Ship performance evaluation and optimization method and system based on neural network

Abstract

The invention provides a ship performance evaluation and optimization method and system based on a neural network, and the method comprises the steps: a ship type imaging step: intercepting a cross section diagram of a generated three-dimensional geometric ship type, generating a plane diagram through the cross section lines in all the diagrams, expressing an enclosed region through different colors, and obtaining a ship type color cross section diagram; a neural network training model step: marking, normalizing and standardizing the hydrostatic power and resistance of the ship, taking the ship type color profile as input, taking the hydrostatic power and resistance of the ship as output, and obtaining a model through neural network training; a step of model calculation of hydrostatic force and resistance: converting the ship to be evaluated into a new ship form graph, inputting the model, and outputting the hydrostatic force and resistance of the ship; and a judgment and optimization step: judging whether the ship hydrostatic power and resistance data output by the model meet requirements or not, converting the ship hydrostatic power and resistance data into a variable in a weighting manner when the ship hydrostatic power and resistance data do not meet the requirements, and performing optimization with corresponding hydrostatic power constraint conditions on the variable by adopting a genetic algorithm so as to optimize the ship type.

Description

Technical Field

[0001] The present application relates to the field of ship performance, and in particular to a method and system for ship performance evaluation and optimization based on neural networks. Background Art

[0002] The resistance characteristics of a ship are one of the important performance indicators of a ship. The quality of resistance performance has a significant impact on energy conservation, emission reduction, cost reduction and efficiency improvement, and has always been of great concern in the field of ship design. The evaluation and optimization of ship resistance is extremely important for the shipbuilding and shipping industries. By reducing the resistance of the ship in the water, the purpose of reducing fuel consumption and emissions can be achieved, which is beneficial to reducing operating costs and environmental impacts. The International Maritime Organization and other organizations are constantly improving the environmental protection standards for ships. Optimizing ship resistance is an effective means to help shipowners meet these regulations. Ships with excellent performance can improve the competitiveness of ship design units, while improving the competitiveness of shipowners in the market, attracting more customers and bringing better economic benefits. Ship type optimization helps the shipping industry respond to global climate change and reflects the responsibility of the ship and shipping industries to society and their commitment to environmental protection.

[0003] At present, ship resistance optimization usually uses numerical simulation as a means, combined with parametric modeling, and after a large number of sample calculations, an optimization algorithm is used to find the optimal parameter combination to obtain the final target ship type. The parameters for building the ship type and the sample set of the corresponding ship type resistance can also be constructed into a proxy model, such as a response surface model, a Kriging model, etc., and the proxy model is used to find the optimal solution. These methods are all based on the parametric expression of the ship type. The actual situation is that the construction parameters of different ship types are not the same. Past sample data sets cannot be applied to the analysis of new ships, resulting in a waste of data resources. Summary of the invention

[0004] In order to solve the problem of waste of data resources in traditional methods due to different construction parameters of different ship types and the inability of past sample data sets to be applied to the analysis of new ships, the present application provides a ship performance evaluation and optimization method and system based on neural networks, which uses past sample data sets to train a ship performance evaluation model, and then can quickly and efficiently evaluate the hydrostatic force, resistance and other performance of different ship types of new ships. Combined with the optimization method, it can easily realize the optimization of ship types with constraints, meet actual use needs, and optimize ship parameters more efficiently.

[0005] This application is implemented through the following technical solutions:

[0006] A ship performance evaluation and optimization method based on neural network comprises the following steps:

[0007] Ship type image generation step: using 3D modeling technology to generate multiple different 3D geometric ship types, intercepting multiple cross-sectional views of each of the 3D geometric ship types, and using the cross-sectional lines in each of the cross-sectional views to generate a plan view, and expressing the areas surrounded by each of the cross-sectional lines in different colors to obtain color cross-sectional views of the ship type corresponding to each of the 3D geometric ship types;

[0008] The neural network training model step includes: marking the ship hydrostatic data and ship resistance data corresponding to each of the three-dimensional geometric ship types; then normalizing and standardizing the ship type color profile and the marked data, and then using the ship type color profile as input, the ship hydrostatic data and the ship resistance data as output, and obtaining a ship performance evaluation model through neural network training;

[0009] The model calculates hydrostatic force and resistance steps: converting the ship to be evaluated into a corresponding new ship type image, and inputting the new ship type image into the trained ship performance evaluation model, and outputting the corresponding ship hydrostatic force data and ship resistance data after model calculation;

[0010] Judgment and optimization steps: The ship hydrostatic data and ship resistance data calculated and output by the model are compared with their respective predetermined parameters to determine whether they meet the requirements. If the requirements are not met, the ship hydrostatic data and ship resistance data calculated and output by the model are converted into a variable in a weighted manner, and the variable is optimized with corresponding hydrostatic constraints using a genetic algorithm to obtain an optimized new ship type image; the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the output ship hydrostatic data and ship resistance data are compared and judged again, and the judgment and optimization are continuously cycled until the requirements are met, and the optimized ship type is output to achieve resistance optimization under hydrostatic constraints.

[0011] Preferably, in the neural network training model step, the ship hydrostatic data involved in the annotation and neural network training of the ship performance evaluation model include displacement data and center of buoyancy position data; the model calculates hydrostatic force and resistance step outputs the corresponding displacement data, center of buoyancy position data and ship resistance data; the judgment and optimization step compares the displacement data, center of buoyancy position data and ship resistance data with their respective predetermined parameters to determine whether the requirements are met. If the requirements are not met, the displacement data, center of buoyancy position data and ship resistance data output by the model calculation are converted into a variable in a weighted manner, and the variable is optimized with a genetic algorithm for loading capacity constraints and hull internal layout constraints to obtain an optimized new ship type picture; and the optimized new ship type picture is input into the ship performance evaluation model again for model calculation, and the displacement data, center of buoyancy position data and ship resistance data are output for comparison and judgment again, and the judgment and optimization are continuously cycled until the requirements are met, and the optimized ship type is output to achieve resistance optimization under several hydrostatic constraints.

