Method and apparatus for detecting an adhering object

Abstract

Embodiments of the present disclosure provide an attachment detection method and device, the method comprising: obtaining a plurality of sets of first attachment state data; for each set of first attachment state data, calculating vibration response data corresponding to the first attachment state data by changing a density parameter of a substructure corresponding to an attachment position in a finite element model of an offshore riser; constructing a first model according to the plurality of sets of first attachment state data and the vibration response data corresponding to the plurality of sets of first attachment state data respectively; obtaining measured vibration response data of the offshore riser; obtaining simulated vibration response data of a density distribution variable to be solved based on the first model; solving the density distribution variable to obtain target density distribution data, with the deviation value between the simulated vibration response data and the measured vibration response data meeting a first preset condition as the target; and determining attachment parameters of external attachments on the offshore riser according to the target density distribution data, thereby timely and effectively achieving accurate detection of external attachments on the offshore riser.

Description

Technical Field

[0001] This disclosure relates to the field of attachment detection technology, and in particular to an attachment detection method and apparatus. Background Technology

[0002] Offshore risers are critical components connecting subsea wellheads to offshore platforms, and their structural safety directly determines the reliability of offshore oil and gas extraction systems. During long-term service, the upper area of ​​the riser is prone to the adhesion of marine organisms such as mussels and corals, forming a biofouling layer. The presence of biofouling alters the mass distribution and surface morphology of the riser, which can easily lead to safety hazards such as riser fatigue damage and tensioner overload.

[0003] Currently, the detection of biofouling on marine risers mainly relies on regular manual inspections. In shallow water, divers conduct visual observations, while in deep water, underwater robots equipped with optical or acoustic devices are used. However, divers' operations are constrained by water depth and weather conditions, making continuous monitoring difficult. Underwater robots are expensive to operate and maintain, and require on-site operation by professional personnel, which cannot meet the long-term, routine monitoring needs of risers.

[0004] Therefore, how to accurately detect the status of organisms attached to the outside of marine risers in a timely and effective manner without adding extra complex hardware equipment is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0005] This disclosure provides a method, apparatus, device, and medium for detecting attachments, thereby at least solving the above-mentioned technical problems existing in the prior art.

[0006] In a first aspect, embodiments of this disclosure provide a method for detecting deposits, the method comprising: Acquire multiple sets of first attachment state data, each set of first attachment state data including multiple attachment locations and the density change corresponding to each attachment location; For each set of first attachment state data, the vibration response data corresponding to the first attachment state data is calculated by changing the density parameters of the substructure corresponding to the attachment position in the finite element model of the marine riser. The first model is constructed based on multiple sets of first attachment state data and the vibration response data corresponding to the multiple sets of first attachment state data. Obtain measured vibration response data for marine risers; Simulated vibration response data of the density distribution variable to be solved are obtained based on the first model; With the objective of satisfying the first preset condition between the deviation between the simulated vibration response data and the measured vibration response data output by the first model, the density distribution variable to be solved is solved to obtain the target density distribution data of the marine riser. Based on the target density distribution data of the marine riser, the attachment parameters of the external attachments on the marine riser are determined, including the attachment location and the attachment thickness.

[0007] Secondly, embodiments of this disclosure provide an apparatus for detecting attachments, the apparatus comprising: The acquisition module is used to acquire multiple sets of first attachment state data. Each set of first attachment state data includes multiple attachment locations and the density change corresponding to each attachment location. The calculation module is used to calculate the vibration response data corresponding to the first attachment state data for each set of first attachment state data by changing the density parameters of the substructure corresponding to the attachment position in the finite element model of the marine riser. The construction module is used to construct the first model based on multiple sets of first attachment state data and the vibration response data corresponding to the multiple sets of first attachment state data respectively; The acquisition module is also used to acquire measured vibration response data of marine risers; The acquisition module is also used to acquire the simulated vibration response data of the density distribution variable to be solved based on the first model; The solution module is used to solve the density distribution variable to be solved with the objective that the deviation between the simulated vibration response data and the measured vibration response data output by the first model meets the first preset condition, so as to obtain the target density distribution data of the marine riser. The determination module is used to determine the attachment parameters of external attachments on the marine riser based on the target density distribution data. The attachment parameters include the attachment location and the attachment thickness.

[0008] Thirdly, embodiments of this disclosure provide an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the attachment detection method of the first aspect.

[0009] Fourthly, embodiments of this disclosure provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the attachment detection method according to the first aspect.

[0010] The beneficial technical effects of the attachment detection method provided in this disclosure are at least as follows: It can acquire multiple sets of first attachment state data, each set including the attachment location and corresponding density change. By adjusting the density parameters of each substructure through a finite element model, vibration response data corresponding to each set of first attachment state data is obtained. Then, based on the one-to-one correspondence between the attachment state data and the vibration response data, a first model is constructed. Next, during actual detection, measured vibration response data of the marine riser can be collected. Then, based on the first model, simulated vibration response data of the density distribution variable to be solved is obtained. By continuously adjusting the value of the density distribution variable, the simulated vibration response data output by the first model gradually approaches the measured vibration response data until the deviation between the two meets a first preset condition, thereby obtaining accurate target density distribution data. Finally, the attachment location and thickness of the external attachments of the marine riser are determined by combining the correspondence between the density distribution data and the attachment parameters. In this way, by generating vibration samples corresponding to the local density changes of the structure under different working conditions, the mapping relationship between the substructure density and vibration response at each attachment location can be accurately constructed. Thus, in actual testing, only sensors need to be deployed on the marine riser to collect vibration signals, eliminating the need for divers or underwater robots to operate on-site. This allows for timely and effective detection of the location and thickness of the attachment without adding extra complex hardware equipment.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] Figure 1 This is a schematic flowchart of an attachment detection method provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram illustrating the setup of an acceleration sensor according to an embodiment of this disclosure; Figure 3 This is a schematic diagram of the structure of an experimental apparatus provided in an embodiment of this disclosure. Figure 1 ; Figure 4 This is a schematic diagram of the structure of an experimental apparatus provided in an embodiment of this disclosure. Figure 2 ; Figure 5 This is a schematic diagram of the structure of an attachment detection device provided in an embodiment of this disclosure; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0013] To make the objectives, features, and advantages of this disclosure more apparent and understandable, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0014] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0015] If the application documents contain similar descriptions such as "first / second", the following explanation shall be added: In the following description, the terms "first / second / third" are used only to distinguish similar objects and do not represent a specific order of objects. It is understood that "first / second / third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0016] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0017] It should be noted that the attachment detection method provided in this disclosure can be executed by an attachment detection device or a control module within that device. This disclosure uses an attachment detection device executing the attachment detection method as an example to describe the attachment detection method provided in this disclosure in detail.

