Ship swaying motion forecasting method based on physical information neural network

Abstract

The invention relates to the field of intelligent forecasting of ship swaying motion, and provides a ship swaying motion forecasting method based on a physical information neural network, which comprises the following steps: simulating heaving motion of a ship in real waves by adopting fluid mechanics, and collecting swaying motion data when the ship moves in the waves; constructing a physical information neural network model, initializing the physical information neural network model and completing data preprocessing; constructing a wave excitation force function by using the obtained motion data, fusing the wave excitation force function into a physical information neural network model, and training the physical information neural network model; and inputting the real-time motion data into the trained physical information neural network model, and predicting the heaving displacement and the pitching angle of the ship.

Description

Technical Field

[0001] The present invention relates to a ship swaying motion prediction method based on physical information neural network. Specifically, the present invention belongs to the cross-technical field of applying machine learning and deep learning technology with physical process simulation. Background Art

[0002] In modern marine engineering and shipping, accurate prediction of the swaying motion of ships in waves is crucial to ensure ship safety and optimize navigation paths. Traditional ship swaying motion prediction mainly relies on physical models and empirical methods. However, these methods often face the problem of insufficient prediction accuracy under complex sea conditions, especially in the face of sudden large waves or complex sea conditions with multiple wave interferences, the limitations of traditional methods are more obvious.

[0003] Limitations of traditional forecasting methods: Physical model methods: Models based on precise physical equations, such as linear and nonlinear wave theory, can provide a certain degree of prediction accuracy. However, these models have high computational complexity and usually require a lot of computing resources. In addition, physical models require precise initial and boundary conditions, otherwise the prediction results may deviate from the actual situation.

[0004] Empirical methods: Empirical methods rely on a large amount of historical data and empirical rules to make predictions through statistics or other means. Although they have faster calculation speeds in some cases, these methods are highly dependent on data and their accuracy is often not guaranteed when faced with atypical wave conditions.

[0005] Hybrid methods: Hybrid methods that combine physical models and empirical methods attempt to take advantage of the advantages of both, but in practical applications, such methods still find it difficult to provide consistent high-precision predictions under various complex sea conditions.

[0006] With the development of deep learning and artificial intelligence technology, physical information neural network has gradually become a powerful tool for solving problems with complex physical background. Physical information neural network introduces physical laws into the neural network architecture. By combining data-driven learning with physical models, neural networks not only perform well in data-rich situations, but also can effectively handle situations where data is scarce or incomplete.

[0007] Using traditional neural networks to solve partial differential equations requires a large number of training sets as support. The principle is to learn the hidden inherent laws in the data through repeated training from a large amount of sample data, and to approximate the function to be solved with arbitrary precision, such as traditional convolutional neural networks, long short-term memory neural networks, etc. These neural networks do not consider the prior physical information of the solution system, but only fit the input and output data of the neural network, resulting in poor interpretability in the solution process, and the solution effect is limited by the number of learning samples. As an emerging technology, Physics-Informed Neural Networks (PINNs) provide a solution that can not only ensure prediction accuracy but also significantly improve computational efficiency by combining machine learning with physical models. The core advantage of physical information neural networks is that they can use existing physical knowledge (such as partial differential equations) to guide the learning of neural networks, so that the behavior of physical systems can be accurately predicted without a large amount of data support. Summary of the invention

[0008] In order to solve the above technical problems, the present invention proposes a ship swaying motion prediction method based on physical information neural network, comprising the following steps: Step 1: Use fluid mechanics to simulate the heaving motion of a ship in real waves, and collect the heaving motion data of the ship when it moves in the waves; Step 2: construct a physical information neural network model, initialize the physical information neural network model and complete data preprocessing; Step 3: construct a wave excitation force function using the swaying motion data obtained in step 1, and train the wave excitation force function using a physical information neural network model; Step 4: Input the real-time motion data into the trained physical information neural network model to predict the heave displacement and pitch angle of the ship.

