Method for carrying out model parameter optimization on wave energy device model test error

Abstract

The invention discloses a method for carrying out model parameter optimization on model test errors of a wave energy device, and particularly relates to the technical field of model parameter optimization, comprising the following steps: S1, collecting long-term accumulated test data of the wave energy device, and establishing a test database; s2, carrying out orthogonal test design; and S3, Bayesian parameter optimization: carrying out training optimization on variable factors based on a machine learning method of a Bayesian Gaussian process so as to reduce a scale effect of a model test. According to the method, the next model parameter is optimized and selected through the existing model test parameters, so that the scale effect of the wave energy device model is minimized, iteration sample points are continuously and automatically selected through a small number of selected sample points by means of a machine learning optimization method, the cost of the model test is reduced, and the test efficiency is improved.

Description

Technical Field

[0001] The invention relates to the technical field of model parameter optimization, and in particular to a method for optimizing model parameters based on model test errors of a wave energy device. Background Art

[0002] Wave energy is an important form of ocean energy. It has abundant reserves and can provide the world with renewable clean energy. With the gradual depletion of fossil fuels and the increasing prominence of environmental problems, the development and utilization of ocean energy has become one of the important means to alleviate the global energy crisis. Ocean energy comes in various forms, including tidal energy, ocean current energy, temperature difference energy and wave energy. Among them, wave energy has become the focus of research and development due to its high energy density and relatively stable characteristics. In recent years, research institutions and companies around the world have been actively developing and optimizing wave energy conversion devices to improve energy conversion efficiency and device reliability.

[0003] In the process of research and development of wave energy devices, model tests are one of the important means to evaluate their performance. Since the construction and testing costs of prototype devices are high and the test conditions are difficult to fully control, experimental studies are usually carried out through scaled models. The key to model tests is how to ensure that the scaled model can accurately reproduce the behavior of the prototype device under real ocean conditions. The similarity criteria commonly used include the Froude similarity criterion and the Reynolds similarity criterion, which are used to ensure the mechanical similarity between the scaled model and the prototype in terms of gravity, inertia, viscosity, friction, etc. However, these two similarity criteria are usually difficult to meet simultaneously under model scaling conditions, especially under the various mechanical effects involved in wave energy devices, which leads to the scale effect. The scale effect will have an adverse effect on the accuracy of the model test results, and thus affect the evaluation of the performance of the prototype device. At present, the model test of wave energy devices mainly uses the Froude similarity criterion for scaling calculations. The Froude similarity is mainly used for gravity-dominated phenomena, such as wave propagation and free surface motion, and is suitable for simulating the main hydrodynamic behaviors in wave energy devices. However, the effects of viscosity and friction need to follow the Reynolds similarity criterion, and in the process of model scaling, these two similarity criteria cannot be met simultaneously. This results in differences in the performance of the scaled model and the prototype device under the action of viscosity and friction, resulting in scale effects that affect the accurate assessment of energy conversion efficiency and performance.

[0004] In the existing technical solutions, although the use of Froude similarity can better simulate the macroscopic behavior of waves, the Reynolds similarity is difficult to achieve, resulting in errors in the model test results. Especially when the wave energy device involves complex flows, viscous effects and multiple dynamic interactions, this error will significantly affect the reliability of the model test results. The main shortcoming of the existing technical solutions is the lack of an efficient and systematic method to reduce the influence of scale effects. Although numerical simulation and experimental correction can partially solve this problem, due to the complexity of the wave energy device and the limitations of the experimental cost, the existing methods still have a lot of room for improvement in efficiency and accuracy. Specifically, the shortcomings of the existing technology include: 1. Lack of systematicity: The existing experimental design and analysis methods lack systematic data management, and are unable to comprehensively analyze and summarize the impact of scale effects on model experiments under various variables (such as device structure, PTO system type, model scale ratio, wave conditions, etc.). There is a lack of means to establish a systematic database to manage experimental data, resulting in poor comprehensiveness of experimental analysis and stability of results.

[0005] 2. Lack of efficient experimental design methods: When faced with multiple variables and experimental conditions, existing technologies usually rely on experience and manual adjustments, making it difficult to design experiments systematically. In order to evaluate the impact of scale effects on model experiments under different experimental conditions, a large number of repeated experiments are often required, which is time-consuming and costly. The lack of efficient experimental methods such as orthogonal experimental design makes it difficult to achieve rapid and low-cost systematic analysis and quantification of multiple variables.

