Ship motion inverse wave method, device and medium based on wave inversion model

Abstract

The application discloses a ship motion inversion wave method and device based on a wave inversion model and a medium, relates to the technical field of wave inversion, and comprises the following steps: acquiring a wave inversion model corresponding to ship physical parameters of a current sailing ship and first ship motion response data corresponding to a preset time interval at a current sailing speed; calculating an average value of the first ship motion response data in the preset time interval to obtain target ship motion response data; and inputting the current sailing speed and the target ship motion response data into the wave inversion model to obtain wave spectrum output by the wave inversion model. The application is used to solve the problem that wave parameters of a sea area where a ship is located cannot be efficiently measured in the prior art, and achieves the purpose of efficient and accurate wave measurement with the ship.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wave inversion, in particular to a ship motion inversion wave method, device and medium based on a wave inversion model. BACKGROUND

[0002] In the technical fields of marine transportation, marine resource development, mineral exploration, offshore deepwater port design, ocean fishing, related marine engineering bonding and marine military activities, it is necessary to predict wave parameters. At present, wave parameters are obtained by receiving weather facsimile maps or satellite cloud images, but the scale of the wave parameters obtained by this method corresponds to the entire sea area, and the wave parameters of the sea area where the ship is located cannot be obtained. Moreover, the autonomous navigation and autonomous operation of the ship require wave parameters of the sea area where the ship is located to support autonomous decision-making to adapt to complex and variable marine environments and determine the successful completion of the task.

[0003] In order to obtain the wave parameters of the sea area where the ship is located, the prior art installs devices such as buoys, radars and visual systems on the sea to measure wave parameters. However, due to the fixed installation position, it is not possible to measure with the ship, or due to the influence of bad weather at sea, it is not possible to measure wave parameters with high precision and a series of problems. SUMMARY

[0004] The present application proposes a ship motion inversion wave method, device and medium based on a wave inversion model to solve the problem of being unable to efficiently measure wave parameters of the sea area where the ship is located in the prior art, and to achieve the purpose of efficient and accurate wave measurement with the ship.

[0005] The application embodiment provides a ship motion inversion wave method based on a wave inversion model, which comprises:

[0006] obtaining a wave inversion model corresponding to ship physical parameters of a current navigation ship and first ship motion response data corresponding to a preset time interval at a current navigation speed, wherein the ship physical parameters include a ship type and a ship width and a ship height corresponding to the ship type, the wave inversion model is pre-trained based on a navigation speed sample, ship motion response data samples corresponding to the ship physical parameters and the navigation speed sample, and wave spectrum samples, and the first ship motion response data is obtained based on a data collector installed on the ship;

[0007] calculating the average value of the first ship motion response data in the preset time interval to obtain target ship motion response data;

[0008] inputting the current navigation speed and the target ship motion response data into the wave inversion model to obtain the wave spectrum output by the wave inversion model.

[0009] According to the ship motion inversion wave method based on the wave inversion model provided in the embodiments of the present application, after the current sailing speed and the target ship motion response data are input into the wave inversion model, the wave spectrum output by the wave inversion model is obtained, the method further comprises:

[0010] obtaining a main wave direction corresponding to the current sailing ship, and extracting a main wave frequency from the wave spectrum based on the main wave direction;

[0011] calculating second ship motion response data under the excitation of regular waves corresponding to the main wave frequency;

[0012] subtracting the second ship motion response data from the target ship motion response data to obtain third ship motion response data;

[0013] inputting the current sailing speed and the third ship motion response data into the wave inversion model to obtain a target wave spectrum output by the wave inversion model.

[0014] According to the ship motion inversion wave method based on the wave inversion model provided in the embodiments of the present application, the ship motion response data sample comprises: a first ship motion response sample under the excitation of regular waves, and a second ship motion response sample under the excitation of irregular waves;

[0015] the wave spectrum sample comprises: a first wave spectrum sample corresponding to the first ship motion response sample, and a second wave spectrum sample corresponding to the second ship motion response sample;

[0016] the training process of the wave inversion model comprises:

[0017] inputting the sailing speed sample and the first ship motion response sample into the wave inversion model to obtain a first predicted wave spectrum output by the wave inversion model; comparing a first consistency of the first wave spectrum sample and the first predicted wave spectrum, and optimizing model parameters of the wave inversion model based on the first consistency;

[0018] and inputting the sailing speed sample and the second ship motion response sample into the wave inversion model to obtain a second predicted wave spectrum output by the wave inversion model; comparing a second consistency of the second wave spectrum sample and the second predicted wave spectrum, and optimizing the model parameters of the wave inversion model based on the second consistency, until the first consistency and the second consistency both reach a preset value, and it is determined that the training of the wave inversion model is completed.

