An artificial intelligence-based reentry vehicle water-entry load and motion trajectory prediction and optimization method

Abstract

The application relates to a method for predicting and optimizing the water entry load and motion trajectory of a navigation body based on artificial intelligence, and relates to the field of water entry and exit of a navigation body across media. The method solves the problems of the existing large-scale navigation body cross-media water entry test, which has a huge cost, and the cross-media water entry problem is solved by using a small-scale mechanism test method, but due to the high cost, it is difficult to carry out on a large scale, and the numerical simulation calculation efficiency is low. The method for predicting the slamming load and motion trajectory of a navigation body when the navigation body enters water at a high speed based on deep learning establishes a navigation body water entry slamming acceleration and motion attitude database through numerical calculation results such as finite element and meshless, or existing test results, predicts the water entry slamming load characteristics and motion trajectory of the navigation body under different cross-sectional shape parameters and water entry parameters, and on this basis, the shape parameters and water entry parameters of the navigation body are reversely optimized and designed by combining the established model and introducing a genetic algorithm, so that the optimal shape parameters and water entry parameters with strong trajectory stability and small slamming acceleration can be quickly given.

Description

Technical Field

[0001] The present invention relates to the technical field of cross-medium entry and exit of a navigation body into water, and in particular to an artificial intelligence-based method for predicting and optimizing the entry load and motion trajectory of a navigation body into water. Background Art

[0002] The study of load characteristics and ballistic stability during the process of a vehicle entering water across a medium has important engineering application value. Due to the huge cost of full-scale vehicle entry tests across a medium and the limitations of safety conditions, the current method for the problem of entering water across a medium mainly uses finite element or meshless methods to carry out numerical calculations and small-scale mechanistic experiments. However, small-scale scaled-down tests are difficult to carry out on a large scale due to the high cost, and numerical simulations have problems such as low computational efficiency. In other words, the above methods cannot efficiently provide the time history curves of the acceleration and motion trajectory of the vehicle during the water entry process. At the same time, in order to ensure that the vehicle maintains the best ballistic stability and reduces the impact load during the process of crossing the medium, the above methods also make it difficult to optimize the shape parameters and entry parameters of the vehicle. Summary of the Invention

[0003] In order to solve the problem in the prior art that the cross-medium water entry test of a full-scale vehicle is extremely expensive and is subject to restrictions such as safety, the present invention currently mainly uses finite element or gridless methods to carry out numerical calculations and small-scale mechanistic tests on the cross-medium water entry problem. In addition, small-scale scaled-down tests are difficult to carry out on a large scale due to their high cost, and numerical simulations have problems such as low computational efficiency, making it difficult to quickly determine the load and motion trajectory of the vehicle after entering the water. In terms of vehicle design, how to quickly and accurately determine the shape parameters and water entry parameters is also an extremely difficult problem. In order to solve the above technical problems, the present invention is implemented through the following technical solutions:

[0004] Solution 1: The present invention proposes an artificial intelligence-based method for predicting and optimizing the water entry load and motion trajectory of a vehicle, the method comprising the following steps:

[0005] Step 1: Use finite element, meshless or experimental methods to perform numerical simulation or experimental measurement of the vehicle's water entry process to obtain the load characteristics and motion trajectory data during the vehicle's water entry process. By changing the vehicle's cross-sectional ratio s, semi-cone angle α, water entry velocity v and water entry angle β, a sample database of vehicle acceleration and position under different initial conditions is obtained;

[0006] Step 2: Based on the sample database established in step 1, divide it into a training set and a validation set, and establish a neural network rapid prediction model for predicting the acceleration history curve and motion trajectory of the vehicle under different initial parameters;

[0007] Step 3: The neural network rapid prediction model of the vehicle acceleration history curve and motion trajectory under different initial parameters obtained in step 2 is embedded into the genetic algorithm to optimize the shape parameters and water entry parameters of the vehicle, and complete the prediction and optimization of the vehicle entry load and motion trajectory.

