A Smart Method for Monitoring the Health Status of Underwater Structures of Offshore Wind Turbines

Abstract

This invention provides an intelligent method for monitoring the health status of underwater structures of offshore wind turbines, belonging to the field of marine engineering structure monitoring technology based on computer data processing. The method involves measuring acceleration signals at typical nodes of the wind turbine above water; acquiring low-order measured frequencies and mode shapes of the offshore wind turbine structure; establishing a finite element model of the wind turbine structure; setting damage degree vectors for underwater structural elements and acquiring simulated frequencies and mode shapes under different damage degrees; establishing a fitness objective function based on the measured and simulated frequencies and mode shapes of the wind turbine structure; classifying the fitness values ​​based on cluster analysis; introducing a multi-population update strategy into a beetle swarm optimization algorithm to solve the objective function and obtain the optimal damage degree vector; and monitoring the health status of the underwater structure through damage degree measurements. This invention only requires a limited number of monitoring sensors to be deployed on the offshore wind turbine structure for sparse measurements to monitor the health status of the underwater structure.

Description

Technical Field

[0001] This invention belongs to the field of marine engineering structure monitoring technology based on computer data processing, and particularly relates to an intelligent method for monitoring the health status of underwater structures of offshore wind turbines. Background Technology

[0002] Offshore wind power is an important source of new clean energy worldwide, and the safe operation of its supporting structure—the offshore wind turbine—is crucial. Typically, an offshore wind turbine structure consists of the turbine blades at the top, the tower structure in the middle, and the underwater foundation structure. The underwater foundation structure is constantly exposed to the complex and harsh marine environment, affected by various natural environmental factors such as wave impact, current erosion, seawater corrosion, and seabed geological changes. Furthermore, sudden events such as ship collisions can easily lead to structural defects, damage, and foundation erosion, thus threatening the overall safety of the offshore wind turbine structure.

[0003] Monitoring of underwater structures of offshore wind turbines primarily relies on shipborne multibeam echo sounders, diver inspections, and underwater sensor networks. While shipborne multibeam echo sounders can acquire relatively detailed seabed topographic information, they have high operational requirements, high costs at sea, and are limited by weather conditions, making real-time continuous monitoring of underwater structures impossible. Diver inspections are not only inefficient, dangerous, and expensive, but prolonged underwater operations also pose significant risks to divers, and they cannot comprehensively cover all parts of the underwater structure. Underwater sensor networks, while enabling real-time monitoring, face difficulties in sensor installation, maintenance, and replacement, resulting in extremely high costs. Furthermore, in complex marine environments, sensors are susceptible to interference, leading to severe data loss and significant reliability issues. Offshore wind turbine structures typically have only a limited number of monitoring sensors installed, and the limited measurement information is not fully utilized, resulting in insufficient intelligent monitoring and early warning capabilities, making it difficult to accurately and promptly assess the health status of the underwater structure. In conclusion, developing a lightweight, low-cost, and intelligent method for monitoring the health status of underwater structures of offshore wind turbines, utilizing the limited measurement information available for the turbine tower structure, is urgently needed and has significant potential for widespread application. Summary of the Invention

[0004] To address the aforementioned issues, this invention utilizes limited measurement information from the above-water structure of offshore wind turbines for real-time and continuous monitoring of the underwater structural health status. It develops a lightweight, low-cost, and intelligent method for monitoring the health status of underwater offshore wind turbine structures, solving the problems of high cost, low efficiency, poor real-time performance, and insufficient intelligence in existing monitoring methods. This enables efficient, accurate, and real-time monitoring and assessment of the health status of underwater offshore wind turbine structures, thereby ensuring the safe operation of offshore wind turbine structures.