[0018] The attachment detection method provided in this disclosure will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] Figure 1 This is a schematic flowchart of an attachment detection method provided in an embodiment of this disclosure.

[0020] like Figure 1 As shown, the entity executing this attachment detection method can be an attachment detection device. Based on this, the attachment detection method provided in this embodiment can include the following steps: S110, acquire multiple sets of first attachment state data.

[0021] In some embodiments, each set of first adhesion state data includes multiple adhesion locations and the density change corresponding to each adhesion location. The density change is used to characterize the degree of adhesion or thickness of the external attachment, and is not specifically limited here.

[0022] In one example, when acquiring multiple sets of first attachment state data, multiple preset attachment state data can be obtained first. These preset attachment state data can include multiple attachment locations and the corresponding attachment thickness at each location. Based on this, the Box-Behnken design method can be used to design experiments on the multiple attachment locations and the corresponding attachment thicknesses included in the preset attachment state data. This converts the attachment thickness at each attachment location into a density change, thereby characterizing the thickness of the external attachment through the change in the density of the marine riser, and thus determining each set of first attachment state data. The corresponding relationship is shown in the following formula: (1) in, Represents the outer diameter of the marine riser, The inner diameter of the marine riser The thickness of the attachment, representing the thickness of external attachments (such as marine organisms). Represents the change in density, This represents the density of external attachments.

[0023] S120: For each set of first attachment state data, the vibration response data corresponding to the first attachment state data is calculated by changing the density parameters of the substructure corresponding to the attachment position in the finite element model of the marine riser.

[0024] The finite element model of the marine riser can be a simulation model based on the structural characteristics of the marine riser. This finite element model can contain multiple substructures, and the density parameters of each substructure can be adjusted independently. This finite element model can be used to calculate and output the vibration response data of the marine riser under corresponding working conditions in response to the input of the density parameters of each substructure. Here, the substructure refers to several finite element elements obtained by dividing the finite element model along the extension direction of the marine riser during the finite element modeling process. Each substructure corresponds to a different position in the finite element model, and the density parameter of each substructure is independently variable to simulate the local density change caused by the presence of external attachments at that position.

[0025] For example, when calculating the vibration response data corresponding to the first attachment state data by changing the density parameters of the substructure corresponding to the attachment position in the finite element model of the marine riser for each set of first attachment state data, a three-dimensional finite element model of the marine riser can be drawn based on finite element software (such as Ansys Workbench), a prestressed modal analysis system can be built, and the first 5 natural frequencies of the marine riser corresponding to each set of first attachment state data can be calculated as the vibration response data corresponding to the first attachment state data.

[0026] S130, a first model is constructed based on multiple sets of first attachment state data and vibration response data corresponding to the multiple sets of first attachment state data.

[0027] Since the first attachment state data includes multiple attachment locations and the density change corresponding to each attachment location, which constitutes the density distribution data of the marine riser, the first model can be constructed based on multiple sets of first attachment state data and their corresponding vibration response data. The first model can be used to characterize the mapping relationship between the density distribution data and the vibration response data of the marine riser. No specific limitations are made here.

[0028] In one example, the first model described above can be constructed using a quadratic polynomial function, as shown in the following formula: (2) in, Representative response values ​​(i.e., vibration response data, such as the first 5 natural frequencies of a marine riser); Represents a constant term; , Representing the The, the Density parameters of individual substructures; Represents the coefficient of the linear term; Represents the coefficient of the quadratic term; Represents the cross term coefficient. The total number of substructures.

[0029] S140, acquire measured vibration response data of the marine riser.

[0030] The measured vibration response data mentioned above can be the vibration characteristic parameters generated by the marine riser when subjected to external excitation. In some embodiments, the measured vibration response data can include the first or more natural frequencies of the marine riser, such as the first 5 natural frequencies, without further limitation here.

[0031] For example, this measured vibration response data can be obtained using sensors deployed on a marine riser. For instance, such as... Figure 2As shown, multiple accelerometers 21, 22, 23, 24, and 25 can be arranged at equal intervals (e.g., 500 meters apart) along the extension direction of the marine riser on its outer wall. Accelerometers collect acceleration signals from the marine riser through each sensor, and then modal analysis is performed on the collected acceleration signals to extract the first few natural frequencies of the marine riser. It should be noted that the method for acquiring the measured vibration response data can be determined according to the actual situation, and no specific limitation is made here.

[0032] S150, based on the first model, obtain the simulated vibration response data of the density distribution variable to be solved.

[0033] It should be noted that density distribution data can be used to characterize the density distribution of a marine riser at various locations along its extension direction. In some embodiments, the marine riser can be divided into multiple substructures along its extension direction, each substructure corresponding to a density parameter, which is an unknown quantity. The density distribution data of the marine riser is composed of the parameters of all substructures. When the surface of the marine riser is covered with a biofouling layer or other deposits, the density parameter of the corresponding substructure will change. Therefore, density distribution data can indirectly reflect the presence and distribution of deposits. Vibration response data can be the simulated vibration response value of the marine riser output by the first model after the density distribution data is input, corresponding to the density distribution data; no specific limitation is made here.

[0034] Therefore, the density distribution variables to be solved are the density parameters corresponding to each substructure, and the simulated vibration response data are the simulated vibration response values ​​obtained after inputting the density distribution variables to be solved into the first model.

[0035] S160, with the goal of satisfying the first preset condition for the deviation between the simulated vibration response data and the measured vibration response data output by the first model, the density distribution variable to be solved is solved to obtain the target density distribution data of the marine riser.

[0036] The first preset condition can be a condition pre-set based on actual experience or circumstances. In one case, the first preset condition can be set to minimize the deviation value. In another case, the first preset condition can be set to the deviation value being less than a preset deviation threshold; no specific limitation is made here.

[0037] S170, based on the target density distribution data of the marine riser, determine the attachment parameters of external attachments on the marine riser.

[0038] The aforementioned adhesion parameters are used to characterize the distribution of adhesions on marine risers. In some embodiments, these adhesion parameters may include adhesion location and adhesion thickness. There may be one or more adhesion locations, with each location corresponding to an adhesion thickness; no specific limitation is made here.

[0039] Specifically, the attachment detection device can acquire multiple sets of first attachment state data, each set including multiple attachment locations and the density change corresponding to each attachment location. For each set of first attachment state data, the density parameters of the substructure corresponding to the attachment location in the finite element model of the marine riser are changed, and simulation calculations are performed to obtain the vibration response data corresponding to that first attachment state data. Subsequently, a first model is constructed based on the multiple sets of first attachment state data and the vibration response data corresponding to each set of first attachment state data.

