An offshore wind power foundation scouring intelligent monitoring method and device

Abstract

This invention proposes an intelligent monitoring method and device for offshore wind power foundation scour. The invention includes: multiple monitoring units simultaneously collecting data related to the seabed, hydrodynamics, structure, and protective structures; edge units preprocessing the data and constructing a comprehensive scour feature vector; using a machine learning model to identify and predict scour stages and generate risk assessment indicators; classifying risk levels based on the indicators, triggering alarms, displaying status trends, and outputting operation and maintenance suggestions. This invention enables intelligent monitoring and early warning of scour status, ensuring the safe operation of wind power foundations.

Description

Technical Field

[0001] This invention relates to the field of intelligent monitoring technology for offshore wind power foundation scour, and in particular to an intelligent monitoring method and device for offshore wind power foundation scour. Background Technology

[0002] Offshore wind turbine foundations, as key supporting structures of offshore wind farms, are subjected to complex marine environmental loads from the combined effects of tides, waves, and currents over long periods. The surrounding seabed is highly susceptible to localized scour, leading to decreased foundation bearing capacity, altered structural vibration characteristics, and accumulated fatigue damage, seriously threatening the safe operation of wind turbines. Related technologies utilize multibeam scanning, underwater robot inspections, and regular diver inspections to construct a scour monitoring system centered on topographic detection. Specifically, this system covers the entire process from seabed topographic scanning to foundation visual inspection, including key aspects such as underwater acoustic detection, visual imaging, and manual inspection.

[0003] However, existing scour monitoring methods rely on periodic offline detection, failing to achieve real-time continuous monitoring. This may result in the early stages of scour going undetected or monitoring operations being difficult to implement in harsh sea conditions, thus affecting the acquisition of the dynamic evolution of scour development and the collaborative assessment of the condition of scour-resistant structures. Furthermore, existing technologies have limited monitoring dimensions and lack the fusion analysis of multi-source data such as hydrodynamic parameters, foundation vibration response, and sediment concentration, making it difficult to support intelligent prediction and proactive early warning of scour trends. Summary of the Invention

[0004] The present invention aims to at least partially solve one of the technical problems in the related art.

[0005] Therefore, the first objective of this invention is to propose an intelligent monitoring method for offshore wind power foundation scour.

[0006] Another objective of this invention is to provide an intelligent monitoring device for offshore wind power foundation scour.

[0007] The third objective of this invention is to provide a computer device.

[0008] A fourth objective of this invention is to provide a non-transitory computer-readable storage medium.

[0009] To achieve the above objectives, a first aspect of the present invention provides a method for intelligent monitoring of offshore wind power foundation scour, comprising:

[0010] S1, through underwater monitoring units deployed in the seabed area around the offshore wind power foundation, distributed optical fiber monitoring units deployed along the outer wall of the foundation and the anti-scour structure, and underwater acoustic scanning units, simultaneously collects seabed scour status data, hydrodynamic characteristic data, structural response data, and protective structure status data. S2, through the data acquisition and edge processing unit set in the wind turbine tower platform, performs time-domain alignment, filtering and noise reduction and outlier removal on the acquired multi-source monitoring data, and constructs a comprehensive scour feature vector from the preprocessed data; S3, based on the comprehensive scour feature vector, the intelligent diagnostic module in the edge processing unit uses a machine learning model to identify and predict the scour development stage, and generates a comprehensive risk assessment index by combining threshold judgment. S4. Based on the comprehensive risk assessment indicators, the risk level is automatically classified and an alarm is triggered by the intelligent early warning unit. At the same time, the scouring status is displayed in real time, the development trend is analyzed, and operation and maintenance decision suggestions are generated through the remote operation and maintenance platform.

[0011] In one embodiment of the present invention, S1 includes: The system uses underwater pressure sensors, flow velocity and direction sensors, seabed elevation monitoring sensors, sediment concentration monitoring sensors, vibration monitoring sensors, and underwater attitude sensors to acquire real-time data on seabed scour depth, flow velocity and direction, suspended sediment concentration, and foundation vibration response. Distributed fiber optic sensors deployed along the outer wall of the wind turbine foundation and inside the anti-scour structure are used to monitor structural strain, local strain, protective layer settlement, and local cavitation data in real time. Real-time acquisition of seabed topographic scanning data, scour pit 3D reconstruction data, and protective structure morphology identification data is achieved using miniature multibeam sonar, ring scan sonar, and underwater imaging sonar.

