Risk management method, system and equipment for offshore converter station and medium

Abstract

The invention discloses a risk management method, system, equipment and medium for an offshore converter station, and belongs to the field of converter stations, and the method comprises the steps: collecting the sediment sample data of the seabed where the offshore converter station is located; performing data fusion processing on the basis of the sediment sample data and the historical geological database to obtain hydrothermal activity data and topographic change data, and performing prediction on the basis of the hydrothermal activity data and the topographic change data to obtain multi-source risk data; performing classification modeling on the multi-source risk data, generating a risk management data set, inputting the risk management data set into a BIM model to simulate and analyze an influence result of terrain micro-heaving on the structure of the offshore converter station, and determining a potential risk area of the offshore converter station based on the influence result; and according to the potential risk area, a structure risk management scheme is generated, and the offshore converter station is managed based on the risk management scheme, so that the risk management accuracy of the offshore converter station can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of converter stations, in particular to a risk management method, system, device and medium for offshore converter stations. BACKGROUND

[0002] The offshore converter station is the core hub of the marine energy transmission network, and its structural safety is directly related to the stable operation of the entire power grid and the safety of huge assets. Due to its long-term presence in a complex deep-sea environment, the foundation stability is directly threatened by dynamic geological activities on the seabed (such as topographic micro-ridges caused by hydrothermal vent activities). Once the structure is damaged due to foundation changes, not only will it cause catastrophic energy supply interruptions and huge economic losses, but it may also cause serious marine ecological disasters. Therefore, forward-looking and accurate risk management of offshore converter stations is a core link in ensuring national energy security and preventing major engineering risks.

[0003] Currently, the risk management of offshore converter stations mainly relies on the integration of real-time monitoring and static topographic, seismic and other data by geographic information systems. However, this type of method relies too much on real-time or present data, seriously neglecting the historical evolution process of geological activities, and is unable to reconstruct the periodicity of hydrothermal activity or quantify the long-term cumulative effects of hydrothermal activity on topographic micro-ridges, ultimately resulting in insufficient comprehensive long-term risk assessment of converter station foundation stability and insufficient prediction accuracy, making it difficult to support accurate risk early warning and proactive prevention and control decisions. SUMMARY

[0004] The present application provides a risk management method, system, device and medium for offshore converter stations, which can improve the accuracy of risk management of offshore converter stations.

[0005] An embodiment of the present application provides a risk management method for offshore converter stations, comprising: collecting sediment sample data of the seabed where the offshore converter station is located; performing data fusion processing on the sediment sample data and a historical geological database to obtain hydrothermal activity data and topographic change data, and performing prediction based on the hydrothermal activity data and the topographic change data to obtain multi-source risk data; performing classification modeling on the multi-source risk data to generate a risk management dataset, inputting the risk management dataset into a BIM model to simulate and analyze the influence of topographic micro-ridges on the structure of the offshore converter station, and determining a potential risk area of the offshore converter station based on the influence result, wherein the BIM model is established based on the hydrothermal activity data and the topographic change data; generating a structural risk management scheme according to the potential risk area, and implementing management of the offshore converter station based on the risk management scheme.

[0006] This invention integrates sediment sample data with historical geological databases, transforming isolated, static geological data into dynamic knowledge with historical depth and causal relationships. This provides reliable historical patterns and predictive basis for risk assessment, fundamentally improving the accuracy of risk judgment. Based on the integrated reliable data, models such as time series analysis can be used to predict future trends of hydrothermal activity and potential topographic changes. This makes "multi-source risk data" no longer a static snapshot, but a dynamic prediction containing future possibilities, significantly improving the foresight and accuracy of risk prediction. By dividing the continuous risk spectrum into different "risk levels" (e.g., high, medium, low), risk management becomes more operational. This application demonstrates several advantages. First, by generating datasets, a complex scientific problem can be transformed into a structured, queryable, and executable dataset, avoiding the subjectivity and uncertainty inherent in relying on human experience, thus improving the scientific rigor and accuracy of decision-making. Second, through mechanical simulations such as finite element analysis, the stress, strain, and displacement of each part of the structure throughout its design life can be precisely calculated, objectively and quantitatively identifying stress concentration points and areas where deformation will exceed limits, thereby accurately locating potential risk areas. Third, by converting the plan into specific control commands and construction parameters that directly affect the converter station, risk management is no longer just a paper report but a precise guide for actual operation, maintenance, and engineering modifications. This "targeted treatment" approach to management avoids resource waste and blind measures, ensuring the accuracy and efficiency of risk control at the final execution level. Compared to existing technologies, this application improves the accuracy of risk management for offshore converter stations.

[0007] Furthermore, the process of fusing the sediment sample data with the historical geological database to obtain hydrothermal activity data and topographic change data includes: Mineral composition ratios, isotopic characteristics, and sedimentary sequence characteristics are extracted from the sediment sample data, and the mineral composition ratios, isotopic characteristics, and sedimentary sequence characteristics are subjected to dimensionality reduction processing to determine the active cycle of hydrothermal vents. The hydrothermal vent activity records for the corresponding period obtained from the historical geological database will be fused with the hydrothermal vent activity cycle by time series analysis to determine the potential relationship pattern of the influence of topographic micro-uplift. Based on the sediment sample data, the historical geological database, and the potential relationship patterns, the hydrothermal activity data and the topographic change data are generated.

