Method and device for rapidly predicting harbor waves and dynamic responses of moored ships

Abstract

The present invention discloses a method for rapidly predicting harbor waves and the dynamic response of moored ships, comprising: S1: constructing a harbor wave numerical model; S2: constructing a mooring numerical model of a preset ship type; S3: using the harbor wave numerical model and the mooring numerical model to establish a training set, the training set including nearshore wave condition parameters, nearshore wind field condition parameters, harbor wave parameters, and moored ship dynamic response data; S4: using the nearshore wave condition parameters and the nearshore wind field condition parameters as inputs and the harbor wave parameters and the moored ship dynamic response data as outputs to train a neural network model; S5: inputting nearshore wave observation data and nearshore wind field observation data into the neural network model to obtain harbor wave and moored ship dynamic response prediction data. The present invention can overcome the shortcomings of the prior art and achieve rapid prediction of harbor waves and moored ship dynamic responses.

Description

Technical Field

[0001] The present invention relates to the technical field related to port engineering, and more specifically, to a method and device for rapidly predicting port waves and the dynamic response of moored ships based on wave numerical simulation, mooring numerical simulation, and an artificial neural network model. Background Art

[0002] The primary function of a port is to provide safe berthing areas for ships to facilitate cargo loading and unloading operations. To ensure safe ship operations, meteorological and hydrological conditions in the port waters must not exceed certain thresholds, and the dynamic responses of moored ships, such as motion, mooring force, and fender reaction, must also not exceed certain standards. Forecasting wave conditions in the port waters and the dynamic responses of moored ships can provide data support for port operations: loading and unloading personnel can rationally arrange dispatch based on future wave conditions in the port waters, as well as ship motion, mooring force, and fender reaction, thereby improving loading and unloading efficiency at the terminal and taking timely early warning and risk avoidance measures before an emergency occurs, ensuring safe port operations.

[0003] However, to avoid disrupting daily port operations, real-time wave monitoring is typically conducted in nearshore waters, outside the harbor. Wave monitoring in harbor waters typically only occurs before the port officially opens. Monitoring the motion, mooring forces, and fender reactions of moored vessels is even more rare. Numerical wave models can be used to simulate wave propagation and deformation, determining the wave conditions in harbor waters. Mooring numerical models can simulate the dynamic response of a ship under varying environmental conditions, including the ship's six degrees of freedom motion, mooring forces, and fender reactions. However, numerical simulation technology can only simulate fixed combinations of operating conditions and cannot directly predict the wave conditions in harbor waters or the dynamic responses of moored vessels, such as motion, mooring forces, and fender reactions, under unknown on-site conditions. Furthermore, numerical simulation technology requires a long calculation time for each operating condition, resulting in poor timeliness and inability to provide real-time predictions, much less meet the requirements of practical applications.

[0004] Therefore, it is necessary to design a technical solution that can overcome the above-mentioned defects. Summary of the Invention

[0005] An object of the present invention is to provide a method and device for rapidly forecasting the dynamic response of waves in a harbor and moored ships, thereby overcoming the defects of the prior art and achieving rapid forecasting of the dynamic response of waves in a harbor and moored ships.

[0006] To achieve these objectives and other advantages of the present invention, according to one aspect of the present invention, there is provided a method for rapidly predicting in-harbor waves and the dynamic response of moored ships, comprising: S1: constructing an in-harbor wave numerical model; S2: constructing a mooring numerical model of a preset ship type; S3: establishing a training set using the in-harbor wave numerical model and the mooring numerical model, wherein the training set includes nearshore wave condition parameters, nearshore wind field condition parameters, in-harbor wave parameters, and moored ship dynamic response data; S4: training a neural network model using the nearshore wave condition parameters and the nearshore wind field condition parameters as inputs and the in-harbor wave parameters and the moored ship dynamic response data as outputs; and S5: inputting nearshore wave observation data and nearshore wind field observation data into the neural network model to obtain predicted data for in-harbor waves and the dynamic response of the moored ship.

