Ship base impedance prediction model, device and construction method based on support vector regression optimized by particle swarm algorithm

Abstract

This invention provides a ship foundation impedance prediction model, device, and construction method based on support vector regression optimized by particle swarm optimization (PSO). It belongs to the field of ship foundation performance testing technology. The model establishment includes the following steps: First, define preset ship foundation vibration reduction and isolation design parameters; then, construct an initial ship foundation structure based on these parameters; next, establish a predictive physical model for ship foundation impedance based on this initial structure; then, establish a ship foundation vibration performance database; finally, use an optimization algorithm combining PSO and support vector regression to learn the structural vibration performance from the ship foundation vibration performance database, thereby obtaining a foundation impedance prediction model based on PSO-optimized support vector regression. This invention can more accurately and efficiently predict the impedance performance of ship foundations, thus providing strong technical support for ship vibration reduction and noise reduction, improving the accuracy of ship foundation impedance prediction, and shortening the ship foundation impedance calculation time.

Description

Technical Field

[0001] This invention belongs to the field of ship foundation performance testing technology, specifically relating to a ship foundation impedance prediction model, device, and construction method based on support vector regression optimized by particle swarm optimization algorithm. Background Technology

[0002] Ship machinery inevitably generates mechanical vibrations during operation. These vibrations are transmitted via the base to the hull frame structure, exciting the frame structure to produce a vibration response, which then propagates outward along the hull as elastic waves, ultimately radiating noise into the surrounding fluid medium. In this transmission path, the ship's base constitutes a key barrier for vibration control, and the core task of its acoustic design is to increase the input mechanical impedance, thereby improving vibration isolation performance.

[0003] The vibration isolation performance of a ship's hull is primarily influenced by two factors: the impedance characteristics of its coupled structure and the degree of impedance matching between it and the vibration isolation system. The impedance characteristics of the hull structure are a crucial indicator of its ability to block vibration energy from mechanical equipment. The impedance value transmitted from mechanical equipment to the hull is inversely proportional to the vibration energy; that is, the higher the impedance value, the lower the sound radiation caused by the vibration of the hull structure. Therefore, accurately predicting the mechanical impedance of the hull is an indispensable and critical step in the acoustic design of ship hulls, directly determining the quality of the hull's vibration isolation performance.

[0004] In practical engineering applications, the mechanical impedance of ship foundations is mainly obtained through three methods: engineering estimation, numerical simulation, and experimental testing. Engineering estimation is simple and quick, but its accuracy is low and its adaptability is poor; numerical simulation has high accuracy, but requires detailed modeling of the foundation, and often necessitates repeated calculations to meet acoustic design requirements, resulting in excessive computation time; experimental testing yields accurate results, but it is costly and difficult to compare the effects of different structural parameters. There is an urgent need for a new ship foundation impedance prediction model to achieve more efficient and accurate prediction of the foundation's input mechanical impedance, providing technical support for the acoustic design of ship foundations.

[0005] A literature search of existing technologies revealed that the publicly available information mainly includes: Patent Document 1, A method for predicting the mechanical impedance of equipment base based on machine learning algorithm (Patent No.: CN202210707271.5); Patent Document 2, A method for predicting the operating conditions of rotating machinery based on particle swarm optimization and support vector regression (Patent No.: ZL201811254907.5).

[0006] Patent document 1 designs a machine learning-based method for predicting the impedance of a ship's base. It performs harmonic response simulation analysis and post-processing on the results to obtain a base velocity impedance database. Through support vector regression, it obtains the prediction results corresponding to each frequency.

[0007] Patent document 2 designs a method for predicting the operating conditions of rotating machinery based on particle swarm optimization and support vector regression, which can effectively predict the vibration data trend of rotating machinery.

[0008] However, there is currently no publicly available literature on ship foundation impedance prediction models based on the Particle Swarm Optimization (PSO) algorithm and the Support Vector Machine Regression (SVR) algorithm, i.e., the PSO-SVR algorithm.