[0040] Based on this, during actual testing, the attachment detection device can acquire the measured vibration response data of the marine riser and obtain the simulated vibration response data of the density distribution variable to be solved based on the first model. By continuously adjusting the value of the density distribution variable to be solved, the simulated vibration response data output by the first model gradually approaches the measured vibration response data. When the deviation between the two meets the first preset condition, the value of the corresponding density distribution variable is the target density distribution data. Thus, the attachment parameters of the external attachments on the marine riser can be determined based on the target density distribution data of the marine riser.

[0041] It should be noted that the present invention does not specifically limit the execution order of the above-described processing steps S110 to S130 and S140.

[0042] Based on the attachment detection method provided in this embodiment, multiple sets of first attachment state data can be acquired. Each set of first attachment state data includes the attachment location and the corresponding density change. The density parameters of each substructure are adjusted using a finite element model to obtain vibration response data corresponding to each set of first attachment state data. Then, based on the one-to-one correspondence between the attachment state data and the vibration response data, a first model is constructed. During actual detection, measured vibration response data of the marine riser can be collected. Then, based on the first model, simulated vibration response data of the density distribution variable to be solved is obtained. By continuously adjusting the value of the density distribution variable, the simulated vibration response data output by the first model gradually approaches the measured vibration response data until the deviation between the two meets a first preset condition, thereby obtaining accurate target density distribution data. Finally, the attachment location and thickness of the external attachments of the marine riser are determined by combining the correspondence between the density distribution data and the attachment parameters. In this way, by generating vibration samples corresponding to the local density changes of the structure under different working conditions, the mapping relationship between the substructure density and vibration response at each attachment location can be accurately constructed. Thus, in actual testing, only sensors need to be deployed on the marine riser to collect vibration signals, eliminating the need for divers or underwater robots to operate on-site. This allows for timely and effective detection of the location and thickness of the attachment without adding extra complex hardware equipment.

[0043] Considering that marine risers can often be divided into multiple substructures, although a first model can be constructed from the density parameters of these substructures, not all parameters show significant correlation with the first model when there are many parameters (i.e., density parameters of multiple substructures). Therefore, in order to ensure model accuracy while simplifying model complexity, parameter selection is necessary.

[0044] Based on this, in order to comprehensively and thoroughly describe the attachment detection method provided by the embodiments of this disclosure, in one embodiment, the attachment detection method provided by the embodiments of this disclosure may include: Based on multiple sets of first attachment state data and the vibration response data corresponding to the multiple sets of first attachment state data, the evaluation value of each substructure is calculated. Based on the evaluation values ​​corresponding to multiple substructures, target substructures whose evaluation values ​​meet the second preset conditions are selected from the multiple substructures, and the first attachment state data is updated according to the selected target substructures.

[0045] The aforementioned evaluation value is used to characterize the degree of influence of the density parameter of the substructure on the vibration response data. In some embodiments, a larger evaluation value indicates a greater influence of the density parameter of the substructure on the vibration response data; conversely, a smaller evaluation value indicates a smaller influence of the density parameter of the substructure on the vibration response data. The number of the aforementioned target substructures can be one or more, and this disclosure does not specifically limit this.

[0046] In one example, the F-test can be used to calculate the evaluation value of each substructure. The specific formula can be seen as follows: (3) in, It is the sum of the squared differences of the density parameters; It is the sum of the squared differences of the test errors; It refers to the degrees of freedom of the density parameter, indicating how many types of marine organisms are present in the thickness of the material. This refers to the degrees of freedom of the test error, indicating how many times the test is repeated for each bio-attachment thickness. ) characterizes the average vibration response fluctuation amplitude caused by changes in the density of external attachments per unit degree of freedom. () represents the strength level of simulation test noise per unit degree of freedom.

[0047] It should be noted that the specific calculation method of the above-mentioned evaluation value is not specifically limited in the embodiments disclosed herein, and will not be elaborated on here.

[0048] In addition, the second preset condition mentioned above can be a pre-set condition based on actual experience or circumstances, used to filter and obtain the target substructure, and no specific limitation is made here.

[0049] Specifically, after obtaining multiple sets of first attachment state data and the corresponding vibration response data, an evaluation value for each substructure in the marine riser can be calculated. This evaluation value characterizes the influence of the substructure's density parameter on the vibration response data. Furthermore, based on the evaluation values ​​corresponding to these substructures, target substructures whose evaluation values ​​meet a second preset condition can be selected. The first attachment state data is then updated according to the selected target substructures. The updated first attachment state data may include the attachment location and density change corresponding to the target substructure.

[0050] Based on this, the steps described above for constructing the first model using multiple sets of first attachment state data and the vibration response data corresponding to each set of first attachment state data may specifically include: The first model is constructed based on the updated first attachment state data and the vibration response data corresponding to the updated first attachment state data.

[0051] Thus, after obtaining the updated first attachment state data, a first model can be constructed based on the updated first attachment state data and the vibration response data corresponding to the updated first attachment state data.

[0052] In this embodiment, the marine riser is divided into multiple substructures. Based on the first attachment state data and the corresponding vibration response data, an evaluation value representing the degree of density influence of each substructure is calculated. Then, based on the evaluation value, target substructures that have a significant impact on the vibration response data are selected, and the first attachment state data is simplified and updated accordingly. The updated first attachment state data is then used to construct the first model. This approach eliminates substructure parameters that have no significant impact on the vibration response of the marine riser, simplifies the input dimensions of the first model, reduces the amount of data computation during model training and subsequent iterative solutions, and eliminates interference from invalid parameters on the fitting of the density-vibration mapping relationship. This effectively improves computational efficiency while ensuring detection accuracy.

[0053] In order to accurately select target substructures that meet preset conditions from multiple substructures and update the first attachment state data accordingly, in one embodiment, the steps of selecting target substructures whose evaluation values ​​meet second preset conditions based on the evaluation values ​​corresponding to multiple substructures, and updating the first attachment state data according to the selected target substructures, may specifically include: The substructure whose evaluation value is greater than or equal to a preset threshold among multiple substructures is identified as the target substructure. Delete the attachment location and density change corresponding to substructures whose evaluation value is less than the preset threshold in the first attachment state data.

[0054] The preset threshold can be set in advance based on actual experience or circumstances, and no specific limitation is made here.

[0055] Specifically, after obtaining the evaluation values ​​corresponding to multiple substructures, since the evaluation values ​​are used to characterize the influence of the density parameters of the corresponding substructures on the simulated vibration response data, the substructures with evaluation values ​​greater than or equal to a preset threshold can be identified as target substructures, and the attachment positions and density changes corresponding to the substructures with evaluation values ​​less than the preset threshold in the first attachment state data can be deleted.

