A method and related device for dynamically assessing the fatigue risk of a submarine cable span

Abstract

This application discloses a method and related equipment for dynamic assessment of fatigue risk of submarine cable suspension spans. The method includes: constructing an original dataset by acquiring submarine cable routing information, hydrographic address information, and marine monitoring data; constructing submarine cable node coordinates and defining a submarine cable suspension span discrimination index based on the original dataset; determining the suspension span state information of the target submarine cable based on the submarine cable node coordinates and the submarine cable suspension span discrimination index, and calculating the dynamic suspension span migration rate of the target submarine cable; identifying risk-related events and classifying node risk states based on the suspension span state information and the dynamic suspension span migration rate, thereby constructing a multimorphic fuzzy Bayesian network; and performing a dynamic fatigue risk assessment of the target submarine cable based on the multimorphic fuzzy Bayesian network to obtain the risk assessment result. The embodiments of this application can fully consider the dynamic migration of suspension spans and the cumulative effect of fatigue damage, improving the accuracy of risk assessment, and can be widely applied in the field of submarine cable safety assessment technology.

Description

Technical Field

[0001] This application relates to the field of submarine cable safety assessment technology, and in particular to a dynamic assessment method and related equipment for submarine cable suspension fatigue risk. Background Technology

[0002] After submarine cables are laid in complex seabed topography, sections often detach from the seabed and become suspended due to topographical changes such as seabed erosion and sand wave migration. These suspended sections experience vortex-induced vibrations under the combined action of ocean currents and waves, generating cyclic stress and leading to accumulated fatigue damage. When the fatigue damage reaches a critical value, the cable will fracture due to fatigue, causing power or communication outages and resulting in significant economic losses.

[0003] Existing methods for fatigue assessment of suspended submarine cables have the following limitations: First, they treat the suspended state as static, failing to consider the dynamic migration characteristics of the suspended position and geometric parameters over time. In actual marine environments, seabed erosion and deposition are continuous processes. A node may be suspended in the first year, but may become non-suspended in the second year due to silting, while adjacent nodes may change from non-suspended to suspended. Fatigue damage has irreversible cumulative characteristics, and static assessments cannot reflect the true extent of damage accumulation at different locations during the suspension migration process. Second, traditional assessment methods rely heavily on deterministic calculations or expert experience, making it difficult to effectively handle the uncertainty and ambiguity of marine environmental parameters. Third, existing methods lack the ability to dynamically track and update the fatigue risk evolution process in real time, hindering risk warnings based on actual monitoring data during engineering operation and maintenance. Summary of the Invention

[0004] The main objective of this application is to propose a dynamic assessment method and related equipment for fatigue risk assessment of submarine cable suspension spans, which can fully consider the dynamic migration of the suspension spans and the cumulative effect of fatigue damage, thereby improving the accuracy of risk assessment.

[0005] To achieve the above objectives, one aspect of this application proposes a method for dynamic assessment of fatigue risk in submarine cable suspension, comprising: Acquire submarine cable routing information, hydrographic information, and marine monitoring data to construct a raw dataset; Based on the original dataset, construct the coordinates of submarine cable nodes and define the submarine cable suspension discrimination index; Based on the cable node coordinates and the cable suspension discrimination index, the suspension status information of the target submarine cable is determined, and the dynamic suspension migration rate of the target submarine cable is calculated. Based on the slack state information and the dynamic slack migration rate, risk-based events are identified and node risk states are divided, thereby constructing a multimorphic fuzzy Bayesian network. The target submarine cable is subjected to dynamic fatigue risk assessment based on the polymorphic fuzzy Bayesian network, and the risk assessment results are obtained.

[0006] In some embodiments, constructing submarine cable node coordinates and defining submarine cable suspension discrimination indicators based on the original dataset includes: A one-dimensional coordinate system is established along the length of the submarine cable, with the cable laying path as the m-axis, and the cable is divided into multiple nodes at equal intervals along the m-axis. The y-axis is defined as the direction parallel to the mean seabed surface and perpendicular to the m-axis, and the z-axis is defined as the direction normal to the seabed. Obtain the submarine cable depth at the node and the corresponding seabed depth; Based on the water depth of the submarine cable and the water depth of the seabed, the suspension discrimination index is calculated.

[0007] In some embodiments, determining the suspension status information of the target submarine cable based on the cable node coordinates and the cable suspension discrimination index includes: When the suspension discrimination index is greater than 0, it means that the cable node is located below the seabed and is either buried or in contact with the seabed, and is judged as a non-suspension state; when the suspension discrimination index is less than or equal to 0, it means that the cable node is exposed above the seabed and is detached from the seabed, and is judged as a fixed suspension state. The fatigue analysis for the fixed suspension state includes: By analyzing the dynamic response and vortex-induced vibration of the suspended section, the fixed suspended submarine cable is simplified into an elastic beam constrained at both ends. By combining the suspension length, cable outer diameter, effective mass per unit length, structural damping, and seabed constraint conditions, the natural frequency and mode shape of the suspended section are calculated, and it is then determined whether the suspended section experiences vortex-induced vibration in the downstream and transverse directions, and the dominant vibration mode and steady-state response amplitude are identified. Based on environmental parameters such as ocean current-induced bottom current velocity, wave-induced bottom current velocity amplitude, and wave period, the bending stress of key sections of the suspended span is calculated, and the alternating stress amplitude caused by vortex-induced vibration and wave load is obtained. The total fatigue damage was calculated based on the Miners linear cumulative damage criterion. The criteria for determining the fatigue failure threshold are as follows: when the total fatigue damage is less than 1, the fatigue damage of the fixed suspension section has not reached the critical level, and the structure is safe; when the total fatigue damage is greater than or equal to 1, the suspension section is determined to have experienced fatigue failure, reaching the critical condition for fatigue failure.

[0008] In some embodiments, calculating the dynamic span migration rate of the target submarine cable includes: The suspension migration rate was directly obtained through multiple phases of on-site measurements of seabed topography and cable attitude. Alternatively, the suspension migration rate can be determined through numerical simulation of sand wave motion and dynamic evolution simulation of seabed topography. Specifically, this step involves determining the suspension migration rate as the rate of sand wave migration along the pipeline length direction based on the ratio of the migration distance of the sand wave characteristic points driving the cable suspension along the pipeline length direction to the monitoring cycle duration within two adjacent monitoring cycles. The formula for calculating the suspension migration rate is as follows: = / ,in, for Hovering mobility; This represents the migration distance of the corresponding sand wave feature point along the pipeline length between adjacent monitoring cycles. This represents the time interval between two consecutive monitoring sessions.