[0007] Furthermore, in said S1, nearshore wave condition information is obtained, and a combination of nearshore wave height, period, and wave direction is determined as input, and a numerical model of in-harbor waves is constructed using a gentle slope equation model or a Boussinesq model to simulate the wave motion in the harbor.

[0008] Furthermore, the method for obtaining the nearshore wave condition information includes: downloading it from the global wave model and wave reanalysis hindcast database, or outputting the nearshore wave condition information through a pre-established regional wave numerical model, or deploying observation equipment to conduct wave observations in the nearshore waters to collect nearshore wave condition information.

[0009] Furthermore, the numerical model of harbor waves adopts a rectangular grid, and the calculation domain includes the entire harbor waters, harbor buildings and part of the nearshore waters.

[0010] Furthermore, in said S2, the floating body equation of formula (1) is used to build a mooring numerical model;

[0011]

[0012] Among them, x k (t) represents the translation and rotation motion of the floating body in six degrees of freedom. The points above represent the differential with respect to time t, M k and a k are the inertial force recovery matrix and the additional mass impulse response matrix, K k is the wave radiation force impulse response matrix, C k is the static force recovery matrix, F D (t) is the wave excitation force, F nl (t) is the nonlinear external force caused by mooring force, fender reaction force, viscous damping, wind force, flow force, second-order wave drift force and friction damping force.

[0013] Furthermore, the parameters of the preset ship type are obtained, combined with the numerical model of the waves in the harbor, and the floating body equation is used to build a mooring numerical model.

[0014] Furthermore, the nearshore wave condition parameters and the nearshore wind field condition parameters include nearshore wave height, wave period, wave direction, wind speed, and wind direction.

[0015] Furthermore, the port wave parameters and the moored ship dynamic response data include the ship's six degrees of freedom motion, mooring force, and fender reaction force.

[0016] According to another aspect of the present invention, there is also provided an apparatus for rapidly predicting the dynamic response of harbor waves and moored ships, comprising: a first building module for building a numerical model of harbor waves; a second building module for building a mooring numerical model of a preset ship type; a building module for building a training set using the harbor wave numerical model and the mooring numerical model, the training set comprising nearshore wave condition parameters, nearshore wind field condition parameters, harbor wave parameters, and moored ship dynamic response data; a training module for training a neural network model using the nearshore wave condition parameters and the nearshore wind field condition parameters as inputs and the harbor wave parameters and the moored ship dynamic response data as outputs; and a prediction module for inputting nearshore wave observation data and nearshore wind field observation data into the neural network model to obtain predicted data of harbor waves and the dynamic response of the moored ship.

[0017] The present invention has at least the following beneficial effects:

[0018] The present invention proposes a scientific method for rapidly predicting the dynamic responses of in-port waves and moored ships based on wave numerical simulation, mooring numerical simulation and artificial neural network model. The method sequentially constructs a numerical model of in-port waves and a numerical model of mooring for a preset ship type, and uses the wave numerical model and the numerical model of mooring for a preset ship type to generate training data. The artificial neural network model is trained to establish a mapping relationship between nearshore waves, wind field conditions and the dynamic responses of in-port waves and ships. Finally, by combining the nearshore wave observation data and the wind field observation data, a rapid prediction of the dynamic responses of in-port waves and moored ships is achieved. This method can help guide terminal operations, improve terminal loading and unloading efficiency, ensure safe port operation, reduce costly and tedious data collection work, and reduce numerical simulations that consume a lot of time and computing resources.