[0056] In one example, when calculating the first of multiple substructures... Evaluation value of each substructure (i.e., the above) After that, when Time represents the first substructure in multiple substructures The density parameters of each substructure have a highly significant impact on the simulated vibration response data; when When, it indicates the first The density parameters of individual substructures have a significant impact on the simulated vibration response data; when When, it indicates the first The density parameters of the individual substructures have no significant impact on the simulated vibration response data. No specific limitations are specified here. Based on this, and according to the above criteria, an appropriate preset threshold can be selected to filter substructures.

[0057] In this embodiment, by identifying substructures with evaluation values ​​greater than or equal to a preset threshold as target substructures, the attachment positions and density changes corresponding to substructures with evaluation values ​​less than the preset threshold in the original first attachment state data are simultaneously deleted, thus completing the simplification of the attachment state data. This effectively eliminates substructure parameters that have no significant impact on the vibration response of the marine riser, simplifies the input dimensions of the first model, and reduces the amount of data computation during model training and subsequent iterative solutions.

[0058] To provide a comprehensive and detailed description of the attachment detection method provided in this disclosure, in one embodiment, the attachment detection method may further include the following steps: Acquire verification sample data, which includes multiple sets of second attachment state data and vibration response data corresponding to the second attachment state data; The second attachment state data from the verification sample data is input into the first model to obtain the predicted vibration response data; The model accuracy of the first model is determined based on the predicted vibration response data and vibration response data corresponding to the second attachment state data.

[0059] In this context, the second attachment state data in the aforementioned verification sample data may be the same as or different from the first attachment state data. In some embodiments, to ensure the accuracy of the verification, the second attachment state data may be different from the first attachment state data, i.e., verification may be performed using data that was not used in the training of the first model; no specific limitation is made here.

[0060] Specifically, after obtaining the validation sample data, each set of second attachment state data from the validation sample data can be input into the first model to obtain the corresponding predicted vibration response data. Then, the predicted vibration response data is compared with the vibration response data corresponding to the second attachment state data, and the degree of deviation between the two is calculated to determine the model accuracy of the first model.

[0061] In one example, the multiple correlation coefficient can be used to evaluate the fitting accuracy of the first model. And the improved multiple correlation coefficient ( As an accuracy evaluation index, the closer its value is to 1, the better the fit. The expression is as follows: (4) (5) in, Representing the Finite element simulation calculation values ​​(i.e. vibration response data) for each sample point. Representing the The surrogate model calculation values ​​for each sample point (i.e., the predicted vibration response data output by the first model). This represents the average value calculated by finite element simulation. Represents the total number of samples. This represents the total number of correction parameters (i.e., substructure density parameters).

[0062] It is the first The difference between the predicted vibration response data and the actual vibration response data at each sample point represents the prediction error of the surrogate model (i.e., the first model) at that sample point. It is the first The difference between the vibration response data of a sample point and its mean represents the degree of fluctuation of that sample point relative to the overall mean. This represents the proportion of variance that the model failed to explain; a smaller value indicates a higher model fit accuracy. For the degrees of freedom of the total sum of squared deviations, ( ) represents the degrees of freedom of the sum of squared residuals.

[0063] in, The multiple correlation coefficient is used to characterize the overall fit of the first model to the training data; the closer its value is to 1, the better the fit. () represents the improved multiple correlation coefficient, which in The number of correction parameters was introduced based on this. The penalty term is used to avoid overfitting due to the introduction of too many irrelevant parameters. Similarly, the closer its value is to 1, the better the model's generalization ability.

[0064] In this embodiment, after the first model is constructed, independent verification sample data is obtained. The second attachment state data within the verification sample data is input into the first model to obtain predicted vibration response data. The accuracy of the first model is determined by comparing the predicted vibration response data with the corresponding vibration response data. In this way, the fitting effect of the model can be verified offline by obtaining the verification sample data, thereby effectively filtering out the first model that does not meet the accuracy standard. This avoids amplifying the calculation error when using low-precision models to solve for density distribution variables with measured data, and effectively improves the reliability of subsequent attachment position and thickness detection results.

[0065] In order to accurately and comprehensively describe the attachment detection method provided in the embodiments of this disclosure, in one embodiment, the above-described S160 may specifically include the following steps: Multiple initial solutions are obtained, each including reference density distribution data for the marine riser; The target density distribution data is obtained by iteratively solving multiple initial solutions until the stopping condition is met, with the deviation between the simulated vibration response data and the measured vibration response data output by the first model as the objective.

[0066] The aforementioned reference density distribution data refers to the initial density parameter values ​​pre-set for each substructure of the marine riser during the initial stage of iterative solution. For example, within the feasible range of density parameter values ​​for the marine riser, multiple sets of reference density distribution data can be generated through random sampling to serve as multiple initial solutions. For instance, 200 initial solutions can be obtained and evenly distributed across the solution space to prevent the algorithm from getting trapped in local optima; no specific limitation is made here.

[0067] The aforementioned stopping conditions can be preset based on practical experience. In some embodiments, the stopping condition may include an iteration count greater than or equal to a preset threshold (e.g., 300 iterations). In other embodiments, the stopping condition may include a deviation between the simulated vibration response data output by the first model and the measured vibration response data being less than a preset deviation threshold (e.g., ...). The preset number of times threshold and preset deviation threshold can be set according to actual experience or circumstances, and are not specifically limited here.

[0068] Specifically, multiple initial solutions are obtained, each including reference density distribution data for the marine riser. Then, with the objective of satisfying a first preset condition regarding the deviation between the simulated vibration response data output by the first model and the measured vibration response data, an optimization algorithm iteratively solves for these initial solutions. During the iteration process, the values ​​of the density distribution variables corresponding to each initial solution are continuously updated, gradually bringing the simulated vibration response data output by the first model closer to the measured vibration response data. When a stopping condition is met, the iteration stops, and the solution whose current deviation value satisfies the first preset condition is determined as the target density distribution data.

[0069] The optimization algorithm described above can be pre-set based on practical experience or computational requirements. For example, the optimization algorithm may include the whale optimization algorithm, without being specifically limited here.

[0070] In this embodiment, multiple initial solutions containing reference density distribution data of the marine riser are generated. The objective is to ensure that the deviation between the simulated vibration response data and the measured vibration response data output by the first model meets a first preset condition. An optimization algorithm iteratively solves these multiple initial solutions simultaneously until a stopping condition is met, outputting the target density distribution data. This approach effectively reduces the probability of iterative optimization converging to a local optimum by covering the feasible range of density parameters with multiple initial solutions. It also significantly improves the matching degree between the obtained target density distribution data and the actual working conditions of the marine riser, reducing calculation errors in the location and thickness of attached materials.

