Marine jacket platform structure damage identification method and system

Abstract

The invention discloses an ocean jacket platform structure damage identification method and system, and belongs to the technical field of ocean platform structure damage identification, and the method comprises the steps: obtaining different types of reference data in a reference database through classification, and determining the statistical values and damage thresholds of damage sensitive features corresponding to the different types of reference data; when the damage sensitive characteristic statistical value corresponding to the test data is greater than the damage threshold value corresponding to the reference data of the current category, judging that the jacket platform structure is damaged, and starting an on-site detection and maintenance process; when no damage is actually detected on site, taking the test data as a new working condition sample, putting the new working condition sample into the reference database, and updating the category label; and otherwise, taking the test data as normal data, classifying the normal data, and incorporating the normal data into the reference data of the corresponding category. According to the method, the influence of the excitation environment change on the structural damage identification result is considered, and the uncertainty of the structural damage identification result of the ocean platform is greatly reduced.

Description

Technical Field

[0001] This invention relates to the field of marine platform structural damage identification technology, and more specifically to a method and system for identifying structural damage to marine jacket platforms. Background Technology

[0002] Jacket platforms are a type of marine engineering structure that provides a place for offshore operations and living quarters for the development and utilization of marine resources. Therefore, health monitoring of jacket platform structures is a very meaningful task.

[0003] Because the system characteristics of offshore platform structures are subject to non-stationary changes due to variations in the external excitation environment, existing structural damage identification methods cannot guarantee the accuracy and reliability of the system identification results. Furthermore, the operating environment and characteristics of offshore platforms dictate that damage identification of offshore platform structures must be carried out under environmental excitation conditions. Therefore, clarifying the impact of changes in the excitation environment on structural damage identification is the key to solving the problem of damage identification of offshore platform structures under environmental excitation conditions.

[0004] Traditional damage identification methods for offshore platform structures under environmental excitation primarily rely on global damage identification, utilizing the monitored structure's output vibration response to reflect its overall condition. This involves placing accelerometers at various nodes and using algorithms to convert the measured acceleration signals into indicators reflecting damage, thereby identifying structural damage. While real-time data and probabilistic statistical analysis are typically employed to address changes in the excitation environment, they fail to fundamentally consider the impact of these changes on the structural system's characteristics. This results in significant uncertainty in the identification results, greatly increasing the cost of offshore platform structural health monitoring. To address this, existing technologies have published a subspace Mahalanobis distance damage detection method resistant to excitation covariance variations. This method, based on the stochastic subspace method, considers the impact of excitation covariance variations on damage identification results, eliminating the influence of excitation environment changes through Hankel matrix standardization of the excitation covariance. However, its application is primarily limited to simple structures such as simply supported beams or indoor models, failing to adapt to the complex working environment of jacket platforms, leading to inaccurate damage identification results. Summary of the Invention

[0005] To address the problems existing in the above-mentioned fields, this invention proposes a method and system for identifying structural damage of a marine jacket platform. Since different types of data often correspond to different states of the jacket platform structure, by establishing a reference database and classifying it, the statistical values ​​of its damage sensitivity features and damage thresholds can be determined for each type of data, making the judgment of structural damage more accurate.

[0006] To address the aforementioned technical problems, this invention discloses a method for identifying structural damage to a marine jacket platform, comprising the following steps: Acquire historical vibration monitoring signals of the on-site jacket platform structure; The signal components in historical vibration monitoring signals are extracted, classified and labeled, and a reference database is established. Reference data of different categories in the reference database are obtained, and the statistical values ​​and damage thresholds of the damage sensitivity characteristics corresponding to the different categories of reference data are determined respectively. The vibration monitoring signal of the jacket platform structure acquired in real time is used as test data. When the statistical value of the damage sensitivity feature corresponding to the test data is greater than the damage threshold corresponding to the reference data of the current category, it is determined that the jacket platform structure has been damaged, and the field inspection and maintenance process is initiated. When the field inspection shows that the jacket platform structure has not actually been damaged, the test data is used as a new working condition sample, included in the reference database, and the category label is updated. When the statistical value of the damage sensitivity feature corresponding to the test data does not exceed the damage threshold corresponding to the reference data of the current category, the test data is regarded as normal data, the normal data is classified, and it is included in the reference data of the corresponding category.