[0009] Traditional base impedance prediction models rely on numerical simulations based on finite element models. This method suffers from long modeling cycles, low simulation efficiency, and inability to perform real-time calculations. Each modification to structural parameters necessitates altering the base geometry model and re-dividing the finite element model. Furthermore, because traditional methods depend on fixed numerical calculation methods and models, they cannot flexibly adjust and optimize parameters according to specific circumstances, resulting in long iteration cycles and making it difficult to find a suitable base design solution in a short period. Summary of the Invention

[0010] The purpose of this invention is to provide a ship foundation impedance prediction model, device, and construction method based on support vector regression optimized by particle swarm optimization algorithm.

[0011] The objective of this invention is achieved through the following technical solution:

[0012] A ship foundation impedance prediction device based on support vector regression optimized by particle swarm optimization algorithm includes: a module that defines preset design parameters for vibration reduction and isolation of ship foundations;

[0013] Based on the vibration reduction and isolation design parameters, construct the module of the initial structure of the ship's foundation;

[0014] A module for establishing a predictive physical model of the ship's foundation impedance based on the initial structure of the ship's foundation;

[0015] A module for establishing a database of ship foundation vibration performance;

[0016] An optimization algorithm combining particle swarm optimization and support vector regression is used to learn the structural vibration performance from a ship foundation vibration performance database, resulting in a module for obtaining a foundation impedance prediction model based on particle swarm optimization and support vector regression.

[0017] The present invention also includes:

[0018] A method for constructing a ship foundation impedance prediction model based on support vector regression optimized by particle swarm optimization algorithm, using the aforementioned prediction device, includes the following steps:

[0019] Step 1: Define the preset design parameters for vibration reduction and isolation of the ship's foundation;

[0020] Step 2: Construct the initial structure of the ship's foundation according to the vibration reduction and isolation design parameters;

[0021] Step 3: Based on the initial structure of the ship's foundation, establish a predictive physical model for the ship's foundation impedance;

[0022] Step 4: Establish a database of ship foundation vibration performance;

[0023] Step 5: Combine the particle swarm optimization algorithm and support vector regression optimization algorithm to learn the structural vibration performance based on the ship foundation vibration performance database, and obtain the foundation impedance prediction model based on particle swarm optimization support vector regression.

[0024] Furthermore, the preset vibration reduction and isolation design parameters for the ship's foundation in step 1 are obtained based on the type, size, weight, and layout of the ship's mechanical equipment.

[0025] Furthermore, the structural design variables of the initial structure of the ship's base in step 2 include structural parameters, material parameters, and mechanical impedance data.

[0026] Furthermore, the application of the forecasting method includes:

[0027] Determine the vibration reduction and isolation design requirements for the ship's foundation based on the type, size, weight, and layout of the ship's mechanical equipment.

[0028] Based on the vibration reduction and isolation design requirements of the ship foundation, select the matching ship foundation type and design the initial structure of the ship foundation;

[0029] Define the initial structural design variables for the ship's foundation, including structural parameters and material parameters;

[0030] A foundation impedance prediction model based on particle swarm optimization support vector regression is used to solve for the initial structural impedance of the ship foundation.

[0031] Based on the initial structural impedance of the ship's foundation, determine whether the vibration reduction effect of the initial structure of the ship's foundation meets the equipment vibration reduction index requirements:

[0032] If the equipment vibration reduction index requirements are met, the final ship equipment vibration reduction structure is obtained based on the initial structure of the ship's foundation.

[0033] Otherwise, adjust the structural design variables of the initial structure of the ship's base and make another judgment until the equipment vibration reduction index requirements are met.

[0034] The present invention may also include:

[0035] A computer storage medium for storing a computer program, which, when read by a computer, executes the above-described method for constructing a forecast model.

[0036] A computer includes a processor and a storage medium, wherein when the processor reads a computer program stored in the storage medium, the computer executes the above-described method for constructing a forecast model.

[0037] A computer program product, which, when executed, implements the above-described method.

[0038] The beneficial effects of this invention are as follows:

[0039] This invention improves the accuracy of ship foundation impedance prediction, shortens the calculation time of ship foundation impedance, improves the efficiency of foundation impedance optimization design, and provides a model with better prediction effect and generalization ability.