[0009] In a preferred embodiment, in step 1, the heave-pitch motion equation is established: ; in, are the first and second derivatives of the heave displacement with respect to time t, is the pitch angle, are the first and second derivatives of the pitch angle with respect to time t, is the lateral coordinate of the ship's center of gravity in the fixed coordinate system of the hull, is the additional mass of the heave, is the longitudinal moment of inertia of the hull, is the additional moment of inertia of pitch, is the additional mass caused by the pitch motion in the heave direction, is the additional moment of inertia caused by the heave motion in the pitch direction, are the linear damping coefficients for heave and pitch, respectively, is the damping coefficient that represents the mutual coupling of heave and pitch motion, are the restoring moment coefficients for heave and pitch, respectively, represents the restoring moment coefficient of the mutual coupling between heave and pitch motion, and is the wave excitation moment in the heave and pitch directions.

[0010] In a preferred embodiment, the heave-pitch coupled motion equation of a ship in waves is established: ; in, is the damped frequency of the ship's heaving motion in waves, is the damped frequency of the ship's pitching motion in waves, ()and () is the nonlinear hydrodynamic function to be determined in the heave and pitch directions, , It is the wave excitation force in the heave and pitch directions.

[0011] In a preferred embodiment, the heave-pitch equation of a ship in still water is established: ; in, is the natural frequency of the ship's heaving motion in still water, is the natural frequency of the ship's pitching motion in still water.

[0012] In a preferred embodiment, when the ship undergoes heave-pitch coupled motion in waves, the damping frequency and the natural frequency thereof satisfy: ; in, is the dimensionless damping coefficient of heave, is the dimensionless damping coefficient of pitch.

[0013] In a preferred embodiment, the wave excitation force , Calculated by the following formula: ; Among them, the wave number is k, the displacement of the ship in the corresponding direction is u, ω represents the frequency information of the ship, the time is t, and the density of water is , the wave acceleration g(t), x represents the x-coordinate of the calculated point in the ship-borne coordinate system established with the coordinates of the hull's buoyancy center as the origin.

[0014] In a preferred embodiment, the physical loss function of the physical information neural network model is: ; ; in, The loss function of the physical equation representing the heave direction; The loss function of the physical equation representing the roll; The prediction loss function of the physical information neural network model is: ; Among them, represents the predicted value of heave displacement; Represents the actual value of the heave displacement; Indicates the predicted value of the roll angle Indicates the actual value of the roll angle; The total loss function of the physical information neural network model is: + .

[0015] Beneficial technical effects of the present invention: The present invention introduces a physical information neural network, which is specially designed for predicting the coupled motion of the heave and pitch of a ship in waves, and has significant practical value and innovation. Compared with the prior art, the present invention has the characteristics of simple structure and clear algorithm, and provides accurate and reliable technical support for ship state prediction. In addition, the method classifies the loss functions under different wave conditions, effectively improving the accuracy and reliability of the prediction of the ship's motion state under complex sea conditions, making the method more widely applicable. In summary, the present invention provides an advanced method for predicting the swaying motion of a ship in waves, and at the same time provides new ideas for related research, which has both theoretical significance and application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is the network framework of the physical information neural network method of the present invention; Figure 2 It is the KCS ship model adopted by the present invention; Figure 3 is the predicted ship heave distribution diagram; Figure 4 is the free surface mesh distribution. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] In the specific implementation drawings of the present invention, in order to better and more clearly describe the working principles of each component in the system, the connection relationship of the various parts in the device is shown, which only clearly distinguishes the relative position relationship between the various components, and cannot constitute a limitation on the signal transmission direction, connection sequence and structural size, size and shape of each part within the component or structure.

[0019] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0020] The ship swaying motion prediction method based on physical information neural network of the present invention specifically comprises the following steps: Step 1: Use fluid mechanics to simulate the heaving motion of a ship in real waves, and collect the heaving motion data of the ship when it moves in the waves.

