Knowledge-driven ship body molded line intelligent design platform and method

Abstract

The invention belongs to but not limited to the technical field of hull profile intelligent design, and discloses a knowledge-driven hull profile intelligent design platform and method.A user layer is used for inputting main element requirements of a design ship and main features of the design ship by a user; the application layer is used for retrieving a similar initial ship type in a mother type library according to the design requirements of a user, and then obtaining ship type characteristic parameters with excellent resistance performance by using a molded line knowledge reasoning model; then parameterized geometric modeling software CAESES is integrated, and a three-dimensional geometric model of the ship body curved surface is generated through a parameterized design module; and the knowledge base layer is used for reasonably and effectively acquiring, representing, classifying and managing expert experience, real ship design data, optimized simulation data, ship design principles and standard knowledge, and establishing a ship body molded line design knowledge base by taking total resistance performance as a key concern object. According to the method, the reasoning molded line scheme meeting the design requirement can be quickly generated, and the method has important engineering application value.

Description

Technical Field

[0001] The present invention belongs to, but is not limited to, the technical field of intelligent design of hull lines, and in particular relates to a knowledge-driven intelligent design platform and method for hull lines. Background Art

[0002] The hull lines determine the navigation performance of the ship and are one of the most important aspects of the overall ship design. With the development of computer technology, intelligent optimization methods for ship forms based on computational fluid dynamics (CFD) have become an important research direction for line design. Feng Baiwei et al. combined simulation-based design technology (SBD) to propose a multi-objective optimization platform for ship forms. The platform integrates CFD numerical simulation technology, hull geometry reconstruction technology, optimization technology, approximation technology, etc., and used this platform to conduct line optimization research on various types of ship forms. Tran et al. used cubic spline interpolation functions to realize the Lackenby deformation of the hull shape, and optimized the hull form of a fishing boat based on CFD, Kriging proxy model and optimization technology, achieving a total resistance reduction of about 8.8%. Kim et al. selected 29 parameter variables to perform a parametric geometric description of a small ship, and combined deep neural network models and genetic algorithms to obtain the optimal hull shape.

[0003] In recent years, the rapid development of artificial intelligence has opened up new directions in the design field. AI requires a vast amount of knowledge for reasoning and decision-making, with knowledge engineering technology being a key focus. In the shipbuilding sector, research on knowledge engineering technology currently focuses on determining primary ship dimensions, structural design, and layout design. Yang Shaoming applied knowledge engineering technology to solve the multi-deck cabin layout problem, using generative and object-oriented representations to represent the knowledge of ship accommodation layouts and completing knowledge reasoning based on cabin layout reasoning strategies. Cui et al. applied design rule methods and interpolation techniques to the design of container ship cargo hold structures, drawing on previous successful cases to guide the design of new ship structures. Zhao Tongming established a database of actual ship cases and a rule library containing design specifications and expert knowledge. Based on multiple reasoning algorithms, he achieved automated and intelligent generation of prototype ship type selection and design solutions. In the field of hull line design, some researchers have studied the implicit relationship between line parameters and ship performance, thereby obtaining design knowledge for hull lines. Zhang Jianyi et al. constructed a knowledge graph of the lines of upright bow and twin skeg bulk carriers in the middle and lower reaches of the Yangtze River, which reflects the variation patterns of different line parameters for this ship type under different block coefficients and scale ratios. Ye Meng et al. used rough set theory to mine KCS container ship optimization simulation data, identifying implicit design rules between ship design variables and wave resistance. Zheng et al. extracted design knowledge from twin-skeg ship optimization data using sensitivity analysis and self-organizing map neural networks, analyzing the implicit relationships between variables and between variables and the objective function.

[0004] In view of the above analysis, the technical problems that urgently need to be solved in the existing technology are: in the field of ships, the research on knowledge engineering technology is currently mainly focused on the determination of the main dimensions of ships, structural design and layout design. Summary of the Invention

[0005] In response to the problems existing in the prior art, the present invention provides a knowledge-driven intelligent design platform and method for hull lines.

