Ship bow design method suitable for river-sea direct ship

Abstract

The invention discloses a ship bow design method suitable for a river-sea direct ship, and the method comprises the steps: defining and constructing a key feature control line through feature parameters, and building a parameterized model of a ship bow; a mother ship type is selected, and initial values, corresponding to the characteristic parameters, of the mother ship are obtained; constructing a variation range of the characteristic parameters relative to an initial value of the mother ship; generating N groups of feature parameter schemes by using a Latin hypercube design method; inputting the N groups of characteristic parameter schemes into a parameterized model to generate N ship body geometric model schemes; calculating the total resistance and the maximum impact pressure of the bow of the N ship body geometric model schemes; respectively establishing a total resistance performance prediction model and a bow maximum impact pressure prediction model by means of a neural network method; an improved differential evolution algorithm is constructed, the ship bow optimization design of the river-sea direct ship is carried out with the aim of reducing the total resistance of the ship and the maximum impact pressure of the ship bow, and a design result is obtained. According to the designed ship bow, the resistance performance of the ship can be improved, and meanwhile the attack performance can be considered.

Description

Technical Field

[0001] The invention relates to the technical field of ship design, and in particular to a bow design method suitable for a river-to-sea direct ship. Background Art

[0002] A ship should have good performance when sailing so that it can sail in bad weather or extreme sea conditions. In addition, the goal of ship design is usually to increase the speed of the ship, that is, how to obtain a ship design with the best speed but using the least engine power, so that the use efficiency of fuel can be improved. The use of engine power is closely related to the ship's resistance.

[0003] As we all know, the shape of the bow of a ship has an important influence on the resistance of the ship during navigation. At present, the mainstream bow is generally defined as 5 types: 1. Straight bow: The bow column is straight and basically perpendicular to the base line. It is mostly seen in barges and special ships. 2. Raked bow: The bow column is straight or slightly curved. This type of bow is not easy to rise on the waves. In the event of a collision, the bow part below the waterline is not easily damaged. 3. Clipper bow: It is designed to be a concave curve above the waterline, with a larger forecastle deck, which is conducive to the arrangement of anchors and mooring equipment, and the bow is not easy to rise on the waves. 4. Ice resistant bow: The bow column below the waterline is inclined, forming a 30° angle with the base line. It is generally seen in icebreakers. 5. Bulbous how: The front of the bow below the waterline is designed with a bulbous protrusion, which is used to reduce wave resistance and shape resistance. It is widely used in seagoing ships. In addition, the bow design has been modified many times in the past. In 2006, the Norwegian Ulstein Group launched the X-shaped bow to improve the fuel efficiency and safety of ships at sea. The farthest point of the X-shaped bow is located at the end of the ship (towards the waterline), thus providing the hull with a continuous sharp bow shape. The sharp design at the front end helps the ship to cross the waves and improve the overall stability.

[0004] In today's context of decreasing fossil energy and increasing greenhouse gas emissions, inland waterway transportation has obvious advantages in environmental protection and economic costs. The proportion of inland waterway transportation in the transportation industry continues to increase, and the river-sea direct transportation method has received widespread attention. From the above, it can be seen that there are currently few bows designed for the characteristics of river-sea direct ships. Considering the characteristics of river-sea direct ships, if the bow of an inland ship is used directly, the bow may be hit by higher waves during the process of entering the sea from the river, reducing the comfort of the ship and causing safety accidents in some extreme cases. If the bow of a seagoing ship is used directly, poor fuel economy and high carbon emissions will occur in inland waterways.

[0005] Therefore, in order to further improve the fuel economy of river-sea direct ships, reduce carbon emissions and improve ship safety, developing a bow shape suitable for river-sea direct ships is a key technical issue that technical personnel in this field need to solve urgently. Summary of the invention

[0006] The main purpose of the present invention is to propose a bow design method suitable for a river-to-sea direct ship. The bow designed by this method can improve the ship's resistance performance while taking into account the impact performance of the river-to-sea direct ship during navigation, thereby reducing fuel consumption and reducing pollution emissions; at the same time, the bow impact phenomenon of the river-to-sea direct ship when entering the sea from the river is reduced, thereby improving the safety of the ship.

[0007] The technical solution adopted by the present invention is:

[0008] A bow design method applicable to a river-to-sea direct ship comprises the following steps:

[0009] S1. Define and construct key feature control lines through feature parameters Pi to establish a parametric model of the bow; the key feature control lines include: bow mid-longitudinal section line, bow upper mid-longitudinal section line, bow flat bottom line, bow maximum concave line, bow widest line, bow waterline, bow deck line; i = 1, 2, ..., M, M is the number of feature parameters;

[0010] S2, selecting a mother ship type, measuring and obtaining an initial value vi of a characteristic parameter Pi corresponding to the mother ship;

[0011] S3, construct the range of variation of the characteristic parameter Pi relative to the initial value vi of the parent ship during the design process;

[0012] S4, generating N sets of characteristic parameter solutions within the variation range constructed in S3 using the Latin hypercube design method according to formula (1);

[0013] P i j =LHS(LBi,UBi) (1)

[0014] Where i = 1, 2, ..., M, j = 1, 2, ..., N, LHS represents the Latin hypercube function, UBi is the upper limit of Pi, LBi is the lower limit of Pi, P i j Represents the value of the characteristic parameter Pi in the jth group of characteristic parameter schemes;

[0015] S5, inputting the N sets of characteristic parameter solutions generated by S4 into the parameterized model in S1 to generate N hull geometry model solutions;

[0016] S6, respectively calculating the total resistance Fj of the N hull geometric model schemes obtained in S5, j = 1, 2, ..., N;

[0017] S7, respectively calculating the maximum bow impact pressure Yj of the N hull geometric model schemes obtained in S5, j = 1, 2, ..., N;

[0018] S8, based on the total resistance and bow maximum impact pressure data collected in S6 and S7, a total resistance performance prediction model Mf and a bow maximum impact pressure prediction model My are established respectively by using a neural network method;

[0019] S9. Construct an improved differential evolution algorithm to optimize the bow design of the river-to-sea direct ship with the goal of reducing the total resistance of the ship and the maximum impact pressure of the bow, and obtain the design results.