[0019] Other advantages, objectives and features of the present invention will be reflected in part from the following description and will be understood by those skilled in the art through study and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1: Flowchart of an implementation of the rapid prediction of harbor waves and the dynamic response of moored ships according to an embodiment of the present application;

[0021] Figure 2 : An example diagram of a wave numerical model according to an embodiment of the present application;

[0022] Figure 3 : An example diagram of ship mooring arrangement in a mooring numerical model according to an embodiment of the present application;

[0023] Figure 4 : An example diagram of an artificial neural network model according to an embodiment of the present application;

[0024] Figure 5-6 : An application example diagram of an embodiment of the present application (taking the prediction of the six degrees of freedom of motion of a moored ship as an example). DETAILED DESCRIPTION

[0025] The present invention will be described in further detail below in conjunction with the accompanying drawings so that those skilled in the art can implement the invention with reference to the description.

[0026] It should be understood that terms such as "having," "comprising," and "including" used in the embodiments of this application do not exclude the presence or addition of one or more other elements or combinations thereof. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are intended only to explain the relative positional relationships and movement of components in a specific posture. If the specific posture changes, the directional indications will also change accordingly. When an element is referred to as being "fixed to" or "disposed on" another element, it can be directly on the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element through an intervening element. References to "first," "second," etc. in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features designated as "first" or "second" may explicitly or implicitly include at least one of such features.

[0027] It should be noted that the technical solutions between the various embodiments of the present application can be combined with each other, but it must be based on the fact that ordinary technicians in this field can implement it. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0028] like Figure 1 As shown, the embodiment of the present application provides a method for rapidly predicting the dynamic response of waves in a harbor and moored ships, including:

[0029] S1: Build a numerical model of harbor waves;

[0030] Numerical models of harbor waves are typically phase-resolving models, including the mild-slope equation and the Boussinesq model. Phase-resolving models resolve phase issues and can simulate physical phenomena such as wave diffraction, reflection, shallow-water deformation, and breaking, improving harbor wave simulation accuracy.

[0031] Taking the Boussinesq wave model as an example, the governing equation of the model is:

[0032]

[0033] Wherein, equation (1) is the continuity equation, equation (2) and equation (3) are the momentum equations in the x-direction and y-direction respectively, n is the porosity, ξ is the water surface height, t is the time, P and Q are the flux densities in the x-direction and y-direction respectively, h is the total water surface height, Rxx, Rxy and Ryy represent the residual momentum generated by the non-uniform velocity distribution, Fx and Fy are the horizontal stresses in the x-direction and y-direction respectively, g is the gravitational acceleration, α and β are the laminar and turbulent resistance coefficients in the porous medium respectively, C is the Xie Cai coefficient, ψx and ψy are the Boussinesq dispersion terms in the x-direction and y-direction respectively; the Boussinesq wave model solves the control equations in time and space by numerical discretization methods, including finite difference, finite element, finite volume and other methods;

[0034] There are many wave numerical models in the existing technology, which can be built with reference to the existing technology. Here, a feasible method is provided. In the S1, the nearshore wave condition information is obtained, and the nearshore wave height, period, and wave direction combination are determined as input. The gentle slope equation model or the Boussinesq model is used to build a numerical model of the waves in the harbor to simulate the wave motion in the harbor. Specifically, the wave height-period-wave direction combination is used to generate irregular incident wave input to simulate the wave motion in the harbor waters under the wave condition. The simulation time must be long enough to stabilize the wave motion state in the harbor. The numerical model of the waves in the harbor adopts a rectangular grid, and the calculation domain includes the entire harbor waters, port buildings, and part of the nearshore waters. Specifically, Figure 2 This is an example of a typical harbor wave numerical model: the grid size needs to be fine enough to depict small-scale terrain and structures such as the harbor waters, channels, and breakwaters. At locations such as beaches, breakwaters, revetments, and pier walls, porous layers are set to simulate incomplete reflection of waves corresponding to different reflection coefficients. At the water-water boundary of the model, sponge layers are set to absorb wave energy to prevent wave energy from reflecting back into the model calculation domain.