[0006] 3. Limited optimization capability: The optimization process in existing methods mainly adjusts parameters through empirical formulas or simple exhaustive methods. It lacks systematic means based on mathematical models and optimization algorithms, and it is difficult to find the global optimal parameter settings under complex multivariable conditions. Summary of the invention

[0007] The purpose of the present invention is to provide a method for optimizing model parameters of wave energy device model test errors, aiming to systematically analyze the main variables affecting the scale effect by combining different means, and reduce the influence of the scale effect on the test results.

[0008] In order to achieve the above-mentioned object, the present invention provides the following technical solution: a method for optimizing model parameters of wave energy device model test errors, comprising the following steps; Step S1, collecting long-term accumulated wave energy device test data and establishing a test database; Step S2, orthogonal experimental design; S2.1, Classification of variable factors; S2.2, design orthogonal test table; S2.3, scale effect assessment: compare the average scale effect difference of the variables, preliminarily determine the importance of the variables in the scale effect, and then perform variance analysis to determine whether the variables have a significant impact on the scale effect; Step S3, Bayesian parameter optimization: Based on the machine learning method of Bayesian Gaussian process, the variable factors are trained and optimized to reduce the scale effect of the model test.

[0009] Preferably, the establishment of the test database in S1 includes: S1.1. Database classification: S1.1.1. Types of wave energy device structures: including oscillating float type, swinging float type, and horizontal oscillating body type; S1.1.2, PTO device types: including hydraulic system, mechanical system and linear generator; S1.1.3 Model scaling: The scaling ratio is selected according to the different prototype devices, such as 1:10, 1:20 or 1:50 scale ratios; S1.1.4, Wave conditions: including wave conditions (regular waves, irregular waves) and wave directions (beam waves, oblique waves); S1.2 Data extraction: S1.2.1. Multi-level screening method based on classification characteristics: According to the wave energy device structure type, PTO device type, and working conditions, a multi-level screening method is used to gradually narrow the data range; S1.2.2, Keyword matching and filtering: In the database, preliminary filtering of data is performed by keyword matching; S1.3、Data optimization: S1.3.1. Statistical method regression analysis: Regression analysis (such as linear regression, polynomial regression) is used to establish the relationship between classification characteristics (such as device structure, PTO device type, model scaling, wave conditions, etc.) and response (scale effect), and weights are assigned to each classification feature, and the test data are optimized based on these weights.

[0010] Preferably, the variable factors in S2.1 include the wave energy device structure type, the PTO device type, the model scaling ratio and the wave conditions.

[0011] Preferably, in S2.2, for four factors, the wave energy device structure type and the PTO device type have three variable levels, and the wave conditions and the model scaling ratio each have two variable levels. In order to ensure that the combination of different factors is fully covered, the present invention uses the L18 orthogonal table for experimental design.

[0012] Preferably, the specific steps of S3 are as follows: S3.1. Input the initial sample point; S3.2, minimize the objective function; S3.3, using Bayesian optimization to establish a proxy model, which is a Gaussian process and is used to approximate the objective function; S3.4. Set the number of iterations. In each iteration, use the known data to calculate the proxy model through the Gaussian process, and select the next evaluation point by the acquisition function. During the iteration process, the proxy model is continuously updated and the parameters are adjusted according to the posterior distribution until the optimal solution is found, thereby reducing the scale effect of the model test.

[0013] Preferably, the optimization model parameters obtained through machine learning iterations need to be trial-calculated and compared with the experimental true values ​​to verify the accuracy of the Bayesian optimization method calculation.

[0014] Preferably, the model parameters after Bayesian optimization are used to design test conditions based on the elimination method of orthogonal experiments. The influence of non-similar factors on the model test is eliminated by the elimination method. Thereafter, the number of independent test conditions is increased according to the number of parameters to be measured, and finally the true value response change law that is not interfered by the scale effect is obtained.