[0006] The present invention is implemented as follows: a knowledge-driven intelligent design platform for hull lines includes a user layer, an application layer, and a knowledge base layer, and each layer can carry out two-way transmission of data, information, and knowledge;

[0007] The user layer is used for users to input the main elements of the ship design requirements, including the length between perpendiculars L, the width B, the draft T, and the square coefficient C B 、Froude number F r , and the main characteristics of the designed ship, including ship type, bow and stern type, design speed, etc.;

[0008] The application layer is used to first search for similar initial ship forms in the prototype library based on the user's design requirements. It then uses the line knowledge inference model to further obtain the characteristic parameters of the ship form with excellent resistance performance. It then integrates the parametric geometry modeling software CAESES and uses the parametric design module to generate a 3D geometric model of the hull surface.

[0009] The knowledge base layer is used to reasonably and effectively acquire, represent, classify and manage expert experience, actual ship design data, optimization simulation data, ship design principles, specifications and other knowledge, focusing on the total resistance performance and establishing a hull line design knowledge base.

[0010] Furthermore, the line design knowledge base includes a line knowledge graph, a master instance library, and a design rule library;

[0011] The line knowledge map is a curve showing the variation of several line parameters (longitudinal position of the center of buoyancy, inner tail fin hypertrophy, tail axis spacing ratio, bow width contraction ratio) with the scale ratio L / B and B / T under different square coefficients;

[0012] The ship characteristic attributes used in the parent instance library include ship number, ship name, ship type, bow shape, stern shape, length between perpendiculars, aspect ratio, breadth-to-draft ratio, squareness coefficient, and design speed. The structural attributes corresponding to each instance are composed of the instance's parametric geometric model, applicable line knowledge graph type, and applicable design rule library type.

[0013] The line design rule library includes cross-sectional area curve class, design waterline class, bow shape and tail shape.

[0014] Furthermore, the important parameters for constructing the geometric model mainly include: (1) global geometric characteristic parameters: parallel mid-body length ratio, inflow section length ratio, outflow section length ratio, longitudinal position of the center of buoyancy, etc.; (2) local geometric characteristic parameters: design waterline inflow angle and outflow angle, bulbous bow parameters, tail fin parameters, etc.

[0015] Furthermore, the construction method of the line knowledge reasoning model includes:

[0016] (1) According to the input design ship requirements, similar ship type instances are retrieved from the parent type instance library, and the line geometry parameters that need to be inferred are determined based on the parametric model of the similar ship type; according to the graph type and design rule library type applicable to the similar ship type, the design ship is matched with the line knowledge graph and design rule library.

[0017] (2) Model reasoning and rule reasoning are used on the corresponding line knowledge graph and design rule base respectively to obtain the global geometric characteristic parameter value or value range of the line to control the global line shape of the hull.

[0018] (3) Obtain the value or value range of the local geometric characteristic parameter of the line, control the local line shape of the hull, and combine it with the global geometric characteristic parameters to form the line parameter scheme of the designed ship.

[0019] Furthermore, the parent instance library knowledge reasoning:

[0020] The commonly used Nearest Neighbor Search (NNS) method is selected to retrieve the parent ship instance; the weighted Euclidean distance formula is selected, which is expressed as:

[0021]

[0022] Where: x i is the i-th characteristic attribute of the design case; y i is the i-th characteristic attribute of the existing case in the database; n is the number of types of characteristic attributes; w i is the weight of the i-th feature attribute.

[0023] Assuming that the influence of each feature attribute on similarity is 1 / n, the similarity between instances is calculated according to the similarity formula. The similarity formula is:

[0024]

[0025] Further, the line knowledge graph reasoning:

[0026] Using the gridded dataset of the profile knowledge graph, and according to the profile parameter variation rules reflected in the knowledge graph, a step-by-step interpolation reasoning model for the profile parameters with respect to CB, L / B, and B / T is established. The profile parameter values ​​under the actual CB, L / B, and B / T are obtained based on the profile curve reasoning. The interpolation formula is shown below:

[0027]

[0028] The process of the inference model is as follows:

[0029] 1) Select two adjacent C B (C B1 and C B2 ):To C B1 First, determine the actual B / T and L / B of the ship based on the main scale elements given by the user, select two adjacent L / B in the line knowledge graph, and interpolate to obtain two sets of parameter values: X skeg1* and X skeg2* ;

[0030] 2) Then interpolate the parameter value X corresponding to the square coefficient based on the actual L / B value skeg3 ;

[0031] 3) Similarly for C B2 The parameter value X is obtained based on the actual L / B interpolation skeg4 ;

[0032] 4) Finally, according to X skeg3 and X skeg4 Interpolation to get the actual X skeg .