[0008] By fusing the sediment sample data with historical geological databases, isolated, static geological data is transformed into dynamic knowledge with historical depth and causal relationships. This provides reliable historical patterns and predictive basis for risk assessment, thereby fundamentally improving the accuracy of risk judgment.

[0009] Furthermore, the prediction based on the hydrothermal activity data and the topographic change data to obtain multi-source risk data includes: The hydrothermal activity data and the topographic change data are fused and standardized to generate multidimensional fused data; Risk feature vectors are extracted from the multidimensional fused data, risk levels are classified based on the risk feature vectors, and the occurrence probability and impact range corresponding to each risk level are calculated. Multi-source risk data are generated based on the risk level, the occurrence probability, and the impact range. The risk feature vectors include hydrothermal activity intensity features, topographic uplift rate features, and environmental factor features.

[0010] By conducting a refined and quantitative assessment of complex geological and environmental risks, vague qualitative understanding is transformed into a structured risk map, providing a reliable data foundation for subsequent accurate structural simulation and risk management, thereby significantly improving the objectivity and accuracy of risk assessment.

[0011] Furthermore, the BIM model is built based on the hydrothermal activity data and the topographic change data, and includes: Based on the hydrothermal activity data and the topographic change data, an initial BIM model is constructed, wherein the initial BIM model includes the stratigraphic structure, the distribution of hydrothermal channels, and the functional relationship between the intensity of hydrothermal activity and the rate of topographic change; Based on the potential relationship pattern, the foundation stability parameters in the initial BIM model are corrected to obtain the corrected BIM model, wherein the foundation stability parameters include foundation bearing capacity, settlement rate and shear strength.

[0012] By constructing and refining BIM models, geological risks can be accurately translated into engineering language, directly improving accuracy.

[0013] Furthermore, the step of classifying and modeling the multi-source risk data to generate a risk management dataset includes: Based on the multi-source risk data, risk thresholds and triggering mechanisms are set for different combinations of hydrothermal activity intensity, topographic uplift degree, and extreme weather conditions. Establish a mapping relationship between risk levels and response measures, and generate a risk management dataset based on the risk threshold, the triggering mechanism, and the mapping relationship.

[0014] By generating datasets in this way, a complex scientific problem can be transformed into a structured, queryable, and actionable dataset, avoiding the subjectivity and uncertainty brought about by relying on human experience, thereby improving the scientific nature and accuracy of decision-making.

[0015] Furthermore, the step of inputting the risk management dataset into the BIM model to simulate and analyze the impact of topographic micro-uplifts on the offshore converter station structure, and determining the potential risk areas of the offshore converter station based on the impact results, includes: The risk management dataset is input into the BIM model, and finite element analysis is performed on the BIM model to calculate the dynamic response of the offshore converter station during its design life, thereby obtaining the stress distribution and deformation displacement of the structure. Based on the stress distribution and the deformation displacement, stress concentration areas where the stress distribution exceeds a preset stress threshold and displacement over-limit locations where the deformation displacement exceeds a preset displacement threshold are identified, and potential risk points are determined based on the stress concentration areas and displacement over-limit locations. By merging adjacent potential risk points, the potential risk areas of the offshore converter station structure are determined.

[0016] In this way, through mechanical simulations such as finite element analysis, the stress, strain, and displacement of each part of the structure can be accurately calculated throughout the entire design life. This allows for the objective and quantitative identification of which parts are stress concentration points and which areas will exceed the deformation limit, thereby accurately locating potential risk areas.

[0017] Furthermore, generating a structural risk management plan based on the potential risk areas includes: Based on the potential risk areas, obtain the target risk level and target response measures corresponding to the potential risk areas from the risk management dataset; Based on the target risk level and the target countermeasures, generate an operational parameter adjustment strategy for the offshore converter station; Based on the distribution of risk points within the potential risk area, the cumulative risk value of each structure on the offshore converter station is calculated, and the reinforcement priority of each structure is determined according to the cumulative risk value. The structural risk management scheme includes the reinforcement priority and the operating parameter adjustment strategy.

[0018] By using this method to pinpoint potential risk areas and retrieve precisely matched target response measures from structured datasets, operational parameter adjustment strategies and structural reinforcement priorities are generated. This avoids the blindness of experience-based decision-making and ensures that operational resources and engineering measures can be deployed accurately and effectively, thereby systematically improving the accuracy and efficiency of risk control.

[0019] Another embodiment of the present invention provides a risk management system for an offshore converter station, comprising: a data acquisition module, a processing module, a determination module, and a management module; The acquisition module is used to collect sediment sample data of the seabed where the offshore converter station is located. The processing module is used to perform data fusion processing on the sediment sample data and the historical geological database to obtain hydrothermal activity data and topographic change data, and to make predictions based on the hydrothermal activity data and the topographic change data to obtain multi-source risk data. The determining module is used to classify and model the multi-source risk data, generate a risk management dataset, and input the risk management dataset into the BIM model to simulate and analyze the impact of topographic micro-uplift on the offshore converter station structure, and determine the potential risk areas of the offshore converter station based on the impact results. The BIM model is established based on the hydrothermal activity data and the topographic change data. The management module is used to generate a structural risk management plan based on the potential risk areas, and to manage the offshore converter station based on the risk management plan.