[0015] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. Improve test efficiency and reduce costs: By establishing a test database, collecting and sorting the long-term accumulated wave energy device test data, classifying and screening the test data, and thus reducing the need for repeated tests; 2. Systematic analysis of the impact of multivariate factors: Based on the model test data in the database, orthogonal test design is used to systematically summarize and analyze multiple variables such as different wave energy device structure types, PTO device types, wave conditions, etc., in order to fully understand the impact of various variables on the scale effect, thereby optimizing the test design and result interpretation; 3. Intelligently optimize key parameters and reduce scale effect: Use the Bayesian optimization algorithm to perform proxy modeling on the test data through the Gaussian process, intelligently select the best parameter point for the next test, and gradually optimize key parameters to minimize the power difference between the scale model and the prototype. This method can find the globally optimal parameter setting through a small amount of test data, thereby effectively reducing the impact of the scale effect on the test results and significantly reducing the test cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of the method of the present invention; Figure 2 is the damping force of the PTO device in the embodiment of the present invention And the model output power Relationship diagram; Figure 3 is the damping force of the PTO device in the embodiment of the present invention Relationship diagram of power difference E with objective function; Figure 4 It is a graph showing the convergence process of the objective function power difference E after 20 iterations in an embodiment of the present invention; Figure 5 The third and fourth iteration process prediction functions and acquisition function distribution diagrams in the embodiment of the present invention; (a) Bayesian optimization third iteration Gaussian process prediction diagram; (b) Bayesian optimization third iteration acquisition function distribution diagram; (c) Bayesian optimization fourth iteration Gaussian process prediction diagram; (d) Bayesian optimization fourth iteration acquisition function distribution diagram; Figure 6 The sixth and seventh iterations of the process prediction function and the function distribution diagram in the embodiment of the present invention; (a) Bayesian optimization sixth iteration Gaussian process prediction diagram; (b) Bayesian optimization sixth iteration acquisition function distribution diagram; (c) Bayesian optimization seventh iteration Gaussian process prediction diagram; (d) Bayesian optimization seventh iteration acquisition function distribution diagram; Figure 7 The 17th and 18th iteration process prediction functions and acquisition function distribution diagrams in the embodiments of the present invention; (a) Bayesian optimization 17th iteration Gaussian process prediction diagram; (b) Bayesian optimization 17th iteration acquisition function distribution diagram; (c) Bayesian optimization 18th iteration Gaussian process prediction diagram; (d) Bayesian optimization 18th iteration acquisition function distribution diagram; Figure 8 This is a distribution diagram of the prediction function after 20 iterations in an embodiment of the present invention; DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0018] The present invention provides Figure 1 A method for optimizing model parameters of a wave energy device model test error is shown, comprising the following steps; Step S1: Establish a systematic test database to collect and manage various test data of wave energy devices. The test steps are as follows: S1.1. Database classification: S1.1.1. The main research object of the present invention is an oscillating body type wave energy device. The structural types of wave energy devices are divided into the following types according to the degree of freedom of the floating body: including an oscillating float type, which mainly converts energy by up and down swinging, usually a float (or multiple floats) installed on the sea surface; a swinging float type, which uses the horizontal movement of waves to drive the float to swing back and forth or left and right; a horizontal oscillating body type, which consists of a horizontally placed oscillating body, and uses the horizontal movement of the oscillating body to drive a hydraulic or mechanical system to generate electricity; S1.1.2, PTO device types: including hydraulic systems, mechanical systems and linear generators; S1.1.3 Model scaling: According to the different scaling scales of the prototype, the common ones are 1:10, 1:20 or 1:50 scale ratios; S1.1.4, Wave conditions: Wave conditions (regular waves, irregular waves) and wave direction (beam waves, oblique waves); S1.2 Data extraction: S1.2.1. Multi-level screening method based on classification characteristics: According to the wave energy device structure type, PTO device type, and wave conditions, a multi-level screening method is used to gradually narrow the data range; S1.2.2, Keyword matching and filtering: In the database, preliminary filtering of data is performed by keyword matching (such as "oscillating float type", "regular wave transverse wave", "scaling scale 1 / 10", etc.); S1.3、Data optimization: S1.3.1. Statistical methods regression analysis: Regression analysis (such as linear regression, polynomial regression) is used to establish the relationship between classification features (such as wave energy device structure type, PTO device type, model scaling, wave conditions, etc.) and response (scale effect), and weights are assigned to each classification feature. According to the weights assigned to each classification feature, the data are optimized according to these weights.