[0019] According to the ship motion inversion wave method based on the wave inversion model provided in the embodiments of the present application, regular waves are extracted from irregular waves;

[0020] after the first consistency and the second consistency both reach preset values, further comprising:

[0021] obtaining a main wave direction sample corresponding to the irregular wave, and extracting a main wave frequency sample from the second predicted wave spectrum based on the main wave direction sample;

[0022] calculating a third ship motion response sample under excitation of a regular wave corresponding to the main wave frequency sample;

[0023] subtracting the third ship motion response sample from the second ship motion response sample to obtain a fourth ship motion response sample;

[0024] inputting the current sailing speed and the fourth ship motion response sample into the wave inversion model to obtain a third predicted wave spectrum;

[0025] comparing a third consistency of the second wave spectrum sample and the third predicted wave spectrum, optimizing model parameters of the wave inversion model based on the third consistency, until the first consistency, the second consistency and the third consistency all reach preset values, and determining that the wave inversion model training is completed.

[0026] According to the ship motion inversion wave method based on the wave inversion model provided in the embodiments of the present application, the second ship motion response sample includes a first response sample obtained based on three-dimensional simulation and pool test and a second response sample obtained based on real ship test.

[0027] According to the ship motion inversion wave method based on the wave inversion model provided in the embodiments of the present application, the first ship motion response sample is obtained based on a ship motion response calculation formula of a slice method and three-dimensional simulation.

[0028] According to the ship motion inversion wave method based on the wave inversion model provided in the embodiments of the present application, before the first ship motion response sample is obtained, further comprising:

[0029] outputting an initial ship motion response sample corresponding to a regular wave based on the ship motion response calculation formula;

[0030] verifying actual ship motion response under excitation of a regular wave based on three-dimensional simulation and pool test;

[0031] comparing a fourth consistency of the initial ship motion response sample and the actual ship motion response;

[0032] optimizing the ship motion response calculation formula based on the fourth consistency, so that the ship motion response calculation formula outputs the first ship motion response sample.

[0033] The wave inversion model-based ship motion inversion wave method provided in the embodiments of the present application is based on a basic model including any one of an LSTM network or a one-dimensional CNN network.

[0034] The embodiments of the present application also provide an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the wave inversion model-based ship motion inversion wave method according to any one of the above when executing the program.

[0035] The embodiments of the present application also provide a non-transitory computer-readable storage medium having a computer program stored thereon, and the computer program is executable by a processor to implement the steps of the wave inversion model-based ship motion inversion wave method according to any one of the above.

[0036] The wave inversion model-based ship motion inversion wave method, device and medium provided in the embodiments of the present application can obtain first ship motion response data through a data collector installed on a ship, and can obtain a wave spectrum through a wave inversion model corresponding to a ship physical parameter of a current ship, and the process can obtain a motion response corresponding to a position of the ship in real time to obtain a wave parameter (wave spectrum) of the position of the ship. It can be seen that the wave inversion model corresponding to the propagation physical parameter can better predict the wave parameter at the corresponding ship, and the average value of the first ship motion response data in a preset time interval is used for wave inversion, which can avoid the problem of poor inversion accuracy caused by data fluctuation due to environmental factors. It can be seen that the present application solves the problem that the wave parameter of the sea area where the ship is located cannot be measured efficiently in the prior art, and achieves the purpose of efficient and accurate ship wave measurement. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0038] Figure 1 is one of the flowcharts of the wave inversion model-based ship motion inversion wave method provided in the embodiments of the present application;

[0039] Figure 2 is another flowchart of the wave inversion model-based ship motion inversion wave method provided in the embodiments of the present application;

[0040] Figure 3is a structural schematic diagram of a ship motion inversion wave system based on a wave inversion model provided by an embodiment of the present application.