[0007] Preferably, acquiring the historical vibration monitoring signals of the on-site jacket platform structure specifically includes: Obtain the actual dimensions of the jacket platform structure to be tested, and construct a finite element model of the jacket platform structure using ANSYS software; Numerical simulation of the jacket platform structure was performed based on the finite element model of the jacket platform structure, and the numerical simulation results were obtained. Based on the numerical simulation results, the effective independence method, MAC criterion method and modal kinetic energy method are used to determine the sensor layout scheme; The multi-objective Lichtenberg algorithm is used to optimize the given sensor layout scheme and obtain the optimal sensor layout scheme, including the optimal number of sensors and their placement positions. Based on the optimal sensor layout scheme, a data acquisition system is built; Historical vibration monitoring signals of the on-site jacket platform structure were collected using a data acquisition system.

[0008] Preferably, the step of extracting signal components from historical vibration monitoring signals, classifying and labeling the signal components, and establishing a reference database specifically includes: After the acquired historical vibration monitoring signals are divided into datasets according to the preset acquisition time interval, the signals in the datasets are sequentially subjected to baseline adjustment, detrending processing, and standard deviation standardization. The processed signal is low-pass filtered to remove high-frequency noise and electromagnetic interference. The number of decompositions and filtering parameters of the reduced-order variational mode decomposition method are determined by the particle swarm optimization algorithm. The low-pass filtered signal is then decomposed to extract signal components. By determining the center frequency value and the number of each signal component, the signal components are classified and labeled using the Mahalanobis distance method, and a reference database is established.

[0009] Preferably, the step of acquiring reference data of different categories from the reference database and determining the statistical values ​​and damage thresholds of the damage sensitivity features corresponding to the different categories of reference data specifically includes: Based on a covariance-driven stochastic subspace method, the covariance Hankel matrix of a set of reference data for each class is determined. ; By concatenating the reference data sets for each category, a long dataset is formed, yielding the covariance Hankel matrix for the overall data of that category. ; The dimensions of the Hankel matrix and the system order are determined by the number of each signal component and the number of sensors. Establish damage sensitivity characteristics for: ; Divide the reference database into K Groups, each group of data has a length of [length missing]. K b Estimate the covariance matrix of the reference data for this category. for: ; In the formula, Indicates the first k The Hankel matrix of the reference data set; Based on damage sensitivity characteristics Covariance Matrix Establish statistical values ​​for damage sensitivity characteristics. for: ; Where T is the transpose symbol; Based on the central limit theorem and the law of large numbers, the statistical values ​​of the damage sensitivity characteristics are determined to follow a Gaussian normal distribution. Based on the statistical values ​​of the damage sensitivity characteristics of the catheter platform structure when it is undamaged, its probability distribution is fitted, and the damage threshold is determined using the 3δ principle.

[0010] Preferably, the vibration monitoring signal of the real-time acquired jacket platform structure is used as test data. When the statistical value of the damage sensitivity feature corresponding to the test data is greater than the damage threshold corresponding to the reference data of the current category, it is determined that the jacket platform structure has been damaged, and the on-site inspection and maintenance process is initiated. When the on-site inspection reveals that the jacket platform structure has not actually been damaged, the test data is used as a new working condition sample, included in the reference database, and the category label is updated. Specifically, this includes: By using the same data acquisition system that acquires historical vibration monitoring signals, the vibration monitoring signals of the jacket platform structure are acquired in real time and used as test data. The test data is classified using Mahalanobis distance to obtain different categories of test data; Using any selected category of reference data as a benchmark, obtain the statistical value of the damage sensitivity characteristics corresponding to the test data of the current category; The larger the statistical value, the higher the degree of damage to the jacket platform structure; When the statistical value of the damage sensitivity feature corresponding to the test data is greater than the damage threshold corresponding to the reference data of the current category, it is determined that the jacket platform structure has been damaged. Once damage to the jacket platform structure is determined, the on-site inspection and maintenance process is initiated. When the on-site inspection reveals that the jacket platform structure is not actually damaged, the test data is used as a new working condition sample, added to the reference database, and the category labels of the reference database are updated to obtain reference data of different categories in the updated reference database. Based on the updated reference data of different categories in the updated reference database, update the statistical values ​​and damage thresholds of the damage sensitivity features corresponding to the reference data; This also includes taking temporary control measures for potential risk areas corresponding to new operating conditions until the risks are eliminated.