[0035] Exemplarily, the method for obtaining the nearshore wave condition information includes: downloading from a global wave model and wave reanalysis hindcast database, or outputting the nearshore wave condition information through a pre-established regional wave numerical model, or conducting wave observations in the nearshore waters by deploying observation devices to collect the nearshore wave condition information. Specifically, the nearshore wave condition information can be obtained in one of the following ways: 1. downloading from a global wave model and wave reanalysis hindcast database, which includes: NOAA Wind Wave Model (WAVEWATCH III), ECMWF Wave Modelling Project (WAM), China Communications Construction Fourth Harbor Engineering Institute Global Wave Model (CCCC-FHDI GlobalWave Model), etc.; 2. conducting regional wave numerical simulations of large and medium-scale sea areas through wave numerical models, which can output nearshore wave information; 3. conducting wave observations in the nearshore waters by deploying observation devices such as wave meters and wave measuring buoys to collect nearshore wave information.

[0036] After extracting wave information near the shore, the wave height, period, and direction combinations of typical nearshore wave conditions are determined through statistical analysis methods such as the wave height, period, and direction joint distribution. To make numerical simulation of harbor waves feasible, it is usually possible to combine the wave height, period, and direction based on the joint distribution of nearshore waves. For example, different incident wave heights are selected at intervals of 0.5 to 1.0 m, a representative wave period is selected every 2 to 3 seconds, and a representative wave direction is selected every 22.5° phase angle for numerical simulation.

[0037] S2: Build a mooring numerical model of the preset ship type;

[0038] There are many wave numerical models in the existing technology, which can be built with reference to the existing technology. Here we provide a feasible method, which is to use the floating body equation of formula (4) to build a mooring numerical model;

[0039]

[0040] Among them, x k (t) represents the translation and rotation of the floating body in six degrees of freedom, namely longitudinal movement, transverse movement, heave, rotation, pitch and roll. The above points represent the differential with respect to time t, M k and a k are the inertial force recovery matrix and the additional mass impulse response matrix, K k is the wave radiation force impulse response matrix, C kis the static force recovery matrix, τ is time, and is the integral variable. In equation (4), the first term on the left describes the inertial force, the second term describes the dynamic force (or wave radiation force), the third term describes the static force, and the right side summarizes the wave excitation force F D (t) and other nonlinear external forces F nl (t) is the sum of the external forces, namely:

[0041]

[0042] The terms on the right side of equation (5) represent the nonlinear external forces caused by mooring force, fender reaction force, viscous damping, wind, flow, second-order wave drift force and friction damping force respectively;

[0043] For example, the parameters of the preset ship type are obtained, and the floating body equation is used to build a mooring numerical model in combination with the numerical model of the wave in the harbor. Specifically, the mooring numerical model usually adopts a numerical discretization method, such as the boundary element method, to first calculate the added mass impulse response matrix a k and the wave radiation force impulse response matrix K k , and calculate the inertial force recovery matrix M according to the geometric characteristics of the floating body k and the static force recovery matrix C k , by combining the wave input conditions to calculate the wave excitation force F D (t), and finally solve the motion equation (4) of the floating body in the time domain to calculate the motion of the floating body x k (t) and the mooring force F line (t) and fender reaction force F fender (t) and other parameters; in actual application, the grid is constructed, and the grid area needs to include the berthing waters and major structures such as the dock. According to the preset ship parameters, including ship draft, displacement, windward area, etc. (to determine the geometric characteristics of the ship), the added mass impulse response matrix a is calculated k , inertial force recovery matrix M k and the static force recovery matrix C k , according to the wave field in the harbor waters under the action of typical nearshore wave conditions obtained by S1 through the wave numerical model, the wave radiation force impulse response matrix K is calculated k and wave excitation force F D (t), combining mooring arrangement, cable parameters (relationship between force and deformation), fender parameters (relationship between force and deformation), wind field conditions, etc., to determine the nonlinear external forces caused by viscous damping, wind, flow, second-order wave drift force and friction damping force, and finally solve the floating body motion control equation, simulate the irregular motion of the ship in the moored state, and output the six degrees of freedom motion of the ship corresponding to different preset ship types, typical nearshore wave conditions, and wind field conditions, as well as the dynamic response data such as mooring force and fender reaction force;

