Method and system for simulating collision between ship and fixed structure

Abstract

The invention relates to the technical field of collision simulation in ship and ocean engineering, and discloses a collision simulation method and system for a ship and a fixed structure. The method comprises the following steps: acquiring collision influence parameters in a real environment; and inputting the collision influence parameters into a scale prediction model to obtain a collision parameter scale, calculating the collision influence parameters in a simulation environment according to the collision influence parameters in the real environment and the collision parameter scale, and performing collision simulation of the ship and the fixed structure, thereby improving the accuracy of collision simulation. And the score of each group of collision influence parameters is obtained according to the consistency index and the integrity index of each group of collision influence parameters, and the training set of the scaled scale prediction model is determined, so that the model training efficiency is improved on the premise of ensuring the model prediction accuracy.

Description

Technical Field

[0001] The present application relates to the technical field of collision simulation in ships and marine engineering, and in particular to a method and system for simulating collision between ships and fixed structures. Background Art

[0002] With the development of the global shipping and transportation industries, the number of sailing ships has increased rapidly, and collisions between ships and fixed objects in the waters have occurred frequently, which often cause serious casualties, property losses and environmental pollution. In order to avoid the occurrence of such collision accidents, a large number of ship-fixed structure collision simulation studies have been carried out to help assess and prevent possible serious safety accidents and the economic losses they bring. Through simulation, we can gain an in-depth understanding of the mechanical response during the collision process, optimize the anti-collision design of ships and marine structures, and consider the assessment of the impact of environmental factors on the collision. In addition, simulation plays an important role in risk management, accident investigation, liability determination, and the formulation of environmental protection measures. Overall, collision simulation is an important tool to improve ship safety, reduce economic losses, protect the marine environment, and optimize ship design.

[0003] However, when performing collision simulation, the scales of various parameters in the simulation environment and the real environment are calculated based on the same scale, without considering the differences caused by different types of parameters, which reduces the accuracy of the collision simulation.

[0004] Therefore, there is an urgent need for a ship-fixed structure collision simulation method and system that can accurately and quickly simulate the ship-fixed structure collision. Summary of the invention

[0005] In order to solve the above technical problems, the present application provides a method for simulating a collision between a ship and a fixed structure, comprising the following steps: Acquire collision impact parameters under real environment, wherein the collision impact parameters include the speed of the ship, the acceleration of the ship, the length of the ship, the width of the ship, the height of the ship, the density of water, the relative position of the ship and the fixed structure, the distance between the ship and the fixed structure, and the displacement of the ship; Input the collision impact parameters into a scale prediction model to obtain a collision parameter scale, wherein the collision parameter scale includes a speed scale, a geometric scale, a mass scale and a distance scale; the speed scale is used to calculate the speed of the ship and the acceleration of the ship; the geometric scale is used to calculate the length of the ship, the width of the ship and the height of the ship; the mass scale is used to calculate the displacement of the ship; and the distance scale is used to calculate the relative position of the ship and the fixed structure and the distance between the ship and the fixed structure; The selection of the training set of the scale prediction model includes the following steps: Acquire an initial training set of the scaled prediction model; the initial training set includes multiple groups of collision impact parameters; Calculate the consistency index and integrity index of each group of collision impact parameters respectively; According to the consistency index and integrity index of each group of collision impact parameters and the weight corresponding to each index, the score of each group of collision impact parameters is obtained; Sort each group of collision impact parameters from high to low according to the score; According to the simulation requirements, the top N% of the initial training sets are selected as the training sets of the scaled prediction model; Calculating the collision impact parameter in the simulation environment according to the collision impact parameter in the real environment and the collision parameter scale; A collision simulation between a ship and a fixed structure is performed according to the collision impact parameters in the simulation environment.

[0006] Preferably, the collision impact parameter in the simulated environment is calculated according to the collision impact parameter in the real environment and the collision parameter scale, specifically: Based on the scale relationship between each collision impact parameter in the real environment and the simulation environment, the scale of each collision impact parameter is obtained according to the collision parameter scale; The collision impact parameters in the simulation environment are calculated according to the collision impact parameters in the real environment and the scale of each collision impact parameter.