[0009] In some embodiments, the identification of risk-low events includes: Based on the fatigue damage mechanism of suspended cables, six bottom events affecting fatigue failure of suspended submarine cables were identified as risk root nodes. These risk root nodes include: a first node determined by the ratio of the suspended length to the diameter; a second node determined by the ratio of the suspended height to the diameter; a third node determined by the bottom current velocity induced by ocean currents; a fourth node determined by the bottom current velocity induced by waves; and a fifth node determined by the wave period. The first intermediate event is determined based on the cumulative damage value of the lead sheath, the second intermediate event is determined based on the cumulative damage value of the armor layer, and the third intermediate event is determined based on the cumulative damage value of the copper conductor. The top event is determined based on fatigue failure of the suspended submarine cable.

[0010] In some embodiments, the node risk status classification includes: Based on the principle of minimum reasonable feasibility, the risk status of each risk root node is divided into three levels: high risk, medium risk, and low risk, and the risk leaf nodes are divided into damaged state and undamaged state.

[0011] In some embodiments, the construction process of the polymorphic fuzzy Bayesian network includes: The trapezoidal fuzzy evaluation method with seven levels of linguistic variables is used to obtain the prior probability of each risk root node; Based on the load strength index and the damage index affecting the structure, the vulnerability curve of the structure is plotted, and the damage probability of each leaf node is calculated. Based on the prior probability of the root node and the damage probability of the leaf node, a fault tree model with fatigue failure of the suspended submarine cable as the top event is established. The top event is mapped to the leaf node of the Bayesian network, the intermediate inference node is mapped to the intermediate node, the bottom event is mapped to the root node, and the logical relationship in the fault tree is mapped to the directed edge, thus constructing a complete polymorphic fuzzy Bayesian network model.

[0012] Another aspect of this application embodiment provides a dynamic assessment device for fatigue risk of submarine cable suspension, including: The first module is used to acquire submarine cable routing information, hydrological address information, and marine monitoring data to construct the raw dataset. The second module is used to construct the coordinates of submarine cable nodes and define the submarine cable suspension discrimination index based on the original dataset. The third module is used to determine the suspension status information of the target submarine cable based on the cable node coordinates and the cable suspension discrimination index, and to calculate the dynamic suspension migration rate of the target submarine cable. The fourth module is used to identify risk-based events and classify node risk states based on the suspension state information and the dynamic suspension migration rate, thereby constructing a multimorphic fuzzy Bayesian network. The fifth module is used to perform dynamic fatigue risk assessment on the target submarine cable based on the polymorphic fuzzy Bayesian network, and obtain the risk assessment result.

[0013] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0015] This application also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0016] The embodiments of this application include at least the following beneficial effects: This application provides a method and related equipment for dynamic assessment of fatigue risk of submarine cable suspension. This method constructs an original dataset by acquiring submarine cable routing information, hydrographic address information, and marine monitoring data; constructs cable node coordinates and defines a cable suspension discrimination index based on the original dataset; determines the suspension state information of the target submarine cable based on the cable node coordinates and the cable suspension discrimination index, and calculates the dynamic suspension migration rate of the target submarine cable; identifies risk events and classifies node risk states based on the suspension state information and the dynamic suspension migration rate, thereby constructing a multimorphic fuzzy Bayesian network; and performs dynamic fatigue risk assessment of the target submarine cable based on the multimorphic fuzzy Bayesian network to obtain the risk assessment result. The embodiments of this application can fully consider the dynamic migration of suspension and the cumulative effect of fatigue damage, improving the accuracy of risk assessment. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application; Figure 2 This is a flowchart of the overall steps provided in the embodiments of this application; Figure 3 This is a schematic diagram of the polymorphic fuzzy Bayesian network structure provided in the embodiments of this application; Figure 4 This is an implementation flowchart of a specific application scenario provided in the embodiments of this application; Figure 5 This is a cross-sectional view of the submarine cable suspended or buried at a certain depth, provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of the dynamic assessment device for fatigue risk of submarine cable suspension provided in the embodiments of this application; Figure 7 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0019] It is understood that the terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0022] Before providing a detailed description of the embodiments of this application, some related technologies involved in the embodiments of this application will be described first, as follows: Existing methods for fatigue assessment of suspended submarine cables have the following limitations: First, they treat the suspended state as static, failing to consider the dynamic migration characteristics of the suspended position and geometric parameters over time. In actual marine environments, seabed erosion and deposition are continuous processes. A node may be suspended in the first year, but may become non-suspended in the second year due to silting, while adjacent nodes may change from non-suspended to suspended. Fatigue damage has irreversible cumulative characteristics, and static assessments cannot reflect the true extent of damage accumulation at different locations during the suspension migration process. Second, traditional assessment methods rely heavily on deterministic calculations or expert experience, making it difficult to effectively handle the uncertainty and ambiguity of marine environmental parameters. Third, existing methods lack the ability to dynamically track and update the fatigue risk evolution process in real time, hindering risk warnings based on actual monitoring data during engineering operation and maintenance.

[0023] Therefore, there is an urgent need for a risk assessment method that can fully consider the dynamic migration of the suspension span and the cumulative effect of fatigue damage, and has the ability to handle uncertainty and update in real time. To address the above problems, this invention proposes a dynamic risk assessment method for submarine cable suspension fatigue based on a multimorphic fuzzy Bayesian network.

[0024] This invention provides a dynamic assessment method for fatigue risk of suspended submarine cables based on a multimorphic fuzzy Bayesian network. By establishing a node coordinate discrimination system, the method achieves dynamic identification of the suspension state. Combining fatigue damage accumulation theory and multimorphic fuzzy Bayesian network, it realizes dynamic assessment and real-time updating of fatigue damage risk of suspended submarine cables.

[0025] The method and related equipment for dynamic assessment of fatigue risk of submarine cable suspension provided in this application involve technical fields such as submarine cable safety assessment technology, machine learning, artificial intelligence, computer technology, and marine monitoring. The method for dynamic assessment of fatigue risk of submarine cable suspension provided in this application can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle-mounted terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application that implements the method for dynamic assessment of fatigue risk of submarine cable suspension, but is not limited to the above forms.

[0026] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0027] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0028] like Figure 1 The diagram shown is a schematic representation of an implementation environment provided in an embodiment of this application. (Refer to...) Figure 1 The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected via a network, either wirelessly or via a wired connection, to complete data transmission and exchange.

[0029] Server 101 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0030] Additionally, server 101 can also be a node server in a blockchain network. Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0031] Terminal 102 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc. It can also be a vehicle-mounted terminal of the various device types described above, but is not limited to these. Terminal 102 and server 101 can be directly or indirectly connected via wired or wireless communication, and this embodiment does not impose any limitations.

[0032] Exemplary based on Figure 1 The implementation environment shown in this application embodiment provides a dynamic assessment method for fatigue risk of submarine cable suspension. The following description uses the application of this dynamic assessment method for fatigue risk of submarine cable suspension in server 101 as an example. It can be understood that this method can also be applied to terminal 102.