[0019] Step S2: Orthogonal experiment design. Orthogonal experiment is a systematic experimental design method that can be used to analyze the impact of multiple factors on a certain result and obtain the combined effect of multiple factors and multiple levels through a smaller number of experiments. The specific steps are as follows: S2.1. Classification of variable factors, including wave energy device structure type, PTO device type, wave conditions and model scaling; S2.2. Design an orthogonal test table. For four factors, the wave energy device structure type and PTO device type each have three variable levels, and the wave conditions and model scaling scale each have two variable levels. In order to ensure that the combination of different factors is fully covered, the L18 (3^2 × 2^2) orthogonal table is selected for experimental design. This design can effectively reduce the number of experiments and ensure that each factor combination is fully covered. The orthogonal experimental design is shown in the following table: Test No. PTO device type Wave energy device structure type Wave conditions Model Scale 1 Hydraulic system Oscillating float type rule 1 / 10 2 Hydraulic system Swing float type irregular 1 / 20 3 Hydraulic system Horizontal Oscillation Pose rule 1 / 20 4 Mechanical system Oscillating float type irregular 1 / 10 5 Mechanical system Swing float type rule 1 / 10 6 Mechanical system Horizontal Oscillation Pose irregular 1 / 20 7 Linear generator system Oscillating float type rule 1 / 20 8 Linear generator system Swing float type irregular 1 / 10 9 Linear generator system Horizontal Oscillation Pose rule 1 / 10 10 Hydraulic system Oscillating float type irregular 1 / 20 11 Hydraulic system Swing float type rule 1 / 20 12 Hydraulic system Horizontal Oscillation Pose irregular 1 / 10 13 Mechanical system Oscillating float type rule 1 / 10 14 Mechanical system Swing float type irregular 1 / 20 15 Mechanical system Horizontal Oscillation Pose rule 1 / 20 16 Linear generator system Oscillating float type irregular 1 / 10 17 Linear generator system Swing float type rule 1 / 10 18 Linear generator system Horizontal Oscillation Pose irregular 1 / 20 S2.3, scale effect assessment: Orthogonal test tables can be used to evaluate the impact of each variable factor on the final scale effect. For example, to evaluate the impact of PTO device type on scale effect, the above 18 test data are classified and grouped according to PTO device type: Test numbers for hydraulic system PTO device type: 1, 2, 3, 10, 11, 12; test numbers for mechanical system PTO device type: 4, 5, 6, 13, 14, 15; Test numbers for PTO device type linear generator system: 7, 8, 9, 16, 17, 18; For all tests for each PTO device type, the average response value of the scale error due to scale effect is calculated as follows: Average scale error of PTO device in hydraulic system ; Average scale error of mechanical system PTO device ; Average scale error of PTO device of linear generator system ; in, : The number is the scale error existing in the i-th test.

[0020] Compare the average scale errors corresponding to different PTO device types. If the difference between these average scale error response values ​​is large, it means that the scale effect is greatly affected by the PTO device type. Therefore, by comparing the difference in average scale errors, it can be preliminarily determined whether the PTO device type has a significant impact on the scale effect; S2.4. In order to further quantify the influence of PTO device type on the scale effect, an analysis of variance (ANOVA) was performed. The main steps are as follows: First, the variance between PTO device types (between-group variance) was calculated to quantify the extent to which PTO device type affects the size effect. , : The mean scale error of the i-th group of experiments, : Mean square error of all test samples; Mean square between groups , the degree of freedom between groups in the designed experiment is 2; Subsequently, the within-group variance is calculated to represent the variation in scale effect due to other factors (wave energy device structure type, wave conditions, model scaling). , : The scale error value of the jth test in the i-th group; Mean Square Within groups , the degree of freedom within the group in the designed experiment is 15; Then, the F value was calculated and the F-ratio was used to determine whether the PTO device type had a significant effect on the scale effect. , the calculated F value and critical value Compare the results and assume a significance level , indicating that there is a 5% probability of making mistakes, calculated by statistical software It is approximately equal to 3.68. If the calculated F value is greater than 3.68, it means that at the 95% confidence level, the difference in scale effect between different PTO device types is significant.

