A method for optimizing a structure of a net cage for ship type culture

Abstract

This invention discloses a method for optimizing the structure of a boat-shaped aquaculture cage, comprising: collecting structural parameters through a gateway by simulating the material properties of the cage; constructing a wave-current coupled cage vibration attenuation model to analyze vibration characteristics; calling a boat-shaped cage anti-overturning early warning model to obtain the anti-overturning stability coefficient and risk points; dynamically adjusting the distribution of floats, the tension of the netting, and the anchorage pulling angle using a wave energy buffer adaptive control algorithm; and feeding back data on material stress, fatigue damage, and structural deformation after adjustment through the gateway. Finally, multi-dimensional optimization is performed on parameters such as the cross-sectional dimensions of the cage frame and the size of the netting mesh. The method refines the step-by-step process of anti-overturning assessment, adaptive control, and material property feedback, achieving closed-loop synergy between wave-current coupled analysis, risk early warning, dynamic control, and structural optimization, thereby improving the stability and durability of the cage in complex marine environments.

Description

Technical Field

[0001] This invention relates to the field of aquaculture cage structure optimization technology, and in particular to a method for optimizing the structure of a boat-shaped aquaculture cage. Background Technology

[0002] As the marine aquaculture industry expands into deep-sea areas, boat-shaped aquaculture cages have become core equipment for large-scale aquaculture due to their advantages such as large aquaculture capacity, high space utilization, and adaptability to the open sea environment. However, the wave and current environment in deep-sea areas is complex and variable. The combined effect of waves and currents can easily cause cage vibration, structural deformation, and capsizing risks. Furthermore, long-term exposure to wave and current loads can cause fatigue damage to cage materials, directly affecting aquaculture safety and equipment lifespan. To adapt to the complex marine environment and improve the structural stability and durability of cages, a systematic structural optimization approach is needed. This approach integrates technologies such as wave-current coupling analysis, anti-capsulation early warning, adaptive control, and material performance monitoring to achieve precise matching and dynamic optimization of cage structural parameters, meeting the dual demands of deep-sea aquaculture for equipment reliability and economy.

[0003] Existing ship-type aquaculture cage structure optimization technologies have two significant shortcomings: First, they lack in-depth analysis of the interaction between wave-current coupling and cage structural characteristics, often considering only the effects of single wave or current loads without fully linking the cage vibration propagation law with its anti-overturning performance. This makes the optimization schemes difficult to adapt to the complex and ever-changing marine environment, and structural stability control lacks specificity. Second, the optimization process lacks a closed-loop mechanism for real-time feedback of material properties and dynamic parameter adjustment. Monitoring of fatigue damage accumulation and structural deformation in key components such as cage frames, netting, and connectors is lagging. Furthermore, optimization parameters often rely on empirical settings and fail to incorporate wave energy buffering effects for adaptive control. This makes optimized cages prone to rapid material wear and insufficient structural adaptability during long-term service, making it difficult to balance stability and durability requirements. Summary of the Invention

[0004] In order to overcome the shortcomings and deficiencies of existing technologies, this invention provides a method for optimizing the structure of boat-shaped aquaculture cages.

[0005] The technical solution adopted in this invention is a method for optimizing the structure of a boat-shaped aquaculture cage, comprising the following steps: S1, collecting relevant structural parameters of the main frame elastic modulus, netting weaving density, shear strength of connectors, buoyancy coefficient of the float, anchorage stiffness, and draft of the boat-shaped aquaculture cage through a cage material performance simulation calculation gateway; S2, constructing a wave-current coupled cage vibration attenuation model based on the collected structural parameters, and analyzing the vibration displacement, vibration frequency, and vibration propagation characteristics of different parts of the cage under the combined action of waves and currents using this model; S3, calling the boat-shaped cage anti-overturning early warning model, and combining the vibration analysis results with wave and current velocity, wave... S4. Using wave energy buffering adaptive control algorithm, the distribution position of the floating bodies, the tension of the netting, and the anchorage pulling angle are dynamically adjusted according to the anti-overturning stability coefficient and the risk points. S5. The stress distribution, fatigue damage accumulation, and structural deformation of the netting material after real-time feedback control are calculated through netting material performance simulation. S6. Based on the stress distribution, fatigue damage accumulation, and structural deformation data, the frame cross-sectional dimensions, netting mesh size, number of floating bodies, and anchorage spacing of the boat-shaped aquaculture netting are optimized in multiple dimensions.