[0020] In the above scheme, the characteristic parameters for constructing the longitudinal section line in the bow include: the raised position of the bow bottom (P1), the front edge position of the bow (P2), the raised inclination angle of the bow bottom (P3), the inclination angle of the bow (P4), the straight-line distance of the raised bow bottom (P5), and the straight-line distance of the bow inclination (P6).

[0021] In the above scheme, the characteristic parameters for constructing the upper center longitudinal section line of the bow include: the inclination angle of the starting position of the center longitudinal section line on the bow (P7), the straight-line distance of the starting position of the center longitudinal section line on the bow (P8), the ending position of the center longitudinal section line on the bow (P9), the inclination angle of the ending position of the center longitudinal section line on the bow (P10), and the straight-line distance of the ending position of the center longitudinal section line on the bow (P11).

[0022] In the above scheme, the characteristic parameters for constructing the bow flat bottom line include: the contraction position of the bow flat bottom line (P12), the straight-line distance of the contraction position of the bow flat bottom line (P13), the end position of the bow flat bottom line (P14), the inclination angle of the end position of the bow flat bottom line (P15), and the straight-line distance of the end position of the bow flat bottom line (P16).

[0023] In the above scheme, the characteristic parameters for constructing the maximum inverted concave line of the bow include: the starting position of the maximum inverted concave line of the bow (P17), the inclination angle of the starting position of the maximum inverted concave line of the bow (P18), the straight-line distance of the starting position of the maximum inverted concave line of the bow (P19), the ending position of the maximum inverted concave line of the bow (P20), the inclination angle of the ending position of the maximum inverted concave line of the bow (P21), and the straight-line distance of the ending position of the maximum inverted concave line of the bow (P22).

[0024] In the above scheme, the characteristic parameters for constructing the bow widest line include: the starting position of the bow widest line (P23), the straight-line distance of the starting position of the bow widest line (P24), the ending position of the bow widest line (P25), the straight-line distance of the ending position of the bow widest line (P26), the inclination angle of the middle position of the bow widest line (P27), and the straight-line distance of the middle position of the bow widest line (P28).

[0025] In the above scheme, the characteristic parameters for constructing the bow waterline include: the starting position of the bow waterline (P29), the inclination angle of the starting position of the bow waterline (P30), the straight-line distance of the starting position of the bow waterline (P31), the ending position of the bow waterline (P32), the inclination angle of the ending position of the bow waterline (P33), and the straight-line distance of the ending position of the bow waterline (P34).

[0026] In the above scheme, the characteristic parameters for constructing the bow deck line include: the starting position of the bow deck line (P35), the inclination angle of the starting position of the bow deck line (P36), the straight-line distance of the starting position of the bow deck line (P37), the ending position of the bow deck line (P38), the inclination angle of the ending position of the bow deck line (P39), and the straight-line distance of the ending position of the bow deck line (P40).

[0027] In the above scheme, in step S8, a total resistance performance prediction model Mf and a bow maximum impact pressure prediction model My are established, which specifically includes the following steps:

[0028] S8.1. Normalize the collected resistance and bow maximum impact pressure data into input matrices, MatrixF and MatrixY respectively;

[0029]

[0030] S8.2, MatrixF and MatrixY are normalized by the following formula;

[0031]

[0032] Where: MatrixF k is the k-th column element in MatrixF, MatrixY k is the k-th column element in MatrixY, k = 1, 2, ..., M + 1, MatrixF k ′ and MatrixY k ′ is the normalized result;

[0033] S8.3. MatrixF k ′ and MatrixY k ′ Divide into training set and test set respectively;

[0034] S8.4. Design a neural network structure, including an input layer, a hidden layer, and an output layer; set the number of neurons in the input layer to nm, the number of neurons in the hidden layer to num, and the number of neurons in the output layer to 1; use Relu as the activation function, and set the loss function to the mean square error between the neural network output result and the actual calculation result;

[0035] S8.5. MatrixF k ′ The training set obtained by the division is used as training data to train the neural network model, and the trained neural network model is tested using the test set to obtain the total resistance performance prediction model Mf;

[0036] S8.6. MatrixY k ′ The training set obtained by division is used as training data to train the neural network model, and the trained neural network model is tested using the test set to obtain the bow maximum impact pressure prediction model My.