[0021] Specifically, by changing the wave amplitude, wave steepness and other related data, while paying attention to the heave displacement and pitch angle of the ship, the swaying motion data of the ship when moving in the waves is collected.

[0022] The specific steps include: A control model is constructed based on the CFD method, which includes the heave-pitch equation in still water, the heave-pitch equation in small waves, and the heave-pitch equation in large waves.

[0023] This method only considers the motion of the two degrees of freedom of the ship's heave and pitch. In the case of small swing, the effect of fluid viscosity is small and can be ignored. Therefore, the heave-pitch motion equation of the ship can be expressed as: ; The meanings of the parameters are shown in Table 1.

[0024] Table 1 Parameter meaning:

[0025]

[0026] In order to use the above formula to predict the small amplitude heave-pitch coupled motion of a ship in waves, it is necessary to determine the unknown additional mass and additional inertia moment, damping coefficient and wave excitation force (moment), and normalize the above formula: ; ; In the case of large-scale swaying, the viscosity of the fluid cannot be ignored. Viscosity has an important influence on the swaying of the ship. The heave-pitch coupled motion of the ship is a periodic reciprocating motion. In the case of large-scale swaying, the heave-pitch coupled motion equation of the ship in the waves can be expressed as: (1); The meanings of the parameters are shown in Table 2.

[0027] Table 2 Parameter meaning:

[0028] In still water motion, the wave excitation is 0, so the heave-pitch equation of the ship in still water is:

[0029] (2); The meaning of the parameters is shown in Table 3.

[0030] Table 3 Parameter meaning:

[0031] In addition, when the ship experiences heave-pitch coupled motion in waves, the damping frequency and natural frequency satisfy the following relationship: (3); The meanings of the parameters are shown in Table 4.

[0032] Table 4 Parameter meaning:

[0033] Combining the above equations (1), (2), and (3), we can get: (4); A physical model of the ship and propeller is established to simulate the heave-pitch motion of the ship and propeller in still water, small waves, and large waves, and obtain the heave amplitude and pitch angle under different working conditions. These data can be divided into training sets and test sets to train the neural network.

[0034] like Figure 2 The figure shows the KCS ship model used in the present invention. The present invention takes the KCS ship model entity as an example to study the swaying motion of the ship in the waves. This figure shows the geometric scene where the ship model is located in the CFD coupling simulation model.

[0035] The hull model uses the Kriso Container Ship model with a rudder, with a scaling ratio of 31.599. Detailed parameters are shown in Table 5.

[0036] Table 5 Ship model parameters:

[0037] CFD coupling simulation uses finite element simulation software and adopts the semi-computational domain symmetry method to save computing resources. The grid is locally refined, and the refined areas are: the bow and stern, the free liquid surface, and the bow and stern Kelvin waves. In order to eliminate the invalid results caused by wave reflections caused by the boundary, the simulation adopts the wave damping method. Based on the above pre-processing, the navigation of the KCS ship under different working conditions is simulated to monitor the resistance, moment, and longitudinal and heaving motion of the hull. The main models are: the volume of fluid domain (VOF) of water and air, and the dynamic fluid-solid interaction (DFBI), which are used to calculate the movement of the ship under the action of fluid, simulate the forward and backward movement of the ship, and the free ups and downs and bumps.

[0038] Step 2: Build a physical information neural network model, initialize the physical information neural network model and complete data preprocessing.

[0039] The input parameters of the neural network are wave frequency, wave amplitude, wave steepness and other related parameters as well as the ship's speed. The output of the network is the heave displacement and pitch angle of the ship. The training internal parameter of the network is the wave damping coefficient when the ship is sailing.

[0040] First, sufficient raw data is obtained through computational fluid dynamics (CFD) to improve the accuracy of neural network prediction. Secondly, the raw data must be preprocessed to ensure the consistency of the input data. The main methods include but are not limited to normalization and data denoising.