[0040] This invention's model is built upon the physical principles and fundamental equations of impedance analysis, fully considering the influence of the ship's structure, thereby improving the reliability of the forecast results and exhibiting good generalization ability and prediction accuracy. Compared to traditional data-driven models based on large amounts of data, establishing a predictive physical model reduces the dependence on actual data, lowering the cost and difficulty of data collection and processing. Simultaneously, by utilizing prior knowledge and physical laws for feature selection and weight optimization, important impedance-related features are automatically extracted from the original data, while redundant and irrelevant features are removed, simplifying the forecast model and improving its robustness and generalization ability.

[0041] This invention is the first to establish a physical model of the input mechanical impedance (prediction) of a ship's foundation based on structural mechanics, and uses the particle swarm optimization algorithm (PSO) and the support vector regression optimization algorithm (SVR) to learn from the structural vibration performance database, thus realizing the joint driving force of the physical model and the data.

[0042] The model of this invention realizes the joint driving of the physical model and test data for predicting ship foundation impedance, which improves the prediction accuracy and efficiency of ship foundation impedance, breaks through the limitations of traditional ship foundation design methods, effectively improves the design efficiency of ship foundation, and can be applied to the work of predicting ship foundation impedance. Attached Figure Description

[0043] Appendix Figure 1 This is a flowchart illustrating the forecasting application method of the present invention;

[0044] Appendix Figure 2 This is a schematic diagram of the frequency characteristics of the mechanical impedance of the ship's base according to the present invention;

[0045] Appendix Figure 3 This is a flowchart illustrating the construction method of the present invention. Detailed Implementation

[0046] The present invention will now be further described with reference to the accompanying drawings.

[0047] Example 1:

[0048] This invention provides a ship foundation impedance prediction device based on support vector regression optimized by particle swarm optimization algorithm, comprising: a module defining preset ship foundation vibration reduction and isolation design parameters;

[0049] Based on the vibration reduction and isolation design parameters, construct the module of the initial structure of the ship's foundation;

[0050] A module for establishing a predictive physical model of the ship's foundation impedance based on the initial structure of the ship's foundation;

[0051] A module for establishing a database of ship foundation vibration performance;

[0052] An optimization algorithm combining particle swarm optimization and support vector regression is used to learn the structural vibration performance from a ship foundation vibration performance database, resulting in a module for obtaining a foundation impedance prediction model based on particle swarm optimization and support vector regression.

[0053] In this embodiment, a method for constructing a ship foundation impedance prediction model based on support vector regression optimized by particle swarm optimization is described, applying the aforementioned prediction device, as shown in the attached diagram. Figure 3 As shown, it includes the following steps:

[0054] Step 1: Define the preset design parameters for vibration reduction and isolation of the ship's foundation;

[0055] Step 2: Construct the initial structure of the ship's foundation according to the vibration reduction and isolation design parameters;

[0056] Step 3: Based on the initial structure of the ship's foundation, establish a predictive physical model for the ship's foundation impedance;

[0057] Step 4: Establish a database of ship foundation vibration performance;

[0058] Step 5: Combine the particle swarm optimization algorithm and support vector regression optimization algorithm to learn the structural vibration performance based on the ship foundation vibration performance database, and obtain the foundation impedance prediction model based on particle swarm optimization support vector regression.

[0059] Furthermore, the preset vibration reduction and isolation design parameters for the ship's foundation in step 1 are obtained based on the type, size, weight, and layout of the ship's mechanical equipment.

[0060] Furthermore, the structural design variables of the initial structure of the ship's base in step 2 include structural parameters, material parameters, and mechanical impedance data.

[0061] Specifically, establishing a database of ship foundation vibration performance includes:

[0062] A database of ship foundation vibration performance was established based on a predictive physical model, including foundation material parameters (Young's modulus, density, Poisson's ratio), structural parameters (length, width, and thickness of the face plate, web plate, elbow plate, and rib plate), and corresponding mechanical impedance data.

[0063] When obtaining mechanical impedance data, numerical simulation or experimental testing can be used to apply a frequency of ω to the structure. i The simple harmonic excitation force f(t) is measured, and the vibration response x(t) after entering steady state is obtained. By comparing the amplitude and phase difference of these two simple harmonic waves, the impedance data at a certain frequency can be obtained. Different excitation frequencies ω are obtained through experiments. i By analyzing the impedance data at a given point, the frequency response characteristic curve of the system can be obtained.