[0044] Figure 3 This example shows the ship's mooring arrangement in the numerical mooring model. The mooring arrangement consists of four bow cables, four stern cables, and two fore and aft return cables to control the ship's longitudinal motion. For cable arrangement and parameters, refer to ship design rules and guidelines from international shipping associations, such as the Mooring Equipment Guidelines 4th Edition (MEG4) and the Guidance on Shipboard Towing and Mooring Equipment.

[0045] S3: establishing a training set using the port wave numerical model and the mooring numerical model, wherein the training set includes nearshore wave condition parameters, nearshore wind field condition parameters, port wave parameters, and moored ship dynamic response data;

[0046] Exemplarily, the nearshore wave condition parameters and the nearshore wind field condition parameters include nearshore wave height, wave period, wave direction, wind speed, and wind direction;

[0047] Exemplarily, the in-harbor wave parameters and the moored vessel dynamic response data include the six-degree-of-freedom motion of the vessel, mooring force, and fender reaction force.

[0048] S4: using the nearshore wave condition parameters and the nearshore wind field condition parameters as input, and the port wave parameters and the moored ship dynamic response data as output, to train and obtain a neural network model;

[0049] Exemplarily, the neural network used for training can be a feedforward neural network, a BP neural network, a convolutional neural network, etc.;

[0050] Figure 4 A feasible neural network model is shown: the artificial neural network model consists of an input layer, a hidden layer and an output layer;

[0051] When using artificial neural network models to predict the dynamic response of waves in the harbor and moored ships, the wave conditions and wind conditions at the nearshore location can be selected, namely the nearshore wave height H, wave period T, wave direction D, and wind speed W. s Wind direction W d As the input signal of the model, the dynamic response of the waves in the port and the moored ship, namely the wave height H', wave period T', wave direction D', and the six degrees of freedom motion of the ship x k (k=1,2,...,6), and the mooring force F i line and fender reaction force F j fender(i and j represent the number of mooring cables and fenders, respectively) as the model's desired output. Therefore, the input layer of the artificial neural network model consists of 6 input neurons (including nearshore wave height, period, wave direction, wind speed, wind direction, and a fixed input + 1), and the output layer consists of 9+i+j output neurons (including in-port wave height, period, wave direction, the six degrees of freedom of the moored vessel, as well as mooring forces and fender reaction forces). The hidden layer defaults to 10 hidden neurons, and this number can be further adjusted based on the model's prediction accuracy.

[0052] The analysis data of the artificial neural network model are all derived from the output of the wave numerical model and the dynamic mooring numerical model; the nearshore wave, wind field, harbor wave and ship dynamic response data that need to be analyzed are divided into three subsets: training data is used to train the artificial neural network, and the synaptic weights in the model are adjusted to make the model suitable for wave and ship dynamic response analysis and prediction; cross-validation data, cross-validation data is used to avoid overfitting; when the error between the predicted value and the expected value in the cross-validation data begins to increase, the training will stop, and the artificial neural network model is considered to be the best universal model at this time; test data, test data is used to test the application accuracy of the artificial neural network model; once the model passes training and cross-validation, the synaptic weights are frozen, and the test data is input into the artificial neural network model for prediction, and the predicted value is compared with the expected value to evaluate the model prediction accuracy.

[0053] S5: inputting the nearshore wave observation data and the nearshore wind field observation data into the neural network model to obtain the predicted data of the harbor waves and the dynamic response of the moored ship;

[0054] Through training, cross-validation, and testing of the artificial neural network model, a mapping relationship between nearshore wave and wind conditions and the dynamic response of in-harbor waves and ships was established, which can be used to forecast in-harbor waves and ship dynamic responses. In practical applications, nearshore wave and wind field observation data can be used as inputs to the artificial neural network model, and the dynamic response of in-harbor waves and moored ships can be used as outputs to achieve rapid forecasting of in-harbor waves and the dynamic response of moored ships.