[0011] Preferably, when the statistical value of the damage sensitivity feature corresponding to the test data does not exceed the damage threshold corresponding to the reference data of the current category, the test data is treated as normal data, the normal data is classified, and it is included in the reference data of the corresponding category, specifically including: When the statistical value of the damage sensitivity feature corresponding to the test data does not exceed the damage threshold corresponding to the reference data of the current category, the test data is regarded as normal data. The normal data is classified by Mahalanobis distance. By determining the Mahalanobis distance between each data in the normal data and each reference data in each category in the reference database, each data in the normal data is assigned to the category of the reference data with the smallest Mahalanobis distance. The statistical value of the damage sensitivity feature and the damage threshold corresponding to the reference data are updated.

[0012] Preferably, it also includes a marine jacket platform structural damage identification system, comprising: The data acquisition module is used to acquire historical vibration monitoring signals of the on-site jacket platform structure; The reference data damage threshold determination module is used to extract signal components from historical vibration monitoring signals, classify and label the signal components, and establish a reference database; obtain reference data of different categories in the reference database, and determine the statistical values ​​and damage thresholds of the damage sensitivity features corresponding to different categories of reference data respectively; The damage detection module uses the vibration monitoring signals of the jacket platform structure acquired in real time as test data. When the statistical value of the damage sensitivity feature corresponding to the test data is greater than the damage threshold corresponding to the reference data of the current category, it determines that the jacket platform structure has been damaged and initiates the on-site inspection and maintenance process. When the on-site inspection reveals that the jacket platform structure has not actually been damaged, the test data is used as a new working condition sample, included in the reference database, and the category label is updated. When the statistical value of the damage sensitivity feature corresponding to the test data does not exceed the damage threshold corresponding to the reference data of the current category, the test data is treated as normal data, classified, and included in the reference data of the corresponding category.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The proposed method for identifying structural damage in offshore jacket platforms addresses this issue by establishing a reference database and classifying the data. This allows for the determination of statistical values ​​for damage-sensitive features and damage thresholds for each data category, leading to more accurate damage assessment. By comparing the statistical values ​​of damage-sensitive features corresponding to real-time acquired test data with the damage thresholds corresponding to the current category of reference data, the method quickly determines whether the test data has caused damage to the jacket platform structure. This enables the timely detection of early structural damage, saving valuable time for subsequent maintenance and reinforcement work and preventing further damage and more serious consequences. Simultaneously, the real-time database update mechanism not only increases the amount of reference data, improving the reliability of damage detection results, but also allows for the timely addition of reference data under new operating conditions, expanding the applicability of the historical database. Attached Figure Description

[0014] Figure 1 This is a flowchart of the marine jacket platform structural damage identification method proposed in this invention; Figure 2 Candidate sensor locations and final optimized positions on the marine jacket platform structure provided in this embodiment of the invention; Figure 3 This invention provides a set of multi-channel acquired vibration acceleration signals and their corresponding power spectral density maps. Figure 4The spectrum diagram of the signal components and corresponding center frequencies extracted after processing by the RVMD method is provided in the embodiment of the present invention; Figure 5 This is the damage identification result of a set of monitoring data of a marine jacket platform structure under different excitation environments and in a damaged state, provided in an embodiment of the present invention. Detailed Implementation

[0015] The following will refer to the appendices in the embodiments of the present invention. Figures 1-5 The technical solutions in the embodiments of the present invention will be clearly and completely described. It should be understood that the terminology used in the present invention is only for describing particular implementation methods and is not intended to limit the present invention.

[0016] Example like Figure 1 As shown, this invention proposes a method for identifying structural damage to a marine jacket platform, comprising the following steps: S1: Acquire historical vibration monitoring signals of the on-site jacket platform structure; S2: Extract signal components from historical vibration monitoring signals, classify and label the signal components, and establish a reference database; obtain reference data of different categories in the reference database, and determine the statistical values ​​and damage thresholds of the damage sensitivity characteristics corresponding to different categories of reference data respectively; S3: The vibration monitoring signal of the jacket platform structure acquired in real time is used as test data. When the statistical value of the damage sensitivity feature corresponding to the test data is greater than the damage threshold corresponding to the reference data of the current category, it is determined that the jacket platform structure has been damaged, and the field inspection and maintenance process is initiated. When the field inspection shows that the jacket platform structure has not actually been damaged, the test data is used as a new working condition sample, included in the reference database, and the category label is updated. When the statistical value of the damage sensitivity feature corresponding to the test data does not exceed the damage threshold corresponding to the reference data of the current category, the test data is regarded as normal data, the normal data is classified, and it is included in the reference data of the corresponding category.