[0021] Step S3: Bayesian parameter optimization: After that, assuming that the orthogonal test method verifies that the type of PTO device has a significant impact on the scale effect in the model test, the Bayesian optimization algorithm is then used to optimize the key parameters of the PTO device to reduce the impact of the scale effect and improve the accuracy of the model test. The specific steps of the test are as follows: (1) Establishment of objective function: In the study of model scaling, the PTO system is usually scaled according to Froude similarity. Under the Froude similarity condition, assuming that λ is the geometric scale scaling factor, the force scaling ratio is λ 3 , the speed scaling factor is At this time, the energy conversion efficiency of the scaled model can be ensured to be similar to that of the prototype, that is, the similarity of power can be ensured, and the energy absorption characteristics of the floating body in the model are consistent with those of the prototype; the power generation power of the PTO device ,in, The damping force applied by the PTO device, is the velocity of the floating body in the model test; the scaling ratio of power is ; Due to the velocity of the floating body in the model test It is usually difficult to control, and the energy loss (such as friction loss, leakage of hydraulic system, etc.) may also be different from the prototype. Therefore, by controlling the damping force of the PTO device The energy loss in the scaled model can be matched with the prototype to ensure the consistency of energy conversion efficiency; based on the Bayesian optimization algorithm, the damping force of the PTO device is dynamically adjusted , in order to minimize the defined objective function E, its expression form is as follows:

[0022] in and The power outputs of the PTO devices of the model and the prototype are respectively. The consistency of the power outputs of the model and the prototype is achieved by minimizing the objective function E. To simulate the actual situation, the following assumptions and steps are made: 1. Assuming the PTO device damping force And the model output power There is a nonlinear relationship between Figure 2 As shown, its true expression is a complex black box function; PTO damping force The value range of is between 0 and 630 N / (m / s); the transparent shaded part in the figure is the 95% confidence interval, which simulates the uncertainty in the actual model test by introducing a noise that conforms to the normal distribution; 2. Assuming the power output of the prototype PTO device , geometric scaling factor . Figure 3 Demonstrates the PTO unit damping force The relationship between the power difference E of the objective function, the transparent shaded part is also the 95% confidence interval; (2) Iterative optimization: Call the gp_minimize function in the scikit-optimize library (other optimization libraries can be used instead, such as Optuna or Hyperopt. For example, Optuna can perform adaptive sampling and has efficient parallel optimization features, which is suitable for large-scale optimization tasks; while Hyperopt provides a search method based on distribution estimation, which is suitable for dealing with optimization problems with complex search spaces) and minimize the objective function E based on a surrogate model called Gaussian Process (GP) (other alternative Gaussian processes can be used, such as random forests, support vector regression (SVR) or neural networks, etc. These methods have different advantages when processing different types of data. For example, random forests perform well in processing high-dimensional and nonlinear data, while neural networks are very powerful in modeling complex relationships). The main steps are as follows: 1. Randomly select 3 known sample points within the PTO damping force parameter range and set , as the input of the initial data, to construct a proxy model of the Gaussian process; the Gaussian process is a probability model used to model uncertain functions. It regards the value of the function as a random variable and assumes that the joint distribution of these random variables in the domain of definition is a multivariate normal distribution; the Gaussian process defines a mean function and a covariance function To describe the mean and uncertainty of the objective function; when known sample data is input, the Gaussian process uses Bayes' theorem to update the prior distribution to the posterior distribution, and obtains the posterior prediction of the objective function, thereby quantifying the uncertainty of the unobserved area; 2. After the Gaussian process predicts the objective function based on the existing data, the Bayesian optimization can intelligently select the next input PTO damping force parameter to optimize the objective function; this is achieved through a function called acquisition function α; in the algorithm, the present invention selects a method called Expected Improvement (EI) as the acquisition function, that is, ; The acquisition function is used to select the next evaluation point to maximize the expected improvement of the objective function, ensuring a balance between global search and local development in each iteration; 3. Then, set the number of iterations , represents the maximum number of iterations of Bayesian optimization; Figure 4 The convergence of the objective function after 20 iterations is shown. In each iteration, Bayesian optimization sets a search index for the acquisition function α to intelligently select the next sample point in the search domain. The acquisition function α is used to perform a fine search around the optimal value of the current objective function and to find new sample points in unexplored areas, thereby maintaining a balance between exploration and development. Figure 5 The third and fourth iterations of Bayesian optimization are shown from top to bottom. The red dots in the left figure are known sample points or new sample points updated based on the acquisition function α. ​​The green dotted line represents the prediction of the true objective function by the Gaussian process proxy model based on the existing sample points. The transparent shaded part is the 95% confidence interval. The right figure is the acquisition function distribution diagram. The point corresponding to its maximum value is the sample point that may have the greatest improvement on the objective function. Similarly, Figure 6 and Figure 7 The process of the 6th, 7th, 17th and 18th iterations are shown respectively. In each iteration, the acquisition function α continuously and intelligently selects sample points to update the objective function value, thereby improving the proxy model and adjusting the parameters based on the posterior distribution. After 20 iterations, the optimal objective function value obtained by Bayesian optimization is as follows Figure 8 As shown; when the damping force of the PTO device , objective function power difference Although the same prototype power There is still a small error, but after a limited number of iterations, this error is small enough, indicating that the model has approached the optimal solution; this method can obtain the optimal parameters close to the true value through a small amount of test data, which greatly reduces the cost of model testing and improves test efficiency.