[0012] Preferably, in the neural network training model step, the ship hydrostatic data involved in the annotation and neural network training of the ship performance evaluation model include displacement data, buoyancy center position data, drift center position data and stability data; the model calculates hydrostatic force and resistance step outputs the corresponding displacement data, buoyancy center position data, drift center position data, stability data and ship resistance data; the judgment and optimization step compares the displacement data, buoyancy center position data, drift center position data, stability data and ship resistance data with their respective predetermined parameters to judge whether the requirements are met. If the requirements are not met, the displacement data calculated and output by the model is compared. , center of buoyancy position data, drift center position data, stability data and ship resistance data are converted into a variable in a weighted manner, and a genetic algorithm is used to optimize the variable with respect to loading capacity constraints, hull internal layout constraints and navigation safety constraints, to obtain an optimized new ship type image; and the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the displacement data, center of buoyancy position data, drift center position data, stability data and ship resistance data are output for comparison and judgment again, and the judgment and optimization are continuously circulated until the requirements are met, and the optimized ship type is output to achieve resistance optimization under several hydrostatic constraints.

[0013] Preferably, in the ship type imaging step, the color cross-sectional images of different three-dimensional geometric ship types have the same size and image format, and the color cross-sectional images adopt a red, green, and blue (RGB) color mode.

[0014] Preferably, in the ship form image forming step, a method of intercepting a plurality of cross-sectional views of each of the three-dimensional geometric ship forms and generating a plan view using the cross-sectional lines in each of the cross-sectional views comprises:

[0015] Take the designated station as the dividing position, and the height to the waterline of the ship, and cut the section perpendicular to the line connecting the bow and the stern as the cross-sectional view;

[0016] The cross-section lines in each cross-section view are intercepted to generate a plan view with the left side as the stern direction and the right side as the bow direction.

[0017] Preferably, in the neural network training model step, marking the ship hydrostatic data and ship resistance data corresponding to each of the three-dimensional geometric ship types includes:

[0018] Determine the hydrostatic data of the ship corresponding to each of the three-dimensional geometric ship types by using professional software or self-programming method;

[0019] Determine the ship resistance data corresponding to each of the three-dimensional geometric ship types by using experiments, computational fluid dynamics methods or potential flow methods;

[0020] The ship hydrostatic data and ship resistance data corresponding to each of the three-dimensional geometric ship types are marked.

[0021] Preferably, in the judgment and optimization steps, in addition to the genetic algorithm, a simulated annealing algorithm and / or a particle swarm algorithm are also used to optimize the corresponding hydrostatic constraints of the converted variables, and the ship performance evaluation model is combined to evaluate and screen the optimized ship type.

[0022] A ship performance evaluation and optimization system based on neural network includes an image generation module, a neural network training module, a ship hydrostatic data and ship resistance data evaluation module, and a ship type optimization module connected in sequence; wherein,

[0023] The image generation module is used to generate a plurality of different three-dimensional geometric ship shapes by using three-dimensional modeling technology, intercept a plurality of cross-sectional views of each of the three-dimensional geometric ship shapes, and generate a plan view using the cross-sectional lines in each of the cross-sectional views, and express the areas surrounded by each of the cross-sectional lines in different colors to obtain color cross-sectional views of the ship shapes corresponding to each of the three-dimensional geometric ship shapes;

[0024] The neural network training module is used to annotate the ship hydrostatic data and ship resistance data corresponding to each of the three-dimensional geometric ship types; then the ship type color profile and the annotated data are normalized and standardized, and then the ship type color profile is used as input, and the ship hydrostatic data and ship resistance data are used as output, and a ship performance evaluation model is obtained through neural network training;

[0025] The ship hydrostatic data and ship resistance data evaluation module is used to convert the ship to be evaluated into a corresponding new ship type image, and input the new ship type image into the trained ship performance evaluation model, and the model outputs the corresponding ship hydrostatic data and ship resistance data after calculation;

[0026] The ship type optimization module is used to compare the ship hydrostatic data and ship resistance data output by the model calculation with their respective predetermined parameters to determine whether the requirements are met. If the requirements are not met, the ship hydrostatic data and ship resistance data output by the model calculation are converted into a variable in a weighted manner, and a genetic algorithm is used to optimize the variable with corresponding hydrostatic constraints to obtain an optimized new ship type image; and the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the ship hydrostatic data and ship resistance data are output for comparison and judgment again, and the judgment and optimization are continuously cycled until the requirements are met, and the optimized ship type is output to achieve resistance optimization under hydrostatic constraints.

[0027] Preferably, the ship hydrostatic data involved in the neural network training module and the ship performance evaluation model training by the neural network include displacement data and buoyancy center position data; the ship hydrostatic data and ship resistance data evaluation module outputs the corresponding displacement data, buoyancy center position data and ship resistance data; the ship type optimization module compares the displacement data, buoyancy center position data and ship resistance data with their respective predetermined parameters to determine whether the requirements are met. If the requirements are not met, the displacement data, buoyancy center position data and ship resistance data output by the model calculation are converted into a variable in a weighted manner, and the variable is optimized with a genetic algorithm for loading capacity constraints and hull internal layout constraints to obtain an optimized new ship type image; and the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the displacement data, buoyancy center position data and ship resistance data are output for comparison and judgment again, and the judgment and optimization are continuously cycled until the requirements are met, and the optimized ship type is output to achieve resistance optimization under several hydrostatic constraints.

[0028] Preferably, in the ship type optimization module, in addition to the genetic algorithm, a simulated annealing algorithm and / or a particle swarm algorithm are also used to optimize the corresponding hydrostatic constraints of the converted variables, and the ship performance evaluation model is combined to evaluate and screen the optimized ship type.

