Digital twinborn modeling and evaluation method for typhoon resistance toughness of breeding platform

Abstract

The invention discloses a digital twinning modeling and evaluation method for typhoon resistance toughness of a culture platform, and relates to the technical field of ocean engineering digital twinning and risk evaluation.According to the scheme, a high-fidelity digital twinning body integrating multiple physical field models is constructed, and real-time data bidirectional interaction with a physical platform is established; on the basis, anti-typhoon toughness quantitative indexes including robustness, redundancy and restorability are systematically defined; by using the digital twinborn body, dynamic deduction, real-time evaluation and backtracking analysis of the whole process of the typhoon can be carried out, and the toughness state of the platform can be accurately observed; and finally, based on an evaluation result, simulating, optimizing and recommending an optimal toughness enhancement strategy in a digital space. According to the method, the anti-typhoon capability of the culture platform is predicted from static evaluation to dynamic prediction and from a single safety coefficient to comprehensive toughness management, and a core technical support is provided for safe operation of deep and far sea culture.

Description

Technical Field

[0001] This invention relates to the field of digital twin and risk assessment technology for marine engineering, specifically a digital twin modeling and assessment method for the typhoon resistance resilience of aquaculture platforms. Background Technology

[0002] With the rapid development of deep-sea aquaculture, aquaculture platforms face severe threats from extreme weather events such as typhoons. Currently, the assessment of aquaculture platforms' typhoon resistance relies heavily on hydrodynamic simulations and physical model tests during the design phase. These methods have significant limitations: first, they cannot reflect the actual state of the platform under real sea conditions, especially the structural performance degradation and biofouling that occur with increasing service life; second, static assessment results cannot provide real-time, forward-looking decision support for the dynamic process of typhoon passage; and third, they lack a systematic quantification of the platform's "resilience," i.e., its ability to maintain function and recover quickly after being impacted. Digital twin technology offers a potential solution to these problems. However, existing technologies, such as simple three-dimensional visualization models or simulations of single physical fields, are insufficient to meet the needs of complex systems engineering like typhoon resistance for aquaculture platforms. The challenge lies in how to construct a multi-physics, multi-scale, full-lifecycle twin capable of real-time bidirectional interaction, and on this basis, develop a scientific resilience quantification assessment system to achieve accurate insight and proactive enhancement of the platform's typhoon resistance.

[0003] Therefore, a digital twin modeling and evaluation method for the typhoon resistance resilience of aquaculture platforms is proposed to address the above issues. Summary of the Invention

[0004] In view of this, the technical problem to be solved by the present invention is to propose a digital twin modeling and evaluation method for the typhoon resistance resilience of aquaculture platforms. This method can construct a high-fidelity digital twin that is synchronized with the physical platform in real time, and on this basis, dynamically quantify, predict and optimize the platform's resilience throughout the typhoon process, providing a scientific basis for typhoon resistance decision-making.

[0005] To overcome the shortcomings of existing technologies, this invention provides a digital twin modeling and evaluation method for the typhoon resistance resilience of aquaculture platforms, comprising the following steps: S1: Construct a multi-dimensional high-fidelity digital twin model integrating geometric, physical properties, hydrodynamics, structural mechanics, mooring, and environmental load models; bidirectional coupling and data exchange are performed between the sub-models. The hydrodynamic model is constructed based on potential flow theory or computational fluid dynamics, the structural mechanics model is constructed using the finite element method, and the environmental load model integrates real-time typhoon forecast data and field measured data to generate high-resolution wind, wave, and flow fields. S2: Establish a real-time two-way data interaction channel between the physical platform and the digital twin model; the two-way data interaction includes: Data uplink: Through a sensor network deployed on the physical platform, including attitude sensors, strain gauges, anchor chain tension meters, GPS, anemometers, and wave radar, platform status and environmental data are collected in real time to drive and calibrate the digital twin model.