[0033] Furthermore, we design rule base knowledge reasoning:

[0034] Rule reasoning is used to match problems based on production rules. The basic process is: according to the design parameters input by the user, the rules stored in the rule base are conditionally judged one by one in order. If the rule is met, the conclusion of the rule is output. If it is not met, the rule is skipped until all rules are judged.

[0035] Another object of the present invention is to provide a knowledge-driven hull line intelligent design method based on a knowledge-driven hull line intelligent design platform, comprising the following steps:

[0036] Step 1: The user inputs the main elements of the ship design requirements, including the length between perpendiculars L, the width B, the draft T, and the square coefficient C. B 、Froude number F r , and the main characteristics of the designed ship, including ship type, bow and stern type, design speed, etc.;

[0037] In step 2, based on the user's design requirements, similar initial ship forms are first retrieved from the prototype library. The line knowledge inference model is then used to further determine the characteristic parameters of the ship form with excellent resistance performance. The parametric design module of CAESES, a parametric geometry modeling software, is then integrated to generate a 3D geometric model of the hull surface.

[0038] Step three is to reasonably and effectively acquire, represent, classify and manage expert experience, actual ship design data, optimization simulation data, ship design principles, specifications and other knowledge, focus on total resistance performance, and establish a hull line design knowledge base.

[0039] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the knowledge-driven intelligent design method for hull lines.

[0040] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0041] First, this paper proposes a knowledge-driven intelligent design framework for hull lines, which mainly includes three main components: the user layer, the application layer, and the knowledge base. A knowledge base suitable for line design is constructed to store instance-based knowledge, line knowledge graphs, and rule-based knowledge. Multiple reasoning methods are used to reason about line geometry parameters. Finally, a verification study is conducted using the line design of a 13,000-ton bulk carrier on the Yangtze River as an example. First, similar cases are retrieved from the parent case library to determine the applicable parameterized model, line knowledge graph type, and design rule library type. Second, the line knowledge graph model and design rule library are used to infer the global and local geometric feature parameters of the design ship, and a reasoned ship form is generated. Finally, CFD is used to verify that the reasoned ship form has good resistance performance. This demonstrates that the knowledge-driven intelligent design method for hull lines can quickly generate a reasoned line scheme that meets design requirements and has important engineering application value.

[0042] Second, by employing this technology, the design cycle for hull lines can be shortened from several weeks to just a few minutes. This significantly improves design efficiency and saves significant man-hours while ensuring the quality of the hull line design. This invention is widely applicable to various ship design and R&D organizations and has significant commercial value.

[0043] This invention differs from traditional line design methods, which rely on expert experience or tank testing to determine the optimal solution. This is not only time-consuming but also not necessarily optimal. This invention proposes knowledge-driven 3D design of hull surfaces. By establishing a hull line knowledge base, this approach enables knowledge-guided intelligent design, filling a technological gap in this field.

[0044] For years, people have hoped to use artificial intelligence to design hull lines, completely eliminating the tedious manual process. However, due to the inability to mathematically describe hull surfaces using geometric features, this field has eluded significant breakthroughs. This invention not only solves the problem of parametric expression of hull surfaces based on geometric feature parameters, but also breaks through the rapid design method of geometric feature parameters, truly achieving automated and intelligent hull line design, which is a revolutionary advancement in hull line design. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a knowledge-driven intelligent design framework diagram for hull lines provided by an embodiment of the present invention;

[0046] Figure 2 This is a structural diagram of a profile knowledge base provided by an embodiment of the present invention;

[0047] Figure 3 It is a parameter curve diagram of the profile knowledge graph provided by an embodiment of the present invention;

[0048] Figure 4 This is a framework diagram of a design rule library provided by an embodiment of the present invention;

[0049] Figure 5 is a structural diagram of the reasoning model provided by an embodiment of the present invention;

[0050] Figure 6 This is a model diagram of the line knowledge graph reasoning provided by an embodiment of the present invention;

[0051] Figure 7 is a rule reasoning flow chart provided by an embodiment of the present invention;