[0029] The beneficial effects of this application are:

[0030] The present application provides a ship performance evaluation and optimization method based on neural network. The method uses three-dimensional modeling technology to generate multiple different three-dimensional geometric ship types, intercepts multiple cross-sectional views of each of the three-dimensional geometric ship types, and uses the cross-sectional lines in each of the cross-sectional views to generate a plane view. In this way, a non-parametric expression method of the ship type is established with the cross-sectional view of the ship type, and a general representation method of the ship type is constructed as sample data, which solves the problem of data resource waste caused by different construction parameters of different ship types in traditional methods and the inability of past sample data sets to be applied to the analysis of new ships; the area surrounded by each of the cross-sectional lines is expressed in different colors, and each of the three-dimensional geometric The color profiles of the ship types corresponding to the ship types are respectively obtained. In this way, the color blocks are divided by conventional cross-section lines to generate pictures. The pictures are obtained simply and efficiently, and the color changes of different ship types are clearly distinguished, which is conducive to deep learning and feature extraction; the ship hydrostatic data and ship resistance data corresponding to each of the three-dimensional geometric ship types are annotated, and then the ship type color profiles and the annotated data are normalized and standardized, and then the ship type color profiles are used as input, and the ship hydrostatic data and ship resistance data are used as output. After the neural network training, a ship performance evaluation model is obtained. In this way, the ship type color profile is used as the input feature data, and the picture does not need to be scaled in the two directions of width and height. Or the scaling amplitude is small, the relative relationship between the various parts of the ship type characteristics is maintained, and the training speed and accuracy of the model are improved; the ship to be evaluated is converted into a corresponding new ship type image, and the new ship type image is input into the trained ship performance evaluation model, and the model outputs the corresponding ship hydrostatic data and ship resistance data after calculation. In this way, the ship performance evaluation model is trained using the past sample data set, and then the hydrostatic, resistance and other performances of different types of new ships can be quickly and efficiently evaluated; the ship hydrostatic data and ship resistance data calculated and output by the model are compared with their respective predetermined parameters to determine whether the requirements are met. If the requirements are not met, the model calculation output is The hydrostatic data and resistance data of the ship are converted into a variable in a weighted manner, and the genetic algorithm is used to optimize the variable with corresponding hydrostatic constraints to obtain an optimized new ship type image, and the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the ship hydrostatic data and ship resistance data are output for comparison and judgment again, and the judgment and optimization are continuously cycled until the requirements are met, and the optimized ship type is output to achieve resistance optimization under hydrostatic constraints. In this way, on the basis of the model, combined with the optimization method, it is convenient to optimize the ship type under given constraints, meet actual use needs, and significantly improve the optimization efficiency of ship parameters. After adopting the ship performance evaluation and optimization method based on neural network of this application, the ship performance evaluation model can be obtained by training with past sample data sets, and applied to the analysis of new ships, so as to quickly and efficiently evaluate the hydrostatic, resistance and other performances of different types of new ships.Combined with the optimization method, it is easy to realize the optimization of ship types with constraints, meet the actual use needs, and optimize the ship parameters more efficiently.

[0031] The ship performance evaluation and optimization method based on neural network in this application can also be called a method of ship hydrostatic evaluation and resistance optimization based on deep learning. A convolutional neural network proxy model, namely a ship performance evaluation model, is constructed to express the relationship between ship characteristics and performance. It can not only obtain the ship resistance, but also obtain the hydrostatic data of the corresponding ship type, thus providing a feasible method for ship type optimization under restrictive conditions, and realizing the optimization of resistance performance while meeting the hydrostatic requirements.

[0032] This application applies neural network-deep learning method to establish a proxy model of ship type and ship hydrostatic force and resistance (ship performance evaluation model). This proxy model can not only evaluate the resistance of different ship types, but also evaluate hydrostatic force as needed, such as displacement volume, center of buoyancy, drift center, stability, etc., that is, the ship hydrostatic force data can further involve displacement data, center of buoyancy position data, or further involve displacement data, center of buoyancy position data, drift center position data and stability data. Compared with the traditional solution, it provides richer output content and can more comprehensively characterize the various characteristics of the ship, thereby ensuring that the trained ship performance evaluation model can achieve more accurate ship performance evaluation. In actual engineering, for ship performance optimization, there are ship hydrostatic force requirements, such as general displacement (displacement volume), which is related to loading capacity; center of buoyancy position is related to the internal layout of the hull; stability is related to navigation safety, etc. It is necessary to achieve optimal resistance under certain requirements (constraints). In the past, the calculation of ship hydrostatic force required complex processes or professional software, which could not be carried out simultaneously with resistance evaluation. The required work was complicated and required the cooperation of multiple people. Since the hydrostatic force and resistance of a ship are both related to the ship's lines, deep learning is used to unify the evaluation of different performances with the ship's lines images, simplifying the workflow and making it more suitable for actual engineering use.

[0033] On the basis of the proxy model (ship performance evaluation model), combined with the optimization method, it is easy to realize the optimization of ship types with constraints to meet the actual use needs. Constraints refer to hydrostatic constraints, such as displacement cannot be less than a fixed value, otherwise the ship cannot load enough cargo. Since the ship type is expressed in pictures, its acquisition method is diverse and convenient. The proxy model combined with the optimization method can quickly evaluate a large number of solutions. Optimization can use artificial experience or optimization algorithms, such as genetic algorithms, simulated annealing algorithms, particle swarm algorithms, etc. The use of the above optimization algorithms combined with the proxy model can evaluate and screen excellent ship types in a large number in a short time, thereby improving work efficiency.

[0034] In the present application, the color profiles of different three-dimensional geometric ship types have different color distributions, and the color changes are clearly distinguished, so that different ship types have obvious distinguishing features, which is conducive to the extraction of features by deep learning, thereby making the training speed of the ship performance evaluation model faster and the convergence better.

[0035] This application divides color blocks by conventional cross-section station lines, which is friendly to ship designers. Pictures can be obtained from the type value table, reducing extra work.