[0006] Data downlink: Sending simulation prediction results or control commands from the digital twin to the control system of the physical platform for early warning or direct control of the actuators; S3: Define and quantify the platform's typhoon resilience indicators in the digital twin, including robustness, redundancy, and recoverability; form a comprehensive resilience index through weighted fusion, specifically: Robustness is quantified by the platform's maximum structural stress, anchoring force safety factor, and motion attitude indicators under typhoon impact; redundancy is quantified by simulating the system's performance retention capability after the failure of key components; and recoverability is quantified by the estimated repair time and cost. S4: Based on the aforementioned digital twin, conduct dynamic resilience simulation and assessment of the entire typhoon passage process, including: Forecast-based simulation: Based on typhoon forecasts, simulate changes in platform response and resilience under different future scenarios; Real-time assessment: Combine real-time data with online correction models to simultaneously calculate current resilience indicators; Retrospective analysis: Records data throughout the entire process for optimizing models and strategies; S5: Based on the evaluation results, generate and recommend resilience enhancement strategies; specifically, simulate the impact of different typhoon-resistant operation strategies (including adjusting the platform heading, changing the mooring tension configuration, actively submerging the cage, etc.) on the resilience index in a digital twin, and determine the optimal strategy through comparative analysis.

[0007] Preferably, the hydrodynamic model described in S1 is constructed based on potential flow theory or computational fluid dynamics, and the core formula is the wave load calculation formula, as follows:

[0008] In the formula, It is the acceleration due to gravity. The wave surface elevation, Let be the velocity potential function. The wetted surface area of ​​the platform. This is the normal vector of the wet surface; The structural mechanics model is constructed using the finite element method, and the core formula for calculating the structural dynamic response is as follows:

[0009] In the formula, M is the structural mass matrix; C is the damping matrix; K is the stiffness matrix; and u represents the structural displacement vector. Represented as a velocity vector; Represented as an acceleration vector; It is represented as a dynamic load vector.

[0010] As a preferred method, the model calibration in S2 uses the Kalman filter algorithm, the core formula of which is:

[0011]

[0012] middle, Let k be the corrected model state vector. Predict the state vector at time k. Here is the Kalman gain matrix. This is the measured data vector. For the observation matrix, For the prediction error covariance matrix, To measure the noise covariance matrix, It is an identity matrix.

[0013] Preferably, the robustness described in S3 is quantified by the platform's maximum structural stress under typhoon impact, anchoring force safety factor, and motion attitude index, as shown in the formula:

[0014] In the formula, , , The weights are 1, For allowable stress, For maximum stress, For the allowable anchoring tension, For maximum anchor tension, The maximum roll angle, To allow for roll angle; The redundancy described in S3 is quantified by simulating the system's performance retention capability after the failure of critical components, using the following formula:

[0015] In the formula, The number of critical failure components. These are the performance indicators of the component when it is functioning normally. Performance indicators after component failure; The restorability described in S3 is quantified by the estimated repair time and cost, using the following formula:

[0016] In the formula, , To allow for the longest possible repair time, To cover repair costs, The total asset value of the platform; The specific formula for forming the comprehensive resilience index through weighted fusion, as described in S3, is as follows:

[0017] In the formula, , , All are represented as weights and their sum is 1.

[0018] As a preferred embodiment, S4 uses typhoon forecasting to simulate platform response and resilience changes under different future scenarios, with a time span covering several hours to several days. The anchoring system tension calculation uses the following formula:

[0019] In the formula These represent the initial horizontal and vertical tensions, respectively. For anchor chain density, The cross-sectional area of ​​the anchor chain is... For the depth of insertion, For ocean current load density, Wave load density; Preferably, the simulation analysis of the typhoon resistance operation strategy described in S5 includes the prediction of the trend of resilience index changes after the strategy is implemented, as well as the quantitative comparison of the cost and benefit of the strategy implementation.

[0020] A digital twin modeling system for the typhoon resilience of an aquaculture platform includes a sensor network and a data acquisition unit deployed on the physical aquaculture platform for collecting platform status data and environmental data. A digital twin model server is used to store and run the multi-dimensional high-fidelity digital twin model; A data processing and simulation engine is used to perform model calculations, resilience assessments, and strategy analysis. A bidirectional data communication interface is used to enable uplink and downlink data transmission between the physical platform and the digital twin model; The visualization and human-computer interaction interface can display the comprehensive resilience index and various sub-resilience indicators in real time in the form of a dashboard, and can also display the forecast and real-time comparison of typhoon path, platform stress cloud map, and motion trajectory.

[0021] Preferably, the data processing and simulation engine integrates a multiphysics coupling calculation module, a resilience index quantification analysis module, and a strategy simulation optimization module, supporting parallel computing to improve simulation and evaluation efficiency.