[0037] In the above scheme, in step S9, an improved differential evolution algorithm is constructed to optimize the bow design of the river-sea direct access ship with the goal of reducing the total resistance of the ship and the maximum impact pressure of the bow. The specific steps are as follows:

[0038] S9.1, setting the maximum number of iterations gmax of the algorithm, and randomly generating I initial river-to-sea direct access ship bow optimization design schemes according to the variation range of the characteristic parameters defined in S3 according to formula (2);

[0039]

[0040] Where: i = 1, 2, ... M, m = 1, 2, ... I, is the optimal design scheme of the bow of the mth initial river-sea direct access ship, r m,g is a random value between 0 and 1, g is the number of iterations, and is recorded as 1 in this step;

[0041] S9.2, according to formula (3), the randomly generated I initial river-sea direct access ship bow optimization design schemes are subjected to chaotic mapping;

[0042]

[0043] Where: is the optimal design scheme of the bow of the mth river-sea direct access ship after chaotic mapping, r m,g A random value between 0 and 1;

[0044] S9.3, randomly divide the I river-sea direct access ship bow optimization design schemes after chaotic mapping into two groups, and mark them as I1 and I2 respectively;

[0045] S9.4, using the I / 2 river-sea direct access ship bow optimization design schemes after chaotic mapping marked as I1 to generate further river-sea direct access ship bow optimization design schemes by using formula (4);

[0046]

[0047] Where: n1=1,2,…,I / 2, The n1th generated further optimized design scheme for the bow of the river-sea direct access ship, r1, r2 and r3 are random integers from 1 to I / 2; F is the scaling factor and takes 0.5;

[0048] S9.5, using the I / 2 chaotically mapped bow optimization design schemes marked as I2 to generate further bow optimization design schemes for river-sea direct access ships by using formula (5);

[0049]

[0050] In the formula: n2=I / 2+1,…,I, The n2th generated further optimized design scheme for the bow of the river-sea direct ship, r4, r5, r6, r7 and r8 are random integers from I / 2+1 to I, and F is the scaling factor and takes 0.5;

[0051] S9.6. Merger and for m=1,2,…,I;

[0052] S9.7, refining the further optimized design scheme of the bow of the river-sea direct access ship constructed by formula (6) to generate a refined optimized design scheme of the bow of the river-sea direct access ship;

[0053]

[0054] In the formula, i rand is a random integer from 1 to M, and r is a random value from 0 to 1;

[0055] S9.8. Input into Mf in S8 to obtain That is, the total resistance performance prediction model Mf of the ship constructed in S8 is used to calculate the total resistance performance of the generated initial river-sea direct access ship bow optimization design scheme and the refined river-sea direct access ship bow optimization design scheme;

[0056] S9.9. Enter it into My in S8 to get That is, the maximum impact pressure prediction model My of the ship bow constructed in S8 is used to calculate the maximum impact pressure of the ship bow for the generated initial river-sea direct access ship bow optimization design scheme and the refined river-sea direct access ship bow optimization design scheme;

[0057] S9.10, according to formula (7) The corresponding ship bow optimization design scheme is selected and the selected scheme is assigned to The iteration number indicator g is updated to iter, and iter=g+1, that is, the solution with smaller total resistance and maximum impact pressure of the bow of the ship generated in this iteration is retained for the next iteration calculation;

[0058]

[0059] In the formula, represents the initial optimized design scheme of the bow of the river-sea direct access ship in the next iterative calculation process;

[0060] S9.11, determine whether iter is greater than gmax, if it is less than, jump to S9.3, and set g in S9.3 to the value of iter for the next iteration calculation, if it is greater, The corresponding total resistance and the solution with the smallest maximum impact pressure on the bow of the ship are output and determined as the optimal design.

[0061] The beneficial effects produced by the present invention are:

[0062] In this application, the constructed bow parameterized model can achieve a large deformation of the bow shape, that is, it can achieve different forms of bow scheme deformation. Different forms of bow schemes can be quickly obtained by this method. To a certain extent, the design space can be expanded and more design schemes can be realized. In addition, the total resistance performance prediction model Mf and the prediction model My of the maximum bow impact pressure established in S8 can be used for the rapid prediction of resistance and bow impact characteristics of other design schemes, which helps to improve the design efficiency during preliminary design. Finally, the improved differential evolution algorithm in S9 further improves the algorithm's ability to solve the optimization design of the bow of the river-sea direct ship with the goal of reducing the total resistance of the ship and the maximum bow impact pressure. It has been verified that the composite bow scheme designed by the method of the present invention can take into account the impact performance of the river-sea direct ship during navigation while improving the ship's resistance performance, thereby reducing fuel consumption and reducing pollution emissions; at the same time, it reduces the bow impact phenomenon of the river-sea direct ship when entering the sea from the river, and improves the safety of the ship. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1 It is a schematic diagram of the key characteristic control lines of the bow of a ship;

[0065] Figure 2 It is a schematic diagram of the characteristic parameters corresponding to each key characteristic control line; among them, (2-1) is a schematic diagram of the characteristic parameters of the bow middle longitudinal section line; (2-2) is a schematic diagram of the characteristic parameters of the bow upper middle longitudinal section line; (2-3) is a schematic diagram of the characteristic parameters of the bow flat bottom line; (2-4) is a schematic diagram of the characteristic parameters of the bow maximum concave line; (2-5) is a schematic diagram of the characteristic parameters of the bow widest line; (2-6) is a schematic diagram of the characteristic parameters of the bow waterline; (2-7) is a schematic diagram of the characteristic parameters of the bow deck line;

[0066] Figure 3 Schematic diagrams of CAD geometric models of two bow schemes generated in the processes S4 and S5 of the embodiment of the present invention, wherein (3-1) is a schematic diagram of the constructed bulbous bow scheme, and (3-2) is a schematic diagram of the upright bow scheme;