[0041] Figure 4 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0042] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in a clear and complete manner with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0043] An embodiment of the present application provides a ship motion inversion wave method based on a wave inversion model. The method can be applied to an intelligent terminal, can also be applied to a server, and can also be applied to a controller of an underwater vehicle. The present application takes the method applied to the controller of the underwater vehicle as an example for description, and some other descriptions in the embodiments are for example description and do not limit the protection scope of the present application. The specific implementation of the method is as shown in Figure 1

[0044] In step 101, a wave inversion model corresponding to a ship physical parameter of a current sailing ship is obtained, and first ship motion response data corresponding to a preset time interval at a current sailing speed is obtained.

[0045] The ship physical parameter includes a ship type and a ship width and a ship height corresponding to the ship type. The wave inversion model is pre-trained based on a sailing speed sample, ship motion response data samples corresponding to the ship physical parameter and the sailing speed sample, and wave spectrum samples. The first ship motion response data is obtained based on a data collector installed on the ship.

[0046] In step 102, an average value of the first ship motion response data in the preset time interval is calculated to obtain target ship motion response data.

[0047] In step 103, the current sailing speed and the target ship motion response data are input into the wave inversion model to obtain wave spectrum output by the wave inversion model.

[0048] ​The ship motion inversion wave method based on the wave inversion model provided in the embodiments of the present application can obtain the first ship motion response data through the data collector installed on the ship, and perform wave inversion through the wave inversion model corresponding to the ship physical parameters of the current sailing ship to obtain the wave spectrum. This process can obtain the motion response corresponding to the position of the ship in real time to obtain the wave parameters (wave spectrum) of the position of the ship. It can be seen that the wave inversion model corresponding to the propagation physical parameters is used in the present application, which can better predict the wave parameters at the corresponding ship. In addition, the average value of the first ship motion response data in the preset time interval is used for wave inversion in the present application, which avoids the problem of poor inversion accuracy caused by data changes due to environmental factors. It can be seen that the present application solves the problem that the wave parameters of the sea area where the ship is located cannot be measured efficiently in the prior art, and achieves the purpose of efficiently and accurately completing the wave measurement with the ship.

[0049] In one specific embodiment, after the current sailing speed and the target ship motion response data are input into the wave inversion model, the wave spectrum output by the wave inversion model is obtained, the main wave direction corresponding to the current sailing ship is obtained, and the main wave frequency is extracted from the wave spectrum based on the main wave direction. The second ship motion response data under the regular wave excitation corresponding to the main wave frequency is calculated. The second ship motion response data is subtracted from the target ship motion response data to obtain the third ship motion response data. The current sailing speed and the third ship motion response data are input into the wave inversion model to obtain the target wave spectrum output by the wave inversion model.

[0050] The ship motion response data of the ship in the wave includes any one or more of six-degree-of-freedom motion parameters, dynamic response characteristic parameters and coupled motion parameters. The six-degree-of-freedom motion parameters include surge motion, sway motion, heave motion, roll motion, pitch motion and yaw motion. The dynamic response characteristic parameters include amplitude, phase angle and acceleration. The coupled motion parameters include slamming, green water and propeller out of water.

[0051] Specifically, the main wave direction is evaluated based on machine vision to obtain the main wave direction.

[0052] Specifically, the second ship motion response data under the regular wave excitation corresponding to the main wave frequency is calculated based on the ship motion response calculation formula of the slice method.

[0053] The ship motion response calculation formula based on the slice method is prior art, and the basic idea is as follows: a general motion equation of the ship in regular waves is established; the ship body is divided into a plurality of slices along the ship length direction, and the damping coefficient and the added mass on each slice are calculated by two-dimensional flow calculation; the disturbance force and the moment on each slice are calculated according to the wave shape; the coefficients of the motion equation under various wave frequencies and speeds are determined; the frequency response function under various wave frequencies and speeds is calculated by solving the equation; and the ship motion response in waves is predicted under the assumption of a stationary random process by using a statistical analysis method.

[0054] In one specific embodiment, the base model of the wave inversion model includes any one of an LSTM network or a one-dimensional CNN network.

[0055] The LSTM network is a kind of time recurrent network and can be used for a prediction task.

[0056] The one-dimensional CNN network is a kind of feedforward neural network with convolution calculation and deep structure, and belongs to one of the deep learning algorithms.

[0057] In one specific embodiment, the first ship motion response sample is obtained based on the ship motion response calculation formula and the three-dimensional simulation.