[0022] Preferably, the sensor network is deployed to cover key components of the platform, the mooring system, the aquaculture area, and monitoring points in the surrounding environment to ensure the comprehensiveness and representativeness of the data collection.

[0023] Compared with existing technologies, the digital twin modeling and evaluation method for the typhoon resistance of aquaculture platforms provided by this invention has the following beneficial effects: Compared with the prior art, the advantages of the present invention are as follows: From static assessment to dynamic prediction: It realizes a full-process, forward-looking dynamic assessment of the typhoon resistance capability of aquaculture platforms, transforming passive response into proactive prediction and intervention.

[0024] More comprehensive assessment dimensions: For the first time, the "resilience" of the aquaculture platform is systematically quantified within the digital twin framework, covering robustness, redundancy, and recoverability, surpassing the traditional single safety coefficient assessment.

[0025] High model accuracy and real-time performance: Real-time data-driven and model calibration ensures a high degree of consistency between the digital twin and the physical state, making the evaluation results more realistic and reliable.

[0026] Strong decision support capabilities: It provides a secure "sandbox" environment for testing and optimizing various typhoon resistance strategies, significantly improving the scientific nature and effectiveness of decision-making, and maximizing the protection of platform security and asset value.

[0027] Full lifecycle management: This digital twin can accompany the platform throughout its entire lifecycle, continuously evolving through accumulated data and optimizing its typhoon resistance performance assessment and management. Attached Figure Description

[0028] Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the system framework of the present invention; Figure 3 This is a schematic diagram illustrating the changing trends of the overall resilience index and its sub-indices in this invention. Figure 4 This is a schematic diagram showing the structural response and anchor chain tension variation trend of the present invention. Detailed Implementation

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0030] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments.

[0031] Example Please refer to Figure 1 As shown: To address the problems mentioned in the technical solutions, this application provides a digital twin modeling and evaluation method for the typhoon resilience of aquaculture platforms. The hardware architecture of the digital twin system built in this embodiment includes: a physical platform sensor network, a satellite communication module, edge computing nodes, a cloud computing cluster (including 8 GPU servers), and a shore-based monitoring center. The software architecture is built based on the Unity3D visualization engine, the ANSYS multiphysics simulation kernel, and the MongoDB time-series database, supporting real-time processing and simulation iteration of over 1000 data points per second.

[0032] (I) S1: Construction of a multi-dimensional high-fidelity digital twin model; Geometric model construction: Based on the platform design drawings and laser scanning measurement data, a 1:1 full-size geometric model was constructed in ANSYS SpaceClaim, including the main truss structure of the platform, the anchoring system, the integrated modeling of anchor chains and anchors, the aquaculture cages, the netting elastomer model, the sensor mounting base and other key components, with a total mesh count of 2.8 million, of which the key load-bearing components adopted a refined hexahedral mesh.

[0033] Multiphysics sub-model construction and coupling; Hydrodynamic model: Constructed using potential flow theory (based on ANSYS AQWA software), the core calculation focuses on the combined effects of wave and current loads. Input parameters include: seawater density 1025 kg / m³. 3 Gravitational acceleration: 9.81 m / s² 2 The wave frequency range is 0.5-2.5 rad / s, and the wave direction angle is 0°-360° (each calculation step is 15°). The velocity potential function φ is solved using the boundary element method, combined with the wetted surface area S of the platform (dynamically varying from 3200-3800 m² under typhoon influence). 2 The specific formula for calculating wave loads is as follows:

[0034] In the formula, It is the acceleration due to gravity. The wave surface elevation, Let be the velocity potential function. Let n be the wetted surface area of ​​the platform, and n be the wetted surface normal vector. During the application of the formula, the wave surface elevation η is dynamically updated based on real-time wave height data, and the wetted surface normal vector n is calculated through real-time attitude iteration using the geometric model.

[0035] Structural mechanics model: Constructed using the finite element method (ANSYS Mechanical). The main platform truss uses BEAM188 beam elements, the cage frame uses SHELL181 shell elements, and the anchor chains use LINK180 rod elements, considering both axial tension and bending coupling deformation. The core formula for calculating the structural dynamic response is as follows:

[0036] In the formula, M is the structural mass matrix; C is the damping matrix; K is the stiffness matrix; and u represents the structural displacement vector. Represented as a velocity vector; Represented as an acceleration vector; It is represented as a dynamic load vector.