[0041] Step 3: construct a wave excitation force function using the swaying motion data obtained in step 1, and train the wave excitation force function using a physical information neural network model.

[0042] The following motion data have been obtained in step 1: the damping frequency of the heave motion of the ship in waves, the damping frequency of the pitch motion of the ship in waves, the natural frequency of the heave motion of the ship in still water, the natural frequency of the pitch motion of the ship in still water, the wave excitation force, the pitch angle, the heave displacement, and the relationship between the various motion data is: ; The wave excitation force , It can be calculated by the following formula: ; Wherein, x represents the x-coordinate of the calculated point in the ship-borne coordinate system established with the coordinates of the hull's buoyancy center as the origin.

[0043] The input of the physical information neural network model is the characteristic parameters of the wave, which include: k represents the wave number, u represents the displacement of the ship in the corresponding direction, ω represents the frequency information of the ship, t represents the time, represents the density of water and g(t) represents the acceleration of the wave.

[0044] The output of the physical information neural network model is the heave displacement z and pitch angle , the internal parameters of the training are and .in, is the damped frequency of the ship's heaving motion in waves, is the damped frequency of the ship's pitching motion in waves, is the natural frequency of the ship's heaving motion in still water, The natural frequency of the ship's pitching motion in still water, the physical loss function of the physical information neural network model is: ; in, The loss function of the physical equation representing the heave direction; Loss function representing the physical equation for rolling.

[0045] The prediction loss function of the physical information neural network model is: ; Among them, represents the predicted value of heave displacement; Represents the actual value of the heave displacement; Indicates the predicted value of the roll angle Indicates the actual value of the roll angle The total loss function of the physical information neural network model is: + ; like Figure 4 The grid in the figure is the grid distribution of the free liquid surface. The local refinement on it can simulate the distribution of waves on the free liquid surface more carefully and reduce the waste of computing resources.

[0046] like Figure 3 The figure shows the predicted distribution of the ship's heave. The wave height distribution of the water surface waves observed vertically downward from the top of the ship along the negative direction of the coordinate system's z-axis. Different colors represent different wave heights.

[0047] Step 4: Input the real-time motion data into the trained physical information neural network model to predict the heave displacement and pitch angle of the ship.

[0048] The prediction results of the physical information neural network are compared with the experimental data to prove the feasibility of this method.

[0049] By comparing the prediction results of the physical information neural network with those of computational fluid dynamics (CFD), a comprehensive analysis of the prediction results of the two methods shows that the physical information neural network and computational fluid dynamics (CFD) have similar effects in terms of accuracy. However, in terms of applicability, PINN can be applied to more complex wave conditions, and can ensure higher accuracy when dealing with still water, small waves, and large waves. At the same time, PINN has a more obvious advantage in the rapidity of prediction compared to computational fluid dynamics.

[0050] like Figure 1 The figure shows the network framework of the physical information neural network method of the present invention. The entire neural network can be divided into an input layer, a hidden layer, and an output layer. The input parameters of the input layer are wave characteristic parameters such as wave steepness, frequency, amplitude, and ship speed, and the output parameters of the output layer are the heave displacement and bow roll angle of the ship, heave frequency, and other parameters. The prediction results of the neural network are brought into the heave and trim equations of the ship, and the error values ​​are passed into the Adam and L-FBGS optimizers to minimize the loss until the loss value is less than the allowable range. The combination strategy of Adam and LBFGS optimizers is used to train the neural network, ensuring the efficiency of the training process and the accuracy of the model. The Adam optimizer can generate adaptive learning rates for different parameters and quickly approach the global optimal solution, while the LBFGS optimizer has the advantages of fast convergence speed and low memory overhead.

[0051] The trained neural network model is used to predict the data in the test set, focusing on the model's performance in predicting flow field velocity and pressure. The model prediction results are compared with the results obtained by computational fluid dynamics (CFD) to verify the effectiveness and superiority of the physical information neural network in predicting ship swaying motion.