[0058] Specifically, the ship motion response calculation formula and the three-dimensional simulation are used to calculate the ship motion response under different regular wave excitations, and the first ship motion response sample for a given ship type is generated.

[0059] In one specific embodiment, before the first ship motion response sample is obtained, an initial ship motion response sample corresponding to a regular wave is output based on the ship motion response calculation formula; the actual ship motion response under the regular wave excitation is verified based on the three-dimensional simulation and the tank test; the fourth consistency of the initial ship motion response sample and the actual ship motion response is compared; and the ship motion response calculation formula is optimized based on the fourth consistency, so that the first ship motion response sample is output by the ship motion response calculation formula.

[0060] Specifically, first, the ship motion response calculation formula and the three-dimensional simulation are used to calculate the ship motion response under different regular wave excitations, and the initial ship motion response sample for a given ship type is generated. Then, the same working condition is tested based on the tank test, the parameters of the ship motion response calculation formula are adjusted by comparing the data differences, so that the ship motion response calculation formula with higher output result accuracy is obtained. Finally, the first ship motion response sample is obtained based on the ship motion response calculation formula.

[0061] In one specific embodiment, the second ship motion response sample includes a first response sample obtained based on the three-dimensional simulation and the tank test, and a second response sample obtained based on the real ship test.

[0062] Specifically, based on three-dimensional simulation and pool test, the calculation of ship motion response under different irregular wave excitations is performed to obtain the first response sample. At the same time, the corresponding wave parameters are obtained through the buoy or shore-based visual system or radar during the test to verify the second response sample, and the second response sample that passes the verification is taken as the final second response sample.

[0063] The test conditions include wave incident direction, ship speed, wave amplitude and frequency, etc.

[0064] Specifically, the second response sample is obtained based on the real ship test.

[0065] It can be seen that the sample data of the application is obtained based on the physical formula (ship motion response calculation formula) and three-dimensional simulation, three-dimensional simulation and pool test, and real sea test of the real ship. A large amount of sample data makes the generalization ability of the wave inversion model stronger, and the accuracy of the output result higher.

[0066] In one specific embodiment, the application is a wave inversion prediction with a ship. The embodiment is only described by taking a preset time interval as an example. The whole process is a continuous prediction process, so it is necessary to predict the wave parameters based on the preset time interval step by step.

[0067] In one specific embodiment, the ship motion response data sample includes: a first ship motion response sample under regular wave excitation, and a second ship motion response sample under irregular wave excitation. The wave spectrum sample includes: a first wave spectrum sample corresponding to the first ship motion response sample, and a second wave spectrum sample corresponding to the second ship motion response sample.

[0068] The training process of the wave inversion model includes:

[0069] The sailing speed sample and the first ship motion response sample are input into the wave inversion model to obtain the first predicted wave spectrum output by the wave inversion model; the first consistency of the first wave spectrum sample and the first predicted wave spectrum is compared, and the model parameters of the wave inversion model are optimized based on the first consistency.

[0070] And the sailing speed sample and the second ship motion response sample are input into the wave inversion model to obtain the second predicted wave spectrum output by the wave inversion model; the second consistency of the second wave spectrum sample and the second predicted wave spectrum is compared, and the model parameters of the wave inversion model are optimized based on the second consistency, until the first consistency and the second consistency both reach a preset value, and it is determined that the training of the wave inversion model is completed.

[0071] In one specific embodiment, the regular wave is extracted from the irregular wave.

[0072] After the first consistency and the second consistency both reach the preset value, a main wave direction sample corresponding to the irregular wave is obtained, and a main wave frequency sample is extracted from the second predicted wave spectrum based on the main wave direction sample; a third ship motion response sample under a regular wave excitation corresponding to the main wave frequency sample is calculated; the third ship motion response sample is subtracted from the second ship motion response sample to obtain a fourth ship motion response sample; the current sailing speed and the fourth ship motion response sample are input into the wave inversion model to obtain a third predicted wave spectrum; a third consistency of the second wave spectrum sample and the third predicted wave spectrum is compared, and model parameters of the wave inversion model are optimized based on the third consistency until the first consistency, the second consistency and the third consistency all reach the preset value, and it is determined that the wave inversion model training is completed.

[0073] Next, the application is specifically described as follows: Figure 2 The application is specifically described as follows:

[0074] In step 201, training samples are obtained based on physical formulas and three-dimensional simulation, three-dimensional simulation and pool test, and real sea test of a real ship.