[0052] Figure 8 This is a flow chart of the application of the intelligent design method for mold lines provided by an embodiment of the present invention;

[0053] Figure 9 This is the inference ship geometry model of the Yangtze River 13,000-ton bulk carrier provided by an embodiment of the present invention; (a) stern front view; (b) side view; (c) bottom bottom view;

[0054] Figure 10 is a grid distribution diagram provided by an embodiment of the present invention;

[0055] Figure 11 The embodiment of the present invention provides Figure 11 Comparison of the lines of the inferred ship type (red dashed line) and the initial ship type (black solid line); (a) transverse line comparison; (b) longitudinal line comparison; (c) waterline comparison;

[0056] Figure 12 1 is a comparison diagram of the hull surface pressure distribution diagram provided by the embodiment of the present invention; (a) the initial ship type hull surface pressure distribution; (b) the inferred ship type hull surface pressure distribution. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to examples. It should be understood that the specific examples described herein are only used to explain the present invention and are not intended to limit the present invention.

[0058] This paper, combining knowledge engineering techniques, establishes a knowledge base and hybrid reasoning model suitable for Yangtze River cargo ship line design, developing a knowledge-driven intelligent hull line design platform. Using a 13,000-ton bulk carrier on the Yangtze River as an example, the knowledge-driven hull line design process is discussed, and the resulting line scheme is validated.

[0059] like Figure 1 The knowledge-driven intelligent design platform for hull lines includes a user layer, an application layer, and a knowledge base layer, and each layer can carry out two-way transmission of data, information, and knowledge;

[0060] The user layer is used for users to input the main elements of the ship design requirements, including the length between perpendiculars L, the width B, the draft T, and the square coefficient C B 、Froude number F r , and the main characteristics of the designed ship, including ship type, bow and stern type, design speed, etc.;

[0061] The application layer is used to first search for similar initial ship forms in the prototype library based on the user's design requirements. It then uses the line knowledge inference model to further obtain the characteristic parameters of the ship form with excellent resistance performance. It then integrates the parametric geometry modeling software CAESES and uses the parametric design module to generate a 3D geometric model of the hull surface.

[0062] The knowledge base layer is used to reasonably and effectively acquire, represent, classify and manage expert experience, actual ship design data, optimization simulation data, ship design principles, specifications and other knowledge, focusing on the total resistance performance and establishing a hull line design knowledge base.

[0063] 1. Construction of the Line Knowledge Base

[0064] The knowledge base constructed by the present invention includes a line knowledge graph, a master instance library, and a design rule library. The knowledge base is the basis and core of subsequent knowledge reasoning. Figure 2 shown.

[0065] (1) This paper establishes an example library for Yangtze River cargo ship types and stores several parent ship design examples in the relational database MySQL. These design examples all use a parametric expression method and construct geometric models based on CAESES software. The important parameters for constructing the geometric model mainly include: (1) global geometric characteristic parameters: parallel mid-body length ratio, inflow section length ratio, outflow section length ratio, longitudinal position of the center of buoyancy, etc.; (2) local geometric characteristic parameters: design waterline inflow angle and outflow angle, bulbous bow parameters, tail fin parameters, etc.

[0066] The ship characteristic attributes used in the master instance library include ship number, ship name, ship type, bow, stern, length between perpendiculars, aspect ratio, breadth-to-draft ratio, block coefficient, and design speed. The structural attributes corresponding to each instance consist of the instance's parametric geometry model, applicable line knowledge graph type, and applicable design rule base type. SQL can then be used to search for similar instances based on these characteristic attributes to obtain the parametric geometry model and knowledge base type required for the design. The established master instance library is shown in Tables 1 and 2.

[0067] Table 1. Master type instance table (feature attributes)

[0068]

[0069] Table 2 Master instance table (structural attributes)

[0070]

[0071] (2) Line knowledge graph

[0072] The line knowledge graph is a curve showing the variation of several line parameters (longitudinal position of the center of buoyancy, inner fatness of the tail fin, tail axis spacing ratio, bow width contraction ratio) with the scale ratio L / B and B / T under different square coefficients. This curve reflects the mapping relationship between the geometric characteristic parameters of the line and the overall resistance performance. Some curves of the line knowledge graph are as follows: Figure 3 shown.