[0017] This method significantly improves the adaptability of the monitoring system of the marine jacket platform in complex environments by optimizing the sensor layout scheme, upgrading the acquisition system hardware, and combining dynamic maintenance of the reference database with algorithm robustness design, thereby improving the reliability of damage identification.

[0018] Specifically, in step S1, the vibration monitoring signal of the on-site jacket platform structure is acquired, including: Obtain the actual dimensions of the jacket platform structure to be tested, and construct a finite element model of the jacket platform structure using ANSYS software.

[0019] Modal analysis was performed based on the finite element model of the jacket platform structure, and numerical simulation was conducted on the jacket platform structure to obtain the numerical simulation results.

[0020] Based on the numerical simulation results, the effective independence method, MAC criterion method and modal kinetic energy method were used to preliminarily determine the layout scheme of the sensors and determine the initial placement points of the acceleration sensors on the upper platform of the jacket.

[0021] The Multi-objective Lichtenberg Algorithm (MOLA) is employed, with the objective functions of maximizing the eigenvector product of the initial sensor locations and minimizing the number of sensors. This optimizes the initially determined sensor layout to obtain the optimal sensor layout, including the optimal number and location of sensors. Figure 2 As shown, there are four optimal sensors, which are arranged on the top of the upper platform of the jacket.

[0022] Based on the optimal sensor layout scheme, low-frequency acceleration sensors are arranged sequentially and connected to a multi-channel data acquisition instrument via cables. The data is then transmitted to a computer via network cables to build a data acquisition system.

[0023] The historical vibration monitoring signals of the on-site jacket platform structure were collected through the data acquisition system.

[0024] By constructing a finite element model of the duct platform structure and optimizing the sensor layout, the adaptability of the signal duct platform monitoring system in complex environments can be significantly improved, thereby enhancing the reliability of damage identification.

[0025] In step S2, the historical vibration monitoring signals of the acquired on-site jacket platform structure are divided into datasets according to a preset acquisition time interval (10 minutes), and the signals in the datasets are sequentially subjected to baseline adjustment, detrending processing, and standard deviation standardization, such as... Figure 3 The image shows the processed signal, including the time-domain waveform (left) and the spectrum (right).

[0026] In the time-domain waveform diagram, the horizontal axis represents time. t The unit is seconds (s). It describes how the signal changes over time, showing the signal value at different moments. The vertical axis "Leg1#-X / g", "Leg1#-Y / g", etc., represent the acceleration signal in the corresponding direction (X direction or Y direction), and the unit is gravitational acceleration g. It reflects the magnitude of the vibration acceleration of the structure in the corresponding direction at a specific moment.

[0027] In a spectrum graph, the horizontal axis represents frequency. fThe unit is Hertz (Hz), which shows the different frequency components contained in the signal. The vertical axis represents the power spectral density (PSD), and the unit is g. 2 The Power Distribution Scale (PSS) describes the distribution of signal power across different frequencies, i.e., the contribution of each frequency component to the total signal power. A higher PSD value indicates a higher proportion of energy allocated to that frequency component in the signal.

[0028] The processed signal is low-pass filtered to remove high-frequency noise and electromagnetic interference.

[0029] The number of decompositions and filtering parameters for Reduced-order Vvariational Mode Decomposition (RVMD) were determined using particle swarm optimization. The low-pass filtered signal was then decomposed to extract effective signal components from historical vibration monitoring signals from multiple sensors. Figure 4 As shown, the number of valid signal components is determined, and the center frequency value of the valid signal components is obtained by recording.

[0030] The number of decompositions and filtering parameters for the RVMD method are determined using a particle swarm optimization algorithm. The search process for these two parameters consists of two steps: First, with fixed initial values ​​for the filtering parameters, the optimal number of decompositions is searched. RVMD decomposition is performed on the signal components under different decomposition settings, and the maximum value of the correlation coefficient between the signal components is calculated and set to be less than a threshold. Calculate the energy percentage of each signal component, and ensure that the minimum energy percentage is greater than a threshold. The minimum number of decompositions that satisfy the conditions is taken as the optimal value; Secondly, with a fixed number of decompositions, RVMD decomposition is performed on the signal components under different filter parameter settings. The sum of the energy entropy of each signal component is calculated, and the filter parameter with the minimum sum of signal energy entropy is taken as the optimal value. The energy proportion of each signal component at this point is calculated, and the energy proportion is set to be greater than a threshold. The signal components are valid, and the center frequency value of the valid signal components is recorded.