[0067] Figure 4 are partial test results of the accuracy of the trained neural network models Mf and My in Example S8 of the present invention, wherein (4-1) is a partial test result of the total resistance performance prediction model Mf, and (4-2) is a partial test result of the bow maximum impact pressure prediction model My;

[0068] Figure 5 It is the calculation iteration process in Embodiment S9 of the present invention;

[0069] Figure 6 is the bow of the river-to-sea direct ship obtained by iterative calculation in an embodiment of the present invention, wherein (6-1) is a side view and (6-2) is a front view;

[0070] Figure 7 are three existing bow schemes used in the resistance performance verification in the embodiments of the present invention, wherein (7-1) is a conventional bulbous bow scheme, (7-2) is a conventional upright bow scheme, and (7-3) is an upright bow scheme with a retracted waterline;

[0071] Figure 88-1 is a schematic diagram of the distribution of slamming pressure measuring points of the bow structure in the slamming performance verification in an embodiment of the present invention, wherein (8-1) is a typical bulbous bow, and (8-2) is the bow of the river-to-sea direct ship in an embodiment of the present invention;

[0072] Fig. 9 is a curve showing the peak value of slamming pressure at different measuring points in the embodiment of the present invention as the bottom of the ship changes in the positive direction along the X-axis;

[0073] Fig.10 is a positive change curve of the slamming pressure peak value along the Z axis of the first group of pressure measuring points in the embodiment of the present invention;

[0074] Fig.11 is a curve showing a positive change in the peak value of the impact pressure along the Z axis at the second group of pressure measuring points in the embodiment of the present invention;

[0075] Fig.12 It is the positive change curve of the slamming pressure peak value along the Z axis of the third group of pressure measuring points in the embodiment of the present invention. DETAILED DESCRIPTION

[0076] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0077] It should be noted that the illustrations provided in the embodiments of the present invention are only used to illustrate the basic concept of the present invention in a schematic manner. Therefore, the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout type may also be more complicated.

[0078] In the present invention, it is also necessary to explain that, if the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, if the terms "first" and "second" appear, they are only used for description and distinction purposes, and cannot be understood as indicating or implying relative importance.

[0079] The present invention proposes a bow design method suitable for river-sea direct access ships, which constructs a parametric model of the hull bow three-dimensional model, uses an intelligent optimization algorithm combined with simulation and neural network method drive, and takes resistance performance and bow impact performance as the target to find an energy-saving and low-impact bow suitable for river-sea direct access ships. The method specifically includes:

[0080] S1. Define and construct key characteristic control lines through characteristic parameters Pi, and establish a parametric model of the bow. Figure 1 As shown in FIG. 1 , the key feature control lines include: bow mid-longitudinal section line, bow upper mid-longitudinal section line, bow flat bottom line, bow maximum concave line, bow widest line, bow waterline, bow deck line; i = 1, 2, …, M, where M is the number of feature parameters.

[0081] As shown in Figure (2-1), the characteristic parameters for constructing the longitudinal section line in the bow include: the raised position of the bow bottom (P1), the position of the foremost edge of the bow (P2), the raised inclination angle of the bow bottom (P3), the inclination angle of the bow (P4), the straight-line distance of the raised bow bottom (P5), and the straight-line distance of the bow inclination (P6).

[0082] As shown in Figure (2-2), the characteristic parameters for constructing the upper center longitudinal section line of the bow include: the inclination angle of the starting position of the center longitudinal section line on the bow (P7), the straight-line distance of the starting position of the center longitudinal section line on the bow (P8), the ending position of the center longitudinal section line on the bow (P9), the inclination angle of the ending position of the center longitudinal section line on the bow (P10), and the straight-line distance of the ending position of the center longitudinal section line on the bow (P11).

[0083] As shown in Figure (2-3), the characteristic parameters for constructing the bow flat bottom line include: the contraction position of the bow flat bottom line (P12), the straight-line distance of the contraction position of the bow flat bottom line (P13), the end position of the bow flat bottom line (P14), the inclination angle of the end position of the bow flat bottom line (P15), and the straight-line distance of the end position of the bow flat bottom line (P16).

[0084] As shown in Figure (2-4), the characteristic parameters for constructing the maximum inverted concave line of the bow include: the starting position of the maximum inverted concave line of the bow (P17), the inclination angle of the starting position of the maximum inverted concave line of the bow (P18), the straight-line distance of the starting position of the maximum inverted concave line of the bow (P19), the ending position of the maximum inverted concave line of the bow (P20), the inclination angle of the ending position of the maximum inverted concave line of the bow (P21), and the straight-line distance of the ending position of the maximum inverted concave line of the bow (P22).

[0085] As shown in Figure (2-5), the characteristic parameters for constructing the widest bow line include: the starting position of the widest bow line (P23), the straight-line distance from the starting position of the widest bow line (P24), the ending position of the widest bow line (P25), the straight-line distance from the ending position of the widest bow line (P26), the inclination angle of the middle position of the widest bow line (P27), and the straight-line distance of the middle position of the widest bow line (P28).

[0086] As shown in Figure (2-6), the characteristic parameters for constructing the bow waterline include: the starting position of the bow waterline (P29), the inclination angle of the starting position of the bow waterline (P30), the straight-line distance of the starting position of the bow waterline (P31), the ending position of the bow waterline (P32), the inclination angle of the ending position of the bow waterline (P33), and the straight-line distance of the ending position of the bow waterline (P34).