[0037] The structural mass matrix M is determined by the material density (7850 kg / m³ for steel). 3 The damping matrix C is obtained by integrating with the element volume. Rayleigh damping is used, with α=0.02 and β=0.001. The stiffness matrix K is assembled from the element stiffness matrix and takes into account material nonlinearity. The dynamic load vector F(t) includes wave load, wind load, flow load, and the weight of the cultured organisms.

[0038] Anchoring system model: The anchor chain is discretized using the lumped mass method, with each segment divided into 20 mass points, each weighing 0.8 kg, connected by spring-damped elements to simulate the tensile, bending, and torsional deformation of the anchor chain. The anchorage is modeled using an embedded approach, considering the soil friction coefficient and the anchorage pull-out force, with a design value of 800 kN.

[0039] Environmental load model: The model is integrated with the China Meteorological Administration's typhoon forecast API, which updates hourly with on-site measured data to generate a high-resolution spatiotemporal field. The wind field uses a logarithmic wind profile model to calculate wind speeds at different heights, the wave field uses the JONSWAP spectrum to simulate irregular waves, and the flow field is based on on-site ADCP measured data, with a vertical distribution model constructed at three depths of 5m, 10m, and 15m.

[0040] Sub-model coupling mechanism: A two-way coupling channel is established through ANSYS System Coupling. The load data calculated by the hydrodynamic model is transmitted to the structural mechanics model every 0.1s. The platform displacement and attitude data calculated by the structural mechanics model are fed back to the hydrodynamic model to correct the wetted surface area and load application angle. The mooring system model and the structural mechanics model are coupled through nodal force balance to transmit the anchor chain tension and platform constraint reaction force in real time.

[0041] (ii) S2: Real-time data interaction between the physical platform and the digital twin model; Sensor network deployment and data acquisition; Deployment list: 3 attitude sensors, accuracy ±0.1°, sampling frequency 10Hz, installed at the center of the platform deck and the top of the trusses on both sides; 32 stress strain gauges, range ±2000με, installed at the welds and stress concentration areas of the main truss components; 6 anchor chain tension gauges, range 0-1000kN, accuracy ±1%FS, installed at the connection between the anchor chain and the platform; 2 GPS positioning modules, positioning accuracy ±0.5m, sampling frequency 5Hz; 2 anemometers, range 0-70m / s, accuracy ±0.3m / s, installed at the top of the platform mast at a height of 20m; 1 wave radar, measuring range 0-20m wave height, accuracy ±0.1m, installed at the edge of the deck; and water temperature and salinity sensors.

[0042] Data preprocessing: The raw data collected by the sensors is filtered by edge computing nodes, including initial processing with Kalman filtering, outlier removal based on the 3σ criterion, and format standardization. The core formula is:

[0043]

[0044] In the formula, Let k be the corrected model state vector. Predict the state vector at time k. Here is the Kalman gain matrix. This is the measured data vector. For the observation matrix, For the prediction error covariance matrix, To measure the noise covariance matrix, It is an identity matrix.

[0045] Data uplink: Preprocessed real-time data is uploaded to the cloud-based digital twin model server via a maritime satellite communication link (10Mbps bandwidth) for model driving and calibration. For example, GPS-collected platform location coordinates (latitude, longitude, and altitude) are used to correct the spatial attitude of the digital twin, and stress-strain gauge data are used to verify the calculation accuracy of the structural mechanics model.

[0046] Downlink data: Cloud simulation of the resilience index change in the next 24 hours, prediction of anchor chain tension warning value, and control commands for platform heading adjustment angle and anchor chain tension control threshold are sent to the PLC control system of the physical platform through the same communication link. The sending frequency is 1 time / minute, with emergency commands having the highest priority and a transmission delay of ≤300ms.

[0047] Model calibration and application of Kalman filtering algorithm; The state vector x is defined as: platform roll angle, pitch angle, heave displacement, maximum stress of main truss components, and maximum tension of anchor chain.

[0048] The observation matrix H is a 5×5 identity matrix, and the measurement noise covariance matrix R is determined through sensor calibration experiments. The stress strain gauge R = diag([10 -4 10 -4 ,...,10 -4 The initial value of the prediction error covariance matrix P is set to diag([0.1,0.1,0.01,10,100]). Kalman filter calibration is performed every 10 sampling periods (1s) to correct the state parameters of the digital twin model and ensure that the deviation between the model prediction value and the measured value is ≤5% (e.g., roll angle deviation ≤0.5°, stress deviation ≤10MPa).

