Intelligent early warning method and device for scouring of offshore wind turbine foundation and storage medium

Abstract

The invention discloses an intelligent early warning method and device for offshore wind turbine foundation scouring and a storage medium, and belongs to the technical field of structure safety early warning. The method comprises the following steps that foundation structure parameters of an offshore wind turbine are obtained, and a finite element model is established; foundation scouring simulation is conducted, and time domain data of pile top displacement and pile body node stress are collected; establishing a plurality of agent models, dividing the time domain data into a training set and a verification set, and obtaining training and verification results; optimizing an optimal agent model by using two verification indexes, namely a verification error and a remaining-one error; and taking different scouring conditions as input parameters, obtaining a basic response of the fan, comparing the basic response with a set safety early warning threshold value, and if the basic response of the fan reaches or exceeds the safety early warning threshold value, carrying out safety alarm. According to the method, the problems that initial conditions of a traditional experiment method are difficult to reproduce, an experiment scale affects a measurement result and the cost is high can be solved, and the problem that finite element simulation cannot achieve full coverage of the scouring condition is solved.

Description

Technical Field

[0001] The invention relates to an intelligent early warning method, device and storage medium for offshore wind turbine foundation scour, belonging to the technical field of engineering detection. Background Art

[0002] As the global demand for clean energy continues to increase, offshore wind energy, as a clean and renewable energy form, is receiving more and more attention. However, the construction and operation of offshore wind farms face many technical challenges, among which the problem of offshore wind turbine foundation scouring is particularly prominent. Seabed scouring not only causes the natural frequency of the unit support structure to change, but also may reduce the buckling bearing capacity of the structure, seriously threatening the stable operation and economic benefits of offshore wind farms.

[0003] Existing research on the scouring characteristics of offshore wind turbine foundations mainly relies on finite element simulation and experimental methods. However, finite element simulation requires large amounts of computation, and simulating the foundation response under different scouring effects consumes a large amount of computing resources, which cannot fully cover complex scouring. The experimental method has shortcomings such as difficulty in reproducing initial conditions, the influence of experimental scale on measurement results, and high experimental costs. Summary of the invention

[0004] The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide an intelligent early warning method, device and storage medium for offshore wind turbine foundation scour, which can solve the problems that the initial conditions of traditional experimental methods are difficult to reproduce, the influence of experimental scales on measurement results, and the high cost, as well as the problem that finite element simulation cannot achieve full coverage of scour conditions.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] An intelligent early warning method for offshore wind turbine foundation scour comprises the following steps:

[0007] Obtain the foundation structure parameters of the offshore wind turbine and establish a finite element model based on the foundation structure parameters;

[0008] The established finite element model is used to simulate foundation scour and collect time domain data of pile top displacement and pile body node stress;

[0009] Establish several proxy models, divide the time domain data into training sets and validation sets, import them into each proxy model for training and validation, and obtain training and validation results;

[0010] Based on the training and validation results, the validation error and leave-one-out error are used to select the proxy model that meets the prediction accuracy and requires the smallest training set as the best proxy model.

[0011] Different scour conditions are used as input parameters of the optimal proxy model to obtain the wind turbine foundation response predicted by the optimal proxy model. The wind turbine foundation response is compared with the set safety warning threshold. If the wind turbine foundation response reaches or exceeds the safety warning threshold, a safety alarm is issued.

[0012] The obtaining of the foundation structure parameters of the offshore wind turbine and establishing a finite element model according to the foundation structure parameters includes: establishing a corresponding finite element model using ABAQUS software according to the offshore wind turbine foundation structure drawings.

[0013] The method of simulating foundation scour on the established finite element model and collecting time domain data of pile top displacement and pile body node stress includes: using the Coulomb friction model to simulate the pile-soil interaction, using the life-death unit analysis method to remove the specified area unit to simulate the local scour process, and then obtaining the wind turbine foundation stress cloud map through static analysis, and then obtaining the time domain data of pile top displacement and pile body node stress through finite element post-processing of the finite element model.