[0031] Using Mahalanobis distance, the center frequency value and the number of each effective signal component are used as sample data to construct a two-dimensional feature vector of the sample data. By determining the mean and covariance matrix of the feature vector of each category, the center frequency values ​​and the number of effective signal components are classified and labeled to construct a reference database.

[0032] When new data samples are added to the reference database, each new data sample is assigned to the category of the reference data whose Mahalanobis distance is minimized by determining the Mahalanobis distance between each new data sample and each reference data in each category.

[0033] Based on the allocation results, add category labels to the new data samples and update the reference database.

[0034] like Figure 4 The image shows the two signal components (IMF1 and IMF2) extracted after RVMD decomposition and their corresponding spectrograms. Analysis... Figure 4 As shown in the left figure, observing the two signal components (IMF1 and IMF2) in the time domain (the horizontal axis represents time) reveals... t The waveform changes (in seconds). The amplitudes (vertical axis, in grams) of IMF1 and IMF2 fluctuating over time reflect the dynamic characteristics of their respective signal components.

[0035] Figure 4 The horizontal axis of the right-hand graph (spectrum) represents frequency. f The unit is Hertz (Hz), and the vertical axis is the power spectral density (PSD), with the unit being g. 2 / Hz. The frequency corresponding to the peak in each spectrum is the center frequency of that signal component. As can be seen from the figure, the center frequencies of IMF1 and IMF2 are both around 5Hz, but there may be slight differences. The center frequency reflects the main vibration frequency of the signal component, and different center frequencies correspond to different vibration modes of the structure.

[0036] Depend on Figure 4 It can be seen that the number of center frequencies of signals in this category n ref =2.

[0037] In step S3, the Hankel matrix of the excitation covariance is standardized for different categories of reference data to determine the statistical values ​​and damage thresholds of the damage sensitivity features corresponding to different categories of reference data. Specifically, this includes: Based on a covariance-driven stochastic subspace method, the covariance Hankel matrix of a set of reference data for each class is determined. ; By concatenating the reference data sets for each category, a long dataset is formed, yielding the covariance Hankel matrix for the overall data of that category. ; The dimensions of the Hankel matrix and the system order are determined by the number of each valid signal component and the number of sensors. Dimensions of the Hankel matrix p For (2) nref +1) × number of sensors, system order is set to 2. n ref This invention p The value is 30, and the system order is set to 4.

[0038] Establish damage sensitivity characteristics for: (1) The reference database is divided into K groups, each with a data length of [length missing]. K b Estimate the covariance matrix of the reference data for this category. for: (2) In the formula, Indicates the first k The Hankel matrix of the reference data set; Based on equations (1) and (2), statistical values ​​of damage sensitivity characteristics are established. for: (3) Where T is the transpose symbol; Based on the central limit theorem and the law of large numbers, the statistical values ​​of the damage sensitivity characteristics are determined to satisfy a Gaussian distribution. Based on the statistical values ​​of the damage sensitivity characteristics of the catheter platform structure when it is undamaged, its probability distribution is fitted, and the damage threshold is determined using the 3δ principle, including: A warning is issued when the significance level of the statistical value exceeds 95%; a damage report is sent when the significance level of the statistical value reaches 99%.

[0039] This invention sets the warning threshold to 10.9 and the damage threshold to 11.8 for different categories of reference data in the reference database. Figure 5 As shown.

[0040] In step S3, the vibration monitoring signal of the jacket platform structure is acquired in real time through the same data acquisition system that acquires historical vibration monitoring signals, and is used as test data. The test data is classified using Mahalanobis distance to obtain different categories of test data; Test data from any category is selected from different test data sets. Using this selected category as a benchmark, it is matched against the classification results of the reference data to obtain the difference between the center frequency values ​​of the current category's test data and the reference data for that category. When this difference meets a preset error requirement, the match is successful, and a Hankel matrix of the test data is constructed. The Hankel matrix of the incentive covariance is standardized to obtain the Hankel matrix of the test data for each class. .