[0064] Example 2:

[0065] This embodiment provides a method for predicting ship foundation impedance based on support vector regression optimized by particle swarm optimization algorithm, as shown in the attached figure. Figure 1 As shown, the application method applies the prediction method described in Embodiment 1 to the vibration reduction and isolation design method for ship foundations. The application method includes:

[0066] The steps for determining the vibration reduction and isolation design requirements of a ship's foundation, based on the type, size, weight, and layout of the ship's mechanical equipment, specifically include:

[0067] Step S11, determine the type of ship machinery and equipment to be installed on the base: based on the purpose and function of the ship, determine the type of machinery and equipment installed on the ship, such as main engine, generator, pump, etc., and clarify which type of ship machinery and equipment base needs to be impedance predicted.

[0068] Step S12, evaluate the inherent vibration characteristics of the ship structure: evaluate the inherent vibration characteristics of the ship structure, including parameters such as natural frequency and mode shape;

[0069] Step S13: Determine the size, weight, and deployment of the ship's mechanical equipment: Analyze the vibration characteristics that the ship's mechanical equipment may generate during operation, including vibration frequency and vibration amplitude, and evaluate its vibration characteristics;

[0070] Step S14: Based on the results of steps S11, S12, and S13, and taking into account the inherent vibration characteristics of the ship structure and the vibration characteristics of the mechanical equipment, determine the requirements for vibration reduction and isolation design of the ship's foundation.

[0071] Based on the vibration reduction and isolation design requirements of ship foundations, the steps for selecting a matching ship foundation type and designing the initial structure of the ship foundation include:

[0072] Step S21, Select the appropriate ship foundation type: Based on the structural characteristics of the ship and the design requirements for foundation vibration reduction and isolation, select the appropriate ship foundation type; common foundation types include wall-mounted foundation, straight foundation, square foundation, non-square foundation, etc., select the foundation type that can effectively reduce vibration based on the ship's vibration frequency, vibration amplitude and the characteristics of the foundation material;

[0073] Step S22, Design the initial structure of the ship's base: Based on the selected type of ship's base, consider factors such as the material, shape, and size of the base to design the initial structure of the ship's base; ensure that the base can withstand the weight and vibration of the ship's mechanical equipment and has a good vibration reduction and isolation effect; during the design process, existing base design experience and specifications can be referenced to ensure the stability and reliability of the base.

[0074] The steps for defining the initial structural design variables (including structural parameters, material parameters, etc.) of a ship's foundation;

[0075] The steps for solving the initial structural impedance of the ship's foundation using the foundation impedance prediction model based on particle swarm optimization support vector regression as described in Implementation Method 1;

[0076] The steps to determine whether the vibration reduction effect of the initial structure of the ship's foundation meets the equipment vibration reduction requirements based on the initial structural impedance of the ship's foundation are as follows:

[0077] If the equipment vibration reduction index requirements are met, the final ship equipment vibration reduction structure is obtained based on the initial structure of the ship's foundation.

[0078] Otherwise, adjust the structural design variables of the initial structure of the ship's base and make another judgment until the equipment vibration reduction index requirements are met.

[0079] Example 3:

[0080] This embodiment provides a computer storage medium for storing a computer program. When the computer program is read by a computer, the computer executes the method for constructing the forecast model described in this embodiment.

[0081] This embodiment also includes a computer, comprising a processor and a storage medium. When the processor reads a computer program stored in the storage medium, the computer executes the method for constructing a forecast model as described in Embodiment 1.

[0082] In addition, this embodiment also provides a computer program product, which is characterized in that, when the computer program is executed, it implements the method described in embodiment 1.

[0083] Example 4:

[0084] This embodiment is further described in detail based on the technical solution provided above:

[0085] The step of establishing a predictive physical model of the ship foundation impedance based on the initial structure of the ship foundation specifically includes:

[0086] For the coupled system of "equipment-base-hull structure" of a ship, the calculation of the mechanical impedance of the base, as an intermediate structure, usually needs to consider the base itself and all structures connected to the hull plates. Generally, the base and hull structure can be regarded as a spatial structure composed of several basic structural units such as plates, beams, and shells. The mutual coupling between the structural units makes the "equipment-hull structure" a complex structural vibration system with relatively complex boundary conditions.