[0005] This invention provides an intelligent method for monitoring the health status of underwater structures of offshore wind turbines, characterized by comprising the following processes:

[0006] S1, Real-time measurement of acceleration signals at typical node locations of the offshore wind turbine's water structure - tower;

[0007] S2, uses online modal recognition methods to obtain real-time data on the low-order measured frequencies and mode shapes of offshore wind turbine structures;

[0008] S3. A finite element model of the offshore wind turbine structure is established based on the overall structural dimensions, material parameters, constraints, and design data.

[0009] S4. Based on the number and properties of the finite element model elements, the underwater element damage degree vector is set, and the simulation frequency and mode shape data under different damage degree vectors are obtained based on numerical simulation.

[0010] S5. Based on the measured frequency and modal data of the offshore wind turbine structure and the simulated frequency and modal data of the finite element model, an objective function that comprehensively considers the frequency and modal data is established, transforming the condition monitoring problem into the problem of minimizing the difference between the measured modal parameters and the simulated modal parameters.

[0011] S6, based on cluster analysis, classifies fitness values ​​and introduces multiple population update strategies into the beetle swarm optimization algorithm. By minimizing the objective function, the optimal (minimum fitness value) damage vector is obtained.

[0012] S7, the optimal damage degree vector represents the damage degree of the underwater unit of the offshore wind turbine structure. The damage degree is used to monitor the health status of the underwater structure and assess the degree of potential damage.

[0013] Furthermore, typical locations in S1 include the tower top location, the connection location between tower sections, and the connection location between the tower section and the foundation.

[0014] Furthermore, in S2, the number of measured nodes is ≥3, and the modal order identified by the measured response is ≥2.

[0015] Furthermore, the finite element model of the offshore wind turbine structure in S3 is established in MATLAB, ANSYS, or ABAQUS software, and includes at least the tower, three-pile foundation, nacelle, and blades. The nacelle and blades can be equivalently replaced by applying a concentrated mass method at the top of the tower. The three-leg foundation at the bottom of the model adopts fixed constraints.

[0016] Furthermore, in step S4, the parameters are set according to the number and properties of the finite element elements, including... Damage vector of underwater unit: Selected For each underwater unit of an offshore wind turbine, a damage level value is randomly assigned, with the value ranging from (-1, 0), forming a damage level vector, as follows:

[0017] ;

[0018] in: Represents initialization of the first A vector of damage levels; For the first The set damage level for each underwater unit;

[0019] Establish containing Initialization damage level matrix for each damage level vector The details are as follows:

[0020] ;

[0021] Numerical simulation was used to obtain simulation frequency and modal data under different damage levels; for the first Damage degree vector In this regard, the baseline stiffness matrix of the finite element model of the offshore wind turbine structure is updated accordingly. This forms a potential damage stiffness matrix that includes the damage. The specific process is as follows:

[0022] ;

[0023] in: For the first The element stiffness matrix corresponding to each underwater element;

[0024] By solving the characteristic equation To obtain the frequency of potentially damaged structures and mode shape ;in This is the reference mass matrix for the finite element model of an offshore wind turbine structure.

[0025] Furthermore, the objective function in S5 is an objective function that integrates measured and potential damage modal parameters, specifically:

[0026] ;

[0027] in:

[0028] ;

[0029] ;

[0030] In the formula: and For the first part of the potentially damaged structure and the measured structure First-order mode shape and The Middle Modal displacements with one degree of freedom; and The measured modal order and degrees of freedom; The weighting coefficients between the frequency and coordinate modal confidence criteria; when the modal parameters (frequency, mode shape) of the potentially damaged structure are the same as the measured structural parameters, = 0; otherwise, >0;

[0031] Through the Numerical simulation and feature extraction were performed on the damage degree vector to obtain... The frequency and mode shape data of the potentially damaged structure are used for calculation; based on this, the following can be obtained. A fitness value.