[0041] The obtained Hankel matrix and The singular value decomposition is performed in parallel, and the decomposition process is represented as follows: (4) In the formula, E 1 represents the first two singular values ​​of the left singular value matrix. n ref List, E 2 represents the remaining columns of the left singular value matrix. F 1 is the first 2 n ref A singular value, F 2 represents the residual singular value. The first two right singular value matrices n ref The matrix in the row related to the reference data, The first two right singular value matrices n ref The matrix in the row related to the test data, This refers to the matrix in the remaining rows of the right singular value matrix that is related to the reference data. Let be the matrix in the remaining rows of the right singular value matrix that relates to the test data. Incentive environment , Incentive environment To ensure that the two data points are in the same stimulus environment, use... Replace In After the incentive environment is standardized The obtained Hankel matrix and Establish damage sensitivity characteristics and its statistical values And compare it with the damage threshold, when the statistical value When the damage value exceeds the damage threshold, the catheter platform structure is considered to be damaged, and the statistical value... The higher the value, the greater the degree of damage. For example... Figure 5 The image shows the damage identification results for two sets of damage condition data (excitation environment 1 and excitation environment 2). Excitation environment 1 involves disassembling one horizontal brace of the jacket platform structure, while excitation environment 2 involves disassembling two additional diagonal braces. Excitation environment 1 refers to the jacket platform structure being excited in a relatively stable environment, while excitation environment 2 refers to the jacket platform structure being excited in a sinusoidal environment with a load magnitude of 1.5 kN and a load frequency of 0.2 Hz.

[0042] Using any selected category of test data as a benchmark, obtain the statistical value of the damage sensitivity feature corresponding to the test data of the current category; The larger the statistical value, the higher the degree of damage to the jacket platform structure; When the statistical value of the damage sensitivity feature corresponding to the test data is greater than the damage threshold corresponding to the reference data of the current category, it is determined that the jacket platform structure has been damaged. Once it is determined that the jacket platform structure has been damaged, the on-site inspection and maintenance process is initiated. When the on-site inspection reveals that the jacket platform structure has not actually been damaged, the test data is used as a new working condition data sample, added to the reference database, and the category labels of the reference database are updated to obtain reference data of different categories in the updated reference database. Based on the updated reference data of different categories in the updated reference database, update the statistical values ​​and damage thresholds of the damage sensitivity features corresponding to the reference data; This also includes taking temporary control measures for potential risk areas corresponding to new operating conditions until the risks are eliminated.

[0043] When the statistical value of the damage sensitivity feature corresponding to the test data does not exceed the damage threshold corresponding to the reference data of the current category, the test data is regarded as normal data. The normal data is classified by Mahalanobis distance. By determining the Mahalanobis distance between each data in the normal data and each reference data in each category in the reference database, each data in the normal data is assigned to the category of the reference data with the smallest Mahalanobis distance. The statistical value of the damage sensitivity feature and the damage threshold corresponding to the reference data are updated.

[0044] like Figure 5 As shown, this is the damage identification result of two sets of damage condition data, namely, excitation environment 1 and excitation environment 2.

[0045] This invention also proposes a damage identification system for marine jacket platform structures, comprising: The data acquisition module is used to obtain the actual dimensions of the jacket platform structure to be tested, construct a finite element model of the jacket platform structure, determine the sensor layout scheme, build a data acquisition system, and collect historical vibration monitoring signals of the jacket platform structure on site. The reference data damage threshold determination module is used to extract effective signal components from historical vibration monitoring signals, classify and label the signal components, and establish a reference database; it also acquires reference data of different categories from the reference database and determines the statistical values ​​and damage thresholds of the damage sensitivity features corresponding to different categories of reference data. The damage detection module uses the vibration monitoring signals of the jacket platform structure acquired in real time as test data. When the statistical value of the damage sensitivity feature corresponding to the test data is greater than the damage threshold corresponding to the reference data of the current category, it determines that the jacket platform structure has been damaged and initiates the on-site inspection and maintenance process. When the on-site inspection reveals that the jacket platform structure has not actually been damaged, the test data is used as a new working condition sample, included in the reference database, and the category label is updated. When the statistical value of the damage sensitivity feature corresponding to the test data does not exceed the damage threshold corresponding to the reference data of the current category, the test data is treated as normal data, classified, and included in the reference data of the corresponding category.