[0071] Based on this, the above steps of iteratively solving multiple initial solutions until the stopping condition is met to obtain the target density distribution data can specifically include: In the Tth iteration, based on the deviation values ​​corresponding to multiple candidate solutions, the candidate solution with the smallest deviation value is determined as the current optimal solution, and the position vector of the current optimal solution is obtained; According to the preset position update strategy, the position vectors of candidate solutions other than the current best solution are updated so that the position vectors of the updated candidate solutions are closer to the position vectors of the current best solution. Based on the updated position vectors of the candidate solutions and the measured vibration response data, the deviation values ​​corresponding to the candidate solutions are updated respectively; If the stopping condition is not met, update T=T+1 and return to the step of determining the candidate solution with the smallest deviation value based on the deviation values ​​corresponding to multiple candidate solutions, until the stopping condition is met, and then determine the current optimal solution as the target density distribution data.

[0072] Here, a candidate solution refers to a set of reference density distribution data currently used in the iteration process. In the first iteration, multiple initial solutions participate in the iteration as current candidate solutions; in each subsequent iteration, the candidate solution is the reference density distribution data obtained after solving the previous iteration.

[0073] The aforementioned position vector is used to characterize the specific value of the reference density distribution data corresponding to the candidate solution. The aforementioned position update strategy is used to guide the movement direction of the candidate solution in the solution space, so that the candidate solution gradually moves closer to a better solution; no specific limitations are made here.

[0074] Specifically, in the T-th iteration, the deviation value corresponding to each candidate solution is first calculated, and the candidate solution with the smallest deviation value is determined as the current optimal solution, and its position vector is obtained. Then, according to a preset position update strategy, the position vectors of other candidate solutions besides the current optimal solution are updated, so that the updated candidate solution position vectors are closer to the current optimal solution position vector. Next, based on the updated candidate solution position vectors and the measured vibration response data, the deviation values ​​corresponding to each candidate solution are updated. It is then determined whether the stopping condition is met. If it is, the iteration stops and the current optimal solution is determined as the target density distribution data; if not, T = T + 1 is set, the current optimal solution is re-determined, and the iteration continues until the stopping condition is met.

[0075] In one example, when the optimization algorithm is the whale optimization algorithm, the position update strategy can include a prey encirclement phase, a bubble net attack phase, and a prey search phase. The combination of these phases enables the candidate solution position to move closer to the current optimal solution position.

[0076] In the prey-encircling phase, the position update of candidate solutions is controlled by the following equation: (6) (7) in, This represents the current iteration number, i.e., T mentioned above. This is the position vector of the current optimal solution. Let be the position vector of the candidate solution. Let be the distance vector, representing the relative distance between the candidate solution and the current optimal solution in the density solution space. It is the position vector of the updated candidate solution. and For the coefficient vector, Represents absolute value. This represents element-wise multiplication. If a better solution is found during the iteration process,... It should be updated in each iteration.

[0077] The above coefficient vector and The calculation is performed using the following formula: (8) (9) in, The convergence factor decreases linearly from 2 to 0 during the iteration process. It is a random vector between [0, 1].

[0078] During the bubble net attack phase, candidate solutions move along a spiral path around the current optimal solution, and their positions are updated in the following way: (10) in, The random probability coefficient is between [-1, 1]. This is the distance vector between the candidate solution and the optimal solution. The constant for the spiral shape. Let be a random iteration factor with a value range of [-1, 1].

[0079] During the prey-finding phase, candidate solutions are randomly searched based on each other's positions, and their positions are updated as follows: (11)

[0080] In the formula: Let be a position vector randomly selected from the current pool of candidate solutions. Let be the position vector of the candidate solution to be updated.

[0081] The algorithm passes The value of determines whether to proceed to one of the above three stages for iteration. Specifically: when At this time, it enters the prey-hunting stage; when At this time, it enters either the prey encirclement phase or the bubble net attack phase, where random numbers between [0,1] are used. Decision, when When entering the stage of surrounding the prey, when It then enters the bubble web attack phase.

[0082] In this embodiment, the candidate solution with the smallest deviation value is selected as the current optimal solution in a single iteration, and the position vector representing the density distribution is extracted. Following a preset update strategy, the position vectors of the remaining candidate solutions are made to converge towards the optimal solution. After updating the vectors, the deviation values ​​of each group of candidate solutions are recalculated. This process is repeated iteratively until a stopping condition is met, at which point the optimal density distribution is output as the target density distribution data. In this way, iteratively solving for candidate solutions simultaneously completes global search and local fine-tuning of parameters, which can stably reduce the deviation between the simulated vibration response and the measured vibration response, accelerate the iterative convergence speed, and shorten the overall detection time for external attachments.

[0083] In one embodiment, the step of updating the deviation values ​​corresponding to the candidate solutions based on the updated position vectors of the candidate solutions and the measured vibration response data may include: The reference density distribution data corresponding to the position vector of the candidate solution is input into the first model to obtain the simulated vibration response data corresponding to the candidate solution; The simulated vibration response data and measured vibration response data corresponding to the candidate solutions are input into the objective function to obtain the deviation value corresponding to the candidate solutions. The objective function characterizes the degree of difference between the simulated vibration response data and the measured vibration response data corresponding to the same density distribution data.

[0084] The objective function mentioned above can be used to quantify the degree of difference between simulated vibration response data and measured vibration response data, and no specific limitations are made here.

[0085] Specifically, after updating the position vectors of candidate solutions according to the position update strategy, the reference density distribution data corresponding to the updated candidate solution's position vector is input into the first model. The first model outputs the simulated vibration response data corresponding to the candidate solution. Then, this simulated vibration response data and the measured vibration response data obtained in S110 are input into the objective function to calculate the deviation value corresponding to the candidate solution. This deviation value is used to quantify the degree of difference between the density distribution data corresponding to the candidate solution and the actual density distribution of the marine riser. The above process is then repeated to obtain the deviation value corresponding to each candidate solution.

[0086] In one example, the objective function described above is constructed as follows: (13) in, This represents the output value of the objective function, i.e., the deviation value of the candidate solution; The total order representing the vibration response data (e.g., natural frequencies); Representing the The order identifier of the vibration response data; Representing the The weighting coefficients of the vibration response data of different orders are used to characterize the importance of vibration response data of different orders in the objective function; Representing the Experimental test values ​​of vibration response data (i.e., measured vibration response data); Representing the The surrogate model response value of the first-order vibration response data (i.e., the simulated vibration response data output by the first model).