[0014] The proxy model is constructed based on the Uqlab toolbox in Matlab software, including a Kriging model, a PCE (polynomial chaos expansion) model, a PCK (polynomial chaos Kriging) model and a SVR (support vector machine regression) model.

[0015] The input parameters of the proxy model are one-dimensional vectors {X1, X2, X3, …}, including but not limited to the ratio of scour pit depth to pile diameter, the ratio of scour pit diameter to pile diameter, and the scour pit angle. The output parameters are one-dimensional vectors {Y1, Y1, Y3, …}, including but not limited to the displacement of the foundation pile top and the stress of the pile body node. The input parameters and output parameters are combined accordingly and randomly divided into training sets and validation set Two parts.

[0016] Verification Error and leave-one-out error The calculation methods are:

[0017] E ν a l = K − 1 K [ Σ i = 1 K ( ℳ ( X ν a l ( i ) ) − ℳ · ( X ν a l ( i ) ) ) 2 Σ i = 1 K ( ℳ ( X ν a l ( i ) ) − μ ^ Y ν a l ) 2 ] ;

[0018] ;

[0019] In the formula: As a validation set, is the sample mean of the validation set responses, is the number of samples in the validation set, To be the first The proxy model is obtained by removing sample points from the complete experimental design. is the sample mean of the experimental design response, is the value of X in the validation set, is the Y value in the validation set, Output of the trained proxy model.

[0020] The criteria for prediction accuracy are: and .

[0021] The warning threshold is ,in It is the horizontal displacement of the tall structure under wind-dominated loads. It is a tall structure.

[0022] In a second aspect, the present invention provides an intelligent early warning device for offshore wind turbine foundation scour, comprising a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method.

[0023] In a third aspect, the present invention provides a computer-readable storage medium having a computer program / instruction stored thereon. When the computer program / instruction is executed by a processor, the steps of the intelligent early warning method for offshore wind turbine foundation scour are implemented.

[0024] Beneficial effects of the present invention: The present invention provides an intelligent early warning method, device and storage medium for offshore wind turbine foundation scour, which uses a small amount of finite element calculation data to train four different proxy models, and then uses two indicators to optimize the proxy model with the best prediction effect, so as to accurately predict the response of the offshore wind turbine foundation under different scour conditions, overcoming the shortcomings of traditional experimental methods that the initial conditions are difficult to reproduce and the cost is high, and the finite element simulation cannot achieve full coverage of scour conditions, achieving "instant" and "accurate" response prediction and can perform early warning supervision and judgment on structural safety and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a flow chart of an intelligent early warning method for offshore wind turbine foundation scour according to the present invention;

[0026] Figure 2 This is a finite element model diagram of an offshore wind turbine foundation established in the present invention;

[0027] Figure 3 This is a comparison chart of prediction accuracy of different proxy models in the present invention;

[0028] Figure 4 It is an error comparison diagram of the displacement-stress prediction model established in the present invention. DETAILED DESCRIPTION

[0029] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and are not intended to limit the protection scope of the present invention.

[0030] Example 1

[0031] The present invention discloses an intelligent early warning method for offshore wind turbine foundation scour, comprising the following steps:

[0032] Step 1: obtaining the foundation structure parameters of the offshore wind turbine and establishing a finite element model based on the foundation structure parameters;

[0033] Step 2: Conduct foundation scour simulation on the established finite element model and collect time domain data of pile top displacement and pile body node stress;

[0034] Step 3: Establish several proxy models, divide the time domain data into training sets and validation sets, and import them into each proxy model for training and validation, and obtain training and validation results;

[0035] Step 4: Based on the training and validation results, the validation error and leave-one-out error are used to select the proxy model that meets the prediction accuracy and requires the smallest training set as the best proxy model.

[0036] Step five, using different scouring conditions as input parameters of the optimal proxy model, obtaining the wind turbine foundation response predicted by the optimal proxy model, and comparing the wind turbine foundation response with the set safety warning threshold. If the wind turbine foundation response reaches or exceeds the safety warning threshold, a safety alarm is issued.