[0023] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for optimizing model parameters of wave energy device model test errors, characterized in that: The method comprises the following steps: Step S1, collecting long-term accumulated wave energy device test data and establishing a test database; Step S2, orthogonal experimental design; S2.1, Classification of variable factors; S2.2, design orthogonal test table; S2.3, scale effect assessment: compare the average scale effect difference of the variables, preliminarily determine the importance of the variables in the scale effect, and then perform variance analysis to determine whether the variables have a significant impact on the scale effect; Step S3, Bayesian parameter optimization: Based on the machine learning method of Bayesian Gaussian process, the variable factors are trained and optimized to reduce the scale effect of the model test.

2. A method for optimizing model parameters of wave energy device model test errors according to claim 1, characterized in that: The establishment of the experimental database in S1 includes: S1.

1. Database classification: S1.1.

1. Types of wave energy device structures: including oscillating float type, swinging float type, and horizontal oscillating body type; S1.1.2, PTO device types: including hydraulic system, mechanical system and linear generator type; S1.1.3, Model scaling: Select the scaling scale according to the different prototype devices; S1.1.4, Wave conditions: including wave conditions and wave direction; S1.2 Data extraction: S1.2.

1. Multi-level screening method based on classification characteristics: According to the wave energy device structure type, PTO device type, model scaling ratio, and wave conditions, a multi-level screening method is used to gradually narrow the data range; S1.2.2, Keyword matching and filtering: In the database, preliminary filtering of data is performed by keyword matching; S1.3、Data optimization: S1.3.

1. Statistical Methods Regression Analysis: Regression analysis is used to establish the relationship between classification features and responses, and weights are assigned to each classification feature. The test data are optimized based on these weights.

3. A method for optimizing model parameters of wave energy device model test errors according to claim 2, characterized in that: The variable factors in S2.1 include the wave energy device structure type, PTO device type, model scaling and wave conditions.

4. A method for optimizing model parameters of wave energy device model test errors according to claim 3, characterized in that: In S2.2, there are four factors, among which the wave energy device structure type and PTO device type have three variable levels, and the wave conditions and model scaling scale each have two variable levels. In order to ensure that the combination of different factors is fully covered, the L18 orthogonal table is used for experimental design.

5. A method for optimizing model parameters of wave energy device model test errors according to claim 1, characterized in that: The specific steps of S3 are as follows: S3.

1. Input the initial sample point; S3.2, minimize the objective function; S3.3, using Bayesian optimization to establish a proxy model, which is a Gaussian process and is used to approximate the objective function; S3.

4. Set the number of iterations. In each iteration, use the known data to calculate the proxy model through the Gaussian process, and select the next evaluation point by the acquisition function. During the iteration process, the proxy model is continuously updated and the parameters are adjusted according to the posterior distribution until the optimal solution is found, thereby reducing the scale effect of the model test.

6. A method for optimizing model parameters of wave energy device model test errors according to claim 1, characterized in that: The optimization model parameters obtained through machine learning iterations need to be calculated and compared with the true experimental values ​​to verify the accuracy of the Bayesian optimization method calculations.

7. A method for optimizing model parameters of wave energy device model test errors according to claim 1, characterized in that: After the model parameters are optimized by Bayesian method, the test conditions are designed based on the elimination method of orthogonal test. The influence of non-similar factors on the model test is eliminated by the elimination method. Then, according to the number of parameters to be tested, the number of independent test conditions is increased, and finally the change law of the true value response without interference from the scale effect is obtained.

Images