[0073] (3) Design rule library

[0074] The present invention establishes a rule library for line design based on the influence of line geometry parameters on ship resistance. Figure 4 shown.

[0075] Taking the description of the full-load waterline inflow angle as an example, the knowledge representation using production rules is shown in Table 3. In the table, CP is the prismatic coefficient of the designed ship, VS (kn) is the speed, LE (m) is the inflow section length, and Fr is the Froude number.

[0076] Table 3 Recommended range of full load waterline inflow angle

[0077]

[0078] For the range of values ​​of the full-load waterline inflow angle, the rule knowledge can be expressed as:

[0079] Rule 001: IF (CP > 0.78) THEN (30° < Inflow Angle < 40°)

[0080] Rule 002: IF (0.75 < CP < 0.78) AND (Fr < 0.182) THEN (26° < inlet angle < 28°)

[0081] …

[0082] 2. Model of Line Knowledge Reasoning

[0083] The present invention adopts case-based reasoning (CBR), model-based reasoning (MBR) and rule-based reasoning (RBR) for the master instance library, the line knowledge map and the design rule library respectively. Figure 5 As shown, it is mainly divided into the following three steps:

[0084] 1) Based on the input design ship requirements, similar ship type instances are retrieved from the parent type instance library. The line geometry parameters that need to be inferred are determined based on the parametric model of the similar ship type. Based on the graph type and design rule library type applicable to the similar ship type, the design ship is matched with the line knowledge graph and design rule library.

[0085] 2) Model reasoning and rule reasoning are used on the corresponding line knowledge graph and design rule base respectively to obtain the global geometric characteristic parameter value or value range of the line to control the global line shape of the hull.

[0086] 3) Obtain the local geometric characteristic parameter value or value range of the line, control the local line shape of the hull, and combine it with the global geometric characteristic parameters to form the line parameter scheme of the designed ship.

[0087] (1) Knowledge Reasoning of the Master Instance Database

[0088] This paper selects the commonly used Nearest Neighbor Search (NNS) method to retrieve parent ship instances. The core of the Nearest Neighbor Search method is to calculate the concept distance, assign weights, and calculate the similarity. This paper selects the weighted Euclidean distance formula, which is expressed as:

[0089]

[0090] Where: x i is the i-th characteristic attribute of the design case; y i is the i-th characteristic attribute of the existing case in the database; n is the number of types of characteristic attributes; w i is the weight of the i-th feature attribute.

[0091] Assuming that the influence of each feature attribute on similarity is 1 / n, the similarity between instances is calculated according to the similarity formula. The similarity formula is:

[0092]

[0093] (2) Line Knowledge Graph Reasoning:

[0094] Using the gridded dataset of the profile knowledge graph, and according to the profile parameter variation rules reflected in the knowledge graph, a step-by-step interpolation reasoning model for the profile parameters with respect to CB, L / B, and B / T is established. The profile parameter values ​​under the actual CB, L / B, and B / T are obtained based on the profile curve reasoning. The interpolation formula is shown below:

[0095]

[0096] The atlas parameter of the hypertrophy degree of the inner side of the tail fin is X skegFor example, the inference model is Figure 6 As shown, the main process is as follows:

[0097] 1) Select two adjacent C B (C B1 and C B2 ):To C B1 First, determine the actual B / T and L / B of the ship based on the main scale elements given by the user, select two adjacent L / B in the line knowledge graph, and interpolate to obtain two sets of parameter values: X skeg1* and X skeg2* ;

[0098] 2) Then interpolate the parameter value Xskeg3 corresponding to the square coefficient according to the actual L / B value;

[0099] 3) Similarly for C B2 The parameter value Xskeg4 is obtained based on the actual L / B interpolation;

[0100] 4) Finally, according to X skeg3 and X skeg4 Interpolation to get the actual X skeg .

[0101] (3) Design rule base knowledge reasoning

[0102] The design rule base reasoning adopts rule reasoning and matches problems based on production rules. The basic process is: according to the design parameters input by the user, the rules stored in the rule base are judged one by one in order. If the rule is satisfied, the conclusion of the rule is output. If it is not satisfied, the rule is skipped until all the rules are judged. The flowchart is as follows Figure 7 shown.