[0049] (III) S3: Quantification of typhoon resilience index; Weighting: Based on the Delphi method, five experts in the field of marine engineering were invited to score the comprehensive resilience index to determine its weights. The specific formula is as follows:

[0050] In the formula, , , All are represented as weights and their sum is 1, ω R =0.5 (robustness), ω Rd =0.3 (redundancy), ω Re =0.2 (restorative), with a weighted sum of 1, and is a normalized evaluation value between 0 and 1.

[0051] Each indicator is calculated quantitatively; the formula is:

[0052] In the formula, , , The weights are 1, For allowable stress, For maximum stress, For the allowable anchoring tension, For maximum anchor tension, The maximum roll angle, To allow for roll angle; Among them, robustness (R R Allowable stress [σ] allow The main truss components are made of Q355 steel, with a strength of 235 MPa. Maximum stress [σ] max ]: Through real-time calculations using structural mechanics models, the peak pressure during typhoon passage is monitored within the range of 0-200 MPa; Allowable anchor tension F allow 800kN (determined based on anchor chain strength grade); Maximum anchor tension F max : Obtained by fusing actual measurements from anchor chain tension gauges with model predictions; Allowable roll angle θ allow 15° (based on safety operation requirements for aquaculture cages); Maximum roll angle θ max : Measured using an attitude sensor; Weights α=0.4, β=0.3, γ=0.3 (determined by experts, with a focus on structural stress safety).

[0053] If σ max =188MPa, F max =640kN, θ max =12°, then R R =0.4×(235 / 188)+0.3×(800 / 640)+0.3×(1-12 / 15)=0.4×1.25+0.3×1.25+0.3×0.2=0.5+0.375+0.06=0.935.

[0054] The number of critical failure components is n=5, including: main generator, anchor chain #1, anchor chain #2, main controller, and emergency power supply; The performance indicator selected is the effective aquaculture volume retention rate of the platform, which is 100% under normal conditions. Simulating performance after single component failure: For example, after the failure of anchor chain #1, the simulation calculation shows that the aquaculture volume retention rate of the platform is 85%, and under normal conditions, R_i,pre=100%; among which, the performance retention rates after the failure of the five key components are calculated to be 85%, 90%, 88%, 75%, and 92%, respectively. Then R Rd =(85% / 100%+90% / 100%+88% / 100%+75% / 100%+92% / 100%) / 5=(0.85+0.9+0.88+0.75+0.92) / 5=4.3 / 5=0.86.

[0055] Restorative (R) Re ): Maximum allowed repair time t allow =72 hours (determined based on the survival limit of cultured organisms and the threshold for loss due to production interruption); Estimated repair time t repair Based on historical maintenance data and simulation of component damage, the repair time is determined to be 12 hours for minor damage (anchor chain tension exceeding the limit but not broken) and 48 hours for severe damage (deformation of main truss components). Platform total asset value Ct otal =50 million yuan (including platform structure, equipment, and aquaculture organisms); Repair cost C repairMinor damage is estimated at approximately 2 million yuan, while severe damage is estimated at approximately 12 million yuan. In scenarios of minor damage, R Re =0.5×(1-12 / 72)+0.5×(1-200 / 5000)=0.5×(5 / 6)+0.5×(4800 / 5000)=0.5×0.833+0.5×0.96=0.4165+0.48=0.8965.

[0056] Comprehensive resilience index (R): Based on the example data above, R = 0.5 × 0.935 + 0.3 × 0.86 + 0.2 × 0.8965 = 0.4675 + 0.258 + 0.1793 = 0.9048 (normalized to 0.90, which is at a high resilience level).

[0057] (iv) S4: Dynamic simulation and assessment of typhoon resilience throughout its entire process Taking Typhoon Haishen (a severe typhoon with a maximum sustained wind speed of 42 m / s at its center) as an example, the deduction and assessment process is as follows: Forecast-based simulations are initiated 72 hours after the typhoon forms. Scenario settings: Based on three typhoon path forecasts provided by the meteorological department, path A: directly lands in the sea area where the platform is located; path B: passes westward, 50km away from the platform; path C: moves eastward away, 100km away from the platform. Three intensity scenarios are set for each path, for a total of nine simulation scenarios.