[0036] The present application also relates to a ship performance evaluation and optimization system based on a neural network, which corresponds to the above-mentioned ship performance evaluation and optimization method based on a neural network, and can be understood as a system that implements the above-mentioned ship performance evaluation and optimization method based on a neural network, including an image generation module, a neural network training module, a ship hydrostatic data and ship resistance data evaluation module, and a ship type optimization module, wherein the image generation module can use three-dimensional modeling technology to generate a variety of three-dimensional geometric ship types, and intercept multiple cross-sectional views, and construct a non-parametric ship type expression by extracting the cross-sectional lines in each cross-sectional view. That is, a universal ship type representation method. As sample data, it effectively solves the problem of data resource waste caused by the different construction parameters of different ship types in the traditional method, and the past sample data sets cannot be applied to the analysis of new ships. The module further fills the area surrounded by the cross-section lines with different colors to generate color profiles corresponding to each three-dimensional geometric ship type. This image generation method based on the conventional cross-section line division of color blocks is not only simple and efficient, but also has significant color distinction between ship types, which is conducive to the efficient feature extraction of deep learning algorithms; the neural network training module can annotate the ship hydrostatic data and ship corresponding to each three-dimensional geometric ship type. The ship performance evaluation model is obtained by neural network training. In this process, the input color profile image maintains or approximately maintains the original proportions in the width and height dimensions, effectively retaining the relative relationship of the ship characteristics, thereby significantly improving the speed and accuracy of model training. The ship hydrostatic data and ship resistance data evaluation module can convert the ship to be evaluated into the corresponding new ship type image, and input it into the trained ship performance evaluation model. After the model calculation, the corresponding ship hydrostatic data and ship resistance data are output. The ship performance evaluation model is trained using past sample data sets, which can quickly output the hydrostatic, resistance and other data of the new ship type to achieve efficient and accurate performance evaluation; the ship type optimization module uses genetic algorithms to weightedly integrate the ship hydrostatic data and resistance data into a single variable, and optimize the variable under the condition of satisfying hydrostatic constraints, so as to generate a better new ship type image and minimize the resistance under hydrostatic constraints, which is convenient for ship type optimization under given restrictions, meets actual use needs, and significantly improves the efficiency of ship parameter optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flow chart of the ship performance evaluation and optimization method based on neural network in this application;

[0038] Figure 2 RGB color image converted from the cross-section of the ship's model lines in this application;

[0039] Figure 3 This is a framework diagram of the ship performance evaluation model of the neural network in this application;

[0040] Figure 4 Comparison of ship waveforms before and after optimization for this application;

[0041] Figure 5 This is a structural block diagram of the neural network-based ship performance evaluation and optimization system for this application. DETAILED DESCRIPTION

[0042] The present application discloses a method for ship performance evaluation and optimization based on a neural network, which aims to solve the problem of waste of data resources caused by the fact that past sample data sets cannot be applied to the analysis of new ships, and to achieve ship type optimization with restricted conditions. The method can be executed by a processor or an electronic device with processing capabilities.

[0043] At present, the optimization of ship resistance mainly relies on numerical simulation technology, which combines with parametric modeling to calculate a large number of samples and use optimization algorithms to explore the optimal parameter configuration to determine the best ship design. Another strategy is to construct a sample set of ship parameters and corresponding ship resistance to build a proxy model, such as a response surface model or a Kriging model. Use the proxy model to find the optimal solution. Then, these methods are all based on the parametric expression of the ship type, but the actual situation is that the construction parameters of different ship types are not the same, which leads to the fact that past sample data sets cannot be applied to the analysis of new ships, resulting in a waste of data resources. In addition, traditional methods often ignore the construction of proxy models between ship parameters and ship hydrostatics, so that the evaluation of hydrostatics still needs to rely on professional software, involving complex information exchange and the generation of ship geometry.

[0044] In order to overcome these limitations, the present application proposes an innovative method, that is, a non-parametric expression of the ship type is established based on the cross-sectional view of the ship type, and a proxy model between the ship characteristics and performance is constructed, especially using deep learning technology to evaluate ship performance and optimize ship resistance. Specifically, a convolutional neural network proxy model is designed, which can accurately capture and express the complex relationship between ship characteristics and its performance. This model can not only predict the resistance of the ship type, but also provide the hydrostatic value of the corresponding ship type at the same time. This method provides a practical way for ship type optimization under restricted conditions (ship type optimization under given hydrostatic constraints), so that while meeting the hydrostatic requirements, the resistance performance can be optimized. In other words, the present application designs a general, non-parametric ship type expression method, and constructs a proxy model based on this. The proxy model expresses the ship type and the hydrostatic force and resistance of the ship. Combined with the optimization algorithm, the ship type optimization that meets the hydrostatic constraints can be achieved. The non-parametric method of ship type is pictures. The ship type pictures are used as the input of deep learning, and the hydrostatic force and resistance of the corresponding ship type are the deep learning output labels. A neural network model such as VGG16 or a self-built convolutional neural network is used for training to obtain a multi-output deep learning model of the picture about hydrostatic force and resistance. The new ship type picture is input into the model to obtain the hydrostatic force and resistance results. By using geometric modeling, picture editing, self-programming and other methods, the ship type pictures of the same format can be obtained, and the hydrostatic force and resistance data can be calculated using the deep learning model. Apply optimization algorithms, such as genetic algorithms, to control the changes in the picture and find a ship type that meets the requirements.

[0045] like Figure 1 As shown, the dotted box mainly includes the deep learning process and the ship type optimization process. The first is the establishment of a deep learning model (ship performance evaluation model) between the ship type sample image and the ship type hydrostatic force and resistance; the second is the ship type optimization process constructed using this deep learning model (ship performance evaluation model, also called performance evaluation agent model). Specifically, the method includes the following steps:

[0046] 1. Ship type image generation step: Generate multiple different three-dimensional geometric ship types using three-dimensional modeling technology, intercept multiple cross-sectional views of each of the three-dimensional geometric ship types, and generate a plan view using the cross-sectional lines in each of the cross-sectional views, and express the areas surrounded by each of the cross-sectional lines in different colors to obtain color cross-sectional views of the ship types corresponding to each of the three-dimensional geometric ship types. This step involves sample ship type generation and ship type expression.

[0047] Preferably, the embodiment of the present application can use three-dimensional modeling software or professional ship design software to generate a certain number of three-dimensional geometric ship models, and the methods for obtaining the ship models are diverse and convenient.