[0046] The system proposed in this invention transmits the output of the data acquisition module to the reference data damage threshold determination module, and then transmits the reference information output by the latter to the damage detection module, realizing continuous detection and evaluation of the structural status of the jacket platform. Based on the detection and evaluation results and the actual inspection situation, the system dynamically updates the reference database, thus forming a complete, self-learning damage identification system for marine jacket platform structures.

[0047] Compared with traditional methods for identifying structural damage on offshore jacket platforms, this invention considers the impact of changes in the excitation environment on the identification results. Furthermore, through optimized sensor placement, application of statistical analysis methods, and dynamic updates to the reference database, it systematically improves the accuracy and adaptability of damage identification under different operating conditions, providing a new and effective solution for reliable monitoring of the structural health of offshore platforms.

[0048] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

[0049] Furthermore, unless otherwise stated, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. All references to this specification are incorporated by way of citation to disclose and describe methods relating to those references. In the event of any conflict with any incorporated reference, the content of this specification shall prevail.

Claims

1. A method for identifying structural damage to a marine jacket platform, characterized in that, Includes the following steps: Acquire historical vibration monitoring signals of the on-site jacket platform structure; Extract signal components from historical vibration monitoring signals, classify and label the signal components, and establish a reference database; Obtain reference data of different categories from the reference database, and determine the statistical values ​​and damage thresholds of the damage sensitivity features corresponding to the different categories of reference data; The vibration monitoring signal of the jacket platform structure acquired in real time is used as test data. When the statistical value of the damage sensitivity feature corresponding to the test data is greater than the damage threshold corresponding to the reference data of the current category, it is determined that the jacket platform structure has been damaged, and the field inspection and maintenance process is initiated. When the field inspection shows that the jacket platform structure has not actually been damaged, the test data is used as a new working condition sample, included in the reference database, and the category label is updated. When the statistical value of the damage sensitivity feature corresponding to the test data does not exceed the damage threshold corresponding to the reference data of the current category, the test data is regarded as normal data, the normal data is classified, and it is included in the reference data of the corresponding category.

2. The method for identifying structural damage to a marine jacket platform according to claim 1, characterized in that, The acquisition of historical vibration monitoring signals of the on-site jacket platform structure specifically includes: Obtain the actual dimensions of the jacket platform structure to be tested, and construct a finite element model of the jacket platform structure using ANSYS software; Numerical simulation of the jacket platform structure was performed based on the finite element model of the jacket platform structure, and the numerical simulation results were obtained. Based on the numerical simulation results, the effective independence method, MAC criterion method and modal kinetic energy method are used to determine the sensor layout scheme; The multi-objective Lichtenberg algorithm is used to optimize the given sensor layout scheme and obtain the optimal sensor layout scheme, including the optimal number of sensors and their placement positions. Based on the optimal sensor layout scheme, a data acquisition system is built; Historical vibration monitoring signals of the on-site jacket platform structure were collected using a data acquisition system.

3. The method for identifying structural damage to a marine jacket platform according to claim 2, characterized in that, The process of extracting signal components from historical vibration monitoring signals, classifying and labeling these signal components, and establishing a reference database specifically includes: After the acquired historical vibration monitoring signals are divided into datasets according to the preset acquisition time interval, the signals in the datasets are sequentially subjected to baseline adjustment, detrending processing, and standard deviation standardization. The processed signal is low-pass filtered to remove high-frequency noise and electromagnetic interference. The number of decompositions and filtering parameters of the reduced-order variational mode decomposition method are determined by the particle swarm optimization algorithm. The low-pass filtered signal is then decomposed to extract signal components. By determining the center frequency value and the number of each signal component, the signal components are classified and labeled using the Mahalanobis distance method, and a reference database is established.