[0020] Another embodiment of the present invention provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the steps of the risk management method for offshore converter stations as described in the present invention.

[0021] Another embodiment of the present invention also provides a computer-readable storage medium item, including: a stored computer program, which, when the computer program is running, controls the device where the computer-readable storage medium is located to perform the steps of the risk management method for offshore converter stations as described in the present invention. Attached Figure Description

[0022] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating one embodiment of the risk management method for offshore converter stations provided in this application; Figure 2 This is a flowchart illustrating one embodiment of steps S201 to S203 provided in this application; Figure 3 This is a flowchart illustrating one embodiment of steps S301 to S303 provided in this application; Figure 4 This is a flowchart illustrating one embodiment of steps S401 to S403 provided in this application; Figure 5 This is a flowchart illustrating another embodiment of the risk management method for offshore converter stations provided in this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] 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 pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0026] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0027] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0028] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0029] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0030] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0031] Offshore converter stations are core hubs in marine energy transmission networks, and their long-term structural safety is directly threatened by dynamic geological processes such as submarine hydrothermal vent activity. Once the terrain becomes unstable due to minor topographic uplift, it can trigger catastrophic energy supply disruptions, massive economic losses, and marine ecological risks. Therefore, achieving forward-looking and accurate risk management is crucial. However, current methods mainly rely on geographic information systems to integrate real-time and static data, resulting in insufficient long-term risk assessment and prediction accuracy, making it difficult to support effective risk early warning and proactive prevention.

[0032] See Figure 1 To improve the accuracy of risk management for offshore converter stations, an embodiment of the present invention provides a risk management method for offshore converter stations, including steps S101 and S104. Step S101: Collect sediment sample data of the seabed where the offshore converter station is located; In some embodiments, firstly, sampling points are systematically deployed in a key area around the converter station foundation (e.g., covering an area of ​​2 square kilometers) at a predetermined density (e.g., a grid spacing of 5 meters × 5 meters). Then, a deep-sea gravity sampler or similar core sampling equipment is used to obtain sediment sample data at each predetermined sampling point that is long enough to reflect the historical sedimentary sequence (e.g., at least 2 meters in length).

[0033] It should be noted that the location of each sampling point needs to be determined using precise positioning technologies such as acoustic positioning systems, thereby binding each sediment sample with precise geographic coordinates (latitude and longitude) and depth information, providing a foundation for the subsequent construction of a BIM model with spatial attributes.

[0034] Step S102: The sediment sample data and historical geological database are fused to obtain hydrothermal activity data and topographic change data. Based on the hydrothermal activity data and topographic change data, a prediction is made to obtain multi-source risk data. Please refer to Figure 2 In some embodiments, the step of fusing the sediment sample data and historical geological database to obtain hydrothermal activity data and topographic change data includes steps S201 to S203. Step S201: Extract mineral composition ratio, isotopic characteristics and sedimentary sequence characteristics from the sediment sample data, and perform dimensionality reduction processing on the mineral composition ratio, isotopic characteristics and sedimentary sequence characteristics to determine the active cycle of hydrothermal vents; In some embodiments, firstly, sediment sample data are segmented and processed in a laboratory at fixed intervals (e.g., every 5 cm) to obtain several sub-samples. The mass percentage of hydrothermal indicator minerals such as sulfides, carbonates, and silicates in the sub-samples is quantitatively analyzed using X-ray diffraction (XRD) technology to determine the mineral composition ratio. The values ​​of sulfur isotope δ34S and oxygen isotope δ18O are determined using mass spectrometry to determine isotopic characteristics (wherein, a δ34S value close to 0‰ indicates that the sulfur source mainly comes from deep hydrothermal fluids, while a significant decrease in the δ18O value indicates the injection of high-temperature hydrothermal fluids). At the same time, sedimentary sequences are divided based on the abrupt transition interface from coarse sand to silt and anomalies where the magnetic susceptibility exceeds three times the background value. The thickness of each sequence unit and the sedimentation rate calculated based on carbon-14 dating data are recorded. Subsequently, the mineral composition percentage, isotope values, and sequence thickness data of each sequence unit were used to form a multidimensional feature vector. Principal component analysis (PCA) was used to reduce the dimensionality of the multidimensional feature vector. When the calculated cumulative variance contribution rate reached 85%, the top few principal components were extracted as a comprehensive hydrothermal activity intensity index. After sorting the index by geological age to form a time series, the transition nodes between active and quiescent periods were automatically identified from the time series by setting statistical rules (e.g., when the difference between principal component values ​​of adjacent periods exceeds twice the standard deviation of the series mean). This allowed for the accurate determination of the active cycle of hydrothermal vents and the reproduction of their historical activity patterns.