[0048] The embodiment of the present application is based on a three-dimensional geometric ship type. The hull of the three-dimensional geometric ship type is divided into a preset number of stations (in the process of ship design and construction, in order to facilitate construction and management, the hull is usually divided into several longitudinal sections, each section is called a station) through a series of section planes perpendicular to the longitudinal axis of the hull (the so-called longitudinal axis of the hull refers to the direction pointing to the bow, which determines the front and rear direction of the ship, that is, the heading of the ship) and perpendicular to the bottom plane. In the specific operation, we use the designated station as the segmentation position, with the stern on the left and the bow on the right, and intercept in the height direction at the draft position, and intercept the section perpendicular to the line connecting the bow and the stern as the cross-sectional view. Based on the cross-sectional lines formed by the intersection of these section planes with the hull of the three-dimensional geometric ship type, a two-dimensional plane view that integrates all the section plane information is constructed. Figure 2 As shown in the figure, in this two-dimensional plane, the area surrounded by every two adjacent cross-section lines is defined as a color block, and is colored according to the RGB (Red Green Blue) color mode to ensure that the colors of adjacent color blocks are significantly different. It is worth noting that the distinction between different ship models lies in the uniqueness of their color distribution. Dividing the color blocks by conventional cross-section station lines is friendly to ship designers, and pictures can be obtained from the type value table, reducing extra work. The color distribution corresponding to the color profiles of different three-dimensional geometric ship types is different, and the color changes are clearly distinguished. In this way, different ship types will have obvious distinguishing features, which is conducive to deep learning feature extraction, thereby making the training speed of the ship performance evaluation model faster and more convergent. To ensure consistency, the segmentation method of each ship is consistent, and the generated color pictures are also unified in parameters such as format, size, and coverage. Another advantage of representing by cross-section is that during deep learning, the picture does not need to be scaled or the scaling is small in both width and height directions, maintaining the relative relationship between the various parts of the ship type features. A non-parametric expression of ship type was established based on the cross-section of the ship type, and a general representation method of the ship type was constructed as sample data, which can comprehensively characterize the various performance characteristics of the ship, solving the problem of data resource waste caused by the different construction parameters of different ship types in the traditional method, and the past sample data sets cannot be applied to the analysis of new ships. Experienced ship designers can analyze the resistance performance from the characteristics of the cross-section. Deep learning based on the cross-section can provide ship design with a distinction ability similar to human experience, assisting designers to use experience or optimization algorithms to optimize resistance performance and improve the efficiency of ship optimization.

[0049] Preferably, the preset number of stations may be 8 stations, 10 stations, 12 stations, etc.

[0050] Second, the neural network training model step: label the ship hydrostatic data and ship resistance data corresponding to each of the three-dimensional geometric ship types; then normalize and standardize the ship type color profile and the labeled data, and then use the ship type color profile as input, ship hydrostatic data and ship resistance data as output, and obtain a ship performance evaluation model through neural network training. This step involves label data and deep learning training.

[0051] Preferably, the embodiments of the present application can use professional software (such as MAXSURF or MATLAB, etc.) or self-programming methods to determine the hydrostatic data of different ships (including displacement volume, center of buoyancy position, etc.).

[0052] Preferably, the embodiment of the present application can determine the ship resistance data (including resistance value or resistance coefficient) by using experiments, computational fluid dynamics (CFD) method or potential flow method.

[0053] The embodiment of the present application marks the ship hydrostatic data and ship resistance data corresponding to each three-dimensional geometric ship type, which are used to verify the results output during the model training process, thereby ensuring the diversity and accuracy of the output.

[0054] like Figure 3 As shown, the embodiment of the present application can use deep learning frameworks such as Pytorch to build a convolutional neural network, and can use convolutional neural networks such as VGG16 (Visual Geometry Group-16). Among them, the neural network includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. VGG16 has 16 layers of depth (13 convolutional layers and 3 fully connected layers). It provides a strong image feature extraction capability by stacking small convolution kernels (3x3), which is particularly suitable for image classification tasks.

[0055] This embodiment uses deep learning technology to construct a proxy model of ship type and ship hydrostatic and resistance characteristics. This model can not only accurately predict the resistance performance of various ship types, but also comprehensively evaluate multiple hydrostatic parameters including displacement volume, center of buoyancy position, drift center, stability, etc. Compared with traditional methods, it provides more detailed output information and fully reflects the various performance indicators of the ship. In actual engineering applications, ship performance optimization needs to comprehensively consider hydrostatic requirements, such as displacement volume is directly related to loading capacity, center of buoyancy position affects the internal layout of the hull, and stability is the cornerstone of navigation safety, and all of these need to be achieved under the premise of ensuring optimal resistance. In the past, hydrostatic calculations involved cumbersome processes or relied on professional software, and were separated from resistance evaluation, which was labor-intensive and required teamwork. Given that the hydrostatic force and resistance of a ship are both directly affected by the lines, this solution integrates the line image with multiple performance evaluations through deep learning, achieving a significant simplification of the workflow and more in line with actual engineering application needs.

[0056] 3. Model calculation of hydrostatic force and resistance steps: The ship to be evaluated is converted into a corresponding new ship type image, and the new ship type image is input into the trained ship performance evaluation model. After the model calculation, the corresponding ship hydrostatic force data and ship resistance data are output.

[0057] Preferably, in order to evaluate the performance of a new ship, a pictorial representation of its lines is required, which can be achieved in a variety of ways: using 3D modeling software to process the curved surface of the ship to generate a picture; or using a programming language such as Python to write a program to draw a 2D picture; or using image processing software to directly obtain it, etc.

[0058] 4. Judgment and optimization steps: The ship hydrostatic data and ship resistance data calculated and output by the model are compared with their respective predetermined parameters to determine whether they meet the requirements. If the requirements are not met, the ship hydrostatic data and ship resistance data calculated and output by the model are converted into a variable in a weighted manner, and the variable is optimized with corresponding hydrostatic constraints using a genetic algorithm (optimization algorithm) to obtain an optimized new ship type image; the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the output ship hydrostatic data and ship resistance data are compared and judged again, and the judgment and optimization are continuously cycled until the requirements are met, and the optimized ship type is output to achieve resistance optimization under hydrostatic constraints.