[0008] Furthermore, a preferred embodiment is provided, in which the method for optimizing the shape parameters and water entry parameters of the vehicle in step 3 is:

[0009] Input the upper and lower bounds of the four parameters: the vehicle cross-section ratio s, the semi-cone angle α, the water entry velocity v, and the water entry angle β. Randomly sample the parameter combinations within the space formed by the upper and lower bounds to form an initial population. Then calculate the acceleration and ballistic trajectory based on the acceleration and motion trajectory neural network rapid prediction model established in step 2.

[0010] All parameter combinations in the formed initial population are evaluated and screened, crossover and mutation processing is performed on the screened population, the search scale is expanded and a new generation of individuals is generated, the parameters are iterated and gradually optimized, and finally the optimal parameters that meet the above optimization objectives are output.

[0011] Furthermore, a preferred embodiment is provided, in which the ratio of the training set to the validation set described in step 2 is no less than 3:4.

[0012] Furthermore, a preferred embodiment is provided, in which the input variables of the neural network rapid prediction model established in step 2 for predicting the acceleration history curve and motion trajectory of the vehicle under different initial parameters are the four parameters in step 1, and the output variable is the acceleration history data, and the load characteristics and motion trajectory data during the vehicle entering the water are normalized to the minimum and maximum values.

[0013] Furthermore, a preferred embodiment is provided, in which the neural network rapid prediction model of the vehicle acceleration history curve and motion trajectory includes an input layer, an output layer and multiple hidden layers, and the input layer variables are the vehicle cross-sectional ratio s, semi-cone angle α, entry speed v and entry angle β.

[0014] Furthermore, a preferred embodiment is provided, wherein the hyperparameters contained in the input layer, output layer and multiple hidden layers are optimized by methods such as grid search or Bayesian search; similarly, the hyperparameters in the genetic algorithm are optimized by methods such as grid search or Bayesian search.

[0015] Furthermore, a preferred embodiment is provided, in which the output layer of the neural network rapid prediction model of the vehicle acceleration time history curve described in step 2 is the vehicle acceleration time history data.

[0016] Furthermore, a preferred embodiment is provided, in which the output layer of the neural network rapid prediction model of the motion trajectory is the time history data of the vehicle position coordinates.

[0017] Solution 2: A computer device includes a memory and a processor, wherein the memory stores a computer program. When the processor runs the computer program stored in the memory, the processor executes any one of the methods described in Solution 1.

[0018] Solution three: a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of Solution one.

[0019] The present invention is beneficial in that:

[0020] The method described in the present invention uses a deep learning method to conduct in-depth analysis and mining of the cross-medium acceleration load characteristics and motion trajectory results of the vehicle obtained by finite element, gridless or experimental methods, and determines the optimal hyperparameters of the fully connected neural network (such as the number of hidden layers, the number of neurons, etc.) based on methods such as grid search or Bayesian search, and establishes deep neural network models for vehicle acceleration and motion trajectory prediction according to the prediction targets; similarly, the hyperparameters of the genetic algorithm (such as the initial population size, the number of population iterations, etc.) can also be determined by methods such as grid search or Bayesian search.

[0021] When the database is collected based on the experimental method, due to the limitation of the sampling equipment, the acceleration or displacement data is not ideal, and non-equal interval and non-equal length data appear, the output layer length of the fully connected neural network is inconsistent and cannot be used directly. The present invention adopts a good data processing method. For non-equal interval time series data, the original data can be processed by linear or cubic spline interpolation, and then resampled based on equal time intervals to generate equal interval time series data. For non-equal time series data, the original time can be divided by each movement time at the same time to form equal length time series data. For the movement time, a fully connected neural network can be established separately to predict the movement time.