[0035] Step S202 involves performing a time series fusion analysis between the hydrothermal vent activity records for the corresponding period obtained from the historical geological database and the hydrothermal vent activity cycle to determine the potential relationship pattern of the influence of topographic micro-uplift. In some embodiments, firstly, data corresponding to the geological ages of sediment records, such as seafloor temperature anomaly records and seismic activity frequency data, are retrieved from historical geological databases. Next, a time-series fusion analysis is performed on historical hydrothermal vent activity records; that is, the Pearson correlation coefficient between the hydrothermal activity intensity sequence and the temperature anomaly records in the database is calculated. When the correlation coefficient is greater than 0.7, a significant positive correlation is confirmed, establishing a reliable time correspondence to obtain the fused sequence. Then, the fused sequence is fitted using an autoregressive integral moving average (ARIMA) model. The impulse response function of the successfully fitted model is used to quantify the topographic response characteristics, i.e., calculating the lag time (e.g., 3 to 6 months) and response amplitude (12 to 18 months to reach peak) of the topographic micro-uplift rate relative to a unit change in hydrothermal activity intensity. Through this series of analyses, the geological correlation is transformed into a clear, quantifiable potential relationship pattern.

[0036] It should be noted that the standard construction process of the ARIMA model includes: performing a stationarity test on the series, eliminating the trend term through differencing, and determining the optimal order of the model (e.g., ARIMA(2,1,1)) based on the autocorrelation function (ACF) and partial autocorrelation function (PACF) plots. The specific construction process is not the focus of this application, so it will not be elaborated here.

[0037] It should be noted that the potential relationship pattern, namely hydrothermal activity of a certain intensity, will cause micro-uplifts in the terrain with a certain magnitude after a certain delay.

[0038] Step S203: Based on the sediment sample data, the historical geological database, and the potential relationship patterns, generate the hydrothermal activity data and the topographic change data.

[0039] In some embodiments, hydrothermal activity data primarily integrates the hydrothermal vent activity cycle information obtained in step S201 (including the start and end times, peak activity intensity, and duration of each cycle) and relevant activity records extracted from historical databases (such as temperature peaks and eruption durations). Topographic change data mainly originates from the potential relationship patterns determined in step S202, containing key parameters such as the predicted rate, delay time, and response amplitude of topographic micro-uplifts. Ultimately, through steps S201 to S203, isolated, static geological data are transformed into a dynamic knowledge system with historical depth and causal relationships, providing reliable historical patterns and predictive basis for subsequent risk assessment, thereby fundamentally improving the accuracy of risk interpretation.

[0040] By fusing the sediment sample data with historical geological databases, isolated, static geological data is transformed into dynamic knowledge with historical depth and causal relationships. This provides reliable historical patterns and predictive basis for risk assessment, thereby fundamentally improving the accuracy of risk judgment.

[0041] In some embodiments, the step of predicting multi-source risk data based on the hydrothermal activity data and the topographic change data includes: performing data fusion and standardization processing on the hydrothermal activity data and the topographic change data to generate multi-dimensional fused data; extracting risk feature vectors from the multi-dimensional fused data; classifying risk levels based on the risk feature vectors; calculating the occurrence probability and impact range corresponding to each risk level; and generating multi-source risk data based on the risk level, the occurrence probability, and the impact range; wherein the risk feature vectors include hydrothermal activity intensity features, topographic uplift rate features, and environmental factor features.

[0042] In some embodiments, firstly, a min-max normalization method is used to linearly transform the original parameters (hydrothermal activity data and topographic change data) with different dimensions to a standard range of 0 to 1, eliminating modeling bias caused by differences in magnitude. Then, these standardized data are integrated according to three dimensions: time series, spatial coordinates, and parameter type, constructing a structured multidimensional fused data cube. Next, a sliding window time series analysis technique is used to extract feature vectors from the multidimensional fused data. These features are then combined to form a risk feature vector, which is input into a support vector machine (SVM) model with a radial basis function kernel for training and classification. This SVM model precisely classifies risks into five levels, from extremely high to extremely low, by finding the optimal classification hyperplane. Then, since the probability of occurrence for each risk level is determined based on historical statistical data, the impact range is quantified and bound according to the physical characteristics of the risk source (such as the influence radius of hydrothermal vents and the influence range of topographic uplift). Finally, structured multi-source risk data is output, explicitly including risk identification codes, quantitative assessment indicators (probability, degree of impact, etc.), spatial distribution layers, and temporal evolution sequences.

[0043] It should be noted that the multidimensional fusion data cube uses monthly time as the axis, covers a specific range of grid space around the converter station, and integrates more than nine key parameters such as hydrothermal temperature, topographic elevation, and sediment properties, thus forming a standardized data base that is spatiotemporally integrated and correlated with multiple parameters.

[0044] It should be noted that the risk feature vector is extracted from the multidimensional fusion data in the following ways: the mean, coefficient of variation, and dominant frequency obtained by fast Fourier transform of hydrothermal activity intensity are extracted from the hydrothermal activity data; the maximum uplift rate and spatial density of the topographic uplift rate are extracted from the topographic data through kernel density estimation and spatial gradient calculation; at the same time, records such as wind speed, wave height, and rainfall are integrated to form environmental factor features. These features from different dimensions together constitute the risk feature vector.

[0045] By conducting a refined and quantitative assessment of complex geological and environmental risks, vague qualitative understanding is transformed into a structured risk map, providing a reliable data foundation for subsequent accurate structural simulation and risk management, thereby significantly improving the objectivity and accuracy of risk assessment.