[0033] Reference Figure 2 , Figure 2 This is a flowchart illustrating a dynamic assessment method for fatigue risk of submarine cable suspension applied to a server, provided in an embodiment of this application. The execution subject of this method can be any of the aforementioned computer devices (including a server or terminal). (Refer to...) Figure 2 The method may include the following steps S210-S250: S210. Obtain submarine cable routing information, hydrographic information, and marine monitoring data to construct the raw dataset; Information on submarine cable routes can be obtained through route surveys, which are comprehensive surveys conducted before the laying of submarine pipelines and cables. Core components include water depth and topography, seabed obstacles, geological structure, geological hazards, and hydrological and meteorological data. Hydrogeological data primarily comes from the national hydrological monitoring network and marine engineering survey reports, with varying levels of data availability across different regions. In submarine cable route surveys, marine hydrological data (temperature, salinity, tide level, ocean currents, etc.) is a core component, used to assess seabed stability and the corrosive environment.

[0034] S220. Construct the submarine cable node coordinates and define the submarine cable suspension discrimination index based on the original dataset; In some embodiments, step S220 may include: S2201. Establish a one-dimensional coordinate system along the length of the submarine cable, with the cable laying path as the m-axis, and divide the submarine cable into multiple nodes at equal intervals along the m-axis. S2202. The y-axis is the direction parallel to the mean seabed surface and perpendicular to the m-axis, and the z-axis is the direction of the seabed normal. S2203. Obtain the submarine cable depth at the node and the corresponding seabed depth; S2204. Calculate the suspension discrimination index based on the water depth of the submarine cable and the water depth of the seabed.

[0035] Specifically, in the process of establishing the coordinates of submarine cable nodes and determining the suspension state in this embodiment of the application, a one-dimensional coordinate system can be established along the length of the submarine cable, with the cable laying path as the reference point. m Axis, along the submarine cable m The axis is divided into 1000 equally spaced nodes. These nodes are parallel to the mean seabed surface and perpendicular to... m The direction of the axis is y The axis is defined by the direction of the seabed normal. z Axis. Define nodes. i The submarine cable is located at a depth of [missing information]. Z i The seabed depth at the corresponding location is Z bi . Z i and Z bi The data can be obtained through field measurements using seabed topography and cable attitude scanning methods such as multibeam bathymetry, side-scan sonar, and shallow seismic profiling. It can also be obtained by directly extracting route survey records, attitude monitoring data, and burial depth archives from the cable laying and installation process. Define the suspension discrimination index. for: = - (1) when When the value is greater than 0, it indicates that the cable node is located below the seabed, either buried or in contact with the seabed, and is therefore classified as a non-suspension cable. When the value is ≤0, it indicates that the cable node is exposed above the seabed and detached from the seabed, and is judged as a suspended cable. The determination of the suspended cable status is shown in the attached figure. Figure 5 As shown, by collecting and comparing node coordinate data at different time points, the length of the suspended span, the height of the suspension, and their changes over time were determined. S230. Based on the cable node coordinates and the cable suspension discrimination index, determine the suspension status information of the target submarine cable and calculate the dynamic suspension migration rate of the target submarine cable. Among them, the core indicators for judging the suspension of submarine cables can be the suspension length, sag ratio and vortex-induced vibration risk parameters. In engineering, the threshold for initiating intervention is usually set when the suspension length exceeds the critical value (usually 5 to 10m, which requires evaluation; >20m is high risk) or the sag / span ratio is <0.01 to 0.02.

[0036] For example, some of the core criteria include: span length (L): the continuous span of the submarine cable detached from the seabed; generally, fatigue risk monitoring is required when L ≥ 5~10m, and L>20m (depending on tension and flow velocity) is considered high risk and needs to be addressed; the critical span length can be calculated to avoid vortex-induced resonance (the reference value for pipelines under simple support is about 28.4m, and submarine cables need to be calculated specifically due to their flexibility).

[0037] Sag ratio (e / L): The ratio of sag (e) at the midpoint of the span to the span length (L). e / L < 0.01~0.02 indicates that the submarine cable is in a high-tension "string" state, with little influence from bending stiffness, and is prone to vortex-induced vibration; if the sag is too large, it may come into contact with the seabed and cause wear.

[0038] Strocha number to frequency ratio: eddy current shedding frequency (fs=St V / Dfs=St The ratio of V / D to the natural frequency of the submarine cable (fn). fs / fn ≈ 0.8 1.2fs / fn≈0.8 The 1.2 interval is identified as a risk zone for vortex-induced vibration (VIV) resonance, which is crucial for dynamic identification.

[0039] Maximum curvature and stress: Maximum curvature and cyclic stress occur at both ends of the span (separation point from the seabed). If the calculated fatigue life is lower than the design threshold (e.g., <1 year after introducing a safety factor), or if plastic yielding occurs (e.g., the conductor layer L>55m may yield under a 50-year return period condition), it is considered a failure risk.

[0040] In some embodiments, step S230 may include the following steps S2301-S2303: S2301. When the suspension discrimination index is greater than 0, it means that the cable node is located below the seabed and is buried or in contact with the seabed, and is judged as a non-suspension state; when the suspension discrimination index is less than or equal to 0, it means that the cable node is exposed above the seabed and is detached from the seabed, and is judged as a fixed suspension state. The fatigue analysis for the fixed suspension state includes: S23011. By distinguishing the dynamic response and vortex-induced vibration of the suspended section, the fixed suspended submarine cable is simplified into an elastic beam constrained at both ends. Combining the suspension length, cable outer diameter, effective mass per unit length, structural damping and seabed constraint conditions, the natural frequency and mode shape of the suspended section are calculated, and then it is determined whether the suspended section has vortex-induced vibration in the downstream and transverse directions, and the dominant vibration mode and steady-state response amplitude are identified. S23012. Based on environmental parameters such as ocean current-induced bottom current velocity, wave-induced bottom current velocity amplitude, and wave period, calculate the bending stress of key sections of the suspended span to obtain the alternating stress amplitude caused by vortex-induced vibration and wave load. S23013. Calculate the total fatigue damage degree according to Miners' linear cumulative damage criterion. S23014. The determination of the fatigue failure threshold is as follows: when the total fatigue damage is less than 1, the fatigue damage of the fixed suspension section has not reached the threshold, and the structure is safe; when the total fatigue damage is greater than or equal to 1, the suspension section is determined to have fatigue failure, reaching the fatigue failure threshold condition.

[0041] S2302. The suspension migration rate is directly obtained through multiple phases of on-site measurement of seabed topography and cable attitude. Alternatively, S2303, the suspension migration rate is determined through numerical simulation of sand wave motion and dynamic evolution simulation of seabed topography. Specifically, this step involves determining the suspension migration rate as the rate of sand wave migration along the pipeline length direction based on the ratio of the migration distance of the sand wave characteristic points driving the cable suspension along the pipeline length direction to the monitoring cycle duration within two adjacent monitoring cycles. The formula for calculating the suspension migration rate is as follows: = / ,in, for Hovering mobility; This represents the migration distance of the corresponding sand wave feature point along the pipeline length between adjacent monitoring cycles. This represents the time interval between two consecutive monitoring sessions.