[0022] The method described in the present invention aims to achieve rapid prediction of the acceleration and motion trajectory of a vehicle during its entry into water, reduce the cost of experiments and numerical simulations, and improve prediction efficiency, while providing an automated and efficient method for optimizing the shape parameters and entry parameters of the vehicle.

[0023] The present invention introduces a genetic algorithm within the parameter space of the vehicle shape parameters and the water entry parameters. Based on the optimization goals of stable motion trajectory and small impact acceleration, the fully connected neural network established in step 2 is used for prediction under different initial parameters, thereby achieving the optimal design of the vehicle shape parameters and the water entry parameters, thereby saving calculation time and assisting in the design of the vehicle cross-section and water entry parameters, and has high engineering application value.

[0024] By directly predicting the ballistic displacement, the present invention can provide more intuitive information on the motion trajectory of the projectile, helping to quickly understand the projectile's entry process and trajectory change characteristics, and is more in line with application needs. In particular, in scenarios where a precise description of the entry trajectory is required, such as hit accuracy assessment, it can provide more direct and engineering-significant results.

[0025] By combining multiple objective functions into a single weighted objective, this method streamlines the optimization process and is suitable for direct solution within the standard genetic algorithm framework. By setting objective function weights, the importance of different objectives can be flexibly adjusted, avoiding the complexity of the Pareto optimal solution set in multi-objective optimization. This also eliminates the computational overhead of calculating dominance relationships and maintaining multi-objective solution sets in existing techniques. This simplifies the optimization process and is suitable for prioritizing optimization of a specific objective in engineering projects.

[0026] By adjusting the weights, the present invention allows users to flexibly control the relative importance of each objective based on actual needs, allowing the algorithm to better meet the priority requirements of specific applications. In some cases, only one objective may need to be optimized, and using a weighted combination method can more directly and efficiently find the optimal solution.

[0027] The present invention is also applicable to the fields of impact load and motion trajectory prediction during the entry of a navigation body into water, and optimization design of navigation body cross-sectional shape parameters and entry parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a flowchart for quickly predicting the acceleration and motion trajectory of a vehicle entering water as described in Implementation Method 1.

[0029] Figure 2 This is a schematic diagram of the water entry process of the navigation body described in the eleventh embodiment.

[0030] Figure 3 Schematic diagram of the rapid prediction results of acceleration and motion trajectory of the vehicle during water entry as described in Implementation 11.

[0031] Figure 3In the figure, (a) is a schematic diagram showing the error comparison between the time history curve prediction result of the offset during the water entry and the test result; (b) is a schematic diagram showing the error comparison between the time history curve prediction result of the horizontal displacement during the water entry and the test result; (c) is a schematic diagram showing the error comparison between the time history curve prediction result of the vertical displacement during the water entry and the test result; (d) is a schematic diagram showing the error comparison between the time history curve prediction result of the offset during the water entry and the test result.

[0032] Figure 4 This is a schematic diagram of the optimization target and fitness change curve in the vehicle parameter optimization design described in Implementation Method 11.

[0033] Figure 5 This is a schematic diagram of the results of the optimized design of the vehicle parameters described in the eleventh embodiment. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the implementation methods of this application clearer, the technical solutions in the implementation methods of this application will be clearly and completely described below in combination with the drawings in the implementation methods of this application. Obviously, the described implementation methods are only part of the implementation methods of this application, not all of the implementation methods.

[0035] Implementation 1: This implementation provides an artificial intelligence-based method for predicting and optimizing a vehicle's water entry load and motion trajectory. The method comprises the following steps:

[0036] Step 1: Use finite element, meshless or experimental methods to perform numerical simulation or experimental measurement of the vehicle's water entry process to obtain the load characteristics and motion trajectory data during the vehicle's water entry process. By changing the vehicle's cross-sectional ratio s, semi-cone angle α, water entry velocity v and water entry angle β, a sample database of vehicle acceleration and position under different initial conditions is obtained;

[0037] Step 2: Based on the sample database established in step 1, divide it into a training set and a validation set, and establish a neural network rapid prediction model for predicting the acceleration history curve and motion trajectory of the vehicle under different initial parameters;

[0038] Step 3: The neural network rapid prediction model of the vehicle acceleration history curve and motion trajectory under different initial parameters obtained in step 2 is embedded into the genetic algorithm to optimize the shape parameters and water entry parameters of the vehicle, and complete the prediction and optimization of the vehicle entry load and motion trajectory.