[0103] The specific reasoning process is as follows: the user inputs the initial conditions such as the main dimensions, square coefficient, and Froude number of the designed ship, and the computer matches the design rules of the geometric parameters in the library in turn. Taking the design rule of the full load waterline inflow angle as an example, if the C P 0.76, F r is 0.18, first match rule 001, if it does not meet its conditions (C P >0.78), discard; match rule 002, if it meets its conditions (0.75 < C P <0.78 and F r <0.182), then the conclusion of rule 002 is output (26°<inflow angle<28°), thus completing the reasoning of the geometric parameters of the profile. Figure 4 After similar matching is performed on all the geometric parameters of the profiles in the design rule library shown in FIG, the final reasoning result of the design rule library can be obtained.

[0104] Relevant evidence of the technical effects achieved by the examples of the present invention.

[0105] This paper takes the line design of a 13,000-ton bulk carrier on the Yangtze River as an example to illustrate the feasibility of the knowledge-driven intelligent design method for hull lines. Figure 8 shown.

[0106] 1. Hull line scheme generation

[0107] The 13,000-ton bulk carrier on the Yangtze River is a straight bow and twin stern ship type with L / B = 5.8257 and B / T = 3.9636. The main parameters of the ship are shown in Table 4.

[0108] Table 4 Main parameters of 13,000-ton bulk carriers on the Yangtze River

[0109]

[0110] The reasoning process is as follows:

[0111] 1) Based on the listed ship type characteristics and main elements, case-based reasoning was first performed to determine the applicable parametric model, line knowledge graph type, and design rule base type. The similarity of similar ship types in the case base is shown in Table 5. The ship type with the greatest similarity was selected. The straight bow and twin skeg cargo ship line knowledge graph was recommended, and the cargo ship rule base was selected as the design rule base.

[0112] Table 5. Similarity of ship types in the example library

[0113]

[0114] 2) Based on the knowledge graph of the straight bow and twin skeg cargo ship lines and the cargo ship design rule base, the input data are the main dimensions, squareness coefficient and Froude number of the designed ship, and the global geometric characteristic parameter values ​​or value ranges of the lines are obtained, as shown in Table 6.

[0115] Table 6 Global geometric feature parameters

[0116]

[0117]

[0118] 3) Obtain the local geometric characteristic parameter values ​​or value ranges of the profile, as shown in Table 7.

[0119] Table 7 Local geometric feature parameters

[0120]

[0121] 4) Taking into account the layout constraints proposed by the shipowner (such as tail shaft height, gearbox layout, etc.) and the deformation coupling of some parameters, some appropriate global and local geometric characteristic parameters are selected from Tables 6 and 7. Their parameter values ​​are the median values ​​of the value range. Combined with the main scale parameters, the parameterized hull line scheme is generated, as shown in Table 8.

[0122] Table 8 Parameterized ship type scheme

[0123]

[0124]

[0125] 2. Geometric model generation and resistance performance calculation

[0126] Substitute the parameterized hull line scheme into the parameterized geometric model obtained by case reasoning. The final generated geometric model is as follows Figure 9 shown.

[0127] The geometric models of the initial and inferred ship forms were scaled to a scale ratio of 1:25, and the total resistance at the model scale was calculated using the full viscous flow CFD calculation software STAR-CCM+. The front boundary of the calculation domain was set to 1.5 times the ship length, and the rear boundary was set to 2.5 times the ship length. The mesh was refined on the hull surface, around the hull, on the free surface, and at the Kelvin wave locations, while ensuring that the Y+ value of the hull surface was within the normal range. The final generated mesh volume was approximately 1.8 million. The mesh distribution diagram is shown below. Figure 10 The k-ε model is used as the turbulence model, and the time step is set to 0.02s. The total resistance numerical simulation of the initial ship type and the inferred ship type is carried out at the design speed of 18.5km / h.