[0012] In one embodiment of the present invention, it further includes: The changes in the depth of scour around the pile are monitored in real time by seabed elevation monitoring sensors, the changes in suspended sediment near the seabed are monitored in real time by sediment concentration monitoring sensors, and the changes in the vibration response of the foundation caused by scour are monitored in real time by vibration monitoring sensors.

[0013] In one embodiment of the present invention, S2 includes: A unified timestamp synchronization mechanism is used to align the original data in the time domain, through an interpolation function. To achieve unified timeline mapping for different types of monitoring data and establish multi-source synchronized data sequences; A Butterworth low-pass filter was used for vibration monitoring data.

[0014] Suppressing high-frequency noise, among which The cutoff frequency is n, and the filter order is n; the Z-score anomaly detection method is used for abnormal sampled values. ,when Values ​​that are identified as outliers are automatically removed.

[0015] In one embodiment of the present invention, it further includes: For large-scale point cloud data generated by underwater sonar scanning, the Statistical Outlier Removal algorithm is used to remove outliers by calculating the average distance of the point cloud neighborhood. ,when The point is identified as a noise point and deleted.

[0016] In one embodiment of the present invention, S3 includes: Construct a time series prediction model based on long short-term memory networks to assess the depth of scour. Flow rate Sediment concentration and vibration response as input features Output the predicted scour depth at future moments. The Long Short-Term Memory Network (LSTM) uses forget gates, input gates, and output gates to achieve the memory of historical erosion features and the prediction of future trends. Support Vector Machine Classification Model The system intelligently classifies the scouring state, enabling automatic identification of the initial scouring stage, rapid development stage, stable stage, and dangerous scouring stage.

[0017] In one embodiment of the present invention, S4 includes: The monitoring data is compared with the set threshold by the flushing threshold judgment module, and the risk level is automatically classified according to the comprehensive risk assessment index by the risk level assessment module. When the monitoring data exceeds the set threshold, the remote alarm module automatically triggers the audible and visual alarm, the operation and maintenance platform alarm, and the remote data push.

[0018] To achieve the above objectives, a second aspect of the present invention provides an intelligent monitoring device for offshore wind power foundation scour, comprising: The multi-source data acquisition module is used to simultaneously acquire seabed scour status data, hydrodynamic characteristic data, structural response data, and protective structure status data through underwater monitoring units deployed in the seabed area around the offshore wind power foundation, distributed optical fiber monitoring units deployed along the outer wall of the foundation and the anti-scour structure, and underwater acoustic scanning units. The data preprocessing and feature construction module is used to perform time-domain alignment, filtering and noise reduction, and outlier removal on the collected multi-source monitoring data through the data acquisition and edge processing unit set in the wind turbine tower platform, and construct a comprehensive scour feature vector from the preprocessed data. The scour diagnosis and risk assessment module is used to identify and predict the scour development stage based on the comprehensive scour feature vector, through the intelligent diagnosis module in the edge processing unit, using a machine learning model, and generating a comprehensive risk assessment index by combining threshold judgment. The graded early warning and operation and maintenance analysis module is used to automatically classify risk levels and trigger alarms through the intelligent early warning unit based on the comprehensive risk assessment indicators. At the same time, it displays the flushing status in real time, analyzes the development trend, and generates operation and maintenance decision suggestions through the remote operation and maintenance platform.

[0019] The present invention discloses an intelligent monitoring method and device for offshore wind power foundation scour, which can realize real-time monitoring and intelligent early warning of offshore wind power foundation scour status, improve the real-time performance and intelligence of monitoring, and reduce operation and maintenance costs.

[0020] To achieve the above objectives, a third aspect of this application provides a computer device, including a processor and a memory; wherein the processor runs a program corresponding to the executable program code by reading executable program code stored in the memory, for implementing the method described in the first aspect embodiment.

[0021] To achieve the above objectives, a fourth aspect of this application provides a non-transitory computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method described in the first aspect.