[0039] Implementation 2: This implementation further defines the method for predicting and optimizing the water entry load and motion trajectory of a vehicle based on artificial intelligence described in Implementation 1. The method for optimizing the shape parameters and water entry parameters of the vehicle in step 3 is as follows:

[0040] Input the upper and lower bounds of the four parameters: the vehicle cross-section ratio s, the semi-cone angle α, the water entry velocity v, and the water entry angle β. Randomly sample the parameter combinations within the space formed by the upper and lower bounds to form an initial population. Then calculate the acceleration and ballistic trajectory based on the acceleration and motion trajectory neural network rapid prediction model established in step 2.

[0041] Evaluate and screen all parameter combinations in the initial population formed in step 3, perform crossover and mutation on the screened population, expand the search scale and generate a new generation of individuals, iterate and gradually optimize the parameters, and finally output the optimal parameters that meet the above optimization goals.

[0042] Implementation method three: This implementation method further limits the artificial intelligence-based method for predicting and optimizing the water entry load and motion trajectory of a navigation body described in implementation method one. The ratio of the training set and the verification set described in step 2 is no less than 3:4.

[0043] Implementation method 4. This implementation method further limits the artificial intelligence-based method for predicting and optimizing the water entry load and motion trajectory of a vehicle described in implementation method 1. The input variables of the neural network rapid prediction model for predicting the acceleration time history curve and motion trajectory of the vehicle under different initial parameters described in step 2 are the four parameters in step 1, and the output variable is the acceleration time history data. The load characteristics and motion trajectory data during the vehicle entering the water are normalized to the minimum and maximum values.

[0044] Implementation method five. This implementation method is a further limitation of the artificial intelligence-based method for predicting and optimizing the water entry load and motion trajectory of a vehicle described in implementation method five. The neural network rapid prediction model of the vehicle acceleration history curve and motion trajectory includes an input layer, an output layer and multiple hidden layers, and the input layer variables are all the vehicle cross-sectional ratio s, semi-cone angle α, water entry speed v and water entry angle β.

[0045] Implementation method six. This implementation method further limits the artificial intelligence-based method for predicting and optimizing the water entry load and motion trajectory of a navigation body described in implementation method five. The hyperparameters contained in the input layer, output layer and multiple hidden layers (such as the number of hidden layers, the number of neurons, etc.) are obtained by optimizing through methods such as grid search or Bayesian search; similarly, the hyperparameters in the genetic algorithm (such as the initial population size, the number of population iterations, etc.) can also be optimized through methods such as grid search or Bayesian search.

[0046] Implementation method seven. This implementation method further limits the artificial intelligence-based method for predicting and optimizing the water entry load and motion trajectory of a vehicle described in implementation method one. The output layer of the neural network rapid prediction model of the vehicle acceleration time history curve described in step 2 is the vehicle acceleration time history data.

[0047] Implementation method eight. Implementation method one is a further limitation of the method for predicting and optimizing the water entry load and motion trajectory of a vehicle based on artificial intelligence. The output layer of the neural network rapid prediction model of the motion trajectory is the time history data of the vehicle position coordinates.

[0048] Furthermore, a preferred implementation is provided. When the acceleration history curve and motion trajectory training data of the vehicle under different initial parameters in step 2 are non-equally spaced time series data, the original data can be processed by linear or cubic spline interpolation, and then resampled based on equal time intervals to generate equal time series data.