[0075] In step 202, the training samples are input into the wave inversion model, and the wave inversion model is trained to predict the wave spectrum by using the trained wave inversion model.

[0076] In step 203, the current sailing speed and the target ship motion response data are input into the wave inversion model to obtain the wave spectrum output by the wave inversion model.

[0077] In step 204, a main wave direction corresponding to the current sailing ship is obtained, and a directional spectrum is determined from the main wave direction and the wave spectrum.

[0078] In step 205, a wave frequency corresponding to the maximum wave in the directional spectrum and an amplitude corresponding to the wave frequency are determined.

[0079] In step 206, the wave frequency and the amplitude are input into the physical formula to obtain the second ship motion response data.

[0080] In step 207, the second ship motion response data is subtracted from the target ship motion response data to obtain the third ship motion response data.

[0081] In step 208, the current sailing speed and the third ship motion response data are input into the wave inversion model to obtain the target wave spectrum output by the wave inversion model.

[0082] In step 209, it is judged whether the ratio of the current amplitude to the amplitude smaller than the last determined amplitude is smaller than a preset ratio, if yes, step 210 is executed, otherwise, step 211 is executed.

[0083] The current amplitude is the amplitude corresponding to the maximum wave frequency in the directional spectrum corresponding to the target wave spectrum.

[0084] Step 210, combine the current extracted wave frequency, amplitude and target wave spectrum to obtain the final target wave spectrum.

[0085] Step 211, take the third ship motion response data as the target ship motion response data, and return to execute step 205.

[0086] The present application is based on ship motion response inversion wave, which is divided into formula calculation (regular wave) and data inversion (irregular wave) two parts, make full use of the two aspects, improve the precision and environmental adaptability of inversion. And, step by step, layer by layer, to ensure the accuracy of wave measurement, overall reliable, high precision, and strong environmental adaptability.

[0087] The embodiment of the present application also provides a ship motion inversion wave system based on wave inversion model, as shown in Figure 3 The embodiment of the present application also provides a ship motion inversion wave system based on wave inversion model, as shown in

[0088] The attitude sensor 301 is used for measuring the first ship motion response data and outputting to the industrial computer 303.

[0089] The machine vision wave measuring system 302 is used for evaluating the main wave direction and outputting to the industrial computer 303.

[0090] The industrial computer 303 is used for wave inversion prediction based on the first ship motion response data and the main wave direction. For specific implementation, refer to the above-mentioned ship motion inversion wave method based on wave inversion model, and the repeated parts are not described here.

[0091] Figure 4 An example of an entity structure diagram of an electronic device is shown in Figure 4 The electronic device can include a processor 401, a communications interface 402, a memory 403 and a communications bus 404, wherein the processor 401, the communications interface 402 and the memory 403 complete mutual communication through the communications bus 404. The processor 401 can call the logic instructions in the memory 403 to execute the ship motion inversion wave method based on the wave inversion model.

[0092] In addition, the logic instructions in the memory 403 described above can be implemented in the form of a software function unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0093] In another aspect, the present application also provides a computer program product, which comprises a computer program stored on a non-transitory computer readable storage medium, and the computer program comprises program instructions, and when the program instructions are executed by a computer, the computer can execute the ship motion inversion wave method based on the wave inversion model provided by the above-mentioned methods.

[0094] In another aspect, the present application also provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the ship motion inversion wave method based on the wave inversion model provided by the above-mentioned embodiments.

[0095] The device embodiments described above are only schematic, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment. Those skilled in the art can understand and implement without creative labor.

[0096] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course, can also be realized by hardware. Based on such understanding, the above technical solutions essentially or the parts that contribute to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments.

[0097] Finally, it should be noted that the above are only preferred embodiments of the present application, and the present application is not limited to the above embodiments. It can be understood that other improvements and changes directly derived or thought of by those skilled in the art without departing from the spirit and concept of the present application should be considered to be included in the protection scope of the present application.