[0007] Preferably, the calculation method of the consistency index of each collision impact parameter in each group of collision impact parameters is: Calculate the mean of each collision impact parameter in the initial training set respectively; Based on the mean value of each collision impact parameter, the square of the deviation between each parameter in each group of collision impact parameters and the corresponding mean value of each parameter is calculated; According to the square of the deviation between each parameter in each group of collision influence parameters and the corresponding mean value of each parameter, the mean of the square of the deviation of each group of collision influence parameters is obtained; The square root of the mean of the squared deviations is taken to obtain the standard deviation of each group of collision impact parameters; The standard deviation of each group of collision impact parameters is converted into a consistency score, and the consistency score is standardized to obtain the consistency index of each group of collision impact parameters.

[0008] Preferably, the calculation method of the integrity index of each group of collision impact parameters is: Counting the number of collision impact parameters contained in each group of collision impact parameters; Detecting missing values ​​of each collision influence parameter contained in each set of collision influence parameters, and counting the number of collision influence parameters with missing values ​​in each set of collision influence parameters; According to the number of collision influence parameters contained in each group of collision influence parameters and the number of collision influence parameters with missing values ​​in each group of collision influence parameters, the missing value ratio of each group of collision influence parameters is obtained; The missing value ratio of each group of collision impact parameters is converted into a completeness score, and the completeness score is standardized to obtain the completeness index of each group of collision impact parameters.

[0009] Preferably, the score of each group of collision impact parameters is obtained according to the consistency index and integrity index of each group of collision impact parameters and the weight corresponding to each index, and the calculation formula is: ; Among them, H i represents the score of the i-th group of collision impact parameters; A i and B i are the consistency index and integrity index of the i-th group of collision impact parameters, α and β are the weights of the consistency index and integrity index, respectively.

[0010] Preferably, the scale prediction model is a convolutional neural network.

[0011] Preferably, the loss function MSE calculation formula of the scale prediction model is: ; Where n is the number of samples in the training set, m is the number of output parameters, m=4; w j is the weight of the jth output parameter; y ij is the actual value of the jth output parameter of the ith sample, is the actual value of the jth output parameter of the ith sample.

[0012] The present application also provides a collision simulation system between a ship and a fixed structure, which executes any one of the above-mentioned collision simulation methods between a ship and a fixed structure, and the simulation system comprises: a collision influence parameter acquisition module in a real environment, a collision parameter scale prediction module, and a collision influence parameter calculation module in a simulated environment; A collision impact parameter acquisition module in a real environment, used to acquire collision impact parameters in a real environment, wherein the collision impact parameters include the speed of the ship, the acceleration of the ship, the length of the ship, the width of the ship, the height of the ship, the density of water, the relative position of the ship and the fixed structure, the distance between the ship and the fixed structure, and the displacement of the ship; A collision parameter scale prediction module is used to input the collision impact parameters into a scale prediction model to obtain a collision parameter scale, wherein the collision parameter scale includes a speed scale, a geometric scale, a mass scale and a distance scale; the speed scale is used to calculate the speed of the ship and the acceleration of the ship; the geometric scale is used to calculate the length of the ship, the width of the ship and the height of the ship; the mass scale is used to calculate the displacement of the ship; and the distance scale is used to calculate the relative position of the ship and the fixed structure and the distance between the ship and the fixed structure; The collision influence parameter calculation module in the simulation environment is used to calculate the collision influence parameter in the simulation environment according to the collision influence parameter in the real environment and the collision parameter scale.

[0013] The embodiments of the present application have the following technical effects: The collision simulation method between a ship and a fixed structure provided in the present application predicts a speed scale, a geometry scale, a mass scale and a distance scale through a scale prediction model. Each collision impact parameter is calculated through a corresponding scale in a simulation environment. On the premise of following the scale relationship between each collision impact parameter in a real environment and a simulation environment, the collision impact parameters of speed, geometry, mass and distance are taken into consideration, and their respective physical characteristics overcome the scale differences caused by different types of parameters, thereby improving the accuracy of collision simulation.