[0049] Furthermore, a preferred implementation is provided. When the acceleration time history curve and motion trajectory training data of the vehicle under different initial parameters in step 2 are non-equal time series data, the original time can be divided by each movement time at the same time to form equal-length time series data. For the movement time, a fully connected neural network can be established separately to predict the movement time.

[0050] Implementation method 9. This implementation method proposes a computer device including a memory and a processor, wherein the memory stores a computer program. When the processor runs the computer program stored in the memory, the processor executes the method described in any one of implementation methods 1 to 8.

[0051] Implementation 10. This implementation proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method described in any one of Implementation 1 to Implementation 8 are implemented.

[0052] Implementation 11: This implementation provides an example, which is used to explain the above implementations 1 to 8. Specifically, the example is as follows:

[0053] See also Figures 1 to 5 To illustrate this embodiment, the method described in this embodiment includes the following steps:

[0054] Taking the process of a small-scale navigation body entering the water across a medium as an example, the same principle applies to the real scale. Figure 1 The implementation steps of the present invention are described as follows:

[0055] Step 1: First, numerically simulate or experimentally measure the water entry process of the vehicle using finite element, meshless, or experimental methods, and collect acceleration and motion trajectory data of the vehicle under different cross-sectional ratios s, semi-cone angles α, water entry velocities v, and water entry angles β. Take the initial water entry center as the center point, and define the x-axis as the direction parallel to the initial water surface to the right through the center point, and the positive y-axis as the direction perpendicular to the initial water surface and pointing to the free liquid surface through the center point, as follows: Figure 2 For the non-equally spaced data, linear interpolation and equal-interval resampling methods can be used to obtain acceleration sequence data and motion trajectory sequence data at equal time intervals, including the horizontal direction dx and the vertical direction dy.

[0056] Based on the above, by varying any of the variables in the cross-sectional ratio s, semi-cone angle α, water entry velocity v, and water entry angle β, multiple simulations or tests are conducted on the vehicle's water entry process. Acceleration time series data and trajectory data are recorded at different moments to establish a sample database. The sample database is then divided into a training set and a test set, with the training set accounting for at least three-quarters of the total sample size. To accelerate the training process and improve prediction accuracy, the raw data is normalized to its maximum and minimum values ​​and scaled to the range [0, 1].

[0057] Step 2: Based on the sample database established in step 1, the acceleration of the navigation body when entering the water is described in detail. Figure 2 The same approach is used for trajectory prediction, except that the output layer is replaced with displacement time series data. A fully connected neural network deep learning model is developed for predicting acceleration during water entry. The model consists of three main components: an input layer, a hidden layer, and an output layer. The input layer variables include the cross-sectional ratio s, the semi-cone angle α, the water entry velocity v, and the water entry angle β, while the output layer variables are acceleration time series data.

[0058] After establishing a fully connected neural network model, the model hyperparameters need to be pre-set. The quality of the hyperparameter settings directly affects the prediction accuracy and efficiency. Therefore, grid search or Bayesian search methods can be used to find the number of hidden layers and neurons in each hidden layer, activation functions, etc., so as to improve the training efficiency and accuracy of deep neural networks. In order to prevent overfitting and avoid redundant training, an early stopping strategy is adopted. When the loss of the test set no longer decreases or even increases, the training process is terminated. By supervising the average relative error between the predicted value and the validation set data, the hyperparameters of the neural network model are finally determined. According to the deep neural network model established with the above parameters, the test set is input into the model for acceleration prediction. The motion trajectory prediction of the vehicle is similar to the acceleration prediction, and the final result is given as shown in the attached figure. Figure 3 The predicted results of the vehicle acceleration and motion trajectory are shown.