[0087] In a specific experimental scenario, such as Figure 3 As shown, the experimental setup includes a slide rail 1, a top tension adjustment device 2, a support frame 3, a slider 4, attached marine organisms 5, a riser model 6, a hinged support 7, a fixed support 8, and a fixed base plate 9. Figure 4 As shown, the experimental setup also includes a rotating wheel 10, a lead screw 11, a push-pull force gauge 12, a hook 13, a hanging ring 14, and a push-pull force gauge mounting bracket 15. Based on this, one end of the riser model 6 is fixedly connected to the fixed base plate 9 at the bottom of the pool via a fixed support 8, and the other end is connected to the push-pull force gauge 12 via a hinge support 7. Accelerometer sensors are evenly distributed at equal intervals on the riser model 6. By rotating the rotating wheel 10, the lead screw 11 is rotated, causing the push-pull force gauge mounting bracket 15 to move up and down, thereby adjusting the tension at the top of the riser model 6. After adjusting the top tension, the water flow is released, and after the water flow velocity reaches the set value and stabilizes, acceleration data is collected. After collecting the acceleration signal in the absence of marine organisms, a marine organism model 5 is fixed to the upper part of the riser model 6, and acceleration signals are collected again. Modal analysis was performed on the collected acceleration signals to obtain the first five natural frequencies. The attachment position and thickness of the marine organism model 5 were varied, and acceleration sensor data were collected multiple times. Modal analysis was then performed on the collected data to obtain the first five natural frequencies under different attachment states. This yielded experimental vibration response data. The corresponding simulated vibration response data can then be obtained from the first model, and the aforementioned objective function can be constructed based on the experimental and simulated vibration response data.

[0088] In this embodiment, the reference density distribution data corresponding to the position vector of the updated candidate solution is input into the first model to obtain simulated vibration response data. Then, the simulated vibration response data and the measured vibration response data are input into the objective function to quantify the deviation value of each candidate solution. In this way, the difference between the simulated vibration data and the measured vibration response data can be accurately quantified, and the deviation value corresponding to the candidate solution can be accurately obtained, which facilitates the reduction of calculation errors of the attached parameters in subsequent steps.

[0089] In order to provide a comprehensive and detailed description of the method provided by the embodiments of this disclosure, in one embodiment, the above-described S140 may specifically include: The target density distribution data is compared with the initial density distribution data of the marine riser in the absence of external attachments to obtain the density distribution change data of the marine riser. The density distribution change data includes the density change amount corresponding to multiple substructures. The location of each substructure is determined as the attachment location; Based on the density changes of multiple substructures and the correspondence between density changes and adhesion thickness, the adhesion thickness at each adhesion location is calculated.

[0090] The initial density distribution data mentioned above refers to the density distribution data when there are no external attachments on the surface of the marine riser. Additionally, the density distribution variation data includes the density changes corresponding to multiple substructures.

[0091] The relationship between the density change and the adhesion thickness mentioned above can be preset according to actual conditions, and is not specifically limited here.

[0092] Specifically, after obtaining the target density distribution data through iterative solution, this target density distribution data is compared with the initial density distribution data of the marine riser in the absence of external attachments. The density change at each substructure location on the marine riser is calculated to obtain the density distribution change data. Then, the locations of the substructures where the density change changes are determined as the attachment locations of external attachments. Finally, based on a pre-determined correspondence between density change and attachment thickness, the density change corresponding to each attachment location is converted into the attachment thickness at that location. In this way, the attachment locations of all external attachments on the marine riser and the corresponding attachment thickness at each location can be obtained.

[0093] In this embodiment, the target density distribution data obtained through iterative solving is compared with the initial density distribution data under the condition of no external attachments to obtain the density change corresponding to each substructure. The locations of substructures with density changes are designated as attachment locations. Then, the attachment thickness at each location is calculated by combining the correspondence between the density change and the attachment thickness. In this way, the attachment location and attachment thickness of external attachments on the marine riser can be accurately determined.

[0094] Furthermore, based on the same inventive concept, embodiments of this disclosure provide an attachment detection device, which can be specifically combined with attachments. Figure 5 This disclosure provides a detailed description of an attachment detection device according to an embodiment.

[0095] Figure 5 This is a schematic diagram of the structure of an attachment detection device provided in an embodiment of this disclosure.

[0096] like Figure 5 As shown, the attachment detection device 500 may include: The acquisition module 510 is used to acquire multiple sets of first attachment state data, each set of first attachment state data including multiple attachment positions and the density change corresponding to each attachment position; The calculation module 520 is used to calculate the vibration response data corresponding to the first attachment state data for each group of first attachment state data by changing the density parameters of the substructure corresponding to the attachment position in the finite element model of the marine riser. The construction module 530 is used to construct a first model based on multiple sets of first attachment state data and vibration response data corresponding to the multiple sets of first attachment state data respectively. The acquisition module 510 is also used to acquire measured vibration response data of the marine riser; The acquisition module 510 is also used to acquire the simulated vibration response data of the density distribution variable to be solved based on the first model; The solver module 540 is used to solve the density distribution variable to be solved with the objective that the deviation between the simulated vibration response data and the measured vibration response data output by the first model meets the first preset condition, so as to obtain the target density distribution data of the marine riser. The determination module 550 is used to determine the attachment parameters of external attachments on the marine riser based on the target density distribution data of the marine riser. The attachment parameters include the attachment location and the attachment thickness.

[0097] In one embodiment, the attachment detection device provided in this disclosure includes: The calculation module is also used to calculate the evaluation value of each substructure based on multiple sets of first attachment state data and the vibration response data corresponding to the multiple sets of first attachment state data respectively. The evaluation value characterizes the degree of influence of the density parameter of the substructure on the vibration response data. The filtering module is used to filter out target substructures whose evaluation values ​​meet the second preset conditions from multiple substructures based on the evaluation values ​​corresponding to each substructure, and update the first attachment state data according to the selected target substructures. The updated first attachment state data includes the attachment position and density change of the target substructure. The construction module is specifically used to construct the first model based on the updated first attachment state data and the vibration response data corresponding to the updated first attachment state data.

[0098] In one embodiment, the attachment detection device provided in this disclosure includes: The determination module is also used to determine the target substructure among multiple substructures whose evaluation value is greater than or equal to a preset threshold. The deletion module is used to delete the attachment position and density change of substructures whose evaluation value is less than a preset threshold in the first attachment state data.

[0099] In one embodiment, the attachment detection device provided in this disclosure includes: The acquisition module is also used to acquire verification sample data, which includes multiple sets of second attachment state data and vibration response data corresponding to the second attachment state data. The input module is also used to input the second attachment state data from the verification sample data into the first model to obtain the predicted vibration response data; The determination module is also used to determine the model accuracy of the first model based on the predicted vibration response data and vibration response data corresponding to the second attachment state data.

[0100] In one embodiment, the attachment detection device provided in this disclosure includes: The acquisition module is also used to acquire multiple initial solutions, each of which includes reference density distribution data for the marine riser; The solution module is specifically used to obtain the target density distribution data by iteratively solving multiple initial solutions until the stopping condition is met, with the goal of satisfying the first preset condition between the deviation between the simulated vibration response data output by the first model and the measured vibration response data.