[0032] Furthermore, in step S6, the fitness data is classified based on cluster analysis, and the specific process is as follows:

[0033] Step 1, with fitness value As input data, for A fitness value;

[0034] Set the number of cluster populations to [value]. Randomly selected There are 1 cluster center, namely In the formula For the first Cluster centers;

[0035] Step 2, calculate fitness value With cluster center The minimum distance is used to determine the group to which it belongs. :

[0036] ;

[0037] Step 3: Recalculate each category based on the newly divided clusters. Cluster center :

[0038] ;

[0039] Step 4: Repeat steps 1 to 3 until convergence, and output the final clustering results and cluster centers. The distance between the obtained cluster centers and the optimal fitness value is used as the basis for distinguishing the quality of the population, and the population is divided into the best population, the medium population and the poor population.

[0040] Furthermore, in step S6, multiple population update strategies are introduced into the beetle swarm optimization algorithm to obtain the optimal damage vector by minimizing the objective function. The specific process is as follows:

[0041] Step 1, solve the first... In the nth iteration Damage degree vector ;

[0042] Step 2: Generate random direction vectors ;

[0043] Step 3: The longhorn beetle searches for the left antenna in the variable space. ;in For the first The distance between the two whiskers of the longhorn beetle or the antennal sensing diameter in the next iteration;

[0044] Step 4, make a judgment Population classification hierarchy;

[0045] Step 5: Establish different population renewal strategies for different population classification levels, specifically as follows:

[0046] like To optimize the population, the damage level vector of the potential damage structure is updated as follows:

[0047] ;in For the first Iteration step size during iteration and For cognitive coefficient, Represents the symbolic function. This represents the optimal damage level vector;

[0048] like If the population is of medium size, then the damage level vector of the potential damage structure is updated as follows: ;in Let Levy be the flight disturbance variable;

[0049] like For a poor population, the damage level vector of the potential damaged structure is updated as follows: ;in It is a random disturbance variable;

[0050] Step 6, Update the stiffness matrix ;

[0051] Step 7: Solve the characteristic equation Obtain the predicted structural parameters and ;

[0052] Step 8: Calculate the fitness value using the constructed fitness function. ;

[0053] Step nine, if Update the optimal fitness value and the optimal damage vector ;

[0054] Repeat steps one through nine above until the iteration termination condition is met, and output the optimal damage vector. .

[0055] Furthermore, the optimal damage vector obtained in S7 includes The damage level value is calculated as follows: If the damage level value is ≥1%, the corresponding underwater unit may be damaged, and the severity of the damage depends on the magnitude of the damage level value; if the damage level value is <1%, the structure is in a healthy state by default, and its damage level change trend needs to be continuously tracked.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] Significant cost-effectiveness: Compared with comprehensive monitoring methods such as underwater sensor networks, this invention only requires a limited number of monitoring sensors to be deployed on the surface structure of the offshore wind turbine for sparse measurements. There is no need to install sensors underwater to monitor the health status of the underwater structure, which greatly reduces the cost of purchasing, installing and maintaining underwater instruments and equipment.

[0058] Improved real-time performance and accuracy: By collecting dynamic responses such as acceleration of underwater structures in real time and dynamically updating the health status assessment model, the system can promptly reflect changes in the health status of underwater structures caused by environmental changes and their own damage, thereby improving the real-time performance and accuracy of monitoring.

[0059] High monitoring and early warning efficiency: By combining the newly proposed clustering longhorn beetle swarm optimization algorithm for data processing and analysis, a large amount of data processing and health status assessment can be completed in a short time, thereby improving the efficiency of monitoring and early warning. Attached Figure Description

[0060] Figure 1 This is a schematic diagram of the overall process flow of the present invention.

[0061] Figure 2 This is a schematic diagram of the offshore wind turbine structure model of the present invention.

[0062] Figure 3 This is a diagram showing the damage identification results under operating condition A based on the KSBSOA method in an embodiment of the present invention.

[0063] Figure 4 This is a diagram showing the damage identification results under condition B based on the KSBSOA method in an embodiment of the present invention.

[0064] Figure 5This is a diagram showing the damage identification results under operating condition C based on the KSBSOA method in an embodiment of the present invention.