[0046] Step S103: Classify and model the multi-source risk data to generate a risk management dataset, and input the risk management dataset into the BIM model to simulate and analyze the impact of topographic micro-uplift on the offshore converter station structure, and determine the potential risk areas of the offshore converter station based on the impact results. The BIM model is established based on the hydrothermal activity data and the topographic change data. In some embodiments, classifying and modeling the multi-source risk data to generate a risk management dataset includes: based on the multi-source risk data, setting risk thresholds and triggering mechanisms for different combinations of hydrothermal activity intensity, topographic uplift degree, and extreme weather conditions; establishing a mapping relationship between risk levels and countermeasures; and generating a risk management dataset based on the risk thresholds, the triggering mechanisms, and the mapping relationship.

[0047] In some embodiments, firstly, different levels (e.g., dormant period, active period, eruptive period; minor uplift, moderate uplift, strong uplift; normal, severe, extreme) of three key environmental conditions—intensity of hydrothermal activity, degree of topographic uplift, and extreme weather—are arranged and combined to form various typical risk scenarios. For each scenario, the system sets precise risk thresholds (e.g., dynamically adjusting the foundation bearing capacity threshold to 60% of its original value under the most unfavorable combination of hydrothermal eruption period + strong uplift + extreme weather) and multi-level triggering mechanisms (e.g., triggering yellow, orange, and red alerts respectively when monitoring indicators reach 80%, 90%, and 100% of the threshold). Simultaneously, the system establishes a mapping relationship library between risk levels and specific countermeasures; for example, mapping extremely high risks to immediate shutdown and maintenance, emergency foundation reinforcement, and other measures. Ultimately, all this rule-based knowledge—including environmental condition classification matrices, risk thresholds for various scenarios, multi-level triggering mechanisms, and the mapping relationship between risk levels and countermeasures—is integrated and encapsulated to generate a complete risk management dataset that can be directly called by BIM models and operation and maintenance systems, thereby realizing the transformation from complex data to clear management strategies.

[0048] It should be noted that the risk management dataset is like a risk contingency plan library, which pre-sets clear risk thresholds, triggering mechanisms, and most importantly, the mapping relationship between risk levels and countermeasures for different combinations of hydrothermal activity intensity, topographic uplift degree, and extreme weather conditions.

[0049] By generating datasets in this way, a complex scientific problem can be transformed into a structured, queryable, and actionable dataset, avoiding the subjectivity and uncertainty brought about by relying on human experience, thereby improving the scientific nature and accuracy of decision-making.

[0050] In some embodiments, the BIM model is established based on the hydrothermal activity data and the topographic change data, including: constructing an initial BIM model based on the hydrothermal activity data and the topographic change data, wherein the initial BIM model includes the stratigraphic structure, the distribution of hydrothermal channels, and the functional relationship between the intensity of hydrothermal activity and the rate of topographic change; and correcting the foundation stability parameters in the initial BIM model according to the potential relationship pattern to obtain a corrected BIM model, wherein the foundation stability parameters include foundation bearing capacity, settlement rate, and shear strength.

[0051] In some embodiments, firstly, the stratigraphic structure of the model is established based on the spatial coordinates and depth profile data of sediment samples. This is achieved by dividing the study area into tens of thousands of hexahedral finite element meshes, and assigning stratigraphic property parameters such as density, porosity, and permeability obtained from sample analysis to each element. Secondly, the distribution of hydrothermal channels is determined by integrating seismic exploration data from historical geological databases and seafloor topographic features. In the model, these channels are defined as high-permeability vertical or inclined columnar bodies to simulate the main migration paths of hydrothermal fluids. Finally, the core functional relationship between the intensity of hydrothermal activity and the rate of topographic change is a dynamic correlation established through time series analysis. This function adopts a combination of power and exponential functions, and its parameters (such as delay time and response amplitude) are derived from the results of ARIMA model fitting and impulse response analysis of the fused hydrothermal activity cycle and topographic record. For example, the analysis found that after the hydrothermal activity intensifies, the rate of topographic micro-uplift begins to respond after a delay of 3 to 6 months. This quantitative relationship is directly encoded into the BIM model, enabling the model to output a corresponding topographic change prediction that conforms to the laws of geodynamics when any hydrothermal activity intensity parameter is input. After obtaining the initial BIM model, the foundation stability parameters need to be dynamically corrected based on the potential relationship patterns of the topographic micro-uplift influence determined from data fusion, thereby generating a more accurate corrected BIM model. This correction process directly relies on the spatial uplift data provided by the potential patterns: extracting uplift amplitude and uplift rate data at specific coordinate points from the model, and then correcting the foundation bearing capacity, settlement rate, and shear strength based on explicit physical and mechanical laws. Through this series of corrections based on physical mechanisms and data-driven approaches, the foundation stability parameters in the BIM model are updated from ideal static initial values ​​to corrected values ​​that can truly reflect the influence of dynamic geological disturbances, enabling the model to have a high-fidelity ability to simulate and analyze the long-term impact of topographic micro-uplift on the superstructure.