[0087] As shown in Figure (2-7), the characteristic parameters for constructing the bow deck line include: the starting position of the bow deck line (P35), the inclination angle of the starting position of the bow deck line (P36), the straight-line distance of the starting position of the bow deck line (P37), the ending position of the bow deck line (P38), the inclination angle of the ending position of the bow deck line (P39), and the straight-line distance of the ending position of the bow deck line (P40).

[0088] Then, M=40.

[0089] S2. Select a mother ship type, and measure and obtain an initial value vi of a characteristic parameter Pi of the mother ship.

[0090] S3. Construct the range of variation of the characteristic parameter Pi relative to the initial value vi of the parent ship during the design process. Establish an optimization design requirement table, the table format is shown in Table 1:

[0091] Table 1

[0092]

[0093] S4, generating N sets of characteristic parameter solutions within the variation range constructed in S3 using the Latin hypercube design method according to formula (1);

[0094] P i j =LHS(LBi,UBi) (1)

[0095] Where i = 1, 2, ..., M, j = 1, 2, ..., N, LHS represents the Latin hypercube function, UBi is the upper limit of Pi, LBi is the lower limit of Pi, P i j Represents the value of the characteristic parameter Pi in the jth group of characteristic parameter schemes.

[0096] In this embodiment, N=500.

[0097] S5. Input the N sets of characteristic parameter solutions generated by S4 into the parameterized model in S1 to generate N hull geometry model solutions.

[0098] In this embodiment, the 500 sets of characteristic parameter solutions generated in S4 are input into the parameterized model in S1 to generate 500 hull geometry model solutions, such as Figure 3As shown, two different forms of solutions are given.

[0099] S6. Calculate the total resistance Fj of the 500 hull geometry model solutions obtained in S5 respectively, where j = 1, 2, ..., 500.

[0100] S7. Calculate the maximum bow impact pressure Yj of the 500 hull geometry model solutions obtained in S5, where j = 1, 2, ..., 500.

[0101] S8. Based on the total resistance and bow maximum impact pressure data collected in S6 and S7, a total resistance performance prediction model Mf and a bow maximum impact pressure prediction model My are established respectively with the help of a neural network method.

[0102] The specific process is as follows:

[0103] S8.1. Normalize the collected resistance and bow maximum impact pressure data from the input matrices, MatrixF and MatrixY, respectively;

[0104]

[0105] S8.2, MatrixF and MatrixY are normalized by the following formula;

[0106]

[0107] Where: MatrixF k is the k-th column element in MatrixF, MatrixY k is the k-th column element in MatrixY, k = 1, 2, ..., 41. MatrixF k ′ and MatrixY k ′ is the normalized result;

[0108] S8.3. MatrixF k ′ and MatrixY k ′ Divide into training set and test set according to the ratio of 70% and 30%;

[0109] S8.4. In this embodiment, the number of neurons in the input layer of the neural network is set to nm=40, the number of neurons in the hidden layer is num=200, and the number of neurons in the output layer is 1. Relu is used as the activation function, and the loss function is set to the mean square error between the output result of the neural network and the actual calculation result;

[0110] S8.5. MatrixF k′ The training set obtained by the division is used as training data to train the neural network model, and the trained neural network model is tested using the test set to obtain the total resistance performance prediction model Mf;

[0111] S8.6. MatrixY k ′ The training set obtained by division is used as training data to train the neural network model, and the trained neural network model is tested using the test set to obtain the bow maximum impact pressure prediction model My.

[0112] Figures (4-1) and (4-2) are partial test results of the accuracy of Mf and My. It can be seen from the figures that the total resistance of the ship and the maximum bow impact pressure calculated by Mf and My are in good agreement with the simulation results.

[0113] S9. Construct an improved differential evolution algorithm to optimize the bow design of the river-to-sea ship with the goal of reducing the total resistance of the ship and the maximum impact pressure of the bow, and obtain the design results. The specific process is as follows:

[0114] S9.1, setting the maximum number of iterations gmax of the algorithm, in this embodiment, gmax is set to 280, and randomly generating I=50 initial river-sea direct access ship bow optimization design schemes according to the variation range of the characteristic parameters defined in S3 according to formula (2);

[0115]

[0116] Where: is the optimal design scheme of the bow of the mth initial river-sea direct access ship, r m,g is a random value ranging from 0 to 1, g is the number of iterations, which is recorded as 1 in this step; in this embodiment, i=1,2,…40, m=1,2,…50, g=1.

[0117] S9.2, according to formula (3), 50 randomly generated initial river-sea direct access ship bow optimization design schemes are subjected to chaotic mapping;

[0118]

[0119] Where: is the optimal design scheme of the bow of the mth river-sea direct access ship after chaotic mapping, r m,g A random value between 0 and 1.

[0120] S9.3, randomly divide the 50 optimal design schemes of the bow of the river-sea direct access ship after chaotic mapping into two groups, and mark them as I1 and I2 respectively;

[0121] S9.4, the 25 optimal design schemes for the bow of the river-sea direct access ship after chaotic mapping marked as I1 are used to generate further optimal design schemes for the bow of the river-sea direct access ship by means of formula (4);

[0122]

[0123] Where: This is the n1th generated further optimized design scheme for the bow of the river-sea direct ship, n1 = 1, 2, ..., 25, r1, r2 and r3 are random integers from 1 to 25; F is the scaling factor and takes 0.5.