[0065] Figure 6 This is a diagram showing the damage identification results under working condition D based on the KSBSOA method in an embodiment of the present invention.

[0066] Figure 7 This is a diagram showing the damage identification results under operating condition E based on the KSBSOA method in an embodiment of the present invention.

[0067] Figure 8 This is a diagram showing the damage identification results under operating condition E based on the PSO method in an embodiment of the present invention.

[0068] Figure 9 This is a diagram showing the damage identification results under operating condition E based on the BSO method in an embodiment of the present invention. Detailed Implementation

[0069] The present invention will be further described below with reference to embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0070] In this embodiment, an intelligent method for monitoring the health status of underwater structures of offshore wind turbines is described, as follows: Figure 1 As shown.

[0071] 1. Real-time measurement of acceleration signals at typical node locations of the offshore wind turbine's structure-tower.

[0072] First, define typical nodes of the offshore wind turbine's above-water structure and tower, such as... Figure 2 As shown, typical node locations include the tower top, the connection between tower sections, and the connection between the tower section and the foundation; specifically, nodes 15, 16, 17, and 18. Acceleration sensors are deployed at the nodes above water to acquire acceleration signals at the nodes above water under the influence of wind, waves, and currents.

[0073] 2. Real-time acquisition of low-order measured frequencies and mode shapes of offshore wind turbine structures using online modal recognition methods.

[0074] Based on the acquired acceleration signal, the low-order measured frequencies of the offshore wind turbine structure are obtained in real time using modal recognition methods. and modal vibration data In this embodiment, the number of measured nodes is 4, and the measured modal order is 5.

[0075] Online modal identification involves constructing a covariance matrix or Hankel matrix from vibration acceleration output response data, extracting the system subspace using linear algebraic decomposition (such as QR decomposition or SVD), and then identifying modal parameters such as frequency, damping ratio, and mode shape.

[0076] III. Establish a finite element model of the offshore wind turbine structure based on the overall structural dimensions, material parameters, constraints, and design data.

[0077] The establishment of a finite element model of an offshore wind turbine structure is based on the overall structural dimensions, material parameters, constraints, and design data of the offshore wind turbine. The finite element model is established in MATLAB, ANSYS, or ABAQUS software. The mechanical properties of the materials include density, Poisson's ratio, elastic modulus, and yield strength.

[0078] Finite element model establishment for offshore wind power: Offshore wind turbines mainly consist of components such as towers, three-pile foundations, nacelles, and blades. The nacelles and blades can be equivalently replaced by applying a concentrated mass method at the top of the tower. The finite element model diagram in this embodiment is shown below. Figure 2 As shown, the structure contains 18 nodes and 20 elements, all of which are homogeneous beam elements. Specifically: elements 1-9 are leg elements; elements 10-12 are horizontal brace elements; elements 13-15 are diagonal brace elements; elements 16-17 are column elements; and elements 18-20 are tower elements. The structure is 2.5m high. The outer diameter of the leg, horizontal brace, and diagonal brace elements is 20mm, while the outer diameter of the column and tower elements is 30mm. The wall thickness of all elements is 2mm. The bottom of the model uses fixed constraints, while the top turbine unit is simulated using an equivalent model, specifically by adding a concentrated mass of 3.3kg to the top nodes. The basic material properties of the structure include a density of 7.85 × 10⁻⁶. - 6 kg / mm 3 The Poisson's ratio is 0.3, and the elastic modulus is 2.1 × 10⁻⁶. 5 MPa.

[0079] IV. Based on the number and properties of the finite element model elements, the underwater element damage degree vector is set, and the simulation frequency and mode shape data under different damage degree vectors are obtained based on numerical simulation.