[0101] In one embodiment, the attachment detection device provided in this disclosure includes: The determination module is also used in the T-th iteration to determine the candidate solution with the smallest deviation value as the current optimal solution based on the deviation values ​​corresponding to multiple candidate solutions, and to obtain the position vector of the current optimal solution; the candidate solution is determined based on the initial solution; the position vector represents the reference density distribution data corresponding to the candidate solution; the deviation value represents the degree of difference between the simulated vibration response data and the measured vibration response data corresponding to the candidate solution; The update module is used to update the position vectors of candidate solutions other than the current best solution among multiple candidate solutions according to a preset position update strategy, so that the position vectors of the updated candidate solutions are closer to the position vectors of the current best solution. The update module is also used to update the deviation values ​​corresponding to the candidate solutions based on the updated position vectors of the candidate solutions and the measured vibration response data. The update module is also used to update T=T+1 if the stopping condition is not met, and return to the step of determining the candidate solution with the smallest deviation value based on the deviation values ​​corresponding to multiple candidate solutions, until the stopping condition is met, and then determine the current optimal solution as the target density distribution data.

[0102] In one embodiment, the attachment detection device provided in this disclosure includes: The input module is also used to input the reference density distribution data corresponding to the position vector of the candidate solution into the first model to obtain the simulated vibration response data corresponding to the candidate solution; The input module is also used to input the simulated vibration response data and measured vibration response data corresponding to the candidate solution into the objective function to obtain the deviation value corresponding to the candidate solution. The objective function characterizes the degree of difference between the simulated vibration response data and the measured vibration response data corresponding to the same density distribution data. The objective function satisfies the following formula:

[0103] in, The deviation value of the candidate solution. The order of the vibration response data. For the first Order identifier of vibration response data. For the first Measured vibration response data of the first order, For the first Simulated vibration response data of the first order, For the first Weighting coefficients for first-order vibration response data.

[0104] In one embodiment, the attachment detection device provided in this disclosure includes: The comparison module is used to compare the target density distribution data with the initial density distribution data of the marine riser in the absence of external attachments, so as to obtain the density distribution change data of the marine riser. The density distribution change data includes the density change amount corresponding to multiple substructures. The determination module is specifically used to determine the attachment location of each substructure; The calculation module is used to calculate the adhesion thickness corresponding to each adhesion position based on the density change of multiple substructures and the correspondence between the density change and the adhesion thickness.

[0105] It is understood that the attachment detection method apparatus provided in the above embodiments can, as needed, allocate the above processing to different program modules to complete all or part of the processing described above when implementing the corresponding attachment detection method. Furthermore, the apparatus and the corresponding method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiments, and will not be repeated here.

[0106] This application provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform an attachment detection method.

[0107] This application provides a computer-readable storage medium storing executable instructions, wherein the executable instructions are stored and when executed by a processor, the processor will execute the attachment detection method provided in this application.

[0108] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0109] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0110] As an example, executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborating files (e.g., a file that stores one or more modules, subroutines, or code sections).

[0111] As an example, executable instructions can be deployed to execute on a single computing device, or on multiple computing devices located in one location, or on multiple computing devices distributed across multiple locations and interconnected via a communication network.

[0112] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure; as shown below. Figure 6 As shown, the electronic device 60 includes: a processor 601, and a memory 602 communicatively connected to the processor 601; the memory 602 stores instructions executable by the processor 601. The instructions are executed by the processor 601 to enable the processor 601 to perform the following: Multiple sets of first attachment state data are acquired, each set of first attachment state data including multiple attachment locations and the density change corresponding to each attachment location; For each set of first attachment state data, the vibration response data corresponding to the first attachment state data is calculated by changing the density parameter of the substructure corresponding to the attachment position in the finite element model of the marine riser. A first model is constructed based on multiple sets of first adhesion state data and vibration response data corresponding to the multiple sets of first adhesion state data. Obtain the measured vibration response data of the marine riser; Based on the first model, simulated vibration response data of the density distribution variable to be solved are obtained; With the goal of satisfying a first preset condition between the deviation between the simulated vibration response data output by the first model and the measured vibration response data, the density distribution variable to be solved is solved to obtain the target density distribution data of the marine riser. Based on the target density distribution data of the marine riser, the attachment parameters of the external attachments on the marine riser are determined, including the attachment location and the attachment thickness.

[0113] The electronic devices and corresponding attachment detection methods provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0114] In practical applications, the electronic device 60 may further include at least one network interface 603. The various components of the electronic device 60 are coupled together via a bus system 604. It is understood that the bus system 604 is used to implement communication between these components. In addition to a data bus, the bus system 604 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 6 All buses are labeled as bus system 604. The number of processors 601 and the number of memories 602 can be at least one. The network interface 603 is used for wired or wireless communication between the electronic device 60 and other devices.

[0115] The memory 602 in this embodiment is used to store various types of data to support the operation of the electronic device 60.

[0116] The methods disclosed in the above embodiments of this disclosure can be applied to or implemented by processor 601. Processor 601 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 601 or by instructions in software form. The processor 601 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 601 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this disclosure. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this disclosure can be directly manifested as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in memory 602. Processor 601 reads the information in memory 602 and, in conjunction with its hardware, completes the steps of the aforementioned attachment detection method.

[0117] In some embodiments, the electronic device 60 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned methods.

[0118] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0119] In the above description, the term "some embodiments" refers to a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0120] Unless otherwise defined, all technical and scientific terms used in this disclosure have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The terminology used in this disclosure is for the purpose of describing embodiments of this disclosure only and is not intended to be limiting of this disclosure.

[0121] It should be understood that in the various embodiments of this disclosure, the sequence number of each implementation process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this disclosure.

[0122] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise explicitly specified.