[0022] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0023] Figure 1 This is a flowchart of an intelligent monitoring method for offshore wind power foundation scour according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the underwater detection unit structure according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the deployment of a distributed optical fiber monitoring unit according to an embodiment of the present invention; Figure 4 This is a schematic diagram of an underwater acoustic scanning unit according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the data acquisition and edge processing unit structure according to an embodiment of the present invention; Figure 6 This is a schematic diagram of an intelligent early warning unit according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the remote operation and maintenance platform interface according to an embodiment of the present invention; Figure 8 This is a schematic diagram of an energy harvesting and power supply unit according to an embodiment of the present invention; Figure 9 This is a schematic diagram of the health monitoring of the anti-erosion structure according to an embodiment of the present invention; Figure 10 This is a schematic diagram of the applicable basic types according to embodiments of the present invention; Figure 11 This is a structural diagram of an intelligent monitoring and analysis device for offshore wind power foundation scour according to an embodiment of the present invention; Figure 12 It is a computer device according to an embodiment of the present invention. Detailed Implementation

[0024] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] The following description, with reference to the accompanying drawings, describes an intelligent monitoring method and device for offshore wind power foundation scour according to an embodiment of the present invention.

[0027] Figure 1 This is a flowchart of an intelligent monitoring method for offshore wind power foundation scour according to an embodiment of the present invention, such as... Figure 1 As shown, it includes: S1, through underwater monitoring units deployed in the seabed area around the offshore wind power foundation, distributed optical fiber monitoring units deployed along the outer wall of the foundation and the anti-scour structure, and underwater acoustic scanning units, simultaneously collects seabed scour status data, hydrodynamic characteristic data, structural response data, and protective structure status data. S2, through the data acquisition and edge processing unit set in the wind turbine tower platform, performs time-domain alignment, filtering and noise reduction and outlier removal on the acquired multi-source monitoring data, and constructs a comprehensive scour feature vector from the preprocessed data; S3, based on the comprehensive scour feature vector, the intelligent diagnostic module in the edge processing unit uses a machine learning model to identify and predict the scour development stage, and generates a comprehensive risk assessment index by combining threshold judgment. S4. Based on the comprehensive risk assessment indicators, the risk level is automatically classified and an alarm is triggered by the intelligent early warning unit. At the same time, the scouring status is displayed in real time, the development trend is analyzed, and operation and maintenance decision suggestions are generated through the remote operation and maintenance platform.

[0028] This invention proposes an intelligent monitoring system for offshore wind power foundation scour, comprising: an underwater monitoring unit, a distributed optical fiber monitoring unit, an underwater acoustic scanning unit, a data acquisition and edge processing unit, an intelligent early warning unit, and a remote operation and maintenance platform.

[0029] Furthermore, the underwater monitoring unit is deployed in the seabed area surrounding the offshore wind power foundation, such as... Figure 2 As shown, it includes: an underwater pressure sensor; a flow velocity and direction sensor; a seabed elevation monitoring sensor; a sediment concentration monitoring sensor; a vibration monitoring sensor; and an underwater attitude sensor. Among them: the seabed elevation monitoring sensor is used to monitor changes in the depth of scour around the pile in real time; the sediment concentration monitoring sensor is used to monitor changes in suspended sediment near the seabed; and the vibration monitoring sensor is used to monitor changes in the foundation's vibration response caused by scour.

[0030] Furthermore, the distributed optical fiber monitoring unit extends along the outer wall of the wind turbine foundation and the anti-scouring structure, as shown below. Figure 3 As shown (such as some active protection measures, such as turbulence rings and sacrificial piles, and passive protection measures such as rock dumping, sand covering, and interlocking concrete rows), distributed fiber optic sensors are deployed inside to monitor: structural strain, local strain, settlement of the protective layer, and local cavitation.

[0031] Furthermore, the underwater acoustic scanning unit includes, as follows: Figure 4 As shown: miniature multibeam sonar; ring scan sonar; underwater imaging sonar. Used for real-time scanning of seabed topography; 3D reconstruction of scour pits; and identification of protective structure morphology.

[0032] Furthermore, the data acquisition and edge processing unit is located inside the wind turbine tower platform, such as... Figure 5 As shown, it includes: a data acquisition module; an edge computing module; a data caching module; and an intelligent diagnostic module. It is used for: fusing multi-source monitoring data; automatically identifying scour development trends; and determining abnormal scour conditions.

[0033] Furthermore, the data acquisition and edge processing unit is located inside the wind turbine tower platform and mainly includes a data acquisition module, an edge computing module, a data caching module, and an intelligent diagnostic module. It is used for real-time acquisition, fusion analysis, scour trend identification, and anomaly judgment of multi-source monitoring data around the offshore wind power foundation. The system first synchronously acquires seabed scour, hydrodynamic changes, and structural response information through underwater pressure sensors, flow velocity and direction sensors, seabed elevation monitoring sensors, sediment concentration monitoring sensors, vibration monitoring sensors, attitude sensors, distributed fiber optic sensors, and sonar scanning equipment. Because different sensors have different sampling frequencies, the system uses a unified timestamp synchronization mechanism to align the original data in the time domain, through an interpolation function:

[0034] Achieving a unified timeline mapping for different types of monitoring data enables the establishment of multi-source synchronized data sequences.