[0080] In this embodiment, a damage degree vector comprising 17 underwater elements is set according to the number and properties of the finite element elements: 17 underwater elements of the offshore wind turbine are selected, and each element is randomly assigned a damage degree value, wherein the value range is (-1, 0), forming a damage degree vector, as follows:

[0081] ;

[0082] in: Representing the A vector of damage levels; For the first The set damage level for each underwater unit;

[0083] The degree of damage is specifically the ratio of the value obtained by subtracting the initial elastic modulus of the element from the equivalent elastic modulus of the element to the initial elastic modulus of the element. The degree of damage is a dimensionless modulus, and the value range of the degree of damage is (-1, 0). When the degree of damage is 0, it indicates that the element is in a healthy state. When the degree of damage is -1, it indicates that the element has been completely damaged.

[0084] Establish a damage severity matrix containing 60 damage severity vectors. The details are as follows:

[0085] .

[0086] Numerical simulation was used to obtain simulation frequency and modal data under different damage levels; for the first Damage degree vector In this regard, the baseline stiffness matrix of the finite element model of the offshore wind turbine structure is updated accordingly. This forms a potential damage stiffness matrix that includes the damage. The specific process is as follows:

[0087] ;

[0088] in: For the first The element stiffness matrix corresponding to each underwater element;

[0089] By solving the characteristic equation To obtain the frequency of potentially damaged structures and mode shape ;in This is the reference mass matrix for the finite element model of an offshore wind turbine structure.

[0090] V. Based on the measured frequency and modal data of the offshore wind turbine structure and the simulated frequency and modal data of the finite element model, an objective function that comprehensively considers the frequency and modal data is established, transforming the condition monitoring problem into a problem of minimizing the difference between the measured modal parameters and the simulated modal parameters.

[0091] The objective function is a fusion of measured and potential damage modal parameters, specifically:

[0092] ;

[0093] in:

[0094] ;

[0095] ;

[0096] In the formula: and For the first part of the potentially damaged structure and the measured structure First-order mode shape and The Middle Modal displacements with one degree of freedom; These are the measured degrees of freedom; when the modal parameters of the potentially damaged structure are the same as the measured structural parameters, = 0; otherwise, >0; In this embodiment, the total number of degrees of freedom is 0. It is 24.

[0097] By performing numerical simulation and feature extraction on 60 damage degree vectors, we obtain... The data on the frequency and mode shapes of the potentially damaged structures are used to calculate 60 fitness values.

[0098] VI. Based on cluster analysis, fitness values ​​are classified, and a multi-population update strategy is introduced into the beetle swarm optimization algorithm. The optimal damage vector is obtained by minimizing the objective function.

[0099] Step 1, in this embodiment, uses 60 fitness values. As input data, for A fitness value;

[0100] The number of cluster populations was set to 3, and 3 cluster centers were randomly selected, namely: .

[0101] Step 2, calculate fitness value With cluster center The minimum distance is used to determine the group to which it belongs. :

[0102] .

[0103] Step 3: Recalculate each category based on the newly divided clusters. Cluster center :

[0104] .

[0105] Step 4: Repeat steps 1 to 3 until convergence, and output the final clustering results and cluster centers. The distance between the obtained cluster centers and the optimal fitness value is used as the basis for distinguishing the quality of the population, and the population is divided into the best population, the medium population and the poor population.

[0106] A multi-population update strategy is introduced into the longhorn beetle swarm optimization algorithm. The optimal damage vector is obtained by minimizing the objective function. The specific process is as follows:

[0107] Step 1, solve the first... In the nth iteration Damage degree vector ;

[0108] Step 2: Generate random direction vectors ;

[0109] Step 3: The longhorn beetle searches for the left antenna in the variable space. ;in For the first The distance between the two whiskers of the longhorn beetle or the antennal sensing diameter in the next iteration;

[0110] Step 4, make a judgment Population classification hierarchy;

[0111] Step 5: Establish different population renewal strategies for different population classification levels, specifically as follows:

[0112] like To optimize the population, the damage level vector of the potential damage structure is updated as follows:

[0113] ;in For the first Iteration step size during iteration and For cognitive coefficient, Represents the symbolic function. This represents the optimal damage level vector;