4. The method for identifying structural damage to a marine jacket platform according to claim 3, characterized in that, The step of obtaining reference data of different categories from the reference database and determining the statistical values ​​and damage thresholds of the damage sensitivity features corresponding to different categories of reference data specifically includes: Based on a covariance-driven stochastic subspace method, the covariance Hankel matrix of a set of reference data for each class is determined. ; By concatenating the reference data sets for each category, a long dataset is formed, yielding the covariance Hankel matrix for the overall data of that category. ; The dimensions of the Hankel matrix and the system order are determined by the number of each signal component and the number of sensors. Establish damage sensitivity characteristics for: ； Divide the reference database into K Groups, each group of data has a length of [length missing]. K b Estimate the covariance matrix of the reference data for this category. for: ； In the formula, Indicates the first k The Hankel matrix of the reference data set; Based on damage sensitivity characteristics Covariance Matrix Establish statistical values ​​for damage sensitivity characteristics. for: ； Where T is the transpose symbol; Based on the central limit theorem and the law of large numbers, the statistical values ​​of the damage sensitivity characteristics are determined to satisfy a Gaussian distribution. Based on the statistical values ​​of the damage sensitivity characteristics of the catheter platform structure when it is undamaged, its probability distribution is fitted, and the damage threshold is determined using the 3δ principle.

5. The method for identifying structural damage to a marine jacket platform according to claim 4, characterized in that, The vibration monitoring signal of the jacket platform structure acquired in real time is used as test data. When the statistical value of the damage sensitivity feature corresponding to the test data is greater than the damage threshold corresponding to the reference data of the current category, it is determined that the jacket platform structure has been damaged, and the on-site inspection and maintenance process is initiated. When on-site testing reveals that the jacket platform structure has not actually suffered damage, the test data is used as a new working condition sample, included in the reference database, and the category label is updated, specifically including: By using the same data acquisition system that acquires historical vibration monitoring signals, the vibration monitoring signals of the jacket platform structure are acquired in real time and used as test data. The test data is classified using Mahalanobis distance to obtain different categories of test data; Using any selected category of reference data as a benchmark, obtain the statistical value of the damage sensitivity characteristics corresponding to the test data of the current category; The larger the statistical value, the higher the degree of damage to the jacket platform structure; When the statistical value of the damage sensitivity feature corresponding to the test data is greater than the damage threshold corresponding to the reference data of the current category, it is determined that the jacket platform structure has been damaged. Once damage to the jacket platform structure is determined, the on-site inspection and maintenance process is initiated. When the on-site inspection reveals that the jacket platform structure is not actually damaged, the test data is used as a new working condition sample, added to the reference database, and the category labels of the reference database are updated to obtain reference data of different categories in the updated reference database. Based on the updated reference data of different categories in the updated reference database, update the statistical values ​​and damage thresholds of the damage sensitivity features corresponding to the reference data; This also includes taking temporary control measures for potential risk areas corresponding to new operating conditions until the risks are eliminated.

6. The method for identifying structural damage to a marine jacket platform according to claim 5, characterized in that, When the statistical value of the damage sensitivity feature corresponding to the test data does not exceed the damage threshold corresponding to the reference data of the current category, the test data is regarded as normal data, the normal data is classified, and it is included in the reference data of the corresponding category, specifically including: When the statistical value of the damage sensitivity feature corresponding to the test data does not exceed the damage threshold corresponding to the reference data of the current category, the test data is regarded as normal data. The normal data is classified by Mahalanobis distance. By determining the Mahalanobis distance between each data in the normal data and each reference data in each category in the reference database, each data in the normal data is assigned to the category of the reference data with the smallest Mahalanobis distance. The statistical value of the damage sensitivity feature and the damage threshold corresponding to the reference data are updated.

7. A damage identification system for marine jacket platform structures, characterized in that, include: The data acquisition module is used to acquire historical vibration monitoring signals of the on-site jacket platform structure; The reference data damage threshold determination module is used to extract signal components from historical vibration monitoring signals, classify and label the signal components, and establish a reference database. Obtain reference data of different categories from the reference database, and determine the statistical values ​​and damage thresholds of the damage sensitivity features corresponding to the different categories of reference data; The damage detection module uses the vibration monitoring signals of the jacket platform structure acquired in real time as test data. When the statistical value of the damage sensitivity feature corresponding to the test data is greater than the damage threshold corresponding to the reference data of the current category, it determines that the jacket platform structure has been damaged and initiates the on-site inspection and maintenance process. When the on-site inspection reveals that the jacket platform structure has not actually been damaged, the test data is used as a new working condition sample, included in the reference database, and the category label is updated. When the statistical value of the damage sensitivity feature corresponding to the test data does not exceed the damage threshold corresponding to the reference data of the current category, the test data is treated as normal data, classified, and included in the reference data of the corresponding category.

Images