[0058] Time span: 72 hours from now, with a time step of 1 hour. The anchoring system tension is calculated using a specified formula, where the initial horizontal tension F_h0 = 300 kN, the initial vertical tension F_v0 = 50 kN, and the anchor chain density ρ_c = 7850 kg / m³. 3 The cross-sectional area of ​​the anchor chain is A_c = 0.005024 m². 2 Seawater density ρ = 1025 kg / m³ 3 The depth of the descent is z=80m.

[0059] The simulation results are as follows: Under Path B scenario, the platform's overall resilience index will drop to 0.6 (yellow warning threshold) after 36 hours, with the robustness index dropping to 0.55, mainly due to the tension of anchor chain #3 reaching 780kN, close to the allowable value of 800kN. The redundancy index is 0.82, and the recovery index is 0.78. Under Path A scenario, the resilience index will drop to 0.45 (red warning) after 48 hours, indicating a risk of anchor chain breakage.

[0060] Real-time assessment is initiated when the typhoon is 200km away from the platform; Online model calibration: Real-time sensor data is fused every 10 minutes, and the environmental load model and structural response model are corrected by Kalman filtering to ensure that the deviation between the simulation results and the actual state is ≤3%.

[0061] Real-time calculation of indicators: The comprehensive resilience index and sub-indicators are updated every 5 minutes and displayed in real time through the dashboard of the shore-based monitoring center, including: the current resilience index, the real-time values ​​and safety margins of each anchor chain tension, the structural stress cloud map, the platform motion trajectory (roll / pitch / heave curves), and real-time updates and predictions of the typhoon path.

[0062] Retrospective analysis was completed within 72 hours of the typhoon's passage. Data logging: Stores all data throughout the typhoon process, including: raw sensor data, model calibration parameters, simulation results at each time step, resilience index change curves, and strategy execution records.

[0063] Analysis content: Compare the inferred results with actual observations under different path scenarios to optimize model parameters; analyze the key triggering factors for the decline in resilience indicators; evaluate the effectiveness of strategy implementation.

[0064] (v) S5: Generation and optimization of resilience enhancement strategies; Candidate Strategy Design: Three typhoon response strategies are designed to address the yellow alert risk identified through forecasting and extrapolation. Strategy 1: Tighten anchor chains #3 and #4, actively increasing the anchor chain tension to 600kN, with an adjustment range of 100kN, at a cost of 50,000 yuan; Strategy 2: Adjust the platform's heading from 0° (due north) to 45° (northeast), so that the platform's long axis forms a 45° angle with the prevailing typhoon wind direction. The execution cost is 80,000 yuan (including power system energy consumption). Strategy 3: Actively submerge the cages, adjusting the submersion depth from 5m to 10m to reduce the impact of waves on the cages. The execution cost is 120,000 yuan, including the energy consumption of the lifting system and the cost of cage inspection.

[0065] Strategy simulation optimization: Simulate the execution effects of three strategies in a digital twin, with a time span of 24 hours after strategy execution: Strategy 1 simulation results: The maximum tension of anchor chain #3 decreased to 720kN, the toughness index remained at 0.68, but the tension of other anchor chains increased slightly. The total cost was 50,000 yuan, and the profit was about 8 million yuan. Strategy 2 simulation results: The maximum tension of anchor chain #3 decreased to 650kN, the platform roll angle decreased from 12° to 8°, the maximum structural stress decreased from 188MPa to 155MPa, the comprehensive toughness index remained above 0.75, the cost was 80,000 yuan, and the benefit was about 12 million yuan. Strategy 3 simulation results: The impact load on the cage is reduced by 30%, but the toughness index of the main structure of the platform is only increased to 0.62, with a cost of 120,000 yuan and a benefit of about 6 million yuan.

[0066] Determining and executing the optimal strategy: Based on a comprehensive evaluation of the cost-benefit ratio and resilience improvement effect, strategy two has the lowest cost, the most significant resilience improvement, and the least impact on other systems, and is therefore determined to be the optimal strategy.