[0114] like If the population is of medium size, then the damage level vector of the potential damage structure is updated as follows: ;in Let Levy be the flight disturbance variable;

[0115] like For a poor population, the damage level vector of the potential damaged structure is updated as follows: ;in It is a random disturbance variable;

[0116] Step 6, Update the stiffness matrix ;

[0117] Step 7: Solve the characteristic equation Obtain the predicted structural parameters and ;

[0118] Step 8: Calculate the fitness value using the constructed fitness function. ;

[0119] Step nine, if Update the optimal fitness value and the optimal damage vector ;

[0120] Repeat steps one through nine above until the iteration termination condition is met, and output the optimal damage vector. .

[0121] By sequentially calculating the fitness values ​​under all damage severity vectors, a vector consisting of 60 fitness values ​​can be obtained, which can be represented as:

[0122] .

[0123] Population cluster analysis was performed on the fitness values, dividing them into three categories: category 1 (good), category 2 (medium), and category 3 (poor).

[0124] After obtaining the new location of the longhorn beetle through multi-strategy movement updates, a clustering longhorn beetle swarm optimization algorithm is established and executed to output the optimal longhorn beetle location, thereby obtaining a new damage degree vector of the underwater structural unit of the offshore wind turbine, and realizing real-time monitoring of the health status of the underwater structure of the offshore wind turbine.

[0125] Table 1 Damage Conditions in Numerical Simulation

[0126]

[0127] Taking into account different damage locations, damage levels, random noise, modal order, and number of measurement points, four single-damage conditions and one double-damage condition were set up. Condition A considered 15% damage to the brace unit E14, 1% random noise, and the first 5 modes, with 4 measurement points; Condition B considered 15% damage to the brace unit E14, 3% random noise, and the first 5 modes, with 4 measurement points; Condition C considered 15% damage to the brace unit E14, 3% random noise, and the first 3 modes, with 4 measurement points; Condition D considered 15% damage to the brace unit E14, 3% random noise, and the first 3 modes, with 3 measurement points; and Double-damage condition E considered 10% damage to the brace unit E10, 15% damage to the brace E14, 3% random noise, and the first 3 modes, with 3 measurement points. The damage conditions are shown in Table 1. The KSBSO invention was used to identify damage to offshore wind turbine structures under five operating conditions (A, B, C, D, and E). The identification results are as follows: Figures 3-7 As shown.

[0128] For damage conditions A, B, and D, the damage location can be accurately located, and the damage degree can be identified as -0.1499, with an error of 0.067% compared to the set damage degree of -0.15.

[0129] For condition C, the location of the damage can be accurately pinpointed, and the assessment of the degree of damage is error-free.

[0130] Under operating condition E, the damage location of units E10 and E14 can be accurately located. The damage degree of unit E10 is -0.0995 with an identification error of 0.5%, and the damage degree of unit E14 is -0.1491 with an identification error of 0.6%. The KSBSO of this invention can accurately locate the damage location and identify the damage degree, with the damage degree error being less than 1%.

[0131] Damage identification for operating condition E was performed using the PSO and BSO algorithms respectively, and the results are as follows: Figure 8 and Figure 9 .

[0132] from Figure 7 As can be seen, by using the measurement information from 4 nodes on the water to monitor the health status of 17 units of the underwater structure of the offshore wind turbine, KSBSO can accurately locate the damage locations of units E10 and E14. The damage level of unit E10 is -0.0995 with an identification error of 0.5%, and the damage level of unit E14 is -0.1491 with an identification error of 0.6%.

[0133] from Figure 8 As can be seen, the PSO algorithm identified the damage level of unit E10 as -0.223%, with an identification error of 97.77% compared to the set damage level of -10%. The damage level of unit E14 was -7.367%, with an identification error of 50.887% compared to the set damage level of -15%. The identified damage level in the figure has multiple peaks, with unit E5 showing the largest damage level at -11.737%, followed by unit E6 at -8.395%. If a damage level less than -8% is considered as damage, this will lead to the underestimation of structures with actual damage (E10, E14) and the misjudgment of structures without actual damage (E5, E6).