[0052] Finally, according to the results of the prediction and evaluation, the model is iteratively optimized, including but not limited to adjusting the network structure, optimizing the loss function and optimizing the algorithm selection, to further improve the prediction accuracy and generalization ability of the model. Finally, the optimized model is applied to the prediction of the real ship's swaying motion, providing decision support for ship performance evaluation and navigation status prediction.

[0053] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0054] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A ship swaying motion prediction method based on physical information neural network, characterized in that: The following steps are involved: Step 1: Use fluid mechanics to simulate the heaving motion of a ship in real waves, and collect the heaving motion data of the ship when it moves in the waves; Step 2: construct a physical information neural network model, initialize the physical information neural network model and complete data preprocessing; Step 3: construct a wave excitation force function using the swaying motion data obtained in step 1, and train the wave excitation force function using a physical information neural network model; Step 4: Input the real-time motion data into the trained physical information neural network model to predict the heave displacement and pitch angle of the ship.

2. The ship swaying motion prediction method based on physical information neural network according to claim 1 is characterized in that: In step 1, the heave-pitch motion equation is established: ； in, are the first and second derivatives of the heave displacement with respect to time t, is the pitch angle, are the first and second derivatives of the pitch angle with respect to time t, is the lateral coordinate of the ship's center of gravity in the fixed coordinate system of the hull, is the additional mass of the heave, is the longitudinal moment of inertia of the hull, is the additional moment of inertia of pitch, is the additional mass caused by the pitch motion in the heave direction, is the additional moment of inertia caused by the heave motion in the pitch direction, are the linear damping coefficients for heave and pitch, respectively, is the damping coefficient that represents the mutual coupling of heave and pitch motion, are the restoring moment coefficients for heave and pitch, respectively, represents the restoring moment coefficient of the mutual coupling between heave and pitch motion, and is the wave excitation moment in the heave and pitch directions.

3. The ship swaying motion prediction method based on physical information neural network according to claim 2 is characterized in that: The coupled heave-pitch motion equation of a ship in waves is established: ； in, is the damped frequency of the ship's heaving motion in waves, is the damped frequency of the ship's pitching motion in waves, ()and () is the nonlinear hydrodynamic function to be determined in the heave and pitch directions, , It is the wave excitation force in the heave and pitch directions.

4. The ship swaying motion prediction method based on physical information neural network according to claim 3 is characterized in that: Establish the heave-pitch equation of a ship in still water: ； in, is the natural frequency of the ship's heaving motion in still water, is the natural frequency of the ship's pitching motion in still water.

5. The ship swaying motion prediction method based on physical information neural network according to claim 4 is characterized in that: When a ship experiences heave-pitch coupled motion in waves, the damping frequency and natural frequency satisfy the following relationship: ； in, is the dimensionless damping coefficient of heave, is the dimensionless damping coefficient of pitch.

6. The ship swaying motion prediction method based on physical information neural network according to claim 5 is characterized in that: Wave excitation force , Calculated by the following formula: ； Among them, the wave number is k, the displacement of the ship in the corresponding direction is u, ω represents the frequency information of the ship, the time is t, and the density of water is , the wave acceleration g(t), x represents the x-coordinate of the calculated point in the ship-borne coordinate system established with the coordinates of the hull's buoyancy center as the origin.

7. The ship swaying motion prediction method based on physical information neural network according to claim 6 is characterized in that: The physical loss function of the physical information neural network model is: ； ； in, The loss function of the physical equation representing the heave direction; The loss function of the physical equation representing the roll; The prediction loss function of the physical information neural network model is: ； Among them, represents the predicted value of heave displacement; Represents the actual value of the heave displacement; Indicates the predicted value of the roll angle Indicates the actual value of the roll angle; The total loss function of the physical information neural network model is: + 。

Images