[0042] Specifically, the embodiments of this application can conduct fatigue damage analysis of submarine cables under fixed suspension conditions in accordance with the DNV-RP-F105 "Free spanning pipelines" specification, which is used to quantify the fatigue risk of static suspension sections under the combined action of waves and currents, and provide a basis for judgment for subsequent dynamic suspension migration analysis and multi-mode fuzzy Bayesian network evaluation.

[0043] 1) Dynamic response and vortex-induced vibration (VIV) discrimination of the suspended section: The fixed suspended submarine cable is simplified as an elastic beam constrained at both ends, combined with the suspension length. L Outer diameter of submarine cable d Calculate the natural frequency and mode shape of the suspended span, considering the effective mass per unit length, structural damping, and seabed constraints; and calculate the converted velocity according to specifications under the combined action of bottom current and waves. V R , Keulegan-Carpenter number ( KC(Number) to determine whether vortex-induced vibration occurs in the downstream and transverse directions of the suspended span, and to identify the dominant vibration mode and steady-state response amplitude.

[0044] 2) The alternating stress amplitude calculation is based on the hydrodynamic load model and beam theory recommended by DNV-RP-F105. Environmental parameters such as current-induced bottom current velocity, wave-induced bottom current velocity amplitude, and wave period are input to calculate the bending stress at key sections of the suspended span, thus obtaining the alternating stress amplitude caused by vortex-induced vibration and wave load. σ a .

[0045] 3) Fatigue damage accumulation calculation: Combining the unique SN curves of each layer of the submarine cable, the total fatigue damage is calculated based on the Miners linear cumulative damage criterion. D The calculation formula is: D =Σ( / (2) In the formula: For the first i The number of fatigue cycles corresponding to the stress amplitude; For the first i The permissible number of cycles for fatigue failure of a submarine cable under a stress amplitude of level 1.

[0046] 4. The critical fatigue failure condition is determined according to the DNV-RP-F105 Fatigue Limit State (FLS) criterion: when the total fatigue damage degree... D When <1, the fatigue damage of the fixed suspension segment has not reached the critical point, and the structure is safe; when D When the value is ≥1, fatigue failure is determined to have occurred in the suspended segment, reaching the critical condition for fatigue failure.

[0047] Furthermore, it should be noted that seafloor sand wave movement, seabed erosion and deposition, and dynamic topographic changes are the core factors driving the dynamic migration of the cable suspension location, distribution range, and suspension morphology over time. Influenced by continuous hydrodynamic forces and seabed topographic evolution, the suspension state of cable nodes repeatedly switches between adjacent monitoring periods, leading to non-uniform and dynamically cumulative fatigue damage. The suspension migration rate is used to quantify the degree of dynamic change in the suspension location over time. α It can be obtained directly through on-site measurements of seabed topography and cable attitude over multiple periods, or determined through numerical simulations of sand wave movement and dynamic evolution simulations of seabed topography. Define the suspended migration rate. α The migration rate of the sand wave along the pipeline length is the ratio of the migration distance of the sand wave feature point driving the submarine cable across the pipeline along the pipeline length to the monitoring cycle duration within two adjacent monitoring cycles. The calculation formula is as follows: = / (3) in, ΔL The distance (in meters) that corresponds to the sand wave feature point migrates along the pipeline length between adjacent monitoring cycles. ΔT The time interval between two consecutive monitoring sessions (in years).

[0048] S240. Based on the suspension state information and the dynamic suspension migration rate, perform risk-based event identification and node risk state classification, and then construct a multimorphic fuzzy Bayesian network. Specifically, the identification of risk-based events includes: S2401. Based on the fatigue damage mechanism of suspended cables, six bottom events affecting fatigue failure of suspended submarine cables are identified as risk root nodes; wherein, the risk root nodes include: the first node determined based on the ratio of the suspended length to the diameter; the second node determined based on the ratio of the suspended height to the diameter; the third node determined based on the bottom current velocity induced by ocean currents; the fourth node determined based on the bottom current velocity induced by waves; and the fifth node determined based on the wave period. S2402. Determine the first intermediate event based on the cumulative damage value of the lead sheath, determine the second intermediate event based on the cumulative damage value of the armor layer, and determine the third intermediate event based on the cumulative damage value of the copper conductor. S2403. Determine the top event based on the fatigue failure of the suspended submarine cable.

[0049] The node risk status classification includes: S2404. Based on the principle of minimum reasonable feasibility, the risk status of each risk root node is divided into three levels: high risk, medium risk, and low risk, and the risk leaf nodes are divided into damaged state and undamaged state.

[0050] For example, this application embodiment identifies six bottom events affecting the fatigue failure of suspended submarine cables as risk root nodes based on the suspension fatigue damage mechanism: X 1—The ratio of the span length to the diameter ( L / d ); X 2—The ratio of the suspended height to the diameter ( G / d ); X 3—Ocean Current-Induced Bottom Current Velocity ( ); X 4—Wave-induced bottom current velocity ( X5—Wave cycle ( X6—Suspension mobility ( Intermediate events: Y1—lead sheath Miner cumulative damage value; Y2—armor layer Miner cumulative damage value; Y3—copper conductor Miner cumulative damage value. Top event T is fatigue failure of the suspension cable.

[0051] Then, based on the minimum reasonable feasibility principle, the risk status of each root node is divided into three levels: "high risk," "medium risk," and "low risk," denoted as R1, R2, and R3, respectively. Leaf nodes T are divided into two states: "damaged" and "undamaged."

[0052] In some embodiments, the construction process of the polymorphic fuzzy Bayesian network includes: The trapezoidal fuzzy evaluation method with seven levels of linguistic variables is used to obtain the prior probability of each risk root node; Based on the load strength index and the damage index affecting the structure, the vulnerability curve of the structure is plotted, and the damage probability of each leaf node is calculated. Based on the prior probability of the root node and the damage probability of the leaf node, a fault tree model with fatigue failure of the suspended submarine cable as the top event is established. The top event is mapped to the leaf node of the Bayesian network, the intermediate inference node is mapped to the intermediate node, the bottom event is mapped to the root node, and the logical relationship in the fault tree is mapped to the directed edge, thus constructing a complete polymorphic fuzzy Bayesian network model.

[0053] Specifically, in this embodiment, prior probability and conditional probability are first calculated: 1) The trapezoidal fuzzy evaluation method with seven levels of linguistic variables is used to obtain the prior probabilities of each root node. Trapezoidal fuzzy numbers The membership function is: (4) The seven levels of linguistic variables include “Very High (VH)”, “High (H)”, “Relatively High (RH)”, “Medium (M)”, “Relatively Low (RL)”, “Low (L)”, and “Very Low (VL)”, which correspond to the trapezoidal fuzzy number intervals, respectively.

[0054] Several experts were invited to conduct a linguistic evaluation of the probability of each root node being in each risk state. Let the total number of invited experts be... m Several experts participated in the evaluation, the first u The normalized weights of the experts are calculated using the following formula: (5) in The weighted score is determined by a comprehensive evaluation based on the expert's professional title, education, years of service, and time spent engaged in relevant research.