[0037] The present invention uses a small amount of finite element calculation data to train four different proxy models, and then uses two indicators to select the proxy model with the best prediction effect, so as to accurately predict the response of the offshore wind turbine foundation under different scouring conditions. It overcomes the shortcomings of traditional experimental methods, such as the difficulty in reproducing the initial conditions and the high cost, and the inability of finite element simulation to fully cover the scouring conditions, and achieves "instant" and "accurate" response prediction, and can provide early warning supervision and judgment on the safety and reliability of the structure.

[0038] Example 2

[0039] The present invention discloses an intelligent early warning method for offshore wind turbine foundation scour, comprising the following steps:

[0040] Step 1: Obtain the foundation structure parameters of the offshore wind turbine and establish a finite element model based on the foundation structure parameters. The specific modeling method is: Use shell elements to simulate the foundation structure of a large-diameter single-pile wind turbine. The dimensions are based on the 7MW wind turbine dimensions, with a tower height of 106.3m, a tower diameter of 5-7.7m, a wall thickness of 36mm, and a burial depth of 35m. The soil is simulated using solid elements to establish a soil model with a diameter of 20D and a thickness of 50m. The pile-soil interaction is simulated using the Moore-Coulomb model. Figure 2 This is a finite element model diagram of the offshore wind turbine foundation established in the present invention.

[0041] Step 2: Simulate the foundation scour of the established finite element model and collect the time domain data of pile top displacement and pile body node stress. The specific method is: use the birth and death unit analysis method to remove the process of simulating local scour, obtain the wind turbine foundation stress cloud map through static analysis, and then obtain the stress and displacement data of the specified node through finite element post-processing.

[0042] Step three, establish several proxy models, divide the time domain data into training set and validation set, import them into each proxy model for training and validation, and obtain training and validation results. The specific method is: based on the Uqlab toolbox in Matlab software, build four proxy models, the specific categories are: Kriging model, PCE model, PCK model and SVR model. The input parameters of the proxy model are one-dimensional vectors {X1, X2, X3, ...}, including but not limited to the ratio of scour pit depth to pile diameter, the ratio of scour pit diameter to pile diameter, scour pit angle, etc. The output parameters are one-dimensional vectors {Y1, Y1, Y3, ...}, including but not limited to foundation pile top displacement, pile body node stress, etc.; the obtained input and output parameters are combined accordingly and randomly divided into training sets and validation set In two parts, four proxy models are trained using the training set data.

[0043] Step 4: Based on the training and validation results, the validation error and leave-one-out error are used to select the proxy model that meets the prediction accuracy and requires the smallest training set as the best proxy model.

[0044] Verification Error and leave-one-out error The calculation methods are:

[0045] E ν a l = K − 1 K [ Σ i = 1 K ( ℳ ( X ν a l ( i ) ) − ℳ · ( X ν a l ( i ) ) ) 2 Σ i = 1 K ( ℳ ( X ν a l ( i ) ) − μ ^ Y ν a l ) 2 ] ;

[0046] ;

[0047] In the formula: As a validation set, is the sample mean of the validation set responses, is the number of samples in the validation set, To be the first The proxy model is obtained by removing sample points from the complete experimental design. is the sample mean of the experimental design response, is the value of X in the validation set, is the Y value in the validation set, Output of the trained proxy model.

[0048] After training, the proxy model meets the standard of satisfying prediction accuracy: and ; For multiple proxy models that meet this condition, the model with a smaller training set is the best proxy model and is used for wind turbine foundation response prediction. Figure 3 This is a comparison chart of the prediction accuracy of different proxy models. From the data comparison in the figure, we can see that the PCK proxy model meets the accuracy requirements and is selected as the best proxy model. Figure 4 This is the error comparison diagram of the displacement-stress prediction model of the PCK proxy model. It can be seen from the figure that the error of the PCK proxy model for displacement-stress prediction is relatively small.