[0014] When preparing the training set of the scale prediction model, the consistency index and integrity index of each group of collision impact parameters in the initial training set are calculated respectively, and the scores of each group of collision impact parameters are obtained by combining the weights; the scores are sorted from high to low; according to the simulation requirements, the top N% of the initial training sets are selected as the training set of the scale prediction model. Screening the training set with consistency index and integrity index not only improves the quality of the training set to further improve the accuracy of the collision simulation, but also improves the model training speed with high-quality training sets; at the same time, the data volume of the training set can be determined according to the simulation requirements, which improves the flexible selectivity of the model training speed and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 It is a step diagram of a method for simulating a collision between a ship and a fixed structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work belong to the scope of protection of the present application.

[0018] When performing collision simulation, the scales of various parameters in the simulation environment and the real environment are calculated based on the same scale λ, without considering the differences caused by different types of parameters, which reduces the accuracy of the collision simulation.

[0019] For example, velocity scales need to account for kinetic energy and momentum transfer, while geometric scales need to account for the strength and stability of the structure. If the same scale is used for all scales, these different physical similarity requirements may not be met. Dynamic parameters such as velocity and acceleration are related to the dynamic response of the structure, while geometric parameters such as length, width, and height are related to the static characteristics of the structure. Using the same scale to calculate the scales of these parameters may ignore their differences in dynamic and static characteristics.

[0020] In order to solve the above problems, the present application provides a method for simulating a collision between a ship and a fixed structure. Figure 1 It can be seen that the simulation method includes the following steps: S1: Acquire collision impact parameters in a real environment, wherein the collision impact parameters include the speed of the ship, the acceleration of the ship, the length of the ship, the width of the ship, the height of the ship, the density of water, the relative position of the ship and the fixed structure, the distance between the ship and the fixed structure, and the displacement of the ship; S2: Inputting the collision impact parameter into a scale prediction model to obtain a collision parameter scale, wherein the collision parameter scale includes a speed scale, a geometric scale, a mass scale and a distance scale; the speed scale is used to calculate the speed of the ship and the acceleration of the ship; the geometric scale is used to calculate the length of the ship, the width of the ship and the height of the ship; the mass scale is used to calculate the displacement of the ship; and the distance scale is used to calculate the relative position of the ship and the fixed structure and the distance between the ship and the fixed structure; The collision simulation method between a ship and a fixed structure provided in the present application predicts a speed scale, a geometry scale, a mass scale and a distance scale through a scale prediction model. Each collision impact parameter is calculated through a corresponding scale in a simulation environment. On the premise of following the scale relationship between each collision impact parameter in a real environment and a simulation environment, the collision impact parameters of speed, geometry, mass and distance are taken into consideration, and their respective physical characteristics overcome the scale differences caused by different types of parameters, thereby improving the accuracy of collision simulation.

[0021] In order to improve the prediction accuracy of the scaled prediction model, its training set is obtained from real collision cases. The same parameters are often collected in different ways, resulting in large differences. In addition, due to the randomness, instantaneity and unpredictability of collisions, data is often missing in the collection of training sets, so the training sets need to be screened for consistency and completeness.

[0022] Preferably, the selection of the training set of the scale prediction model comprises the following steps: A1: obtaining an initial training set of the scaled prediction model; the initial training set includes multiple groups of collision impact parameters; A2: Calculate the consistency index and integrity index of each group of collision impact parameters respectively; Preferably, the calculation method of the consistency index of each collision impact parameter in each group of collision impact parameters is: A2A1: Calculate the mean of each collision impact parameter in the initial training set; A2A2: Based on the mean of each collision impact parameter, calculate the square of the deviation between each parameter in each group of collision impact parameters and the corresponding mean of each parameter; A2A3: According to the square of the deviation between each parameter in each group of collision influence parameters and the corresponding mean of each parameter, the mean of the square of the deviation of each group of collision influence parameters is obtained; A2A4: Take the square root of the mean of the squared deviations to obtain the standard deviation of each group of collision impact parameters; A2A5: Convert the standard deviation of each group of collision impact parameters into a consistency score, and perform standardization on the consistency score to obtain the consistency index of each group of collision impact parameters.

[0023] When performing consistency score conversion, the standard deviation is converted into a consistency score. Generally, the smaller the standard deviation, the higher the consistency. The purpose of standardization is mainly to normalize the consistency score to the [0,1] interval.