[0006] Furthermore, the expression for the wave-current coupled cage vibration attenuation model is as follows:

[0007] ,

[0008] in, This is the vibration attenuation of the cage. The vibration attenuation coefficient is... The elastic modulus of the main frame. For the mesh weave density, The weighting factor for the influence of flow velocity. For wave velocity, The wave height influence weighting coefficient. For wave height, To ensure the rigidity of the anchorage, This is the buoyancy coefficient of the floating body.

[0009] Furthermore, the expression for the ship-shaped cage anti-overturning early warning model is as follows:

[0010] ,

[0011] in, This refers to the overturning stability coefficient of the cage. This is the overturning resistance correction factor. For the draft of the net cage, For the shear strength of the connector, For the flow direction angle, For wave period, The wave-current direction and period coupling function, This is the vibration attenuation of the cage. To ensure the rigidity of the anchorage.

[0012] Furthermore, the expression for the wave energy buffer adaptive control algorithm is as follows:

[0013] ,

[0014] in, This is the amount of adjustment for the anchorage pulling angle. To adjust the gain coefficient, This refers to the overturning stability coefficient of the cage. The elastic modulus of the main frame. For the mesh weave density, The buoyancy coefficient of the floating body. The number of segments for the net cage. Let i be the vibration attenuation of the i-th segment of the cage. For the flow direction angle, The interval is the segmented angle.

[0015] Furthermore, the parameter output model of the gateway for simulating and calculating the material properties of the cage is as follows:

[0016] ,

[0017] in, Output parameter values ​​for the gateway. For gateway conversion coefficients, This represents the stress distribution value of the material. This represents the amount of structural deformation. This represents the cumulative fatigue damage value. The elastic modulus of the main frame. The weave density of the mesh garment.

[0018] Furthermore, the parameter matching model for optimizing the boat-shaped aquaculture cage structure is as follows:

[0019] ,

[0020] in, To optimize the matching degree of the structure, To optimize the weighting coefficients, For the allowable stress of the material, To allow for cumulative fatigue damage, This represents the actual stress distribution value of the material. This represents the actual cumulative fatigue damage value. To design the elastic modulus, This is the actual elastic modulus. To design the mesh weave density, This refers to the actual mesh weave density.

[0021] Further, step S3 includes the following sub-steps: S31, aligning the vibration displacement and vibration frequency data of the net cage obtained in S2 with the wave velocity, wave height, wave period, and flow direction angle parameters collected by the wave and current monitoring equipment to form a multi-dimensional input dataset; S32, inputting the dataset into the ship-type net cage anti-overturning early warning model, and decomposing the wave and current loads in different directions through the wave and current force calculation module inside the model to determine the difference in lateral thrust, longitudinal tension, and vertical buoyancy force on the net cage; S33, based on the wave and current load decomposition results, combined with the net cage's center of gravity height, buoyancy center position, and metacentric radius parameters, calculating the net cage anti-overturning stability coefficient under different working conditions; S34, using the stability coefficient threshold judgment, locating the risk points where the net cage is prone to overturning under the combined action of waves and currents, and forming a risk point coordinate dataset.

[0022] Further, S4 includes the following sub-steps: S41, extract the anti-overturning stability coefficient and risk point coordinate data output by S3, and establish a mapping relationship model between the control parameters and the stability coefficient; S42, based on the mapping relationship model, calculate the adjustment increment of the floating body distribution position, the adjustment ratio of the net tension, and the change range of the anchor pulling angle through the wave energy buffer adaptive control algorithm; S43, move the floating body installation position according to the calculated adjustment increment, change the extension and retraction of the net tensioning mechanism through the hydraulic control device, and adjust the length of the anchor pulling rope to change the pulling angle; S44, collect the net cage attitude data after control in real time, and feed it back to the wave energy buffer adaptive control algorithm to form a closed-loop control logic.