[0035] Furthermore, in the data preprocessing stage, the system filters and denoises the large amount of wave disturbances, electromagnetic noise, and random anomalies present in the marine environment. For vibration monitoring data, a Butterworth low-pass filter is used:

[0036] High-frequency noise is suppressed, where ωc is the cutoff frequency and n is the filter order. For outlier samples, the Z-score anomaly detection method is used.

[0037] when When an outlier is detected, it is automatically removed to improve data stability and reliability. For large-scale point cloud data generated by underwater sonar scanning, the system uses the Statistical Outlier Removal (SOR) algorithm to remove outliers by calculating the average distance of the point cloud neighborhood.

[0038] when:

[0039] The point is identified as a noise point and deleted, thereby improving the accuracy of the 3D reconstruction of the scour pit.

[0040] Furthermore, during the multi-source data fusion analysis, the system constructs a comprehensive scour feature vector from parameters such as seabed scour depth, sediment concentration, flow velocity, hydrodynamic load, structural vibration response, and fiber optic strain.

[0041] in, For scouring depth, The concentration of sediment. For flow rate, For vibration response, For structural strain, the system employs a weighted fusion model to establish a comprehensive scour index:

[0042] in These are the weighting coefficients for each parameter. Let be the normalized feature parameters, and satisfy:

[0043] Furthermore, the weighting coefficients can be dynamically determined based on the analytic hierarchy process (AHP), entropy weighting, or neural network training methods. To eliminate the influence between different physical dimensions, the system employs a Min-Max normalization method.

[0044] The system achieves unified normalization processing of multi-source data. It further extracts scour development characteristic parameters based on real-time monitoring data. The scour rate is calculated using the relationship between seabed elevation and time.

[0045] in This refers to the real-time flushing depth. When the flushing rate exceeds a set threshold... At that time, the system determined that scour had entered a rapid development stage. Simultaneously, the system identified characteristics of foundation stiffness degradation by analyzing changes in foundation vibration frequency.

[0046] Furthermore, the fundamental natural frequency satisfies:

[0047] in Based on the equivalent stiffness, For structural quality. As scouring progresses, the foundation constraints weaken, the foundation stiffness decreases, and consequently, the structure's natural frequency decreases. The system is further analyzed through the rate of frequency change:

[0048] Furthermore, identify trends in basic stability degradation, among which The initial frequency, This is the real-time frequency. Furthermore, the system is also based on the Rouse sediment transport model:

[0049] Analysis of sediment resuspension characteristics near the seabed, including:

[0050] Used to identify the sediment transport status and local scour activity level in the scour zone.

[0051] Furthermore, to achieve intelligent prediction of scour development trends, the system constructs a time series prediction model based on a Long Short-Term Memory (LSTM) network, using scour depth, flow velocity, sediment concentration, and vibration response as input features:

[0052] Output the predicted scour depth at future moments:

[0053] The LSTM network uses a forget gate, input gate, and output gate to remember historical features and predict future trends. Its core computational process includes:

[0054] This enables early prediction and warning of seabed erosion trends. Simultaneously, the system further employs a Support Vector Machine (SVM) classification model:

[0055] Furthermore, the system intelligently classifies scour states, automatically identifying the initial, rapid development, stable, and dangerous scour stages. During abnormal scour state judgment, the system combines threshold determination with machine learning anomaly detection algorithms for comprehensive analysis. When the real-time scour depth meets the following criteria: hs>1.3D (1.3D is generally the maximum scour depth reserved in the pile foundation design) in When the diameter of the wind turbine foundation piles is less than that, the system determines that it has entered a dangerous scouring state.

[0056] Furthermore, the system establishes comprehensive risk assessment indicators:

[0057] in To flush out the risk index, The weighting coefficient is used. The system automatically classifies risk levels based on the risk index and triggers audible and visual alarms, remote operation and maintenance platform warnings, data pushes, and operation and maintenance decision suggestions to achieve long-term online intelligent monitoring and proactive early warning of the scour status of offshore wind power foundations.