[0055] No. u The expert and the first v The similarity of the risk status assessments of a certain node by the experts is as follows: (6) In the formula, and These represent the trapezoidal fuzzy number evaluation intervals given by the two experts. Similarity is calculated pairwise for all experts to construct a similarity matrix. AM .

[0056] No. u Weighted consensus of experts Relative protocol degree and consensus coefficient The calculations are as follows: (7) (8) (9) In the formula, β Let be the relaxation factor, 0 ≤ β ≤1, used to balance the relative importance of expert self-weight and consensus, taking... β =0.5.

[0057] The aggregated total fuzzy number is: (10) The centroid method is used to defuzzify the aggregated fuzzy numbers, resulting in the fuzzy failure score (FFS). (11) Convert fuzzy failure scores into fuzzy failure probabilities FFP : (12) (13) Suppose a root node has k There are several risk states, and the fuzzy failure probability of each state is... Then the node is in the th position. i The prior probability of the state is: (14) 2) Calculation of conditional probability table for non-root nodes: The conditional probability table for leaf node T is calculated using the Leaky Noisy-Max model. Leaf node T has 6 parent nodes: , ,..., The influence mechanisms of each parent node on T are independent. A leaf node T has two states, denoted as... These represent "not destroyed" and "destroyed," respectively. First, determine the cumulative conditional probability of T under the individual influence of each parent node: (15) because: (16) The formula can be rewritten as follows: (17) Finally, we can derive the following formula for calculating the CPT of child nodes: (18) 3) Referring to the logical concepts of seismic vulnerability analysis, the results of numerical simulation calculations can be incorporated into conditional probability calculations. First, it is necessary to determine a suitable load intensity measure (abbreviated as...). IM Based on this load, the damage measure (or simply damage index) affecting the structure is determined. DM Then, the vulnerability curve of the structure can be plotted, thereby assessing the probability of damage to the structure under different external load intensity levels.

[0058] In vulnerability analysis calculations, it is generally assumed that the vulnerability curve follows a two-parameter log-normal distribution, and its calculation function can be defined as: (19) in, It is a characteristic parameter of a defined load. S Under different conditions, the structure reaches or exceeds a specific damage state. The probability of; Φ The standard normal cumulative probability function is used by the model to establish a quantitative relationship between the external load characteristic parameters and the probability of exceeding the damage state. Its mathematical essence is to describe the probability distribution function of the probability of exceeding a specific damage state as the load characteristic parameters change when the external load parameters follow a log-normal distribution. Indicates causing the first i Load characteristic parameters required for Level 1 damage state S The median value of the threshold; The total log-normal standard deviation is used to describe the total variability associated with each vulnerability curve, and its calculation formula is: (20) The three main sources of uncertainty considered in the formula are: The uncertainty characterizing the structural damage state is taken as 0.4, based on the recommendations for earthquake disaster loss risk assessment. Representing the uncertainty of structural dynamic response and bearing capacity changes, based on the analysis of excavated tunnels, a value of 0.3 is recommended; and different external load input deviations. , which is the average standard deviation of the fitting function of the structural damage obtained under load, is calculated as follows: (twenty one) in, It is the first i One actual value (numerical calculation result); It is the first i A predicted value calculated based on the fitting formula; n It is the number of samples; k It represents the number of parameters estimated in the fitted model.

[0059] Regression analysis was performed on the load and structural damage data obtained from numerical simulation to obtain a fitted curve, combined with the median values ​​of the structural damage index under different states. Substitute this value into DM and IM The corresponding damage state can be obtained from the fitted curve relationship of the index. Therefore, based on the above formula, the damage probability can be calculated, and the corresponding vulnerability curve can be plotted. Based on this probability, the conditional probability table of MFBN can be further calculated according to the Leaky Noisy-Max model and the formula.

[0060] 4) Fault Tree to Bayesian Network Mapping: A fault tree model is established with fatigue failure of the suspended submarine cable as the top event. The top event is mapped to the leaf node of the Bayesian network, intermediate inference nodes are mapped to intermediate nodes, and bottom events are mapped to the root node. Logical relationships in the fault tree are mapped to directed edges. A complete polymorphic fuzzy Bayesian network model is constructed. The structure of the polymorphic fuzzy Bayesian network is shown in the attached figure. Figure 3 As shown.

[0061] S250. Perform dynamic fatigue risk assessment on the target submarine cable based on the polymorphic fuzzy Bayesian network to obtain the risk assessment result.

[0062] Specifically, this application embodiment uses a constructed polymorphic fuzzy Bayesian network to conduct dynamic risk assessment and real-time updates of fatigue failure of suspended submarine cables. The core is to rely on the dynamic evolution of the suspended state and the linear accumulation characteristics of fatigue damage to achieve dynamic tracking of fatigue risk throughout the cable's entire lifecycle. The suspended state of a submarine cable is significantly time-varying, driven by sand wave movement and seabed erosion and deposition. The same cable node or section exhibits three typical dynamic characteristics: a node is suspended in one year and becomes non-suspended the following year due to seabed siltation; a suspended section remains suspended from one year to the following year; a node is non-suspended in one year and forms a new suspended state the following year due to seabed erosion. Because fatigue damage is irreversible, it continuously accumulates according to the Miner linear accumulation damage principle. Suspended fatigue damage in different time periods and sections accumulates periodically, and traditional static assessments cannot reflect this true evolutionary process. Based on the established polymorphic fuzzy Bayesian network, a causal inference algorithm is used to calculate the probability of the top event being in a "failure" state, achieving a quantitative assessment of the fatigue failure risk of suspended submarine cables. When new monitoring data is obtained, the cumulative fatigue damage of each node is first calculated based on the principle of linear superposition. Then, the updated measured values ​​of the suspension geometry parameters and marine environmental parameters are classified according to the node state intervals, the posterior probability of the corresponding root node is updated, and the probability distribution of each node is updated through forward inference of the Bayesian network. The cumulative fatigue damage results of each section of the submarine cable along the entire line are corrected simultaneously, thereby realizing real-time updates and full-process tracking of the dynamic evolution of fatigue risk with the suspension state.

[0063] The implementation process of the embodiments of this application in specific scenarios will be described in detail below with reference to the accompanying drawings: refer to Figure 4 The method for dynamic risk assessment of submarine cable suspension fatigue based on multimorphic fuzzy Bayesian networks provided in this application includes the following steps: AE: A. Establishment of submarine cable node coordinates and determination of suspension status: A one-dimensional coordinate system is established along the length of the submarine cable, with the cable laying path as the reference point. m Axis, along the submarine cable m The axis is divided into 1000 equally spaced nodes. These nodes are parallel to the mean seabed surface and perpendicular to... m The direction of the axis is y The axis is defined by the direction of the seabed normal. z Axis. Define nodes. i The submarine cable is located at a depth of [missing information]. Z i The seabed depth at the corresponding location is Z bi . Z i and Z biThe data can be obtained through field measurements using seabed topography and cable attitude scanning methods such as multibeam bathymetry, side-scan sonar, and shallow seismic profiling. It can also be obtained by directly extracting route survey records, attitude monitoring data, and burial depth archives from the cable laying and installation process. Define the suspension discrimination index. for: = - (1) when When the value is greater than 0, it indicates that the cable node is located below the seabed, either buried or in contact with the seabed, and is therefore classified as a non-suspension cable. When the value is ≤0, it indicates that the cable node is exposed above the seabed and detached from the seabed, and is judged as a suspended cable. The determination of the suspended cable status is shown in the attached figure. Figure 5 As shown, by collecting and comparing node coordinate data at different time points, the length of the suspended span, the height of the suspension, and their changes over time were determined.