[0124] S9.5, the 25 optimal design schemes for the bow of the river-sea direct access ship after chaotic mapping marked as I2 are used to generate further optimal design schemes for the bow of the river-sea direct access ship by means of formula (5);

[0125]

[0126] Where: This is the n2th generated further optimized design scheme for the bow of the river-sea direct ship, n2 = 26, 27, ..., 50, r4, r5, r6, r7 and r8 are random integers from I / 2+1 to I, and F is the scaling factor taking 0.5.

[0127] S9.6. Merger and for m=1,2,…,50;

[0128] S9.7, refining the further optimized design scheme of the bow of the river-sea direct access ship constructed by formula (6) to generate a refined optimized design scheme of the bow of the river-sea direct access ship;

[0129]

[0130] In the formula, i rand is a random integer from 1 to 40, and r is a random value from 0 to 1.

[0131] S9.8. Input into Mf in S8 to obtain That is, the total resistance performance prediction model Mf of the ship constructed in S8 is used to calculate the total resistance performance of the generated initial river-sea direct access ship bow optimization design scheme and the refined river-sea direct access ship bow optimization design scheme.

[0132] S9.9. Enter into S8 and get MP That is, the maximum impact pressure prediction model My of the ship bow constructed in S8 is used to calculate the maximum impact pressure of the ship bow for the generated initial river-sea direct access ship bow optimization design scheme and the refined river-sea direct access ship bow optimization design scheme.

[0133] S9.10, according to formula (7) The corresponding ship bow optimization design scheme is selected and the selected scheme is assigned to The iteration number indicator g is updated to iter, iter = g + 1. That is, the solution with the smaller total resistance and the maximum impact pressure of the bow of the ship generated in this iteration is retained for the next iteration calculation.

[0134]

[0135] In the formula, It represents the initial optimized design scheme of the bow of the river-sea direct access ship in the next iterative calculation process.

[0136] S9.11, determine whether iter is greater than gmax, if it is less than, jump to S9.3, and set g in S9.3 to the value of iter, and perform the next iteration calculation, if it is greater than, The corresponding total resistance and the solution with the smallest maximum impact pressure on the bow of the ship are output and determined as the optimal design.

[0137] The solution process of this embodiment is as follows Figure 5 As shown, Figure 5 It can be seen that after multiple iterations, the algorithm gradually converges and the design result of the embodiment is obtained.

[0138] Finally, the bow shape of the river-to-sea direct ship obtained by iterative calculation in this embodiment is as follows: Figure 6 As shown in the figure, it can be called a composite bow. Compared with the bulbous bow and the typical upright bow, the wet surface area below the waterline of the bow is reduced, which is conducive to further reducing the friction resistance of the ship. In addition, compared with the X-Bow, the bow of the ship is more pointed and thin, which is conducive to further reducing the impact of wave breaking resistance.

[0139] In order to verify the effectiveness of the bow design method of the present invention applicable to river-sea direct access ships, the resistance performance and impact performance of the composite bow designed in this embodiment are analyzed below.

[0140] (1) Resistance performance

[0141] The resistance performance of the river-to-sea direct ship bow constructed in the embodiment is analyzed by taking the other three bow schemes of the same scale as comparative schemes to illustrate the effectiveness of the method of the present invention. Figure 7 A schematic diagram of the three-dimensional model is provided in .

[0142] The CFD method is used to predict the total resistance of the bow scheme of the river-sea direct ship constructed by the above three schemes and the embodiment at the design speed (10.8kn). The prediction results are shown in Table 2. It can be seen that the resistance performance of the bow scheme of the river-sea direct ship (composite bow scheme) constructed by the method of the present invention is better than that of the existing conventional bow scheme.

[0143] Table 2 Optimized ship resistance data at various speeds

[0144] serial number Total resistance N Conventional bulbous bow solution 16.688 Conventional upright bow solution 15.164 Vertical bow solution with shrinking waterline 16.231 Composite bow solution 14.709

[0145] (2) Criticizing performance

[0146] In order to solve the problem of maximum impact pressure on the bow of the present invention, finite element calculation is performed using Ansys / LS-DYNA. A typical bulbous bow model is used as a comparative embodiment. A calculation model is constructed for the bow of the river-sea direct ship (composite bow scheme) constructed in the embodiment and pressure measurement points are set, such as Figure 8 shown.

[0147] Fig. 9 The figure shows the comparison results of the pressure peaks of the composite bow and the bulbous bow at different measuring points. It can be seen that the pressure peak of the bulbous bow is higher than that of the composite bow, and because the inclined angles of the bulbous bow and the composite bow along the positive direction of the X-axis increase rapidly, the vertical water entry slamming pressure of the two structures will show a trend of rapidly decreasing along the positive direction of the X-axis and then tending to a stable decrease.

[0148] like Figure 10-12 The figure shows the comparative analysis of the pressure peak values ​​of three groups of measuring points along the positive direction of the Z axis for the composite bow and the bulbous bow. Fig.10 It can be seen that when the peak slamming pressure of the first group of measuring points is at a low altitude, the bulbous bow is higher than the composite bow. Since the linear change of the composite bow in the height direction is more moderate than that of the bulbous bow, the peak slamming pressure at a higher measuring point is higher than that of the bulbous bow. Fig.11 It can be seen that the peak value of the impact pressure at the second group of measuring points changes with the height in the same way. Fig.12 It can be seen that the measuring points of the third group are at a farther position (closer to the bow), and the peak slamming pressure of the bulbous bow is greater than that of the composite bow.