[0024] Preferably, the calculation method of the integrity index of each group of collision impact parameters is: A2B1: Count the number of collision impact parameters contained in each group of collision impact parameters; A2B2: Detect the missing value of each collision influence parameter contained in each group of collision influence parameters, and count the number of collision influence parameters with missing values ​​in each group of collision influence parameters; A2B3: according to the number of collision influence parameters contained in each group of collision influence parameters and the number of collision influence parameters with missing values ​​in each group of collision influence parameters, obtain the missing value ratio of each group of collision influence parameters; A2B4: Convert the missing value ratio of each group of collision impact parameters into a completeness score, and perform standardization on the completeness score to obtain the completeness index of each group of collision impact parameters.

[0025] Convert the missing value ratio into a completeness score. Generally, the lower the missing value ratio, the higher the completeness. The completeness score needs to be normalized to the interval [0,1].

[0026] Preferably, the score of each group of collision impact parameters is obtained according to the consistency index and integrity index of each group of collision impact parameters and the weight corresponding to each index, and the calculation formula is: ; Among them, H i represents the score of the i-th group of collision impact parameters; A i and B i are the consistency index and integrity index of the i-th group of collision impact parameters, α and β are the weights of the consistency index and integrity index, respectively.

[0027] A3: Obtain the score of each group of collision impact parameters based on the consistency index and integrity index of each group of collision impact parameters and the weights corresponding to each index; A4: Sort each group of collision impact parameters from high to low according to the score; A5: According to the simulation requirements, select the top N% of the initial training sets as the training sets of the scaled prediction model.

[0028] When preparing the training set of the scale prediction model, the consistency index and integrity index of each group of collision impact parameters in the initial training set are calculated respectively, and the scores of each group of collision impact parameters are obtained by combining the weights; the scores are sorted from high to low; according to the simulation requirements, the top N% of the initial training sets are selected as the training set of the scale prediction model. Screening the training set with consistency index and integrity index not only improves the quality of the training set to further improve the accuracy of the collision simulation, but also improves the model training speed with high-quality training sets; at the same time, the data volume of the training set can be determined according to the simulation requirements, which improves the flexible selectivity of the model training speed and accuracy.

[0029] S3: calculating the collision impact parameter in the simulation environment according to the collision impact parameter in the real environment and the collision parameter scale; Preferably, the collision impact parameter in the simulated environment is calculated according to the collision impact parameter in the real environment and the collision parameter scale, specifically: Based on the scale ratio relationship between each collision impact parameter in the real environment and the simulation environment, the scale ratio of each collision impact parameter is obtained according to the collision parameter scale ratio; For example, the scale ratio relationship represents the proportional relationship between the same parameter in the real environment and the simulated environment. For example, the scale ratio of the length of the ship is λ, and the scale ratio of the displacement of the ship is λ. 3 , but they are all calculated based on the same scale λ.

[0030] This application is based on maintaining the scale ratio relationship between the original real environment and the simulated environment, and uses the speed scale, geometric scale, mass scale and distance scale obtained by the scale prediction model to calculate respectively. Use the speed scale to calculate the scale of the ship's speed and the acceleration of the ship; use the geometric scale to calculate the scale of the ship's length, the ship's width and the ship's height; use the mass scale to calculate the scale of the ship's displacement; use the distance scale to calculate the relative position of the ship and the fixed structure and the scale of the distance between the ship and the fixed structure; The collision impact parameters in the simulation environment are calculated according to the collision impact parameters in the real environment and the scale of each collision impact parameter.

[0031] Preferably, the scale prediction model is a convolutional neural network. Thanks to the convolutional neural network's ability to capture local features, understand spatial hierarchical structures, extract multi-scale features, and map nonlinear features, the convolutional neural network can provide higher accuracy in predicting the scale of collision parameters between ships and fixed structures. In order to further improve the prediction accuracy of the convolutional neural network, the network depth, convolution kernel size, and number can be adjusted according to the accuracy requirements.

[0032] Preferably, the loss function MSE calculation formula of the scale prediction model is: ; Where n is the number of samples in the training set, m is the number of output parameters, m=4; w j is the weight of the jth output parameter; y ij is the actual value of the jth output parameter of the ith sample, is the actual value of the jth output parameter of the ith sample.