[0087] Based on the force-electric analogy theory, the vibration system is likened to an admittance circuit, the force of mechanical components is used to simulate the current passing through electrical components, the mass m is equivalent to the capacitance, the damping coefficient c is equivalent to the reciprocal of the resistance, and the spring stiffness k is equivalent to the reciprocal of the inductance.

[0088] Taking the forced vibration differential equation of a single-degree-of-freedom system as an example, assume the excitation force of the system is:

[0089] ;

[0090] The differential equation of motion for the system is:

[0091] ;

[0092] Its forced vibration solution can be expressed as:

[0093] ;

[0094] In the formula: Z is the structural mechanical resistance. .

[0095] The above equation shows that the mechanical impedance of a structure can be obtained from its mass, stiffness, and damping. For ease of discussion, let's assume that the mechanical impedance under the working load of the vibration isolator has been measured and is as follows:

[0096] ;

[0097] Regarding the frequency characteristics of the base mechanical impedance, such as Figure 2 As shown, the estimation and analysis of the dynamic performance parameters of the base structure in each frequency band are presented. The calculations are performed across the following five frequency bands:

[0098] (1) Low frequency band

[0099] When the excitation frequency of the equipment is slightly greater than the first-order bending natural frequency of the hull beam, the impedance of the base mainly manifests as the impedance of the hull beam, which is free at both ends. Figure 2The first segment. At this point, the input impedance of the base can be approximated as:

[0100] ;

[0101] In the formula: Let be the linear density of the beam (kg / m). Let be the bending wave velocity in the beam (m / s); , For the korihoff function, , ; The wave number of the hull beam during bending vibration. This is the length of the ship's hull beam.

[0102] (2) Mid-to-low frequency band

[0103] When the base length exceeds 1 / 4 of the bending wavelength of the hull beam, the beam-shaped bending of the base must be considered. The hull ribs are treated as the elastic foundation of the ship's base, and the ship's base is considered as a straight beam supported on the elastic foundation of the hull ribs. Figure 2 The second section. At this point, the input mechanical impedance of the ship's foundation is mainly caused by static stiffness, and its impedance can be approximately expressed as:

[0104] ;

[0105] In the formula: The moment of inertia of the base section, To account for the section moment of inertia of the hull ribs with attached wing plates, For the width of the boat; The spacing between the hull ribs (the linear density along the length of the base); Forecast frequency; The base length; , The distance of the excitation point from both ends of the base. The average linear density of the base.

[0106] (3) Mid-frequency band

[0107] When the length of the hull ribs is much greater than the bending wavelength of the base, the effect of the hull rib curvature can be ignored, and the elastic foundation beam and the ship's base can be treated as infinitely long beams. Figure 2 The third segment. At this point, the input impedance of the base is mainly determined by its inertial component:

[0108] ;

[0109] In the formula: The longitudinal wave velocity in the steel structure; , The average section radius of inertia of the ribs on the hull; The linear density of the ribs on the ship's hull, where a and c are coefficients.

[0110] (4) Mid-to-high frequency band

[0111] When the dimension of the panel between the base web and the adjacent elbow plate is larger than half the wavelength of the bending wave, the contribution of the panel to the base input impedance will be significantly enhanced. The impedance of the base is mainly determined by the panel, and the mathematical model of the base impedance can be simplified to a panel that is simply supported on three sides (supported between the base web and the adjacent elbow plate) and free on one side. In this case, the mechanical impedance is mainly determined by its static stiffness.

[0112] ;

[0113] In the formula: denoted as , where h is the bending stiffness of the base panel; is the panel thickness; μ is the material Poisson's ratio; a and b are the lengths of the three-sided simply supported plate along the length and width directions of the base; x is the distance from the excitation point to the nearest side of the two elbow plates; y is the distance from the excitation point to the web plate; and α is a coefficient.

[0114] (5) High frequency band

[0115] When the excitation frequency exceeds the first-order bending frequency along the short side of the rectangular simply supported plate, the input impedance of the base plate becomes independent of the boundary conditions. In this case, the plate can be considered an infinitely large flat plate, and its input impedance is:

[0116] ;

[0117] In the formula: ρ is the bending stiffness of the base panel; h is the panel thickness; ρ is the density of the material.