[0149] In summary, the simulation model of the bow slamming pressure of different bow types was established using ANSYS / LS-DYNA software, the distribution of the slamming loads of the bulbous bow and the composite bow was analyzed, and the variation characteristics of the peak slamming pressure of the two bow types along the longitudinal direction and height direction of the ship bottom were further compared. It was concluded that the overall anti-slamming effect of the composite bow is better than that of the bulbous bow.

[0150] It should be pointed out that, according to the needs of implementation, the various steps / components described in this application can be split into more steps / components, and two or more steps / components or partial operations of steps / components can be combined into new steps / components to achieve the purpose of the present invention.

[0151] The order of execution of each step in the above embodiment does not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0152] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all these improvements and changes should fall within the scope of protection of the appended claims of the present invention.

Claims

1. A bow design method suitable for a river-sea direct ship, characterized in that: The following steps are involved: S1. Define and construct key feature control lines through feature parameters Pi to establish a parametric model of the bow; the key feature control lines include: bow mid-longitudinal section line, bow upper mid-longitudinal section line, bow flat bottom line, bow maximum concave line, bow widest line, bow waterline, bow deck line; i = 1, 2, ..., M, M is the number of feature parameters; S2, selecting a mother ship type, measuring and obtaining an initial value vi of a characteristic parameter Pi corresponding to the mother ship; S3, construct the range of variation of the characteristic parameter Pi relative to the initial value vi of the parent ship during the design process; S4, generating N sets of characteristic parameter solutions within the variation range constructed in S3 using the Latin hypercube design method according to formula (1); Where i = 1, 2, ..., M, j = 1, 2, ..., N, LHS represents the Latin hypercube function, UBi is the upper limit of Pi's change, LBi is the lower limit of Pi's change, Represents the value of the characteristic parameter Pi in the jth group of characteristic parameter schemes; S5, inputting the N sets of characteristic parameter solutions generated by S4 into the parameterized model in S1 to generate N hull geometry model solutions; S6, respectively calculating the total resistance Fj of the N hull geometric model schemes obtained in S5, j = 1, 2, ..., N; S7, respectively calculating the maximum bow impact pressure Yj of the N hull geometric model schemes obtained in S5, j = 1, 2, ..., N; S8, based on the total resistance and bow maximum impact pressure data collected in S6 and S7, a total resistance performance prediction model Mf and a bow maximum impact pressure prediction model My are established respectively by using a neural network method; S9. Construct an improved differential evolution algorithm to optimize the bow design of the river-to-sea direct ship with the goal of reducing the total resistance of the ship and the maximum impact pressure of the bow, and obtain the design results.

2. The bow design method for a river-to-sea ship according to claim 1 is characterized in that: The characteristic parameters for constructing the longitudinal section line in the bow include: the bow bottom raised position (P1), the bow front edge position (P2), the bow bottom raised inclination angle (P3), the bow inclination angle (P4), the bow bottom raised straight line distance (P5), and the bow inclination straight line distance (P6).

3. The bow design method for a river-to-sea ship according to claim 1 is characterized in that: The characteristic parameters for constructing the upper middle longitudinal section line of the bow include: the inclination angle of the starting position of the middle longitudinal section line on the bow (P7), the straight-line distance of the starting position of the middle longitudinal section line on the bow (P8), the ending position of the middle longitudinal section line on the bow (P9), the inclination angle of the ending position of the middle longitudinal section line on the bow (P10), and the straight-line distance of the ending position of the middle longitudinal section line on the bow (P11).

4. The bow design method for a river-to-sea ship according to claim 1 is characterized in that: The characteristic parameters for constructing the bow flat bottom line include: the contraction position of the bow flat bottom line (P12), the straight-line distance of the contraction position of the bow flat bottom line (P13), the end position of the bow flat bottom line (P14), the inclination angle of the end position of the bow flat bottom line (P15), and the straight-line distance of the end position of the bow flat bottom line (P16).

5. The bow design method for a river-to-sea ship according to claim 1 is characterized in that: The characteristic parameters for constructing the maximum inverted concave line of the bow include: the starting position of the maximum inverted concave line of the bow (P17), the inclination angle of the starting position of the maximum inverted concave line of the bow (P18), the straight-line distance of the starting position of the maximum inverted concave line of the bow (P19), the ending position of the maximum inverted concave line of the bow (P20), the inclination angle of the ending position of the maximum inverted concave line of the bow (P21), and the straight-line distance of the ending position of the maximum inverted concave line of the bow (P22).

6. The bow design method for a river-to-sea ship according to claim 1 is characterized in that: The characteristic parameters for constructing the bow widest line include: the starting position of the bow widest line (P23), the straight-line distance of the starting position of the bow widest line (P24), the ending position of the bow widest line (P25), the straight-line distance of the ending position of the bow widest line (P26), the inclination angle of the middle position of the bow widest line (P27), and the straight-line distance of the middle position of the bow widest line (P28).

7. The bow design method for a river-to-sea ship according to claim 1 is characterized in that: The characteristic parameters for constructing the bow waterline include: the starting position of the bow waterline (P29), the inclination angle of the starting position of the bow waterline (P30), the straight-line distance of the starting position of the bow waterline (P31), the ending position of the bow waterline (P32), the inclination angle of the ending position of the bow waterline (P33), and the straight-line distance of the ending position of the bow waterline (P34).