[0134] from Figure 9As can be seen, the BSO algorithm identified the damage level of element E14 as -15.318%, with an identification error of 2.12%, and the damage level of element E10 as -0.02794%, with an identification error of 99.72%. The identified damage levels in the figure show a clear peak. If a damage level less than -15% is considered as damage, it will lead to the missed detection of the actually damaged structure (E10). If a damage level less than -0.2% is considered as damage, it will lead to misidentification of elements E1 and E11.

[0135] In summary, Particle Swarm Optimization (PSO) and Beetle Swarm Optimization (BSO) algorithms are ineffective at identifying damage, and the interference from other undamaged elements severely masks structural damage, leading to missed or false damage detections. In contrast, this invention accurately identifies damage, with negligible interference from other undamaged elements.

[0136] In summary, the intelligent method for monitoring the health status of underwater structures of offshore wind turbines using sparse measurement information from the water surface proposed in this invention has high damage identification performance and high computational accuracy.

[0137] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0138] While the specific embodiments of the present invention have been described above, they are not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. An intelligent method for monitoring the health status of underwater structures of offshore wind turbines, characterized in that, Includes the following processes: S1, Real-time measurement of acceleration signals at typical node locations of the offshore wind turbine's water structure - tower; S2, uses online modal recognition methods to obtain real-time data on the low-order measured frequencies and mode shapes of offshore wind turbine structures; S3. A finite element model of the offshore wind turbine structure is established based on the overall structural dimensions, material parameters, constraints, and design data. S4. Based on the number and properties of the finite element model elements, the underwater element damage degree vector is set, and the simulation frequency and mode shape data under different damage degree vectors are obtained based on numerical simulation. S5. Based on the measured frequency and modal data of the offshore wind turbine structure and the simulated frequency and modal data of the finite element model, an objective function that comprehensively considers the frequency and modal data is established, transforming the state monitoring problem into the problem of minimizing the difference between the simulated modal parameters and the measured modal parameters. S6 classifies fitness values ​​based on cluster analysis, introduces multiple population update strategies into the beetle swarm optimization algorithm, and obtains the optimal damage vector by minimizing the objective function. S7, the optimal damage degree vector represents the damage degree of the underwater unit of the offshore wind turbine structure. The damage degree is used to monitor the health status of the underwater structure and assess the degree of potential damage.

2. The intelligent method for monitoring the health status of underwater structures of offshore wind turbines as described in claim 1, characterized in that: Typical locations in S1 include the tower top, the connection between tower sections, and the connection between the tower section and the foundation.

3. The intelligent method for monitoring the health status of underwater structures of offshore wind turbines as described in claim 1, characterized in that: In S2, the number of measured nodes is ≥3, and the modal order identified by the measured response is ≥2.

4. The intelligent method for monitoring the health status of underwater structures of offshore wind turbines as described in claim 1, characterized in that: The finite element model of the offshore wind turbine structure in S3 is established in MATLAB, ANSYS, or ABAQUS software, and includes at least the tower, three-pile foundation, nacelle, and blades. The nacelle and blades can be equivalently replaced by applying a concentrated mass method at the top of the tower. The three-leg foundation at the bottom of the model adopts fixed constraints.

5. The intelligent method for monitoring the health status of underwater structures of offshore wind turbines as described in claim 1, characterized in that: S4 includes settings based on the number and properties of finite element elements. Damage vector of underwater unit: Selected For each underwater unit of an offshore wind turbine, a damage level value is randomly assigned, with the value ranging from (-1, 0), forming a damage level vector, as follows: ； in: Represents initialization of the first A vector of damage levels; For the first The set damage level for each underwater unit; Establish containing Initialization damage level matrix for each damage level vector The details are as follows: ； Numerical simulation was used to obtain simulation frequency and modal data under different damage levels; for the first Damage degree vector In this regard, the baseline stiffness matrix of the finite element model of the offshore wind turbine structure is updated accordingly. This forms a potential damage stiffness matrix that includes the damage. The specific process is as follows: ； in: For the first The element stiffness matrix corresponding to each underwater element; By solving the characteristic equation To obtain the frequency of potentially damaged structures and mode shape ;in This is the reference mass matrix for the finite element model of an offshore wind turbine structure.