[0128] 3. Comparative analysis of resistance performance of inferred ship types

[0129] The resistance calculation results and some hydrostatic data of the initial and theoretical ship forms of the Yangtze River 13,000-ton bulk carrier are compared in Table 9. The total resistance of the theoretical ship form model is 3.06% lower than that of the initial ship form model. Figure 11 is the comparison of the lines of the initial ship type and the inferred ship type, Figure 12 The comparison is for the hull surface pressure distribution diagram. From the data in the table, we can find that the displacement volume of the inferred ship type is slightly increased, but the wet surface area is reduced, which leads to a slight decrease in the friction resistance of the inferred ship type, but the decrease is not large. Therefore, the decrease in total resistance is mainly due to the change in residual resistance. Figure 12 It can be seen that for the pressure distribution at the bow, the area of ​​the high-pressure area of ​​the inferred ship type is smaller, and the absolute value of the low-pressure area at the bottom of the ship is not large. Therefore, the pressure difference at the bow of the inferred ship type is smaller, and the pressure distribution is more uniform. Similarly, for the pressure distribution at the stern, the pressure difference of the inferred ship type is also smaller, and the pressure distribution is more uniform.

[0130] Combining the inferred line geometry parameters and a comparison of the lines between the inferred and initial ship forms reveals significant differences between the bow and stern lines of the two ship forms. Due to the knowledge-based reasoning of bow parameters such as the height ratio at the minimum width of the invisible bulbous bow (inferred value 0.8), the cross-sectional area coefficient at the bow elevation (inferred value 0.345), the invisible bulbous bow curvature (inferred value 0.91), and the bow width contraction ratio (inferred value 0.9065), the indentation of the invisible bulbous bow in the deformed inferred ship form becomes more pronounced, the bow becomes thinner, and the bow cross-section becomes more U-shaped, which can reduce wave-making resistance. Similarly, for the stern, after reasoning about the tunnel inclination angle (inferred value 18), stern plate height ratio (inferred value 0.7), stern axis spacing ratio (inferred value 0.5225), inboard tail fin hypertrophy (inferred value 0.5709), and outboard tail fin hypertrophy (inferred value 0.7), the inferred stern cross-section of the ship model tends to be more V-shaped, which promotes water flow along the longitudinal section line and reduces separation, thus improving resistance performance. However, the initial ship model did not include targeted design of these hull parts and line geometry parameters (based on resistance performance), and its line design still has considerable room for optimization.

[0131] Table 9 Comparison of hydrostatic force and resistance results

[0132]

[0133] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with this technical field within the technical scope disclosed by the present invention and within the spirit and principles of the present invention should be covered by the scope of protection of the present invention.

Claims

1. A knowledge-driven intelligent design platform for hull lines, characterized by: It includes user layer, application layer and knowledge base layer, and each layer can carry out two-way transmission of data, information and knowledge; The user layer is used for users to input the main elements of the ship design requirements, including the length between perpendiculars L, the width B, the draft T, and the square coefficient C B 、Froude number F r , and the main characteristics of the designed ship, including ship type, bow and stern type, and design speed; The application layer is used to first search for similar initial ship types in the mother type library according to the user's design requirements, and then use the line knowledge reasoning model to obtain the characteristic parameters of the ship type with excellent resistance performance; The parametric geometry modeling software CAESES is then integrated to generate a 3D geometric model of the hull surface using the parametric design module. The knowledge base layer is used to reasonably and effectively acquire, represent, classify and manage expert experience, actual ship design data, optimization simulation data, ship design principles and regulatory knowledge, and establish a hull line design knowledge base with the total resistance performance as the focus.

2. The knowledge-driven hull line intelligent design platform according to claim 1, characterized in that: The line design knowledge base includes a line knowledge graph, a master example library, and a design rule library; The line knowledge graph is a curve showing the variation of several line parameters with the scale ratio L / B and B / T under different square coefficients. The line parameters include the longitudinal position of the center of buoyancy, the inner hypertrophy of the tail fin, the tail axis spacing ratio, and the bow width contraction ratio. The ship characteristic attributes used in the parent instance library include ship number, ship name, ship type, bow shape, stern shape, length between perpendiculars, aspect ratio, breadth-to-draft ratio, squareness coefficient, and design speed. The structural attributes corresponding to each instance are composed of the instance's parametric geometric model, applicable line knowledge graph type, and applicable design rule library type. The line design rule library includes cross-sectional area curve class, design waterline class, bow shape and tail shape.