[0064] B. Fatigue analysis of fixed suspension span: Fatigue damage analysis of submarine cables under fixed suspension conditions was carried out in accordance with DNV-RP-F105 "Free spanning pipelines" standard. This analysis was used to quantify the fatigue risk of static suspension sections under the combined action of waves and currents, and to provide a basis for subsequent dynamic suspension migration analysis and multi-mode fuzzy Bayesian network evaluation.

[0065] 1) Dynamic response and vortex-induced vibration (VIV) discrimination of the suspended section: The fixed suspended submarine cable is simplified as an elastic beam constrained at both ends, combined with the suspension length. L Outer diameter of submarine cable d Calculate the natural frequency and mode shape of the suspended span, considering the effective mass per unit length, structural damping, and seabed constraints; and calculate the converted velocity according to specifications under the combined action of bottom current and waves. V R , Keulegan-Carpenter number ( KC (Number) to determine whether vortex-induced vibration occurs in the downstream and transverse directions of the suspended span, and to identify the dominant vibration mode and steady-state response amplitude.

[0066] 2) The alternating stress amplitude calculation is based on the hydrodynamic load model and beam theory recommended by DNV-RP-F105. Environmental parameters such as current-induced bottom current velocity, wave-induced bottom current velocity amplitude, and wave period are input to calculate the bending stress at key sections of the suspended span, thus obtaining the alternating stress amplitude caused by vortex-induced vibration and wave load. σ a .

[0067] 3) Fatigue damage accumulation calculation: Combining the unique SN curves of each layer of the submarine cable, the total fatigue damage is calculated based on the Miners linear cumulative damage criterion. D The calculation formula is: D =Σ( / (2) In the formula: For the first i The number of fatigue cycles corresponding to the stress amplitude; For the first i The permissible number of cycles for fatigue failure of a submarine cable under a stress amplitude of level 1.

[0068] 4) The critical fatigue failure condition is determined according to the DNV-RP-F105 Fatigue Limit State (FLS) criterion: when the total fatigue damage degree... D When <1, the fatigue damage of the fixed suspension segment has not reached the critical point, and the structure is safe; when D When the value is ≥1, fatigue failure is determined to have occurred in the suspended segment, reaching the critical condition for fatigue failure.

[0069] C. Dynamic dangling mobility estimation: Submarine wave movement, seabed erosion and deposition, and dynamic topographic changes are the core factors driving the dynamic migration of the cable suspension location, distribution range, and suspension morphology over time. Influenced by continuous hydrodynamic forces and seabed topographic evolution, the suspension state of cable nodes repeatedly switches between adjacent monitoring periods, leading to non-uniform and dynamically cumulative fatigue damage. The suspension migration rate is used to quantify the degree of dynamic change in the suspension location over time. α It can be obtained directly through on-site measurements of seabed topography and cable attitude over multiple periods, or determined through numerical simulations of sand wave movement and dynamic evolution simulations of seabed topography. Define the suspended migration rate. α The migration rate of the sand wave along the pipeline length is the ratio of the migration distance of the sand wave feature point driving the submarine cable across the pipeline along the pipeline length to the monitoring cycle duration within two adjacent monitoring cycles. The calculation formula is as follows: = / (3) in, ΔL The distance (in meters) that corresponds to the sand wave feature point migrates along the pipeline length between adjacent monitoring cycles. ΔT The time interval between two consecutive monitoring sessions (in years).

[0070] D. Construction of polymorphic fuzzy Bayesian networks: D.1 Fault tree determination: Based on the fatigue damage mechanism of suspended submarine cables, six bottom events affecting fatigue failure of suspended submarine cables were identified as risk root nodes: X 1—The ratio of the span length to the diameter ( L / d ); X 2—The ratio of the suspended height to the diameter ( G / d ); X 3—Ocean Current-Induced Bottom Current Velocity ( ); X 4—Wave-induced bottom current velocity ( X5—Wave cycle ( X6—Suspension mobility ( Intermediate events: Y1—lead sheath Miner cumulative damage value; Y2—armor layer Miner cumulative damage value; Y3—copper conductor Miner cumulative damage value. Top event T is fatigue failure of the suspension cable.

[0071] D.2. Node Risk Status Classification: Based on the minimum reasonable feasibility principle, the risk status of each root node is divided into three levels: "high risk," "medium risk," and "low risk," denoted as R1, R2, and R3, respectively. Leaf nodes T are divided into two states: "damaged" and "undamaged."

[0072] D.3 Calculation of prior probability and conditional probability: 1) The trapezoidal fuzzy evaluation method with seven levels of linguistic variables is used to obtain the prior probabilities of each root node. Trapezoidal fuzzy numbers The membership function is: (4) The seven levels of linguistic variables include “Very High (VH)”, “High (H)”, “Relatively High (RH)”, “Medium (M)”, “Relatively Low (RL)”, “Low (L)”, and “Very Low (VL)”, which correspond to the trapezoidal fuzzy number intervals, respectively.

[0073] Several experts were invited to conduct a linguistic evaluation of the probability of each root node being in each risk state. Let the total number of invited experts be... m Several experts participated in the evaluation, the first u The normalized weights of the experts are calculated using the following formula: (5) in The weighted score is determined by a comprehensive evaluation based on the expert's professional title, education, years of service, and time spent engaged in relevant research.

[0074] No. u The expert and the first v The similarity of the risk status assessments of a certain node by the experts is as follows: (6) In the formula, and These represent the trapezoidal fuzzy number evaluation intervals given by the two experts. Similarity is calculated pairwise for all experts to construct a similarity matrix. AM .

[0075] No. u Weighted consensus of experts Relative protocol degree and consensus coefficient The calculations are as follows: (7) (8) (9) In the formula, β Let be the relaxation factor, 0 ≤ β ≤1, used to balance the relative importance of expert self-weight and consensus, taking... β =0.5.