[0123] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A method for detecting attachments, characterized in that, The method includes: Multiple sets of first attachment state data are acquired, each set of first attachment state data including multiple attachment locations and the density change corresponding to each attachment location; For each set of first attachment state data, the vibration response data corresponding to the first attachment state data is calculated by changing the density parameter of the substructure corresponding to the attachment position in the finite element model of the marine riser. A first model is constructed based on multiple sets of first adhesion state data and vibration response data corresponding to the multiple sets of first adhesion state data. Obtain the measured vibration response data of the marine riser; Based on the first model, simulated vibration response data of the density distribution variable to be solved are obtained; With the goal of satisfying a first preset condition between the deviation between the simulated vibration response data output by the first model and the measured vibration response data, the density distribution variable to be solved is solved to obtain the target density distribution data of the marine riser. Based on the target density distribution data of the marine riser, the attachment parameters of the external attachments on the marine riser are determined, including the attachment location and the attachment thickness. The method further includes: Based on the multiple sets of first attachment state data and the vibration response data corresponding to the multiple sets of first attachment state data, an evaluation value for each substructure is calculated, and the evaluation value characterizes the degree of influence of the density parameter of the substructure on the vibration response data. Based on the evaluation values ​​corresponding to the multiple substructures, a target substructure whose evaluation value meets the second preset condition is selected from the multiple substructures, and the first attachment state data is updated according to the selected target substructure. The updated first attachment state data includes the attachment position and density change corresponding to the target substructure. The first model is constructed based on multiple sets of first adhesion state data and vibration response data corresponding to the multiple sets of first adhesion state data, including: The first model is constructed based on the updated first adhesion state data and the vibration response data corresponding to the updated first adhesion state data; The step of selecting target substructures whose evaluation values ​​satisfy a second preset condition from among the multiple substructures based on their respective evaluation values, and updating the first attachment state data according to the selected target substructures, includes: The substructure whose evaluation value is greater than or equal to a preset threshold among the multiple substructures is identified as the target substructure; Delete the attachment position and density change of the substructure whose evaluation value is less than the preset threshold in the first attachment state data.

2. The method according to claim 1, characterized in that, Also includes: Acquire verification sample data, which includes multiple sets of second attachment state data and vibration response data corresponding to the second attachment state data; Input the second attachment state data from the verification sample data into the first model to obtain the predicted vibration response data; The model accuracy of the first model is determined based on the predicted vibration response data and vibration response data corresponding to the second attachment state data.

3. The method according to claim 1, characterized in that, The method aims to solve for the density distribution variable to be solved, with the deviation between the simulated vibration response data output by the first model and the measured vibration response data satisfying a first preset condition, to obtain the target density distribution data of the marine riser, including: Multiple initial solutions are obtained, each of which includes reference density distribution data of the marine riser; With the goal of satisfying a first preset condition for the deviation between the simulated vibration response data output by the first model and the measured vibration response data, the target density distribution data is obtained by iteratively solving the multiple initial solutions until the stopping condition is met.

4. The method according to claim 3, characterized in that, The process of iteratively solving the multiple initial solutions until a stopping condition is met to obtain the target density distribution data includes: In the Tth iteration, based on the deviation values ​​corresponding to multiple candidate solutions, the candidate solution with the smallest deviation value is determined as the current optimal solution, and the position vector of the current optimal solution is obtained; the candidate solution is determined based on the initial solution; the position vector represents the reference density distribution data corresponding to the candidate solution; the deviation value represents the degree of difference between the simulated vibration response data and the measured vibration response data corresponding to the candidate solution; According to a preset position update strategy, the position vectors of the candidate solutions other than the current optimal solution are updated so that the position vectors of the updated candidate solutions are closer to the position vectors of the current optimal solution. Based on the updated position vectors of the candidate solutions and the measured vibration response data, the deviation values ​​corresponding to the candidate solutions are updated respectively. If the stopping condition is not met, update T=T+1 and return to the step of determining the candidate solution with the smallest deviation value based on the deviation values ​​corresponding to multiple candidate solutions as the current optimal solution, until the stopping condition is met, and the current optimal solution is determined as the target density distribution data.

5. The method according to claim 4, characterized in that, The step of updating the deviation values ​​corresponding to the candidate solutions based on the updated position vectors of the candidate solutions and the measured vibration response data includes: The reference density distribution data corresponding to the position vector of the candidate solution is input into the first model to obtain the simulated vibration response data corresponding to the candidate solution; The simulated vibration response data and the measured vibration response data corresponding to the candidate solutions are input into the objective function to obtain the deviation value corresponding to the candidate solutions. The objective function characterizes the degree of difference between the simulated vibration response data and the measured vibration response data corresponding to the same density distribution data. The objective function satisfies the following formula: in, The deviation value of the candidate solution. The order of the vibration response data. For the first Order identifier of vibration response data. For the first Measured vibration response data of the first order, For the first Simulated vibration response data of the first order, For the first Weighting coefficients for first-order vibration response data.

6. The method according to claim 1, characterized in that, The step of determining the attachment parameters of external attachments on the marine riser based on the target density distribution data of the marine riser includes: The target density distribution data is compared with the initial density distribution data of the marine riser in the absence of external attachments to obtain the density distribution change data of the marine riser. The density distribution change data includes the density change amount corresponding to multiple substructures. The location of the substructure where the density change changes is determined as the attachment location; Based on the density change corresponding to the multiple substructures and the correspondence between the density change and the adhesion thickness, the adhesion thickness corresponding to each adhesion position is calculated.

7. A device for detecting attachments, characterized in that, The device includes: The acquisition module is used to acquire multiple sets of first attachment state data, each set of first attachment state data including multiple attachment positions and the density change corresponding to each attachment position; The calculation module is used to calculate the vibration response data corresponding to the first attachment state data for each group of the first attachment state data by changing the density parameter of the substructure corresponding to the attachment position in the finite element model of the marine riser. A construction module is used to construct a first model based on multiple sets of first attachment state data and vibration response data corresponding to the multiple sets of first attachment state data respectively. The acquisition module is also used to acquire the measured vibration response data of the marine riser; The acquisition module is also used to acquire the simulated vibration response data of the density distribution variable to be solved based on the first model; The solution module is used to solve the density distribution variable to be solved with the objective of satisfying a first preset condition between the deviation between the simulated vibration response data output by the first model and the measured vibration response data, so as to obtain the target density distribution data of the marine riser. The determination module is used to determine the attachment parameters of external attachments on the marine riser based on the target density distribution data of the marine riser, wherein the attachment parameters include attachment location and attachment thickness; the device includes: The calculation module is also used to calculate the evaluation value of each substructure based on the multiple sets of first attachment state data and the vibration response data corresponding to the multiple sets of first attachment state data, wherein the evaluation value characterizes the degree of influence of the density parameter of the substructure on the vibration response data; The filtering module is used to filter out target substructures whose evaluation values ​​meet the second preset conditions from the multiple substructures based on the evaluation values ​​corresponding to the multiple substructures, and update the first attachment state data according to the filtered target substructures. The updated first attachment state data includes the attachment position and density change corresponding to the target substructure. The construction module is specifically used to construct the first model based on the updated first attachment state data and the vibration response data corresponding to the updated first attachment state data. The determining module is further configured to determine the target substructure as the substructure whose evaluation value is greater than or equal to a preset threshold among the multiple substructures; The determining module is further configured to delete the attachment position and density change corresponding to the substructure in the first attachment state data whose evaluation value is less than the preset threshold.

Images