[0059] This step adopts an optimization method with constraints, combined with the hydrostatic force and resistance of the ship type calculated by the neural network proxy model (ship performance evaluation model), and finally obtains a ship type image that meets the corresponding hydrostatic force requirements.

[0060] Preferably, the optimization algorithm of this step can further use a simulated annealing algorithm and / or a particle swarm algorithm to optimize the corresponding hydrostatic constraints of the converted variables, and combine the ship performance evaluation model to evaluate and screen the optimized ship type.

[0061] The embodiment of the present application relies on the model framework and combines the optimization method to conveniently realize the optimization of ship types with constraints, ensuring that the ship meets the actual use requirements such as the minimum hydrostatic limit. The hydrostatic limit can be that the displacement cannot be less than a fixed value, otherwise the ship cannot load enough cargo. The ship type is presented in the form of pictures, which is convenient for diversified collection and processing. Through the combination of proxy models and optimization technology, many design schemes can be quickly evaluated. The optimization process can draw on manual experience, and can also use advanced algorithms such as simulated annealing and particle swarms. This solution can efficiently evaluate and screen out the optimal ship type in a short time, significantly improving work efficiency.

[0062] Preferably, the embodiment of the present application can convert the optimized ship type image into a three-dimensional geometric surface in different ways according to the method of generating the new ship image. If the new ship image comes from three-dimensional geometry, the corresponding three-dimensional geometry can be directly used; if the new ship image comes from a two-dimensional image drawing, it is necessary to reconstruct the three-dimensional ship type in the three-dimensional geometric modeling software based on the corresponding image.

[0063] For example, a cruise ship is taken as an example to carry out optimization of ship resistance. The initial main dimensions of the cruise ship are shown in the following table:

[0064]

[0065] The target variable for optimization is the resistance of 22kn under the design draft, while satisfying the hydrostatic limit of displacement volume and center of buoyancy position within 0.5%. Using the three-dimensional modeling software, the initial parameters of the ship are used as the basic data, and any data in the initial parameters is randomly adjusted to model 100 different three-dimensional geometric ship types. For all three-dimensional geometric ship types, the corresponding color profiles of each three-dimensional geometric ship type are generated. The displacement volume and center of buoyancy position of each three-dimensional geometric ship type are calculated using Rhino software, and the resistance value of each three-dimensional geometric ship type is calculated by CFD method. After normalizing and standardizing each color profile and its corresponding displacement volume, center of buoyancy position and resistance value, each color profile is used as input to output three data of displacement volume, center of buoyancy position and resistance, and the ship performance evaluation model is trained to convergence (training VGG16 convolutional neural network). The trained network realizes the fitting function, recognizes the ship type image (color profile) and gives the corresponding displacement volume, center of buoyancy position and resistance. The test set verified that the calculation error of the displacement volume and the center of buoyancy position is within ±0.5%, and the calculation error of the resistance value is within ±2%.

[0066] The displacement, center of buoyancy and resistance that need to be met are converted into a variable in a weighted manner, and a genetic algorithm is used to optimize this variable. The specific process is as follows: 200 different three-dimensional geometric ship types are randomly generated as the first generation population by parametric modeling, and a color profile corresponding to each three-dimensional geometric ship type is generated. The ship performance evaluation model then calculates the displacement, center of buoyancy, and resistance corresponding to the color profile, converts the three outputs into one data, and the genetic algorithm is used to evaluate and generate the parameter values ​​of the next generation of control ship type, and repeats the above process. After 20 generations of screening, the ship type parameters reached a stable state, and a combination of ship type parameters that met the requirements was obtained. At this time, the displacement volume is reduced by 0.03% compared to the prototype, and the center of buoyancy is shifted back by 0.14% compared to the prototype. Numerical simulation verifies that the effective power of the optimized ship type is reduced by 2.6%, and the waveform is significantly improved (such as Figure 4 As shown in the figure, the upper part is the waveform of the prototype, and the lower part is the optimized waveform), which realizes the optimization of resistance under hydrostatic limitation conditions.

[0067] The above embodiment is described based on the ship hydrostatic data including displacement data and center of buoyancy position data, which is not the only limitation. The ship hydrostatic data can also include other content, and the specific model training, model calculation output, constraint condition setting, and ship type optimization will all change accordingly.

[0068] For example, in the neural network training model step, the ship hydrostatic data involved in the annotation and neural network training of the ship performance evaluation model include displacement data, center of buoyancy position data, drift center position data and stability data; the model calculates hydrostatic force and resistance step outputs the corresponding displacement data, center of buoyancy position data, drift center position data, stability data and ship resistance data; the judgment and optimization step compares the displacement data, center of buoyancy position data, drift center position data, stability data and ship resistance data with their respective predetermined parameters to determine whether the requirements are met. If the requirements are not met, the displacement data, center of buoyancy position data, drift center position data, stability data and ship resistance data calculated by the model are compared. The data, center of buoyancy position data, stability data and ship resistance data are converted into a variable in a weighted manner, and the genetic algorithm is used to optimize the variable with respect to the loading capacity constraints, the internal layout constraints of the hull and the navigation safety constraints, so as to obtain the optimized new ship type image; and the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the output displacement data, center of buoyancy position data, center of buoyancy position data, stability data and ship resistance data are compared and judged with their respective predetermined parameters again, and the judgment and optimization are continuously circulated until the requirements are met, and the optimized ship type is output to realize the resistance optimization under several hydrostatic constraints.

[0069] Based on the same inventive concept, one or more embodiments of the present specification also provide a neural network-based ship performance evaluation and optimization system. Since the principles of the problems solved by the neural network-based ship performance evaluation and optimization system are similar to the aforementioned neural network-based ship performance evaluation and optimization method, the implementation of the neural network-based ship performance evaluation and optimization system can refer to the aforementioned implementation of the neural network-based ship performance evaluation and optimization method, and the repeated parts will not be repeated.