[0076] The aggregated total fuzzy number is: (10) The centroid method is used to defuzzify the aggregated fuzzy numbers, resulting in the fuzzy failure score (FFS). (11) Convert fuzzy failure scores into fuzzy failure probabilities FFP : (12) (13) Suppose a root node has k There are several risk states, and the fuzzy failure probability of each state is... Then the node is in the th position. i The prior probability of the state is: (14) 2) Calculation of conditional probability table for non-root nodes: The conditional probability table for leaf node T is calculated using the Leaky Noisy-Max model. Leaf node T has 6 parent nodes: , ,..., The influence mechanisms of each parent node on T are independent. A leaf node T has two states, denoted as... These represent "not destroyed" and "destroyed," respectively. First, determine the cumulative conditional probability of T under the individual influence of each parent node: (15) because: (16) The formula can be rewritten as follows: (17) Finally, we can derive the following formula for calculating the CPT of child nodes: (18) 3) Referring to the logical concepts of seismic vulnerability analysis, the results of numerical simulation calculations can be incorporated into conditional probability calculations. First, it is necessary to determine a suitable load intensity index (abbreviated as...). IM Based on this load, the damage measure (or simply damage index) affecting the structure is determined. DM Then, the vulnerability curve of the structure can be plotted, thereby assessing the probability of damage to the structure under different external load intensity levels.

[0077] In vulnerability analysis calculations, it is generally assumed that the vulnerability curve follows a two-parameter log-normal distribution, and its calculation function can be defined as: (19) in, It is a characteristic parameter of a defined load. S Under different conditions, the structure reaches or exceeds a specific damage state. The probability of; Φ The standard normal cumulative probability function is used by the model to establish a quantitative relationship between the external load characteristic parameters and the probability of exceeding the damage state. Its mathematical essence is to describe the probability distribution function of the probability of exceeding a specific damage state as the load characteristic parameters change when the external load parameters follow a log-normal distribution. Indicates causing the first i Load characteristic parameters required for Level 1 damage state S The median value of the threshold; The total log-normal standard deviation is used to describe the total variability associated with each vulnerability curve, and its calculation formula is: (20) The three main sources of uncertainty considered in the formula are: The uncertainty characterizing the structural damage state is taken as 0.4, based on the recommendations for earthquake disaster loss risk assessment. Representing the uncertainty of structural dynamic response and bearing capacity changes, based on the analysis of excavated tunnels, a value of 0.3 is recommended; and different external load input deviations. , which is the average standard deviation of the fitting function of the structural damage obtained under load, is calculated as follows: (twenty one) in, It is the first i One actual value (numerical calculation result); It is the first i A predicted value calculated based on the fitting formula; n It is the number of samples; k It represents the number of parameters estimated in the fitted model.

[0078] Regression analysis was performed on the load and structural damage data obtained from numerical simulation to obtain a fitted curve, combined with the median values ​​of the structural damage index under different states. Substitute this value into DM and IM The corresponding damage state can be obtained from the fitted curve relationship of the index. Therefore, based on the above formula, the damage probability can be calculated, and the corresponding vulnerability curve can be plotted. Based on this probability, the conditional probability table of MFBN can be further calculated according to the Leaky Noisy-Max model and the formula.

[0079] 4) Fault Tree to Bayesian Network Mapping: A fault tree model is established with fatigue failure of the suspended submarine cable as the top event. The top event is mapped to a leaf node of the Bayesian network, intermediate inference nodes are mapped to intermediate nodes, and bottom events are mapped to root nodes. Logical relationships in the fault tree are mapped to directed edges. A complete polymorphic fuzzy Bayesian network model is constructed. The structure of the polymorphic fuzzy Bayesian network is shown in the attached figure. Figure 3 As shown.

[0080] E. Dynamic fatigue risk assessment and updating: This step, based on the constructed polymorphic fuzzy Bayesian network, conducts dynamic risk assessment and real-time updates of fatigue failure of suspended submarine cables. The core is to leverage the dynamic evolution of the suspension state and the linear accumulation characteristics of fatigue damage to achieve dynamic tracking of fatigue risk throughout the cable's entire lifecycle. The suspension state of submarine cables exhibits significant time-varying characteristics driven by sand wave movement and seabed erosion and deposition. The same cable node or section can display three typical dynamic features: a node is suspended in one year and becomes non-suspended the following year due to seabed siltation; a suspended section remains suspended from one year to the following year; a node is non-suspended in one year and forms a new suspension the following year due to seabed erosion. Because fatigue damage is irreversible, it continuously accumulates according to the Miner linear accumulation damage principle. Suspension fatigue damage in different time periods and sections will accumulate periodically, and traditional static assessments cannot reflect this true evolutionary process. Based on the established polymorphic fuzzy Bayesian network, a causal inference algorithm is used to calculate the probability of the top event being in a "failure" state, achieving a quantitative assessment of the fatigue failure risk of suspended submarine cables. When new monitoring data is obtained, the cumulative fatigue damage of each node is first calculated based on the principle of linear superposition. Then, the updated measured values ​​of the suspension geometry parameters and marine environmental parameters are classified according to the node state intervals, the posterior probability of the corresponding root node is updated, and the probability distribution of each node is updated through forward inference of the Bayesian network. The cumulative fatigue damage results of each section of the submarine cable along the entire line are corrected simultaneously, thereby realizing real-time updates and full-process tracking of the dynamic evolution of fatigue risk with the suspension state.

[0081] In summary, the risk assessment method provided in this application fully considers the dynamic migration of suspended cables and the cumulative effect of fatigue damage, and has the ability to handle uncertainty and update in real time. This method achieves dynamic identification of the suspended cable state by establishing a node coordinate discrimination system, and combines fatigue damage accumulation theory and multimorphic fuzzy Bayesian networks to achieve dynamic assessment and real-time updating of the fatigue failure risk of suspended submarine cables.

[0082] refer to Figure 6 Another aspect of this application provides a dynamic assessment device 600 for fatigue risk of submarine cable suspension, comprising: The first module 601 is used to acquire submarine cable routing information, hydrological address information and marine monitoring data to construct the raw dataset; The second module 602 is used to construct the submarine cable node coordinates and define the submarine cable suspension discrimination index based on the original dataset. The third module 603 is used to determine the suspension status information of the target submarine cable based on the cable node coordinates and the cable suspension discrimination index, and to calculate the dynamic suspension migration rate of the target submarine cable. The fourth module 604 is used to identify risk-based events and classify node risk states based on the suspension state information and the dynamic suspension migration rate, thereby constructing a multimorphic fuzzy Bayesian network. The fifth module 605 is used to perform dynamic fatigue risk assessment on the target submarine cable based on the polymorphic fuzzy Bayesian network, and obtain the risk assessment result.

[0083] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0084] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned dynamic assessment method for fatigue risk of submarine cable suspension. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0085] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0086] Please see Figure 7 , Figure 7 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 702 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 702 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 702 and is called and executed by the processor 701 using the dynamic assessment method for fatigue risk of submarine cable suspension in the embodiments of this application. The input / output interface 703 is used to implement information input and output; The communication interface 704 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 705 transmits information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704); The processor 701, memory 702, input / output interface 703, and communication interface 704 are connected to each other within the device via bus 705.

[0087] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described dynamic assessment method for fatigue risk of submarine cable suspension.