[0033] The scale prediction model using mean square error (MSE) as the loss function can effectively balance the importance of different output parameters, guide model learning, and handle multi-output problems when simulating collisions between ships and fixed structures. First, by assigning different weights to each output parameter, the MSE loss function allows the model to identify and prioritize those parameters that have a greater impact on the collision simulation results, thereby ensuring that the model's predictions are more consistent with the key factors in actual conditions. This weight allocation enables the model to more accurately capture the specific contribution of each parameter to the final result, improving the accuracy and reliability of the simulation. Second, the MSE loss function provides a clear optimization goal for the model by minimizing the sum of the squared differences between the actual value and the predicted value. The setting of this optimization goal directly guides the model to adjust parameters during the learning process to reduce the prediction error, so that the model can converge to the optimal solution faster, improving the efficiency of model training and the accuracy of the prediction results. Finally, the MSE loss function is particularly suitable for handling multi-output problems, which is particularly important in ship collision simulation because multiple related output parameters such as velocity scale, geometric scale, mass scale, and distance scale need to be predicted simultaneously. MSE can simultaneously consider the prediction errors of these parameters, allowing the model to comprehensively learn the interrelationships and influences between these parameters, thereby improving the accuracy of the simulation overall. This comprehensive optimization of multiple parameters provides a comprehensive and coordinated prediction framework for ship collision simulation.

[0034] S4: performing collision simulation between the ship and the fixed structure according to the collision impact parameters in the simulation environment.

[0035] The present application also provides a collision simulation system between a ship and a fixed structure, which executes any one of the above-mentioned collision simulation methods between a ship and a fixed structure, and the simulation system comprises: a collision influence parameter acquisition module in a real environment, a collision parameter scale prediction module, and a collision influence parameter calculation module in a simulated environment; A collision impact parameter acquisition module in a real environment, used to acquire collision impact parameters in a real environment, wherein the collision impact parameters include the speed of the ship, the acceleration of the ship, the length of the ship, the width of the ship, the height of the ship, the density of water, the relative position of the ship and the fixed structure, the distance between the ship and the fixed structure, and the displacement of the ship; A collision parameter scale prediction module is used to input the collision impact parameters into a scale prediction model to obtain a collision parameter scale, wherein the collision parameter scale includes a speed scale, a geometric scale, a mass scale and a distance scale; the speed scale is used to calculate the speed of the ship and the acceleration of the ship; the geometric scale is used to calculate the length of the ship, the width of the ship and the height of the ship; the mass scale is used to calculate the displacement of the ship; and the distance scale is used to calculate the relative position of the ship and the fixed structure and the distance between the ship and the fixed structure; The collision influence parameter calculation module in the simulation environment is used to calculate the collision influence parameter in the simulation environment according to the collision influence parameter in the real environment and the collision parameter scale.

[0036] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present application.

Claims

1. A method for simulating a collision between a ship and a fixed structure, characterized in that: The steps include: Acquire collision impact parameters under real environment, wherein the collision impact parameters include the speed of the ship, the acceleration of the ship, the length of the ship, the width of the ship, the height of the ship, the density of water, the relative position of the ship and the fixed structure, the distance between the ship and the fixed structure, and the displacement of the ship; Inputting the collision impact parameters into a scale prediction model to obtain a collision parameter scale, wherein the collision parameter scale includes a velocity scale, a geometric scale, a mass scale and a distance scale; The speed scale is used to calculate the speed of the ship and the acceleration of the ship; the geometric scale is used to calculate the length of the ship, the width of the ship and the height of the ship; the mass scale is used to calculate the displacement of the ship; the distance scale is used to calculate the relative position of the ship and the fixed structure and the distance between the ship and the fixed structure; The selection of the training set of the scale prediction model includes the following steps: Acquire an initial training set of the scaled prediction model; the initial training set includes multiple groups of collision impact parameters; Calculate the consistency index and integrity index of each group of collision impact parameters respectively; According to the consistency index and integrity index of each group of collision impact parameters and the weight corresponding to each index, the score of each group of collision impact parameters is obtained; Sort each group of collision impact parameters from high to low according to the score; According to the simulation requirements, the top N% of the initial training sets are selected as the training sets of the scaled prediction model; Calculating the collision impact parameter in the simulation environment according to the collision impact parameter in the real environment and the collision parameter scale; A collision simulation between a ship and a fixed structure is performed according to the collision impact parameters in the simulation environment.