3. The knowledge-driven hull line intelligent design platform according to claim 1, characterized in that: The important parameters for constructing the geometric model include: (1) global geometric characteristic parameters: parallel mid-body length ratio, inflow section length ratio, outflow section length ratio, and longitudinal position of the center of buoyancy; (2) local geometric characteristic parameters: design waterline inflow angle and outflow angle, bulbous bow parameters, and tail fin parameters.

4. The knowledge-driven hull line intelligent design platform according to claim 2, characterized in that: The construction method of the profile knowledge reasoning model includes: (1) According to the input design ship requirements, similar ship type instances are retrieved from the parent type instance library. The geometric parameters of the lines that need to be inferred are determined based on the parametric model of the similar ship type. According to the graph type and design rule library type applicable to the similar ship type, the design ship is matched with the line knowledge graph and design rule library. (2) Model reasoning and rule reasoning are used for the corresponding line knowledge graph and design rule base respectively to obtain the global geometric characteristic parameter value or value range of the line to control the global line shape of the hull; (3) Obtain the value or value range of the local geometric characteristic parameter of the line, control the local line shape of the hull, and combine it with the global geometric characteristic parameters to form the line parameter scheme of the designed ship.

5. The knowledge-driven hull line intelligent design platform according to claim 4, characterized in that: Knowledge reasoning of parent instance library: The commonly used nearest neighbor search method (NNS) is selected to retrieve the parent ship instance; the weighted Euclidean distance formula is selected, which is expressed as: Where: x i is the i-th characteristic attribute of the design case; y i is the i-th characteristic attribute of the existing case in the database; n is the number of types of characteristic attributes; w i is the weight of the i-th feature attribute; Assuming that the influence of each feature attribute on similarity is 1 / n, the similarity between instances is calculated according to the similarity formula. The similarity formula is:

6. The knowledge-driven hull line intelligent design platform according to claim 4, characterized in that: Line knowledge graph reasoning: Using the gridded dataset of the profile knowledge graph, and according to the profile parameter variation rules reflected in the knowledge graph, a step-by-step interpolation reasoning model for the profile parameters with respect to CB, L / B, and B / T is established. The profile parameter values ​​under the actual CB, L / B, and B / T are obtained based on the profile curve reasoning. The interpolation formula is shown below: The process of the inference model is as follows: 1) Select two adjacent C B (C B1 and C B2 ):To C B1 First, determine the actual B / T and L / B of the ship based on the main scale elements given by the user, select two adjacent L / B in the line knowledge graph, and interpolate to obtain two sets of parameter values: X skeg1* and X skeg2* ; 2) Then interpolate the parameter value corresponding to the square coefficient based on the actual L / B value Xskeg3 ; 3) Similarly for C B2 Get parameter value based on actual L / B interpolation Xskeg4 ; 4) Finally, according to X skeg3 and X skeg4 Interpolation to get the actual X skeg .

7. The knowledge-driven hull line intelligent design platform according to claim 4, characterized in that: Design rule base knowledge reasoning: Rule reasoning is used to match problems based on production rules. The basic process is: according to the design parameters input by the user, the rules stored in the rule base are conditionally judged one by one in order. If the rule is met, the conclusion of the rule is output. If it is not met, the rule is skipped until all rules are judged.

8. A knowledge-driven hull line intelligent design method according to the knowledge-driven hull line intelligent design platform as claimed in any one of claims 1 to 7, characterized in that: The following steps are involved: Step 1: The user inputs the main elements of the ship design requirements, including the length between perpendiculars L, the width B, the draft T, and the square coefficient C. B 、Froude number F r , and the main characteristics of the designed ship, including ship type, bow and stern type, and design speed; Step 2: Based on the user's design requirements, similar initial ship types are first retrieved from the prototype library. Then, the line knowledge inference model is used to obtain the characteristic parameters of the ship type with excellent resistance performance. The parametric geometry modeling software CAESES is then integrated to generate a 3D geometric model of the hull surface using the parametric design module. Step three is to reasonably and effectively acquire, represent, classify and manage expert experience, actual ship design data, optimization simulation data, ship design principles and regulatory knowledge, focus on total resistance performance, and establish a hull line design knowledge base.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the knowledge-driven hull line intelligent design method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that A computer program is stored, and when the computer program is executed by a processor, the processor executes the steps of the knowledge-driven hull line intelligent design method according to any one of claims 1 to 7.

Images