[0070] Figure 5 This is a block diagram of a neural network-based ship performance evaluation and optimization system provided in one or more embodiments of this specification. Figure 5 As shown, the neural network-based ship performance evaluation and optimization system includes: an image generation module 101, a neural network training module 102, a ship hydrostatic data and ship resistance data evaluation module 103 and a ship type optimization module 104.

[0071] in,

[0072] The image generation module 101 is used to generate a plurality of different three-dimensional geometric ship shapes using three-dimensional modeling technology, intercept a plurality of cross-sectional views of each three-dimensional geometric ship shape, and use the cross-sectional lines in each cross-sectional view to generate a plan view, and express the area enclosed by each cross-sectional line with different colors to obtain a color cross-sectional view of the ship shape corresponding to each three-dimensional geometric ship shape.

[0073] The neural network training module 102 is used to label the ship hydrostatic data and ship resistance data corresponding to each three-dimensional geometric ship type; then the ship type color profile and the labeled data are normalized and standardized, and then the ship type color profile is used as input, and the ship hydrostatic data and ship resistance data are used as output, and a ship performance evaluation model is obtained through neural network training.

[0074] The ship hydrostatic data and ship resistance data evaluation module 103 is used to convert the ship to be evaluated into a corresponding new ship type image, and input the new ship type image into the trained ship performance evaluation model. After the model calculation, the corresponding ship hydrostatic data and ship resistance data are output.

[0075] The ship type optimization module 104 is used to compare the ship hydrostatic data and ship resistance data calculated and output by the model with their respective predetermined parameters to determine whether the requirements are met. If the requirements are not met, the ship hydrostatic data and ship resistance data calculated and output by the model are converted into a variable in a weighted manner, and the variable is optimized with corresponding hydrostatic constraints using a genetic algorithm to obtain an optimized new ship type image; and the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the ship hydrostatic data and ship resistance data are output for comparison and judgment again, and the judgment and optimization are continuously cycled until the requirements are met, and the optimized ship type is output to achieve resistance optimization under hydrostatic constraints.

[0076] Furthermore, the ship hydrostatic data involved in the neural network training module marking and training the ship performance evaluation model through the neural network include displacement data and center of buoyancy position data; the ship hydrostatic data and ship resistance data evaluation module outputs the corresponding displacement data, center of buoyancy position data and ship resistance data; the ship type optimization module compares the displacement data, center of buoyancy position data and ship resistance data with their respective predetermined parameters to determine whether the requirements are met. If the requirements are not met, the displacement data, center of buoyancy position data and ship resistance data output by the model calculation are converted into a variable in a weighted manner, and a genetic algorithm is used to optimize the variable with respect to the loading capacity constraint conditions and the hull internal layout constraint conditions to obtain an optimized new ship type image; and the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the output displacement data, center of buoyancy position data and ship resistance data are compared and judged with their respective predetermined parameters again, and the judgment and optimization are continuously cycled until the requirements are met, and the optimized ship type is output to achieve resistance optimization under several hydrostatic constraint conditions.

[0077] Furthermore, in the ship type optimization module, in addition to the genetic algorithm, a simulated annealing algorithm and / or a particle swarm algorithm are also used to optimize the corresponding hydrostatic constraints of the converted variables, and the ship performance evaluation model is combined to evaluate and screen the optimized ship type.

[0078] It should be noted that the above-described specific implementations can enable those skilled in the art to more fully understand the invention, but do not limit the invention in any way. Therefore, although this specification has described the invention in detail with reference to the drawings and embodiments, those skilled in the art should understand that the invention can still be modified or replaced by equivalents. In short, all technical solutions and improvements that do not deviate from the spirit and scope of the invention should be included in the protection scope of the patent for the invention.

Claims

1. A ship performance evaluation and optimization method based on neural network, characterized in that: The steps include: Ship type image generation step: using 3D modeling technology to generate multiple different 3D geometric ship types, intercepting multiple cross-sectional views of each of the 3D geometric ship types, and using the cross-sectional lines in each of the cross-sectional views to generate a plan view, and expressing the areas surrounded by each of the cross-sectional lines in different colors to obtain color cross-sectional views of the ship type corresponding to each of the 3D geometric ship types; The neural network training model step includes: marking the ship hydrostatic data and ship resistance data corresponding to each of the three-dimensional geometric ship types; then normalizing and standardizing the ship type color profile and the marked data, and then using the ship type color profile as input, the ship hydrostatic data and the ship resistance data as output, and obtaining a ship performance evaluation model through neural network training; The model calculates hydrostatic force and resistance steps: converting the ship to be evaluated into a corresponding new ship type image, and inputting the new ship type image into the trained ship performance evaluation model, and outputting the corresponding ship hydrostatic force data and ship resistance data after model calculation; Judgment and optimization steps: The ship hydrostatic data and ship resistance data calculated and output by the model are compared with their respective predetermined parameters to determine whether they meet the requirements. If the requirements are not met, the ship hydrostatic data and ship resistance data calculated and output by the model are converted into a variable in a weighted manner, and the variable is optimized with corresponding hydrostatic constraints using a genetic algorithm to obtain an optimized new ship type image; the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the output ship hydrostatic data and ship resistance data are compared and judged again, and the judgment and optimization are continuously cycled until the requirements are met, and the optimized ship type is output to achieve resistance optimization under hydrostatic constraints.

2. The method according to claim 1, characterized in that In the neural network training model step, the ship hydrostatic data involved in the annotation and neural network training of the ship performance evaluation model include displacement data and buoyancy center position data; the model calculates hydrostatic force and resistance step outputs the corresponding displacement data, buoyancy center position data and ship resistance data; the judgment and optimization step compares the displacement data, buoyancy center position data and ship resistance data with their respective predetermined parameters to judge whether the requirements are met. If the requirements are not met, the displacement data, buoyancy center position data and ship resistance data output by the model calculation are converted into a variable in a weighted manner, and the variable is optimized by using a genetic algorithm to optimize the loading capacity constraint conditions and the hull internal layout constraint conditions to obtain an optimized new ship type picture; and the optimized new ship type picture is input into the ship performance evaluation model again for model calculation, and the displacement data, buoyancy center position data and ship resistance data are output for comparison and judgment again, and the judgment and optimization are continuously cycled until the requirements are met, and the optimized ship type is output to achieve resistance optimization under several hydrostatic constraint conditions.