[0067] Command issuance: Issue the Strategy 2 execution command to the physical platform PLC control system 24 hours in advance, including: adjust the target angle of the bow to 45°, the adjustment rate to 5° / min, the execution window period, and the emergency termination conditions; Execution monitoring: Track the platform's heading adjustment process in real time, verify the adjustment accuracy (deviation ≤1°) through GPS data, and continuously monitor the changes in resilience indicators after the adjustment is completed to ensure that the expected results are achieved.

[0068] like Figure 3 As shown in the figure, the dynamic display shows the changes in the comprehensive resilience index and its core sub-indicators (robustness, redundancy, and recoverability) of the aquaculture platform throughout the entire process of the typhoon's passage. It clearly indicates that when the typhoon's impact was most severe, the resilience index dropped below the red warning threshold. However, after implementing the optimal strategy recommended by the digital twin system (such as adjusting the platform's heading) (approximately 60 hours), all indicators rebounded significantly, and the platform successfully escaped the high-risk state. Resilience Enhancement Effect: By implementing the optimal strategy, the platform's comprehensive resilience index was as low as 0.76 during the typhoon (higher than the yellow warning threshold of 0.6), and no red warning was triggered; the maximum tension of anchor chain #3 was 640kN, with a safety margin of 20%; the maximum structural stress was 152MPa, lower than the allowable stress of 235MPa; the maximum roll angle of the platform was 8.5°, lower than the allowable value of 15°; and there was no damage to components or loss of aquaculture.

[0069] Model accuracy verification: The average deviations of the anchor chain tension and structural stress predicted by the digital twin model from the measured values ​​were 3.2% and 4.5%, respectively. The deviation between the predicted typhoon path and the actual path was ≤10km, which meets the requirements for engineering applications (deviation threshold ≤5%).

[0070] Economic benefits: By taking proactive measures, major accidents such as platform anchor chain breakage and cage damage were avoided, directly reducing economic losses by approximately RMB 12 million (including losses of aquaculture organisms, equipment maintenance costs, and production interruption losses), with an input-output ratio of 1:150.

[0071] In summary, the core concept of this solution is to move from "passive disaster relief" to "proactive foresight and control." It utilizes a high-fidelity digital twin to achieve real-time diagnosis, dynamic prediction, and strategy optimization of the aquaculture platform's typhoon resistance capabilities. For example... Figure 3 and Figure 4 As shown, it can not only provide early warnings of risks, but also accurately simulate the effects of different response strategies, thereby recommending and executing the optimal decision. This ensures that the platform can always maintain a highly resilient, safe, and controllable state under extreme typhoon loads, ultimately greatly protecting the platform's structural safety and asset value.

[0072] Please refer to the above work process. Figure 1 It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0073] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A digital twin modeling and assessment method for typhoon resilience of a farming platform, characterized in that, Comprise the following steps: S1: Construct a multi-dimensional high-fidelity digital twin model integrating geometry, physical properties, hydrodynamic, structural mechanics, mooring and environmental load models; bidirectional data exchange between sub-models, wherein the hydrodynamic model is constructed based on potential flow theory or computational fluid dynamics, the structural mechanics model is constructed using the finite element method, and the environmental load model accesses real-time typhoon forecast data and field measured data to generate high-resolution wind, wave and current fields; S2: Establish a real-time data bidirectional interaction channel between the physical platform and the digital twin model; the data bidirectional interaction includes: Data upload: Real-time collection of platform state and environmental data through the deployment of a sensor network on the physical platform, including attitude sensors, stress strain gauges, anchor chain tension gauges, GPS, anemometers, and wave radars, for driving and calibrating the digital twin model; Data download: The simulation prediction results or control instructions of the digital twin are sent to the control system of the physical platform for early warning or direct control of the actuator; S3: Define and quantify the typhoon resistance resilience index of the platform in the digital twin, including robustness, redundancy and recovery; form a comprehensive resilience index by weighted fusion, specifically: Robustness is quantified by the maximum structural stress, mooring force safety factor and motion attitude of the platform under typhoon impact; redundancy is quantified by the performance retention ability of the system after simulating the failure of key components; recovery is quantified by the estimated repair time and cost; S4: Based on the digital twin, perform dynamic deduction and evaluation of resilience throughout the typhoon passage, including: Predictive deduction: Based on typhoon forecasts, simulate the platform response and resilience changes under different future scenarios; Real-time evaluation: Combine real-time data to correct the model online and calculate the current resilience index synchronously; Retrospective analysis: Record the entire process data for model and strategy optimization; S5: Based on the evaluation results, generate and recommend resilience enhancement strategies; specifically, simulate the impact of different typhoon resistance operation strategies on the resilience index in the digital twin, and determine the optimal strategy through comparative analysis.