[0059] Step 3: Embed the predicted vehicle acceleration prediction model and motion trajectory prediction model in Step 2 into the genetic algorithm to optimize the design of the vehicle cross-sectional shape and water entry parameters. First, input the optimization range of the vehicle parameters and set the number n of parameter combinations calculated in each iteration. The larger the value of n, the higher the single calculation amount, which can be set according to the computing resource configuration. The algorithm will randomly initialize n different parameter combinations (s i , α i , v i , β i ), denoted as M0. After initialization, introduce the fast prediction model into the genetic algorithm. With (s i , α i , v i , β i ) as the input, quickly calculate the acceleration and motion trajectory under each parameter combination. Evaluate the results under all parameter combinations based on the optimization objective. The combination with smaller acceleration and less deviation of the motion trajectory has higher fitness. Since the difference in the x direction of the motion trajectory is not significant, the definitions of the x and y directions are as shown in Figure 2 . It is mainly manifested that it gradually deviates from the predetermined orbit or even turns in the y direction. To more accurately capture the stability of the navigation trajectory, use the displacement curve in the y direction to measure. When the slope of the time history curve is smaller, the offset is also smaller, and the trajectory is more stable. Therefore, extract the acceleration peak value of all individuals and the minimum value k min of the slope of the time history curve in the y direction, and normalize them to be denoted as f1 and f2 respectively. The fitness function is selected as 1 / (w1×f1 + w2×f). w1 and w2 are weight coefficients. When more emphasis is placed on optimizing the ballistic stability, set w2>w1. When more emphasis is placed on optimizing the load reduction, set w2<w1. When there are no special requirements, w2 = w1 can be set. After evaluating all combinations according to the fitness, start automatically generating a new generation of search population M1.

[0060] The new population M1 is generated using genetics techniques such as crossover, mutation, and selection. First, the decimal encoding of individuals in M0 is converted to binary encoding. With a crossover probability of 0.80, 80% of the individuals in M0 are randomly selected to undergo crossover of their encoding segments. For example, [0,0,0] and [1,1,1] cross over starting at the second position to generate [0,1,1] and [1,0,0]. With a mutation probability of 0.01, 1.00% of the individuals in M0 are randomly selected to undergo encoding segment mutation. For example, [0,0,0] is mutated to [0,1,0]. Individuals in M0 are randomly selected based on their fitness, with individuals with higher fitness being more likely to be retained. The combinations generated by these three operations are then merged to form the new population M1. To retain the best individuals in M0 and prevent individuals with high fitness from being left out, the M0 population is merged with M1, duplicates are removed, and the top n combinations are selected from highest to lowest fitness as the final M1. This completes the generation of a new population. Fitness evaluation and population generation are repeated, while the optimization objective and fitness curve are monitored simultaneously. When fitness no longer increases, the optimization results converge and the optimization process stops.

[0061] Individuals with high fitness are screened out through selection operations, and the scope of optimization is continuously expanded by combining crossover and mutation. The above population generation and fitness evaluation process is iterated until the fitness curve reaches the maximum and tends to be stable. The optimization algorithm stops, such as Figure 4 As shown in the figure, as the number of iterations increases, the minimum value k of the slope of the y-direction displacement history curve min The peak value of acceleration and the acceleration value tend to be minimum, and the fitness increases continuously to the maximum and then stabilizes. Output the best parameter combination [s, α, v, β] after optimization design, as shown in the following example: Figure 5 Optimization results of acceleration and vertical motion trajectory are shown.

[0062] In summary, deep neural networks have demonstrated significant advantages in processing multi-source data, capturing data mapping relationships, and enabling rapid prediction. Based on the complexity of the problem being studied and the size of the dataset, this paper designs a deep neural network to obtain an intrinsic logical relationship between input and output that approximates the true solution, thereby enabling the prediction of the acceleration and motion trajectory of a vehicle during water entry.

[0063] The above implementation steps are used to understand the core idea of ​​the patent of this invention. For engineers and technicians in this field, modifications and improvements based on the idea of ​​the invention, such as using different artificial intelligence algorithms and hyperparameter optimization methods to establish a neural network model, predicting or optimizing other physical quantities such as the water entry speed of the navigation body, etc., are also within the scope of protection of the patent of this invention.