[0049] Step 5: Use different scouring conditions as input parameters of the best proxy model to obtain the wind turbine foundation response predicted by the best proxy model, and compare the wind turbine foundation response with the set safety warning threshold. If the wind turbine foundation response reaches or exceeds the safety warning threshold, a safety alarm is issued. Specifically, the determination of the warning threshold is based on the provisions of GB50135: "Design Code for Tall Structures". When a tall structure is under wind-dominated load, its horizontal displacement shall not exceed 1 / 75 of the height. Therefore, It is defined as the tower top displacement warning limit value, and the wind turbine foundation node stress in this state is defined as the pile body stress warning limit value.

[0050] Example 3

[0051] This embodiment discloses an intelligent early warning device for offshore wind turbine foundation scour, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method described in Example 1 or 2.

[0052] Example 4

[0053] This embodiment introduces a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in Embodiment 1 or 2 are executed.

[0054] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0055] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0056] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0058] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent early warning method for offshore wind turbine foundation scour, characterized by: The following steps are involved: Obtain the foundation structure parameters of the offshore wind turbine and establish a finite element model based on the foundation structure parameters; The established finite element model is used to simulate foundation scour and collect time domain data of pile top displacement and pile body node stress; Establish several proxy models, divide the time domain data into training sets and validation sets, import them into each proxy model for training and validation, and obtain training and validation results; Based on the training and validation results, the validation error and leave-one-out error are used to select the proxy model that meets the prediction accuracy and requires the smallest training set as the best proxy model. Different scour conditions are used as input parameters of the optimal proxy model to obtain the wind turbine foundation response predicted by the optimal proxy model. The wind turbine foundation response is compared with the set safety warning threshold. If the wind turbine foundation response reaches or exceeds the safety warning threshold, a safety alarm is issued.

2. The intelligent early warning method for offshore wind turbine foundation scour according to claim 1 is characterized by: The obtaining of the foundation structure parameters of the offshore wind turbine and establishing a finite element model according to the foundation structure parameters includes: establishing a corresponding finite element model using ABAQUS software according to the offshore wind turbine foundation structure drawings.

3. The intelligent early warning method for offshore wind turbine foundation scour according to claim 1 is characterized by: The method of simulating foundation scour on the established finite element model and collecting time domain data of pile top displacement and pile body node stress includes: using the Coulomb friction model to simulate the pile-soil interaction, using the life-death unit analysis method to remove the specified area unit to simulate the local scour process, and then obtaining the wind turbine foundation stress cloud map through static analysis, and then obtaining the time domain data of pile top displacement and pile body node stress through finite element post-processing of the finite element model.

4. The intelligent early warning method for offshore wind turbine foundation scour according to claim 1 is characterized by: The proxy model is constructed based on the Uqlab toolbox in Matlab software, including Kriging model, PCE model, PCK model and SVR model.

5. The intelligent early warning method for offshore wind turbine foundation scour according to claim 4 is characterized in that: The input parameters of the proxy model are one-dimensional vectors {X1, X2, X3, …}, including but not limited to the ratio of scour pit depth to pile diameter, the ratio of scour pit diameter to pile diameter, and the scour pit angle. The output parameters are one-dimensional vectors {Y1, Y1, Y3, …}, including but not limited to the displacement of the foundation pile top and the stress of the pile body node. The input parameters and output parameters are combined accordingly and randomly divided into training sets and validation set Two parts.

6. The intelligent early warning method for offshore wind turbine foundation scour according to claim 5 is characterized by: Verification Error and leave-one-out error The calculation methods are: ； ； In the formula: As a validation set, is the sample mean of the validation set responses, is the number of samples in the validation set, To be the first The proxy model is obtained by removing sample points from the complete experimental design. is the sample mean of the experimental design response, is the value of X in the validation set, is the Y value in the validation set, Output of the trained proxy model.

7. The intelligent early warning method for offshore wind turbine foundation scour according to claim 6 is characterized by: The criteria for prediction accuracy are: and .

8. The intelligent early warning method for offshore wind turbine foundation scour according to claim 1 is characterized by: The warning threshold is ,in It is the horizontal displacement of the tall structure under wind-dominated loads. It is a tall structure.

9. An intelligent early warning device for offshore wind turbine foundation scour, characterized in that: It comprises a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the steps of the intelligent early warning method for offshore wind turbine foundation scour described in any one of claims 1-8 are implemented.

Images