[0088] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0089] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0090] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0091] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0092] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0093] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0094] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0095] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0096] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0097] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks. The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A dynamic assessment method for fatigue risk of submarine cable suspension, characterized in that, include: Acquire submarine cable routing information, hydrographic information, and marine monitoring data to construct a raw dataset; Based on the original dataset, construct the coordinates of submarine cable nodes and define the submarine cable suspension discrimination index; Based on the cable node coordinates and the cable suspension discrimination index, the suspension status information of the target submarine cable is determined, and the dynamic suspension migration rate of the target submarine cable is calculated. Based on the slack state information and the dynamic slack migration rate, risk-based events are identified and node risk states are divided, thereby constructing a multimorphic fuzzy Bayesian network. The target submarine cable is subjected to dynamic fatigue risk assessment based on the polymorphic fuzzy Bayesian network, and the risk assessment results are obtained.

2. The method for dynamic assessment of fatigue risk of submarine cable suspension as described in claim 1, characterized in that, The step of constructing submarine cable node coordinates and defining submarine cable suspension discrimination indicators based on the original dataset includes: A one-dimensional coordinate system is established along the length of the submarine cable, with the cable laying path as the m-axis, and the cable is divided into multiple nodes at equal intervals along the m-axis. The y-axis is defined as the direction parallel to the mean seabed surface and perpendicular to the m-axis, and the z-axis is defined as the direction normal to the seabed. Obtain the submarine cable depth at the node and the corresponding seabed depth; Based on the water depth of the submarine cable and the water depth of the seabed, the suspension discrimination index is calculated.

3. The method for dynamic assessment of fatigue risk of submarine cable suspension as described in claim 2, characterized in that, The step of determining the suspension status information of the target submarine cable based on the cable node coordinates and the cable suspension discrimination index includes: When the suspension discrimination index is greater than 0, it means that the cable node is located below the seabed and is either buried or in contact with the seabed, and is judged as a non-suspension state; when the suspension discrimination index is less than or equal to 0, it means that the cable node is exposed above the seabed and is detached from the seabed, and is judged as a fixed suspension state. The fatigue analysis for the fixed suspension state includes: By analyzing the dynamic response and vortex-induced vibration of the suspended section, the fixed suspended submarine cable is simplified into an elastic beam constrained at both ends. By combining the suspension length, cable outer diameter, effective mass per unit length, structural damping, and seabed constraint conditions, the natural frequency and mode shape of the suspended section are calculated, and it is then determined whether the suspended section experiences vortex-induced vibration in the downstream and transverse directions, and the dominant vibration mode and steady-state response amplitude are identified. Based on environmental parameters such as ocean current-induced bottom current velocity, wave-induced bottom current velocity amplitude, and wave period, the bending stress of key sections of the suspended span is calculated, and the alternating stress amplitude caused by vortex-induced vibration and wave load is obtained. The total fatigue damage was calculated based on the Miners linear cumulative damage criterion. The criteria for determining the fatigue failure threshold are as follows: when the total fatigue damage is less than 1, the fatigue damage of the fixed suspension section has not reached the critical level, and the structure is safe; when the total fatigue damage is greater than or equal to 1, the suspension section is determined to have experienced fatigue failure, reaching the critical condition for fatigue failure.

4. The method for dynamic assessment of fatigue risk of submarine cable suspension as described in claim 1, characterized in that, The calculation of the dynamic suspension migration rate of the target submarine cable includes: The suspension migration rate was directly obtained through multiple phases of on-site measurements of seabed topography and cable attitude. Alternatively, the suspension migration rate can be determined through numerical simulation of sand wave motion and dynamic evolution simulation of seabed topography. Specifically, this step involves determining the suspension migration rate as the rate of sand wave migration along the pipeline length direction based on the ratio of the migration distance of the sand wave characteristic points driving the cable suspension along the pipeline length direction to the monitoring cycle duration within two adjacent monitoring cycles. The formula for calculating the suspension migration rate is as follows: = / ,in, for Hovering mobility; This represents the migration distance of the corresponding sand wave feature point along the pipeline length between adjacent monitoring cycles. This represents the time interval between two consecutive monitoring sessions.

5. The method for dynamic assessment of fatigue risk of submarine cable suspension as described in claim 1, characterized in that, The identification of risk-low events includes: Based on the fatigue damage mechanism of suspended cables, six bottom events affecting fatigue failure of suspended submarine cables were identified as risk root nodes. These risk root nodes include: a first node determined by the ratio of the suspended length to the diameter; a second node determined by the ratio of the suspended height to the diameter; a third node determined by the bottom current velocity induced by ocean currents; a fourth node determined by the bottom current velocity induced by waves; and a fifth node determined by the wave period. The first intermediate event is determined based on the cumulative damage value of the lead sheath, the second intermediate event is determined based on the cumulative damage value of the armor layer, and the third intermediate event is determined based on the cumulative damage value of the copper conductor. The top event is determined based on fatigue failure of the suspended submarine cable.

6. The method for dynamic assessment of fatigue risk of submarine cable suspension as described in claim 5, characterized in that, The node risk status classification includes: Based on the principle of minimum reasonable feasibility, the risk status of each risk root node is divided into three levels: high risk, medium risk, and low risk, and the risk leaf nodes are divided into damaged state and undamaged state.

7. The method for dynamic assessment of fatigue risk of submarine cable suspension as described in claim 1, characterized in that, The construction process of the polymorphic fuzzy Bayesian network includes: The trapezoidal fuzzy evaluation method with seven levels of linguistic variables is used to obtain the prior probability of each risk root node; Based on the load strength index and the damage index affecting the structure, the vulnerability curve of the structure is plotted, and the damage probability of each leaf node is calculated. Based on the prior probability of the root node and the damage probability of the leaf node, a fault tree model with fatigue failure of the suspended submarine cable as the top event is established. The top event is mapped to the leaf node of the Bayesian network, the intermediate inference node is mapped to the intermediate node, the bottom event is mapped to the root node, and the logical relationship in the fault tree is mapped to the directed edge, thus constructing a complete polymorphic fuzzy Bayesian network model.

8. A dynamic assessment device for fatigue risk of submarine cable suspension, characterized in that, include: The first module is used to acquire submarine cable routing information, hydrological address information, and marine monitoring data to construct the raw dataset. The second module is used to construct the coordinates of submarine cable nodes and define the submarine cable suspension discrimination index based on the original dataset. The third module is used to determine the suspension status information of the target submarine cable based on the cable node coordinates and the cable suspension discrimination index, and to calculate the dynamic suspension migration rate of the target submarine cable. The fourth module is used to identify risk-based events and classify node risk states based on the suspension state information and the dynamic suspension migration rate, thereby constructing a multimorphic fuzzy Bayesian network. The fifth module is used to perform dynamic fatigue risk assessment on the target submarine cable based on the polymorphic fuzzy Bayesian network, and obtain the risk assessment result.

9. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement the method as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images