[0118] In a circuit, electrical components (capacitors, resistors, and inductors) are connected in two ways: parallel and series. Similarly, in a vibration system, the connection methods for the three discrete components are also the same: parallel mechanical systems correspond to parallel electrical systems, and series mechanical systems correspond to series electrical systems. For a combined system composed of multiple components, if each component has the same vibration velocity (displacement) under the action of the excitation force, then these components are considered to be connected in parallel; otherwise, they are considered to be connected in series.

[0119] The impedance characteristic of a parallel system is: the total impedance of the entire system, composed of any number of discrete components, at the excitation point. For the impedance of each component sum:

[0120] ;

[0121] The admittance characteristic of a series system is: the total admittance of the entire system, composed of any number of discrete components, at the excitation point. For the admittance of each component The sum of these, the total impedance is its derivative:

[0122] ;

[0123] Combining the differential equation of single-degree-of-freedom forced vibration and the definition of mechanical impedance, we know that the velocity impedances of the spring, mass, and damper elements are respectively... , , For the installation foundation of marine mechanical equipment, a force F acts perpendicularly on the base panel. The displacement of the point of application of the force F consists of two parts: the displacement of the base itself and the displacement of the hull structure connected to the base. Since the displacements of the base itself and the hull structure are not equal, the combined structure is a series structure, and the total input impedance Z of the combined system is the reciprocal of the total input admittance.

[0124] ;

[0125] Calculate the input impedance level for a typical mounting configuration:

[0126] ;

[0127] In the formula, the impedance reference value Z0 = 1 N / (m / s).

[0128] Example 5:

[0129] This embodiment combines Figure 1-3 The technical solutions provided above are described in further detail as follows:

[0130] The step described is to use a combined particle swarm optimization and support vector regression (PSO-SVR) algorithm to learn the structural vibration performance based on a ship foundation vibration performance database and obtain a foundation impedance prediction model based on PSO-optimized support vector regression. PSO-SVR is an optimization algorithm that combines particle swarm optimization and support vector regression, which can improve the learning performance and generalization ability of support vector regression. Specifically, it includes:

[0131] Step S441, Prepare the dataset: Divide the ship foundation vibration performance database into training set, validation set and test set using the hold-out method.

[0132] Step S442, establish the initial model of support vector regression: regard the ship foundation impedance prediction problem as a support vector regression problem, that is, seek the optimal hyperplane that minimizes the total error of all sample points from the hyperplane.

[0133] Step S443, Initialize the particle swarm: Define the number of particles and the dimension of each particle. The dimension of each particle corresponds to the parameters of the SVR model. Randomly generate the position and velocity of the particles.

[0134] Step S444, calculate fitness: For each particle, train the SVR model and calculate the fitness (using regression error here) based on the SVR parameters represented by its position.

[0135] Step S445: Determine if the termination condition is met: Determine if the particle fitness meets the termination condition or if the maximum number of iterations has been reached. If the termination condition is met, proceed to step S448; otherwise, proceed to step S446.

[0136] Step S446, Update particle velocity and position: Based on the idea of ​​particle swarm optimization and the fitness calculation results, update the particle velocity and position.

[0137] Step S447, calculate the fitness of the updated particles: For the updated particle velocity and position, calculate the fitness of the support vector regression, and proceed to step S445.

[0138] Step S448, output the optimal position of the particle swarm: the SVR parameters represented by the optimal position of the particle swarm are used as the optimal parameters of the PSO-SVR model.

[0139] Step S449, train the support vector regression model: use the training set divided in step S441 to train the support vector regression model, find the optimal hyperplane to maximize the margin of training samples that satisfy the marginal constraints, and limit the error between the prediction results and the true values.

[0140] Step S4410, validate the support vector regression model: Input the validation set partitioned in step S441 into the model for prediction, and compare the prediction results with the actual values ​​on the validation set. Calculate an evaluation metric to measure the model's prediction accuracy on the validation set. Based on the evaluation results of the validation set, further adjust the model parameters.

[0141] Step S4411, Test the support vector regression model: Input the test set divided in step S441 into the model for prediction, compare the prediction results with the actual values ​​of the test set, and evaluate the model's generalization ability on unknown data by calculating evaluation indicators.