3. The method according to claim 1, characterized in that In the neural network training model step, the ship hydrostatic data involved in the annotation and neural network training of the ship performance evaluation model include displacement data, buoyancy center position data, drift center position data and stability data; the model calculates hydrostatic force and resistance step outputs the corresponding displacement data, buoyancy center position data, drift center position data, stability data and ship resistance data; the judgment and optimization step compares the displacement data, buoyancy center position data, drift center position data, stability data and ship resistance data with their respective predetermined parameters to judge whether the requirements are met. If the requirements are not met, the displacement data, buoyancy center position data, drift center position data, stability data and ship resistance data calculated by the model are compared. The center position data, drift center position data, stability data and ship resistance data are converted into a variable in a weighted manner, and the genetic algorithm is used to optimize the variable with respect to the loading capacity constraints, the hull internal layout constraints and the navigation safety constraints, so as to obtain the optimized new ship type image; and the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the displacement data, buoyancy center position data, drift center position data, stability data and ship resistance data are output for comparison and judgment again, and the judgment and optimization are continuously circulated until the requirements are met, and the optimized ship type is output to realize the resistance optimization under several hydrostatic constraints.

4. The method according to any one of claims 1 to 3, characterized in that In the ship type image forming step, the color profiles of different three-dimensional geometric ship types have the same size and image format, and the color profiles adopt a red, green, and blue (RGB) color mode.

5. The method according to any one of claims 1 to 3, characterized in that In the ship type image forming step, a method of intercepting a plurality of cross-sectional views of each of the three-dimensional geometric ship types and generating a plan view using the cross-sectional lines in each of the cross-sectional views comprises: Take the designated station as the dividing position, the height to the waterline of the ship, and cut the section perpendicular to the line connecting the bow and the stern as the cross-sectional view; The cross-section lines in each cross-section view are intercepted to generate a plan view with the left side as the stern direction and the right side as the bow direction.

6. The method according to any one of claims 1 to 3, characterized in that In the neural network training model step, the ship hydrostatic data and ship resistance data corresponding to each of the three-dimensional geometric ship types are marked, including: Determine the hydrostatic data of the ship corresponding to each of the three-dimensional geometric ship types by using professional software or a self-programming method; Determine the ship resistance data corresponding to each of the three-dimensional geometric ship types by using experiments, computational fluid dynamics methods or potential flow methods; The ship hydrostatic data and ship resistance data corresponding to each of the three-dimensional geometric ship types are marked.

7. The method according to any one of claims 1 to 3, characterized in that In the judgment and optimization steps, in addition to the genetic algorithm, the simulated annealing algorithm and / or the particle swarm algorithm are also used to optimize the corresponding hydrostatic constraints of the converted variables, and the ship performance evaluation model is combined to evaluate and screen the optimized ship type.

8. A ship performance evaluation and optimization system based on neural network, characterized in that: It includes a picture generation module, a neural network training module, a ship hydrostatic data and ship resistance data evaluation module, and a ship type optimization module connected in sequence; among them, The image generation module is used to generate a plurality of different three-dimensional geometric ship shapes by using three-dimensional modeling technology, intercept a plurality of cross-sectional views of each of the three-dimensional geometric ship shapes, and generate a plan view using the cross-sectional lines in each of the cross-sectional views, and express the areas surrounded by each of the cross-sectional lines in different colors to obtain color cross-sectional views of the ship shapes corresponding to each of the three-dimensional geometric ship shapes; The neural network training module is used to annotate the ship hydrostatic data and ship resistance data corresponding to each of the three-dimensional geometric ship types; then the ship type color profile and the annotated data are normalized and standardized, and then the ship type color profile is used as input, and the ship hydrostatic data and ship resistance data are used as output, and a ship performance evaluation model is obtained through neural network training; The ship hydrostatic data and ship resistance data evaluation module is used to convert the ship to be evaluated into a corresponding new ship type image, and input the new ship type image into the trained ship performance evaluation model, and the model outputs the corresponding ship hydrostatic data and ship resistance data after calculation; The ship type optimization module is used to compare the ship hydrostatic data and ship resistance data output by the model calculation with their respective predetermined parameters to determine whether the requirements are met. If the requirements are not met, the ship hydrostatic data and ship resistance data output by the model calculation are converted into a variable in a weighted manner, and a genetic algorithm is used to optimize the variable with corresponding hydrostatic constraints to obtain an optimized new ship type image; and the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the ship hydrostatic data and ship resistance data are output for comparison and judgment again, and the judgment and optimization are continuously cycled until the requirements are met, and the optimized ship type is output to achieve resistance optimization under hydrostatic constraints.

9. The system according to claim 8, characterized in that The ship hydrostatic data involved in the neural network training module and the neural network training of the ship performance evaluation model include displacement data and buoyancy center position data; the ship hydrostatic data and ship resistance data evaluation module outputs the corresponding displacement data, buoyancy center position data and ship resistance data; the ship type optimization module compares the displacement data, buoyancy center position data and ship resistance data with their respective predetermined parameters to determine whether the requirements are met. If the requirements are not met, the displacement data, buoyancy center position data and ship resistance data output by the model calculation are converted into a variable in a weighted manner, and the genetic algorithm is used to optimize the variable for loading capacity constraints and hull internal layout constraints to obtain an optimized new ship type image; and the optimized new ship type image is input into the ship performance evaluation model again for model calculation, and the displacement data, buoyancy center position data and ship resistance data are output for comparison and judgment again, and the judgment and optimization are continuously circulated until the requirements are met, and the optimized ship type is output to achieve resistance optimization under several hydrostatic constraints.

10. The system according to claim 8 or 9, characterized in that In the ship type optimization module, in addition to the genetic algorithm, the simulated annealing algorithm and / or the particle swarm algorithm are also used to optimize the corresponding hydrostatic constraints of the converted variables, and the ship performance evaluation model is combined to evaluate and screen the optimized ship type.

Images