2. The digital twin modeling and evaluation method for the typhoon resistance of a farming platform according to claim 1, characterized in that, The hydrodynamic model in S1 is constructed based on potential flow theory or computational fluid dynamics, and the core formula is the wave load calculation formula, which is as follows: wherein is the gravitational acceleration, is the wave surface elevation, is the velocity potential function, is the wetted surface area of the platform, is the wet surface normal vector; The structural mechanics model is constructed using the finite element method, and the core formula is the structural dynamics response calculation formula: In the formula, M is a structural mass matrix; C is a damping matrix; K is a stiffness matrix; u represents a structural displacement vector; represents a velocity vector; represents an acceleration vector; represents a dynamic load vector.

3. The digital twin modeling and evaluation method for the typhoon resistance of a farming platform according to claim 1, characterized in that, The model calibration in S2 uses the Kalman filter algorithm, and the core formula is: wherein is the corrected model state vector at time k, is the predicted state vector at time k, is the Kalman gain matrix, is the measured data vector, is the observation matrix, is the prediction error covariance matrix, is the measurement noise covariance matrix, is the identity matrix.

4. The digital twin modeling and evaluation method for the typhoon resistance of a farming platform according to claim 1, characterized in that, The robustness in S3 is quantified by the maximum structural stress, mooring force safety factor and motion attitude of the platform under typhoon impact, and the formula is: wherein , , are weights and sum to 1, is the allowable stress, is the maximum stress, is the mooring allowable tension, is the maximum mooring tension, is the maximum roll angle, is the allowable roll angle; The redundancy in S3 is quantified by the performance retention ability of the system after simulating the failure of key components, and the specific formula is: wherein is the number of critical failed components, is the performance index of the component when normal, is the performance index of the component after failure; The recovery in S3 is quantified by the estimated repair time and cost, and the specific formula is: wherein , is the longest repair time allowed, is the repair cost, is the total asset value of the platform; The comprehensive resilience index in S3 is formed by weighted fusion, and the specific formula is: wherein , , all are expressed as weights and sum to 1.

5. The digital twin modeling and evaluation method for the typhoon resistance of a farming platform according to claim 1, characterized in that, The simulation of platform response and resilience changes under different future scenarios in S4 based on typhoon forecasts covers a time span of several hours to several days, and the anchor system tension calculation uses the formula: wherein are the initial horizontal and vertical tension, respectively, is the chain density, is the chain cross-sectional area, is the depth of penetration, is the current load density, is the wave load density.

6. The digital twin modeling and evaluation method for the typhoon resistance of a farming platform according to claim 1, characterized in that, The simulation analysis of the typhoon resistance operation strategy described in S5 includes the prediction of the trend of resilience index changes after the strategy is implemented, as well as the quantitative comparison of the cost and benefit of the strategy implementation.

7. A digital twin modeling system for implementing the method of any one of claims 1-6, wherein, This includes a sensor network and data acquisition units deployed on the physical aquaculture platform to collect platform status data and environmental data; A digital twin model server is used to store and run the multi-dimensional high-fidelity digital twin model; A data processing and simulation engine is used to perform model calculations, resilience assessments, and strategy analysis. A bidirectional data communication interface is used to enable uplink and downlink data transmission between the physical platform and the digital twin model; The visualization and human-computer interaction interface can display the comprehensive resilience index and various sub-resilience indicators in real time in the form of a dashboard, and can also display the forecast and real-time comparison of typhoon path, platform stress cloud map, and motion trajectory.

8. The digital twin modeling system for typhoon resilience of a farming platform of claim 7, wherein, The data processing and simulation engine integrates a multiphysics coupling calculation module, a resilience index quantification analysis module, and a strategy simulation optimization module, and supports parallel computing to improve simulation and evaluation efficiency.

9. The digital twin modeling system for typhoon resilience of a farming platform of claim 8, wherein, The sensor network is deployed to cover key components of the platform, the anchoring system, the aquaculture area, and surrounding environmental monitoring points, ensuring the comprehensiveness and representativeness of the data collection.

Images