[0055] Figure 5-6An application example of the six degrees of freedom (DOF) motion of a moored vessel predicted by this embodiment is demonstrated, achieving a predicted curve of the six degrees of freedom motion of a moored vessel over time. Furthermore, by combining ship operation wave standards with ship motion, mooring force, and fender reaction force standards, terminal operations can be guided, terminal loading and unloading efficiency can be improved, and safe port operations can be ensured. Ship operation wave standards, ship motion, mooring force, and fender reaction force standards can be referenced in cable and fender product manuals and the following specifications and guidelines: "General Design Code for Seaports JTS 165-2013," "Criteria for Movements of Moored Ships in Harbours: A Practical Guide," and "Criteria for the (Un)loading of Container Vessels."

[0056] It can be seen that this embodiment proposes a scientific method for rapidly predicting the dynamic response of port waves and moored ships based on wave numerical simulation, mooring numerical simulation, and an artificial neural network model. The method sequentially builds a numerical model of port waves and a numerical mooring model of a preset ship type, and uses the wave numerical model and the numerical mooring model of the preset ship type to generate training data. The artificial neural network model is trained to establish a mapping relationship between nearshore waves, wind field conditions, and the dynamic response of port waves and ships. Ultimately, by combining nearshore wave observation data and wind field observation data, a rapid prediction of the dynamic response of port waves and moored ships is achieved. Compared with the existing technology, this embodiment overcomes the defects of the existing technology in monitoring the movement of port waters and moored ships, the mooring force, and the fender reaction force, and overcomes the defect of the numerical model that cannot be predicted in real time. It achieves a rapid prediction of the dynamic response of port waves and moored ships, which can help guide terminal operations, improve terminal loading and unloading efficiency, ensure safe port operations, and reduce the costly and tedious data collection work.

[0057] An embodiment of the present application further provides an apparatus for rapidly predicting port waves and the dynamic response of moored ships, comprising: a first building module for building a port wave numerical model; a second building module for building a mooring numerical model of a preset ship type; a building module for using the port wave numerical model and the mooring numerical model to establish a training set, the training set including nearshore wave condition parameters, nearshore wind field condition parameters, port wave parameters, and moored ship dynamic response data; a training module for training a neural network model using the nearshore wave condition parameters and the nearshore wind field condition parameters as inputs and the port wave parameters and the moored ship dynamic response data as outputs; and a prediction module for inputting nearshore wave observation data and nearshore wind field observation data into the neural network model to obtain predicted data on port waves and the dynamic response of the moored ship.

[0058] Based on the same inventive concept as the above-mentioned embodiment, this embodiment uses a computer program to complete the construction of a first building module, a second building module, a building module, a training module and a prediction module. For any port that needs to be predicted, the first building module is used to build a numerical model of port waves, the second building module is used to build a numerical model of mooring of a preset ship type, the building module is used to generate data and establish a training set based on the numerical model of port waves and the numerical model of mooring of the preset ship type, the training module is used to train a neural network prediction model, and the neural network prediction model is used to predict the dynamic response of port waves and moored ships based on nearshore wave observation data and nearshore wind field observation data. Compared with the existing technology, this embodiment overcomes the defects of the existing technology in monitoring the movement amount, mooring force and fender reaction force of port waters and moored ships, and overcomes the defect that the numerical model cannot be predicted in real time, and realizes the rapid prediction of the dynamic response of port waves and moored ships, which can help guide terminal operations, improve terminal loading and unloading efficiency, and ensure safe port operation.

[0059] Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the description and implementation methods. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and illustrations shown and described herein.