[0052] It should be noted that the correction for foundation bearing capacity is achieved by introducing a reduction factor negatively correlated with the heave amplitude. When the heave amplitude reaches 2 meters, the reduction factor decreases according to a negative exponential function of e^(-αh). The correction for settlement rate adopts the principle of linear superposition, adding the initial settlement rate of the model to the additional settlement rate calculated by multiplying the heave rate by the soil compression modulus. The shear strength parameter is optimized by correlation analysis with the particle size distribution curve and liquid / plastic limit index of the sediment samples.

[0053] By constructing and refining BIM models, geological risks can be accurately translated into engineering language, directly improving accuracy.

[0054] Please refer to Figure 3In some embodiments, the step of inputting the risk management dataset into the BIM model to simulate and analyze the impact of topographic micro-uplift on the offshore converter station structure, and determining the potential risk areas of the offshore converter station based on the impact results, includes steps S301 to S303. Step S301: Input the risk management dataset into the BIM model and perform finite element analysis on the BIM model to calculate the dynamic response of the offshore converter station during its design life, and obtain the stress distribution and deformation displacement of the structure. In some embodiments, load amplification factors (e.g., 1.5 for extremely high risk) and material elastic modulus reduction factors (e.g., 70% of the original value for extremely high risk) corresponding to different risk levels are extracted from the risk management dataset, and these parameters are updated in the BIM model to simulate the aggravated impact of extreme environmental conditions on the structure. Simultaneously, spatial distribution data of topographic micro-uplifts are applied as displacement boundary conditions to the model's foundation. Subsequently, the corrected BIM model is meshed using finite element methods, with mesh refinement at key structural locations (e.g., foundation contact surfaces, pile connections) to ensure computational accuracy. Then, time-history analysis methods (e.g., the Newmark-β method) are used, with the design life of the converter station as the simulation duration, to solve the equations of motion of the structure under time-varying loads and displacement boundaries, thereby outputting the stress distribution and dynamic response sequence of the entire structure at each time step throughout its lifespan.

[0055] This step transforms abstract geological risks into concrete, quantifiable structural mechanical responses, providing a precise data foundation for risk identification.

[0056] Step S302: Based on the stress distribution and the deformation displacement, identify the stress concentration area where the stress distribution exceeds a preset stress threshold and the displacement over-limit location where the deformation displacement exceeds a preset displacement threshold, and determine the stress concentration area and the displacement over-limit location as potential risk points. In some embodiments, the von Mises equivalent stress criterion is used to determine stress distribution. When the equivalent stress in a region exceeds a preset threshold of the material's allowable stress (e.g., 0.8 times the yield strength), that region is marked as a stress concentration point, which is usually the starting point for plastic deformation or fatigue damage in the structure. For deformation displacement, allowable deformation thresholds are set based on engineering specifications, such as a horizontal displacement limit of 1 / 500 of the structural height and a vertical displacement limit of 1 / 400 of the span; any node whose displacement exceeds this threshold is marked as an over-limit location. These two criteria ensure structural safety from both strength and stiffness dimensions, and any point that meets either criterion will be automatically captured by the system and marked as a potential risk point.

[0057] This process is entirely driven by preset, objective quantitative thresholds, eliminating the interference of subjective judgment and ensuring the accuracy and consistency of risk identification.

[0058] Step S303: Merge adjacent potential risk points to determine the potential risk area of ​​the offshore converter station structure.

[0059] In some embodiments, an improved DBSCAN density clustering algorithm is used to scan all discrete potential risk points, with two key parameters set: neighborhood radius (e.g., 2 meters) and minimum number of points (e.g., 5). The algorithm aggregates a group of risk points whose distances to each other are less than the neighborhood radius and whose total number meets the minimum point requirement into a continuous potential risk region. Meanwhile, a few isolated risk points that do not meet the density requirement (e.g., fewer than 3) are ignored by the system to avoid overreacting to insignificant risks.

[0060] In this way, through mechanical simulations such as finite element analysis, the stress, strain, and displacement of each part of the structure can be accurately calculated throughout the entire design life. This allows for the objective and quantitative identification of which parts are stress concentration points and which areas will exceed the deformation limit, thereby accurately locating potential risk areas.

[0061] Step S104: Generate a structural risk management plan based on the potential risk areas, and implement management of the offshore converter station based on the risk management plan.

[0062] Please refer to Figure 4 In some embodiments, generating a structural risk management plan based on the potential risk area includes steps S401 and S403: Step S401: Based on the potential risk area, obtain the target risk level and target response measures corresponding to the potential risk area from the risk management dataset; In some embodiments, once the spatial coordinates of potential risk areas are accurately identified through finite element analysis of the BIM model, this location information is immediately used as an index key to backtrack and query the structured information already generated and stored in the risk management dataset. Therefore, for each identified risk area, the system can automatically and quickly match and retrieve its specific target risk level (e.g., the area is at extremely high risk) and a set of preset target response measures (e.g., immediate shutdown for maintenance, increasing monitoring frequency to three times, etc.).