8. The bow design method for a river-to-sea ship according to claim 1 is characterized in that: The characteristic parameters for constructing the bow deck line include: the starting position of the bow deck line (P35), the inclination angle of the starting position of the bow deck line (P36), the straight-line distance of the starting position of the bow deck line (P37), the ending position of the bow deck line (P38), the inclination angle of the ending position of the bow deck line (P39), and the straight-line distance of the ending position of the bow deck line (P40).

9. The bow design method for a river-to-sea ship according to claim 1, characterized in that: In step S8, a total resistance performance prediction model Mf and a bow maximum impact pressure prediction model My are established, which specifically includes the following steps: S8.

1. Normalize the collected resistance and bow maximum impact pressure data into input matrices, MatrixF and MatrixY respectively; S8.2, MatrixF and MatrixY are normalized by the following formula; Where: MatrixF k is the k-th column element in MatrixF, MatrixY k is the k-th column element in MatrixY, k = 1, 2, ..., M + 1, MatrixF k ′ and MatrixY k ′ is the normalized result; S8.

3. MatrixF k ′ and MatrixY k ′ are divided into training set and test set respectively; S8.

4. Design a neural network structure, including an input layer, a hidden layer, and an output layer; set the number of neurons in the input layer to nm, the number of neurons in the hidden layer to num, and the number of neurons in the output layer to 1; use Relu as the activation function, and set the loss function to the mean square error between the neural network output result and the actual calculation result; S8.

5. MatrixF k The training set obtained by ′ division is used as training data to train the neural network model, and the trained neural network model is tested using the test set to obtain the total resistance performance prediction model Mf; S8.

6. MatrixY k The training set obtained by dividing is used as training data to train the neural network model, and the trained neural network model is tested using the test set, so as to obtain the bow maximum impact pressure prediction model My.

10. The bow design method for a river-to-sea ship according to claim 1, characterized in that: In step S9, an improved differential evolution algorithm is constructed to optimize the bow design of the river-sea direct access ship with the goal of reducing the total resistance of the ship and the maximum impact pressure of the bow. The specific steps are as follows: S9.1, setting the maximum number of iterations gmax of the algorithm, and randomly generating I initial river-to-sea direct access ship bow optimization design schemes according to the variation range of the characteristic parameters defined in S3 according to formula (2); Where: i = 1, 2, ... M, m = 1, 2, ... I, is the optimal design scheme of the bow of the mth initial river-sea direct access ship, r m,g is a random value between 0 and 1, g is the number of iterations, and is recorded as 1 in this step; S9.2, according to formula (3), the randomly generated I initial river-sea direct access ship bow optimization design schemes are subjected to chaotic mapping; Where: is the optimal design scheme of the bow of the mth river-sea direct access ship after chaotic mapping, r m,g A random value between 0 and 1; S9.3, randomly divide the I river-sea direct access ship bow optimization design schemes after chaotic mapping into two groups, and mark them as I1 and I2 respectively; S9.4, using the I / 2 river-sea direct access ship bow optimization design schemes after chaotic mapping marked as I1 to generate further river-sea direct access ship bow optimization design schemes by using formula (4); Where: n1=1,2,…,I / 2, The n1th generated further optimized design scheme for the bow of the river-sea direct access ship, r1, r2 and r3 are random integers from 1 to I / 2; F is the scaling factor and takes 0.5; S9.5, using the I / 2 chaotically mapped bow optimization design schemes marked as I2 to generate further bow optimization design schemes for river-sea direct access ships by using formula (5); In the formula: n2=I / 2+1,…,I, The n2th generated further optimized design scheme for the bow of the river-sea direct ship, r4, r5, r6, r7 and r8 are random integers from I / 2+1 to I, and F is the scaling factor and takes 0.5; S9.

6. Merger and for S9.7, refining the further optimized design scheme of the bow of the river-sea direct access ship constructed by formula (6) to generate a refined optimized design scheme of the bow of the river-sea direct access ship; In the formula, i rand is a random integer from 1 to M, and r is a random value from 0 to 1; S9.

8. Input into Mf in S8 to obtain That is, the total resistance performance prediction model Mf of the ship constructed in S8 is used to calculate the total resistance performance of the generated initial river-sea direct access ship bow optimization design scheme and the refined river-sea direct access ship bow optimization design scheme; S9.

9. Enter it into My in S8 to get That is, the maximum impact pressure prediction model My of the ship bow constructed in S8 is used to calculate the maximum impact pressure of the ship bow for the generated initial river-sea direct access ship bow optimization design scheme and the refined river-sea direct access ship bow optimization design scheme; S9.10, according to formula (7) The corresponding ship bow optimization design scheme is selected and the selected scheme is assigned to The iteration number indicator g is updated to iter, and iter=g+1, that is, the solution with smaller total resistance and maximum impact pressure of the bow of the ship generated in this iteration is retained for the next iteration calculation; In the formula, represents the initial optimized design scheme of the bow of the river-sea direct access ship in the next iterative calculation process; S9.11, determine whether iter is greater than gmax, if it is less than, jump to S9.3, and set g in S9.3 to the value of iter for the next iteration calculation, if it is greater, The corresponding total resistance and the solution with the smallest maximum impact pressure on the bow of the ship are output and determined as the optimal design.

Images