[0142] The above description of several specific embodiments further details the technical solution provided by the present invention in order to highlight the advantages and benefits of the technical solution provided by the present invention. However, the above-described specific embodiments are not intended to limit the present invention. Any reasonable modifications and improvements to the present invention, combinations of embodiments, and equivalent substitutions based on the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0143] In the description of this specification, only preferred embodiments of the present invention are described, and should not be construed as limiting the scope of the invention. Furthermore, the use of terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples" indicates that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or N embodiments or examples. Furthermore, those skilled in the art can combine and integrate the different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction. Additionally, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of the present invention, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified. Any process or method described in the flowcharts or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logical functions or processes, and the scope of preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order according to the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain. The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, a “computer-readable medium” can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples of computer-readable media (a non-exhaustive list) include the following: electrical connections having one or N wires (electronic devices), portable computer disks (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM).Furthermore, the computer-readable medium can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory. It should be understood that various parts of the invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0144] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments. Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

Claims

1. A ship foundation impedance prediction device based on particle swarm optimization support vector regression, characterized by, include: A module for defining preset design parameters for vibration reduction and isolation of ship foundations; Based on the vibration reduction and isolation design parameters, construct the module of the initial structure of the ship's foundation; A module for establishing a predictive physical model of the ship's foundation impedance based on the initial structure of the ship's foundation; A module for establishing a database of ship foundation vibration performance; An optimization algorithm combining particle swarm optimization and support vector regression is used to learn the structural vibration performance from a ship foundation vibration performance database, resulting in a module for obtaining a foundation impedance prediction model based on particle swarm optimization and support vector regression.

2. A method for constructing a ship foundation impedance prediction model based on a support vector regression optimized by a particle swarm algorithm, characterized in that, The application of the forecasting device according to claim 1 includes the following steps: Step 1: Define the preset design parameters for vibration reduction and isolation of the ship's foundation; Step 2: Construct the initial structure of the ship's foundation according to the vibration reduction and isolation design parameters; Step 3: Based on the initial structure of the ship's foundation, establish a predictive physical model for the ship's foundation impedance; Step 4: Establish a database of ship foundation vibration performance; Step 5: Combine the particle swarm optimization algorithm and support vector regression optimization algorithm to learn the structural vibration performance based on the ship foundation vibration performance database, and obtain the foundation impedance prediction model based on particle swarm optimization support vector regression.

3. The method of claim 2, wherein the method is characterized by: The preset vibration reduction and isolation design parameters for the ship's foundation in step 1 are obtained based on the type, size, weight, and layout of the ship's mechanical equipment.

4. The method of claim 2, wherein the method is characterized by: The structural design variables of the initial structure of the ship's base in step 2 include structural parameters, material parameters, and mechanical impedance data.

5. The method for constructing a ship foundation impedance prediction model based on support vector regression optimized by particle swarm optimization according to claim 2, characterized in that, The applications of the forecasting method include: Determine the vibration reduction and isolation design requirements for the ship's foundation based on the type, size, weight, and layout of the ship's mechanical equipment. Based on the vibration reduction and isolation design requirements of the ship foundation, select the matching ship foundation type and design the initial structure of the ship foundation; Define the initial structural design variables for the ship's foundation, including structural parameters and material parameters; A foundation impedance prediction model based on particle swarm optimization support vector regression is used to solve for the initial structural impedance of the ship foundation. Based on the initial structural impedance of the ship's foundation, determine whether the vibration reduction effect of the initial structure of the ship's foundation meets the equipment vibration reduction index requirements: If the equipment vibration reduction index requirements are met, the final ship equipment vibration reduction structure is obtained based on the initial structure of the ship's foundation. Otherwise, adjust the structural design variables of the initial structure of the ship's base and make another judgment until the equipment vibration reduction index requirements are met.

6. A computer storage medium for storing computer programs, characterized in that, When the computer program is read by the computer, the computer executes the method for constructing the forecast model as described in claim 2.

7. A computer, comprising a processor and a storage medium, characterized in that, When the processor reads the computer program stored in the storage medium, the computer executes the method for constructing the forecast model as described in claim 2.

8. A computer program product, as a computer program, characterized in that, When the computer program is executed, it implements the method of claim 2.

Images