[0063] Step S402: Generate an operational parameter adjustment strategy for the offshore converter station based on the target risk level and the target countermeasures; In some embodiments, after determining the target risk level and target response measures, historical hydrothermal activity records and topographic change data (including activity intensity time series, temperature peaks, uplift rates, etc.) related to the risk area, extracted from the risk management dataset, are used to quantify the strength of the relationship between hydrothermal activity and topographic uplift by calculating the Pearson correlation coefficient. Based on the strength of this correlation (e.g., strong correlation, moderate correlation), preset, quantified operating parameter adjustment rules are triggered. For example, when a strong correlation is determined, the strategy will adjust the operating load to 60% of the rated power, increase the monitoring frequency to three times the original frequency, and increase the cooling water flow rate by 50%.

[0064] Step S403: Based on the distribution of risk points within the potential risk area, calculate the cumulative risk value of each structure on the offshore converter station, and determine the reinforcement priority of each structure according to the cumulative risk value. The structural risk management scheme includes the reinforcement priority and the operating parameter adjustment strategy.

[0065] In some embodiments, for each critical structural component (such as individual pile foundations) of an offshore converter station, considering the distribution of all identified potential risk points, three core factors are comprehensively considered: the number, severity (i.e., risk level), and spatial distribution density of surrounding risk points. Subsequently, a weighted summation method (with weights of 0.3, 0.5, and 0.2) is used to calculate a comprehensive cumulative risk value for each component, reflecting the overall level of risk faced by each component. Finally, components are ranked according to this cumulative risk value, with higher values ​​assigned higher reinforcement priorities, thus forming a data-driven, objective list of reinforcement actions. Finally, the operational parameter adjustment strategy is integrated with this structural reinforcement priority list to constitute a structural risk management plan.

[0066] By using this method to pinpoint potential risk areas and retrieve precisely matched target response measures from structured datasets, operational parameter adjustment strategies and structural reinforcement priorities are generated. This avoids the blindness of experience-based decision-making and ensures that operational resources and engineering measures can be deployed accurately and effectively, thereby systematically improving the accuracy and efficiency of risk control.

[0067] This invention integrates sediment sample data with historical geological databases, transforming isolated, static geological data into dynamic knowledge with historical depth and causal relationships. This provides reliable historical patterns and predictive basis for risk assessment, fundamentally improving the accuracy of risk interpretation. Based on the integrated reliable data, models such as time series analysis can be used to predict future trends of hydrothermal activity and potential topographic changes. This transforms multi-source risk data from static snapshots into dynamic predictions encompassing future possibilities, significantly enhancing the foresight and accuracy of risk forecasting. Furthermore, dividing the continuous risk spectrum into different risk levels (e.g., high, medium, low) makes risk management more operational. By generating datasets, a complex scientific problem can be transformed into a structured, queryable, and executable dataset, avoiding the subjectivity and uncertainty brought about by relying on human experience, thereby improving the scientific nature and accuracy of decision-making. Through mechanical simulations such as finite element analysis, the stress, strain, and displacement of each part of the structure can be accurately calculated throughout the entire design life, thus objectively and quantitatively identifying which parts are stress concentration points and which areas will exceed the deformation limit, thereby accurately locating potential risk areas. By converting the plan into specific control instructions and construction parameters, which are directly applied to the converter station, risk management is no longer just a paper report, but can accurately guide actual operation and maintenance and engineering modification actions. This targeted management avoids the waste of resources and the blindness of measures, ensuring the accuracy and efficiency of risk control from the final execution level. Compared with existing technologies, this application can improve the accuracy of risk management for offshore converter stations.

[0068] like Figure 5 As shown, based on the above method embodiments, corresponding apparatus embodiments are provided; One embodiment of the present invention provides a risk management system for an offshore converter station, comprising: a data acquisition module 100, a processing module 200, a determination module 300, and a management module 400; The acquisition module 100 is used to acquire sediment sample data of the seabed where the offshore converter station is located. The processing module 200 is used to perform data fusion processing on the sediment sample data and the historical geological database to obtain hydrothermal activity data and topographic change data, and to make predictions based on the hydrothermal activity data and the topographic change data to obtain multi-source risk data. The determining module 300 is used to classify and model the multi-source risk data, generate a risk management dataset, and input the risk management dataset into the BIM model to simulate and analyze the impact of topographic micro-uplift on the offshore converter station structure, and determine the potential risk areas of the offshore converter station based on the impact results. The BIM model is established based on the hydrothermal activity data and the topographic change data. The management module 400 is used to generate a structural risk management plan based on the potential risk area, and to manage the offshore converter station based on the risk management plan.

[0069] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can implement the risk management method for offshore converter stations provided by any of the above-described method embodiments of the present invention.

[0070] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0071] Based on the above-described embodiments of the risk management method for offshore converter stations, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the risk management method for offshore converter stations according to any embodiment of the present invention.

[0072] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0073] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0074] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0075] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the risk management method for offshore converter stations described in any of the above-described method embodiments of the present invention.

[0076] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0077] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A risk management method for offshore converter stations, characterized in that, include: Collect sediment sample data from the seabed where the offshore converter station is located; The sediment sample data and historical geological database are fused to obtain hydrothermal activity data and topographic change data. Based on the hydrothermal activity data and topographic change data, predictions are made to obtain multi-source risk data. The multi-source risk data is classified and modeled to generate a risk management dataset, which is then input into a BIM model to simulate and analyze the impact of micro-topographic uplift on the structure of the offshore converter station. Based on the impact results, potential risk areas of the offshore converter station are determined. The BIM model is established based on the hydrothermal activity data and the topographic change data. Based on the potential risk areas, a structural risk management plan is generated, and the offshore converter station is managed based on the risk management plan.