[0058] Furthermore, the intelligent early warning unit includes, as follows: Figure 6 As shown: The system includes a flushing threshold judgment module, a risk level assessment module, and a remote alarm module. When monitored data exceeds the set threshold, it automatically triggers: audible and visual alarms; an alarm on the operation and maintenance platform; and remote data push.

[0059] Furthermore, the remote operation and maintenance platform is connected to the offshore wind farm via a wireless communication system, such as... Figure 7 As shown, it is used for: real-time display of scour status; analysis of scour development trends; historical data storage; health assessment of protective structures; and operation and maintenance decision support.

[0060] Furthermore, this invention employs multi-parameter fusion analysis, considering hydrodynamic parameters, seabed elevation changes, foundation vibration response, and sediment concentration changes. A machine learning model is used to identify the following stages: initial scour phase, rapid development phase, stable phase, and dangerous scour phase. This achieves "early scour warning."

[0061] Furthermore, the system may also include a wave or vibration energy harvesting module, such as... Figure 8 As shown, power generation is achieved by utilizing the low-frequency vibration of the wind turbine, wave motion, or ocean current vibration to power the underwater monitoring unit.

[0062] Furthermore, this invention can not only monitor seabed erosion, such as... Figure 9 As shown, it can also simultaneously monitor the settlement of the riprap layer, the displacement of the interlocking piles, the cracking of the solidified soil, and the erosion of the sand. It can achieve long-term online monitoring and has automatic analysis of scour trends. It is applicable to monopile foundations, jacket foundations, and offshore substation foundations, such as... Figure 10 As shown.

[0063] To achieve the above embodiments, such as Figure 11 As shown, this embodiment also provides an intelligent monitoring device 10 for offshore wind power foundation scour, comprising: The multi-source data acquisition module 100 is used to simultaneously acquire seabed scour status data, hydrodynamic characteristic data, structural response data, and protective structure status data through underwater monitoring units deployed in the seabed area around the offshore wind power foundation, distributed optical fiber monitoring units deployed along the outer wall of the foundation and the anti-scour structure, and underwater acoustic scanning units. The data preprocessing and feature construction module 200 is used to perform time-domain alignment, filtering and noise reduction and outlier removal on the collected multi-source monitoring data through the data acquisition and edge processing unit set in the wind turbine tower platform, and construct a comprehensive scour feature vector from the preprocessed data. The scour diagnosis and risk assessment module 300 is used to identify and predict the scour development stage based on the comprehensive scour feature vector, through the intelligent diagnosis module in the edge processing unit, using a machine learning model, and generating a comprehensive risk assessment index in combination with threshold judgment. The graded early warning and operation and maintenance analysis module 400 is used to automatically classify risk levels and trigger alarms through the intelligent early warning unit based on the comprehensive risk assessment indicators, and at the same time display the flushing status in real time, analyze the development trend and generate operation and maintenance decision suggestions through the remote operation and maintenance platform.

[0064] An intelligent monitoring device for offshore wind power foundation scour according to an embodiment of the present invention can realize real-time monitoring and intelligent early warning of the scour status of offshore wind power foundations, improve the real-time performance and intelligence of monitoring, and reduce operation and maintenance costs.

[0065] To implement the methods of the above embodiments, the present invention also provides a computer device, such as... Figure 12 As shown, the computer device 600 includes a memory 601 and a processor 602; wherein, the processor 602 reads executable program code stored in the memory 601 to run a program corresponding to the executable program code, so as to implement the various steps of the method described above.

[0066] To implement the above embodiments, this application also proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method described in the foregoing embodiments.

[0067] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0068] 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 invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

Claims

1. A method for intelligent monitoring of scour of offshore wind power foundations, characterized in that, include: S1, through underwater monitoring units deployed in the seabed area around the offshore wind power foundation, distributed optical fiber monitoring units deployed along the outer wall of the foundation and the anti-scour structure, and underwater acoustic scanning units, simultaneously collects seabed scour status data, hydrodynamic characteristic data, structural response data, and protective structure status data. S2, through the data acquisition and edge processing unit set in the wind turbine tower platform, performs time-domain alignment, filtering and noise reduction and outlier removal on the acquired multi-source monitoring data, and constructs a comprehensive scour feature vector from the preprocessed data; S3, based on the comprehensive scour feature vector, the intelligent diagnostic module in the edge processing unit uses a machine learning model to identify and predict the scour development stage, and generates a comprehensive risk assessment index by combining threshold judgment. S4. Based on the comprehensive risk assessment indicators, the risk level is automatically classified and an alarm is triggered by the intelligent early warning unit. At the same time, the scouring status is displayed in real time, the development trend is analyzed, and operation and maintenance decision suggestions are generated through the remote operation and maintenance platform.