Claims

1. A method for rapidly predicting the dynamic response of harbor waves and moored ships, characterized in that: include: S1: Build a numerical model of harbor waves; S2: Build a mooring numerical model of the preset ship type; S3: establishing a training set using the port wave numerical model and the mooring numerical model, wherein the training set includes nearshore wave condition parameters, nearshore wind field condition parameters, port wave parameters, and moored ship dynamic response data; S4: using the nearshore wave condition parameters and the nearshore wind field condition parameters as input, and the port wave parameters and the moored ship dynamic response data as output, to train and obtain a neural network model; S5: Inputting the nearshore wave observation data and the nearshore wind field observation data into the neural network model to obtain the port wave and the moored ship dynamic response prediction data.

2. The method for rapidly predicting the dynamic response of harbor waves and moored ships according to claim 1, characterized in that: In the S1, nearshore wave condition information is obtained, and a combination of nearshore wave height, period, and wave direction is determined as input. A numerical model of harbor waves is constructed using a gentle slope equation model or a Boussinesq model to simulate the wave motion in the harbor.

3. The method for rapidly predicting the dynamic response of harbor waves and moored ships according to claim 2, characterized in that: The method for obtaining the nearshore wave condition information includes: downloading from the global wave model and wave reanalysis hindcast database, or outputting the nearshore wave condition information through a pre-established regional wave numerical model, or deploying observation equipment to conduct wave observations in the nearshore waters to collect the nearshore wave condition information.

4. The method for rapidly predicting the dynamic response of harbor waves and moored ships according to claim 2, characterized in that: The numerical model of harbor waves adopts rectangular grids, and the calculation domain includes the entire harbor waters, harbor buildings and part of the nearshore waters.

5. The method for rapidly predicting the dynamic response of harbor waves and moored ships according to claim 1, characterized in that: In said S2, the floating body equation of formula (1) is used to build a mooring numerical model; Among them, x k (t) represents the translation and rotation motion of the floating body in six degrees of freedom. The points above represent the differential with respect to time t, M k and a k are the inertial force recovery matrix and the additional mass impulse response matrix, K k is the wave radiation force impulse response matrix, C k is the static force recovery matrix, F D (t) is the wave excitation force, F nl (t) is the nonlinear external force caused by mooring force, fender reaction force, viscous damping, wind force, flow force, second-order wave drift force and friction damping force.

6. The method for rapidly predicting harbor waves and the dynamic response of moored ships according to claim 5, characterized in that: The parameters of the preset ship type are obtained, and the numerical model of mooring is constructed using the floating body equation in combination with the numerical model of the wave in the harbor.

7. The method for rapidly predicting harbor waves and the dynamic response of moored ships according to claim 1, characterized in that: The nearshore wave condition parameters and the nearshore wind field condition parameters include nearshore wave height, wave period, wave direction, wind speed, and wind direction.

8. The method for rapidly predicting harbor waves and the dynamic response of moored ships according to claim 1, characterized in that: The wave parameters in the harbor and the dynamic response data of the moored ship include the six-degree-of-freedom motion of the ship, the mooring force, and the fender reaction force.

9. A device for rapidly predicting the dynamic response of harbor waves and moored ships, characterized in that: include: The first building module is used to build a numerical model of waves in the harbor; The second building module is to build a mooring numerical model of a preset ship type; An establishment module is used to establish a training set using the port wave numerical model and the mooring numerical model, wherein the training set includes nearshore wave condition parameters, nearshore wind field condition parameters, port wave parameters, and moored ship dynamic response data; a training module, configured to train a neural network model using the nearshore wave condition parameters and the nearshore wind field condition parameters as inputs and the port wave parameters and the moored vessel dynamic response data as outputs; The prediction module is used to input the nearshore wave observation data and the nearshore wind field observation data into the neural network model to obtain the predicted data of the port waves and the dynamic response of the moored ship.

Images