Claims

1. A method for predicting and optimizing the water entry load and motion trajectory of a vehicle based on artificial intelligence, characterized in that: The method comprises the following steps: Step 1: Use finite element, gridless or experimental methods to simulate or test the process of the vehicle entering the water, obtain the load characteristics and motion trajectory data during the vehicle entering the water, and change the cross-sectional ratio of the vehicle. s , half cone angle α , water entry speed v and water entry angle β Four parameters are used to obtain a sample database of vehicle acceleration and position under different initial conditions; Step 2: Based on the sample database obtained in step 1, the database is divided into a training set and a validation set, and a neural network rapid prediction model is established for predicting the acceleration history curve and motion trajectory of the vehicle under different initial parameters. Step 3: The neural network rapid prediction model of the vehicle acceleration history curve and motion trajectory under different initial parameters obtained in step 2 is embedded into the genetic algorithm to optimize the shape parameters and water entry parameters of the vehicle, thereby completing the prediction and optimization of the vehicle's water entry load and motion trajectory; The method for optimizing the shape parameters and water entry parameters of the vehicle in step 3 is: Input vehicle cross-section ratio s , half cone angle α , water entry speed v and water entry angle β The upper and lower bounds of the four parameters are used, and the parameter combinations within the space formed by the upper and lower bounds are randomly sampled to form an initial population. The acceleration and trajectory are calculated based on the acceleration and motion trajectory neural network rapid prediction model established in step 2, and the results under all parameter combinations are evaluated based on the optimization goal. Evaluate and screen all parameter combinations in the initial population formed in step 3, perform crossover and mutation on the screened population, expand the search scale and generate a new generation of individuals, iterate and gradually optimize the parameters, and finally output the optimal parameters that meet the above optimization goals.

2. The method for predicting and optimizing the water entry load and motion trajectory of a vehicle based on artificial intelligence according to claim 1 is characterized in that: The ratio of the training set to the validation set described in step 2 should be no less than 3:

4.

3. The method for predicting and optimizing the water entry load and motion trajectory of a vehicle based on artificial intelligence according to claim 1 is characterized in that: The input variables of the neural network rapid prediction model for predicting the acceleration time history curve and motion trajectory of the vehicle under different initial parameters described in step 2 are the four parameters in step 1, the output variable is the acceleration time history data, and the load characteristics and motion trajectory data during the vehicle entering the water are normalized to the minimum and maximum values.

4. The method for predicting and optimizing the water entry load and motion trajectory of a vehicle based on artificial intelligence according to claim 1 is characterized in that: The neural network rapid prediction model of the vehicle acceleration history curve and motion trajectory includes an input layer, an output layer and multiple hidden layers, and the input layer variables are all vehicle cross-sectional ratios. s , half cone angle α , water entry speed v and water entry angle β .

5. The method for predicting and optimizing the water entry load and motion trajectory of a vehicle based on artificial intelligence according to claim 4 is characterized in that: The hyperparameters included in the input layer, output layer and multiple hidden layers are obtained by optimizing through grid search or Bayesian search method; similarly, the hyperparameters in the genetic algorithm are obtained by optimizing through grid search or Bayesian search method.

6. The method for predicting and optimizing the water entry load and motion trajectory of a vehicle based on artificial intelligence according to claim 1 is characterized in that: The output layer of the neural network rapid prediction model of the vehicle acceleration time history curve described in step 2 is the vehicle acceleration time history data.

7. The method for predicting and optimizing the water entry load and motion trajectory of a vehicle based on artificial intelligence according to claim 1 is characterized in that: The output layer of the neural network rapid prediction model of motion trajectory is the time history data of the vehicle position coordinates.

8. A computer device comprising a memory and a processor, characterized in that A computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images