Claims

1. A ship motion-inversion wave method based on a wave inversion model, characterized by, The method comprises: obtaining a wave inversion model corresponding to a ship physical parameter of a current sailing ship, and first ship motion response data corresponding to a preset time interval at a current sailing speed, wherein the ship physical parameter comprises a ship type and a ship width and a ship height corresponding to the ship type, the wave inversion model is pre-trained based on a sailing speed sample, a ship motion response data sample corresponding to the ship physical parameter and the sailing speed sample, and a wave spectrum sample, and the first ship motion response data is obtained based on a data collector installed on the ship; calculating an average value of the first ship motion response data in the preset time interval to obtain target ship motion response data; inputting the current sailing speed and the target ship motion response data into the wave inversion model to obtain a wave spectrum output by the wave inversion model; wherein, after inputting the current sailing speed and the target ship motion response data into the wave inversion model to obtain the wave spectrum output by the wave inversion model, the method further comprises: obtaining a main wave direction corresponding to the current sailing ship, and extracting a main wave frequency from the wave spectrum based on the main wave direction; calculating second ship motion response data under regular wave excitation corresponding to the main wave frequency; subtracting the second ship motion response data from the target ship motion response data to obtain third ship motion response data; inputting the current sailing speed and the third ship motion response data into the wave inversion model to obtain a target wave spectrum output by the wave inversion model.

2. The wave inversion model based ship motion inversion wave method according to claim 1, characterized in that, The ship motion response data sample comprises first ship motion response samples under regular wave excitation and second ship motion response samples under irregular wave excitation; The wave spectrum sample comprises first wave spectrum samples corresponding to the first ship motion response samples and second wave spectrum samples corresponding to the second ship motion response samples; The training process of the wave inversion model comprises: inputting the sailing speed sample and the first ship motion response sample into the wave inversion model to obtain a first predicted wave spectrum output by the wave inversion model; comparing a first consistency of the first wave spectrum sample and the first predicted wave spectrum, and optimizing model parameters of the wave inversion model based on the first consistency; and inputting the sailing speed sample and the second ship motion response sample into the wave inversion model to obtain a second predicted wave spectrum output by the wave inversion model; comparing a second consistency of the second wave spectrum sample and the second predicted wave spectrum, and optimizing the model parameters of the wave inversion model based on the second consistency, until the first consistency and the second consistency both reach a preset value, and determining that the training of the wave inversion model is completed.

3. The wave inversion model based ship motion inversion wave method according to claim 2, characterized in that, Regular waves are extracted from irregular waves; After the first consistency and the second consistency both reach the preset value, the method further comprises: obtaining a main wave direction sample corresponding to irregular waves, and extracting a main wave frequency sample from the second predicted wave spectrum based on the main wave direction sample; calculating third ship motion response samples under regular wave excitation corresponding to the main wave frequency sample; subtracting the third ship motion response sample from the second ship motion response sample to obtain a fourth ship motion response sample; inputting the current sailing speed and the fourth ship motion response sample into the wave inversion model to obtain a third predicted wave spectrum; comparing a third consistency of the second wave spectrum sample and the third predicted wave spectrum, and optimizing model parameters of the wave inversion model based on the third consistency until the first consistency, the second consistency and the third consistency all reach preset values, to determine that the wave inversion model training is completed.

4. The wave inversion model based ship motion inversion wave method of claim 2, wherein, The second ship motion response sample includes a first response sample based on three-dimensional simulation and pool test and a second response sample based on real ship test.

5. The wave inversion model based ship motion inversion wave method according to claim 2, wherein, The first ship motion response sample is obtained based on a ship motion response calculation formula of slice method and three-dimensional simulation.

6. The wave inversion model based ship motion inversion wave method according to claim 5, characterized in that, Before obtaining the first ship motion response sample, the method further includes: outputting an initial ship motion response sample corresponding to regular wave based on the ship motion response calculation formula; verifying actual ship motion response under regular wave excitation based on three-dimensional simulation and pool test; comparing a fourth consistency of the initial ship motion response sample and the actual ship motion response; optimizing the ship motion response calculation formula based on the fourth consistency, so that the ship motion response calculation formula outputs the first ship motion response sample.

7. The wave inversion model based ship motion inversion wave method according to claim 1, characterized in that, The base model of the wave inversion model includes any one of LSTM network or one-dimensional CNN network.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the steps of the ship motion inversion wave method based on the wave inversion model according to any one of claims 1 to 7 when executing the program. 9.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program implements the steps of the ship motion inversion wave method based on the wave inversion model according to any one of claims 1 to 7 when executed by the processor.

Images