characteristic parameters. The coefficient determination unit is used to determine a first flow-induced drift coefficient and a first wind-induced drift coefficient based on the observed drift velocity, the corresponding surface water flow characteristic parameters, and wind characteristic parameters, and to determine the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient, wherein the perturbation range of the flow-induced drift coefficient is determined based on the standard deviation of a second flow-induced drift coefficient that meets a first preset condition, and the perturbation range of the wind-induced drift coefficient is determined based on the standard deviation of a second wind-induced drift coefficient that meets a second preset condition; The disturbance determination unit is used to randomly determine the flow-induced drift disturbance coefficient within the disturbance range of the flow-induced drift coefficient, and to randomly determine the wind-induced drift disturbance coefficient within the disturbance range of the wind-induced drift coefficient, wherein the disturbance range of the flow-induced drift coefficient is a reliable fluctuation range of the flow-induced drift coefficient determined based on mathematical statistics, and the disturbance range of the wind-induced drift coefficient is a reliable fluctuation range of the wind-induced drift coefficient determined based on mathematical statistics; The wave-induced drift velocity estimation unit is used to calculate the wave-induced drift velocity estimate based on the drift velocity observation value, the corresponding surface water flow characteristic parameters and wind characteristic parameters, as well as the first flow-induced drift coefficient, the first wind-induced drift coefficient, the flow-induced drift disturbance coefficient and the wind-induced drift disturbance coefficient. The model training unit is used to train the wave-induced drift model using the estimated wave-induced drift velocity and the corresponding wave feature parameters. The process of determining the first flow-induced drift coefficient and the first wind-induced drift coefficient based on the observed drift velocity values, corresponding surface water flow characteristic parameters, and wind characteristic parameters, as well as determining the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient, includes: The observed drift velocity values, corresponding surface water flow characteristic parameters, and wind characteristic parameters are fitted to determine the first flow-induced drift coefficient and the first wind-induced drift coefficient, as well as the perturbation range of the flow-induced drift coefficient and the perturbation range of the wind-induced drift coefficient.

8. 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 1-6.

9. 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 1-6.

Images