6. The intelligent method for monitoring the health status of underwater structures of offshore wind turbines as described in claim 5, characterized in that: The objective function in S5 is a fusion of measured and potential damage modal parameters, specifically: ； in: ； ； In the formula: and For the first part of the potentially damaged structure and the measured structure First-order mode shape and The Middle Modal displacements with one degree of freedom; and The measured modal order and degrees of freedom; The weighting coefficients between the frequency and coordinate mode confidence criteria; when the modal parameters of the potentially damaged structure are the same as the measured structural parameters. = 0; otherwise, > 0; Through the Numerical simulation and feature extraction were performed on the damage degree vector to obtain... The frequency and mode shape data of the potentially damaged structure are used for calculation; based on this, the following can be obtained. A fitness value.

7. The intelligent method for monitoring the health status of underwater structures of offshore wind turbines as described in claim 6, characterized in that: The process of classifying fitness data based on cluster analysis in S6 is as follows: Step 1, with fitness value As input data, For the first A fitness value; Set the number of cluster populations to [value]. Randomly selected There are 1 cluster center, namely: In the formula For the first Cluster centers; Step 2, calculate fitness value With cluster center The minimum distance is used to determine the group to which it belongs. : ； Step 3: Recalculate each category based on the newly divided clusters. Cluster center : ； Step 4: Repeat steps 1 to 3 until convergence, and output the final clustering results and cluster centers. The distance between the obtained cluster centers and the optimal fitness value is used as the basis for distinguishing the quality of the population, and the population is divided into the best population, the medium population and the poor population.

8. The intelligent method for monitoring the health status of underwater structures of offshore wind turbines as described in claim 7, characterized in that: In step S6, a multi-population update strategy is introduced into the beetle swarm optimization algorithm. The optimal damage vector is obtained by minimizing the objective function. The specific process is as follows: Step 1, solve the first... In the nth iteration Damage degree vector ; Step 2: Generate random direction vectors ; Step 3: The longhorn beetle searches for the left antenna in the variable space. ;in For the first The distance between the two whiskers of the longhorn beetle or the antennal sensing diameter in the next iteration; Step 4, make a judgment Population classification hierarchy; Step 5: Establish different population renewal strategies for different population classification levels, specifically as follows: like To achieve the optimal population, the damage level vector of the potential damage structure is updated as follows: ;in For the first Iteration step size during iteration and For cognitive coefficient, Represents the symbolic function. This represents the optimal damage level vector. like If the population is of medium size, then the damage level vector of the potential damage structure is updated as follows: ;in Let Levy be the flight disturbance variable; like For a poor population, the damage level vector of the potential damaged structure is updated as follows: ;in It is a random disturbance variable; Step 6, Update the stiffness matrix ; Step 7: Solve the characteristic equation Obtain the predicted structural parameters and ; Step 8: Calculate the fitness value using the constructed fitness function. ; Step nine, if Update the optimal fitness value and the optimal damage vector ; Repeat steps one through nine above until the iteration termination condition is met, and output the optimal damage vector. .

9. The intelligent method for monitoring the health status of underwater structures of offshore wind turbines as described in claim 8, characterized in that: The optimal damage vector obtained in S7 includes The damage level value of each underwater element: If the damage level value is ≥1%, the corresponding underwater element may be damaged, and the severity of the damage depends on the magnitude of the damage level value; if the damage level value is <1%, the structure is in a healthy state by default, and its damage level change trend needs to be continuously tracked.

Images