2. The method as described in claim 1, characterized in that, S1 includes: The system uses underwater pressure sensors, flow velocity and direction sensors, seabed elevation monitoring sensors, sediment concentration monitoring sensors, vibration monitoring sensors, and underwater attitude sensors to acquire real-time data on seabed scour depth, flow velocity and direction, suspended sediment concentration, and foundation vibration response. Distributed fiber optic sensors deployed along the outer wall of the wind turbine foundation and inside the anti-scour structure are used to monitor structural strain, local strain, protective layer settlement, and local cavitation data in real time. Real-time acquisition of seabed topographic scanning data, scour pit 3D reconstruction data, and protective structure morphology identification data is achieved using miniature multibeam sonar, ring scan sonar, and underwater imaging sonar.

3. The method as described in claim 2, characterized in that, The method further includes: The changes in the depth of scour around the pile are monitored in real time by seabed elevation monitoring sensors, the changes in suspended sediment near the seabed are monitored in real time by sediment concentration monitoring sensors, and the changes in the vibration response of the foundation caused by scour are monitored in real time by vibration monitoring sensors.

4. The method as described in claim 1, characterized in that, The S2 includes: A unified timestamp synchronization mechanism is used to align the original data in the time domain, through an interpolation function. To achieve unified timeline mapping for different types of monitoring data and establish multi-source synchronized data sequences; A Butterworth low-pass filter was used for vibration monitoring data. Suppressing high-frequency noise, among which The cutoff frequency is n, and the filter order is n; the Z-score anomaly detection method is used for abnormal sampled values. ,when Values ​​that are identified as outliers are automatically removed.

5. The method as described in claim 4, characterized in that, The method further includes: For large-scale point cloud data generated by underwater sonar scanning, the Statistical Outlier Removal algorithm is used to remove outliers by calculating the average distance of the point cloud neighborhood. ,when The point is identified as a noise point and deleted.

6. The method as described in claim 1, characterized in that, The S3 includes: Construct a time series prediction model based on long short-term memory networks to assess the depth of scour. Flow rate Sediment concentration and vibration response as input features Output the predicted scour depth at future moments. The Long Short-Term Memory Network (LSTM) uses forget gates, input gates, and output gates to achieve the memory of historical erosion features and the prediction of future trends. Support Vector Machine Classification Model The system intelligently classifies the scouring state, enabling automatic identification of the initial scouring stage, rapid development stage, stable stage, and dangerous scouring stage.

7. The method as described in claim 1, characterized in that, The S4 includes: The monitoring data is compared with the set threshold by the flushing threshold judgment module, and the risk level is automatically classified according to the comprehensive risk assessment index by the risk level assessment module. When the monitoring data exceeds the set threshold, the remote alarm module automatically triggers the audible and visual alarm, the operation and maintenance platform alarm, and the remote data push.

8. An intelligent monitoring device for offshore wind power foundation scour, characterized in that, include: The multi-source data acquisition module is used to simultaneously acquire seabed scour status data, hydrodynamic characteristic data, structural response data, and protective structure status data through underwater monitoring units deployed in the seabed area around the offshore wind power foundation, distributed optical fiber monitoring units deployed along the outer wall of the foundation and the anti-scour structure, and underwater acoustic scanning units. The data preprocessing and feature construction module is used to perform time-domain alignment, filtering and noise reduction, and outlier removal on the collected multi-source monitoring data through the data acquisition and edge processing unit set in the wind turbine tower platform, and construct a comprehensive scour feature vector from the preprocessed data. The scour diagnosis and risk assessment module is used to identify and predict the scour development stage based on the comprehensive scour feature vector, through the intelligent diagnosis module in the edge processing unit, using a machine learning model, and generating a comprehensive risk assessment index by combining threshold judgment. The graded early warning and operation and maintenance analysis module is used to automatically classify risk levels and trigger alarms through the intelligent early warning unit based on the comprehensive risk assessment indicators. At the same time, it displays the flushing status in real time, analyzes the development trend, and generates operation and maintenance decision suggestions through the remote operation and maintenance platform.

9. A computer device, characterized in that, Including processor and memory; The processor reads executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the method as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images