2. A method for simulating a collision between a ship and a fixed structure according to claim 1, characterized in that: According to the collision impact parameter in the real environment and the collision parameter scale, the collision impact parameter in the simulation environment is calculated, specifically: Based on the scale relationship between each collision impact parameter in the real environment and the simulation environment, the scale of each collision impact parameter is obtained according to the collision parameter scale; The collision impact parameters in the simulation environment are calculated according to the collision impact parameters in the real environment and the scale of each collision impact parameter.

3. The method for simulating a collision between a ship and a fixed structure according to claim 1, characterized in that: The calculation method of the consistency index of each collision impact parameter in each group of collision impact parameters is: Calculate the mean of each collision impact parameter in the initial training set respectively; Based on the mean value of each collision impact parameter, the square of the deviation between each parameter in each group of collision impact parameters and the corresponding mean value of each parameter is calculated; According to the square of the deviation between each parameter in each group of collision influence parameters and the corresponding mean value of each parameter, the mean of the square of the deviation of each group of collision influence parameters is obtained; The square root of the mean of the squared deviations is taken to obtain the standard deviation of each group of collision impact parameters; The standard deviation of each group of collision impact parameters is converted into a consistency score, and the consistency score is standardized to obtain the consistency index of each group of collision impact parameters.

4. A method for simulating a collision between a ship and a fixed structure according to claim 1, characterized in that: The calculation method of the integrity index of each group of collision impact parameters is: Counting the number of collision impact parameters contained in each group of collision impact parameters; Detecting missing values ​​of each collision influence parameter contained in each set of collision influence parameters, and counting the number of collision influence parameters with missing values ​​in each set of collision influence parameters; According to the number of collision influence parameters contained in each group of collision influence parameters and the number of collision influence parameters with missing values ​​in each group of collision influence parameters, the missing value ratio of each group of collision influence parameters is obtained; The missing value ratio of each group of collision impact parameters is converted into a completeness score, and the completeness score is standardized to obtain the completeness index of each group of collision impact parameters.

5. The method for simulating a collision between a ship and a fixed structure according to claim 1, characterized in that: According to the consistency index and integrity index of each group of collision impact parameters and the weights corresponding to each index, the score of each group of collision impact parameters is obtained. The calculation formula is: ； Among them, H i represents the score of the i-th group of collision impact parameters; A i and B i are the consistency index and integrity index of the i-th group of collision impact parameters, α and β are the weights of the consistency index and integrity index, respectively.

6. A method for simulating a collision between a ship and a fixed structure according to claim 1, characterized in that: The scale prediction model is a convolutional neural network.

7. A method for simulating a collision between a ship and a fixed structure according to claim 1, characterized in that: The loss function MSE calculation formula of the scale prediction model is: ； Where n is the number of samples in the training set, m is the number of output parameters, m=4; w j is the weight of the jth output parameter; y ij is the actual value of the jth output parameter of the ith sample, is the actual value of the jth output parameter of the ith sample.

8. A ship-fixed-structure collision simulation system, which executes a ship-fixed-structure collision simulation method according to any one of claims 1 to 7, characterized in that: The simulation system comprises: a collision influence parameter acquisition module in a real environment, a collision parameter scale prediction module and a collision influence parameter calculation module in a simulation environment; A collision impact parameter acquisition module in a real environment, used to acquire collision impact parameters in a real environment, wherein the collision impact parameters include the speed of the ship, the acceleration of the ship, the length of the ship, the width of the ship, the height of the ship, the density of water, the relative position of the ship and the fixed structure, the distance between the ship and the fixed structure, and the displacement of the ship; A collision parameter scale prediction module is used to input the collision impact parameters into a scale prediction model to obtain a collision parameter scale, wherein the collision parameter scale includes a speed scale, a geometric scale, a mass scale and a distance scale; the speed scale is used to calculate the speed of the ship and the acceleration of the ship; the geometric scale is used to calculate the length of the ship, the width of the ship and the height of the ship; the mass scale is used to calculate the displacement of the ship; and the distance scale is used to calculate the relative position of the ship and the fixed structure and the distance between the ship and the fixed structure; The collision influence parameter calculation module in the simulation environment is used to calculate the collision influence parameter in the simulation environment according to the collision influence parameter in the real environment and the collision parameter scale.

Images