2. The risk management method for offshore converter stations according to claim 1, characterized in that, The process of fusing the sediment sample data with historical geological databases to obtain hydrothermal activity data and topographic change data includes: Mineral composition ratios, isotopic characteristics, and sedimentary sequence characteristics are extracted from the sediment sample data, and the mineral composition ratios, isotopic characteristics, and sedimentary sequence characteristics are subjected to dimensionality reduction processing to determine the active cycle of hydrothermal vents. The hydrothermal vent activity records for the corresponding period obtained from the historical geological database will be fused with the hydrothermal vent activity cycle by time series analysis to determine the potential relationship pattern of the influence of topographic micro-uplift. Based on the sediment sample data, the historical geological database, and the potential relationship patterns, the hydrothermal activity data and the topographic change data are generated.

3. The risk management method for offshore converter stations according to claim 1, characterized in that, The prediction based on the hydrothermal activity data and the topographic change data yields multi-source risk data, including: The hydrothermal activity data and the topographic change data are fused and standardized to generate multidimensional fused data; Risk feature vectors are extracted from the multidimensional fused data, risk levels are classified based on the risk feature vectors, and the occurrence probability and impact range corresponding to each risk level are calculated. Multi-source risk data are generated based on the risk level, the occurrence probability, and the impact range. The risk feature vectors include hydrothermal activity intensity features, topographic uplift rate features, and environmental factor features.

4. The risk management method for offshore converter stations according to claim 2, characterized in that, The BIM model is built based on the hydrothermal activity data and the topographic change data, and includes: Based on the hydrothermal activity data and the topographic change data, an initial BIM model is constructed, wherein the initial BIM model includes the stratigraphic structure, the distribution of hydrothermal channels, and the functional relationship between the intensity of hydrothermal activity and the rate of topographic change; Based on the potential relationship pattern, the foundation stability parameters in the initial BIM model are corrected to obtain the corrected BIM model, wherein the foundation stability parameters include foundation bearing capacity, settlement rate and shear strength.

5. The risk management method for offshore converter stations according to claim 4, characterized in that, The process of classifying and modeling the multi-source risk data to generate a risk management dataset includes: Based on the multi-source risk data, risk thresholds and triggering mechanisms are set for different combinations of hydrothermal activity intensity, topographic uplift degree, and extreme weather conditions. Establish a mapping relationship between risk levels and response measures, and generate a risk management dataset based on the risk threshold, the triggering mechanism, and the mapping relationship.

6. The risk management method for offshore converter stations according to claim 1, characterized in that, The step of inputting the risk management dataset into the BIM model to simulate and analyze the impact of micro-topographic uplift on the offshore converter station structure, and determining the potential risk areas of the offshore converter station based on the impact results, includes: The risk management dataset is input into the BIM model, and finite element analysis is performed on the BIM model to calculate the dynamic response of the offshore converter station during its design life, thereby obtaining the stress distribution and deformation displacement of the structure. Based on the stress distribution and the deformation displacement, stress concentration areas where the stress distribution exceeds a preset stress threshold and displacement over-limit locations where the deformation displacement exceeds a preset displacement threshold are identified, and potential risk points are determined based on the stress concentration areas and displacement over-limit locations. By merging adjacent potential risk points, the potential risk areas of the offshore converter station structure are determined.

7. The risk management method for offshore converter stations according to claim 1, characterized in that, The step of generating a structural risk management plan based on the potential risk areas includes: Based on the potential risk areas, obtain the target risk level and target response measures corresponding to the potential risk areas from the risk management dataset; Based on the target risk level and the target countermeasures, generate an operational parameter adjustment strategy for the offshore converter station; Based on the distribution of risk points within the potential risk area, the cumulative risk value of each structure on the offshore converter station is calculated, and the reinforcement priority of each structure is determined according to the cumulative risk value. The structural risk management scheme includes the reinforcement priority and the operating parameter adjustment strategy.

8. A risk management system for an offshore converter station, characterized in that, include: Acquisition module, processing module, determination module, and management module; The acquisition module is used to collect sediment sample data of the seabed where the offshore converter station is located; The processing module is used to perform data fusion processing on the sediment sample data and the historical geological database to obtain hydrothermal activity data and topographic change data, and to make predictions based on the hydrothermal activity data and the topographic change data to obtain multi-source risk data. The determining module is used to classify and model the multi-source risk data, generate a risk management dataset, and input the risk management dataset into the BIM model to simulate and analyze the impact of topographic micro-uplift on the offshore converter station structure, and determine the potential risk areas of the offshore converter station based on the impact results. The BIM model is established based on the hydrothermal activity data and the topographic change data. The management module is used to generate a structural risk management plan based on the potential risk areas, and to manage the offshore converter station based on the risk management plan.

9. A terminal device, characterized in that, include: One or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the steps of the risk management method for offshore converter stations as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, include: A stored computer program, wherein, when the computer program is executed, the device containing the computer-readable storage medium controls the execution of the steps of the risk management method for offshore converter stations as described in any one of claims 1-7.

Images