[0023] Further, step S5 includes the following sub-steps: S51, activating the stress monitoring module of the cage material performance simulation calculation gateway, collecting real-time stress data of the cage frame, netting, and connectors through distributed sensors, and generating a stress distribution cloud map; S52, using the fatigue damage calculation module of the gateway, calculating the cumulative fatigue damage value of the material in each part of the cage based on the stress distribution data and the material SN curve; S53, using the deformation monitoring module of the gateway, acquiring the linear deformation of the main frame of the cage and the in-plane deformation of the netting using laser ranging technology; S54, converting and compressing the stress distribution cloud map, cumulative fatigue damage value, and deformation data, and transmitting them to the structural optimization decision module.

[0024] A method for optimizing the structure of a boat-shaped aquaculture cage is proposed. This method is implemented through different units, including: a structural parameter acquisition unit, a wave-current coupling vibration analysis unit, an anti-overturning risk assessment unit, a wave energy buffering and control unit, a material performance feedback unit, and a multi-dimensional optimization decision-making unit.

[0025] The structural parameter acquisition unit establishes a data transmission connection with the cage material performance simulation calculation gateway to collect the elastic modulus of the main frame and the structural parameters of the netting weave density of the boat-shaped aquaculture cage and transmit them to the wave-current coupled vibration analysis unit. After receiving the structural parameters, the wave-current coupled vibration analysis unit analyzes the vibration characteristics of the cage through its built-in wave-current coupled cage vibration attenuation model and sends the vibration analysis results to the anti-overturning risk assessment unit. The anti-overturning risk assessment unit calls the boat-shaped cage anti-overturning early warning model, calculates the anti-overturning stability coefficient and risk points in combination with wave-current parameters, and outputs them to the wave energy buffer control unit. The wave energy buffer control unit adopts a wave energy buffer adaptive control algorithm to dynamically adjust the distribution of the cage float, the tension of the netting, and the anchor pull angle, while feeding back the control commands to the material performance feedback unit. The material performance feedback unit obtains the stress distribution, fatigue damage accumulation, and structural deformation data after control through the cage material performance simulation calculation gateway and transmits them to the multi-dimensional optimization decision unit. The multi-dimensional optimization decision unit optimizes the cage frame cross-sectional dimensions and netting mesh size parameters based on the received data to form the final optimization scheme.

[0026] The present invention has the following beneficial effects:

[0027] This invention proposes a structural optimization method for boat-shaped aquaculture cages. Through multi-model collaboration and closed-loop control mechanisms, it achieves precision and adaptability in structural optimization. Key structural parameters are comprehensively collected through cage material performance simulation calculations via a gateway. Combined with a wave-current coupled cage vibration attenuation model, the vibration characteristics of the cage under the combined action of waves and currents are deeply analyzed, overcoming the limitations of single-load analysis and accurately capturing the coupling influence between waves, currents, and the structure. A boat-shaped cage anti-overturning early warning model is used to locate risk points, and a wave energy buffer adaptive control algorithm is used to dynamically adjust the distribution of floating bodies, the tension of the netting, and the anchorage angle, constructing a targeted control logic that solves the problem of lack of dynamic adaptability in traditional optimization. Through real-time feedback of material properties and multi-dimensional parameter optimization, the correlation between structural parameters and material stress, fatigue damage, and deformation is established, enabling dynamic iteration of the optimization scheme and overcoming the shortcomings of existing technologies such as monitoring lag and reliance on empirical parameters. This invention forms a complete closed loop of "parameter acquisition - vibration analysis - risk assessment - adaptive control - performance feedback - parameter optimization", which not only improves the overturning stability and vibration attenuation capability of the cage in complex wave and current environments, but also extends the service life of the materials, taking into account both structural safety and economy, and fully adapts to the harsh environmental requirements of deep-sea aquaculture. Attached Figure Description

[0028] Figure 1 This is a flowchart illustrating the overall process of the method of the present invention.

[0029] Figure 2 This is a flowchart of method step S3 of the present invention;

[0030] Figure 3 This is a flowchart of method step S4 of the present invention;

[0031] Figure 4 This is a flowchart of step S5 of the method of the present invention;

[0032] Figure 5 This is a diagram showing the system unit composition of the present invention. Detailed Implementation

[0033] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0034] like Figure 1 As shown, a method for optimizing the structure of a boat-shaped aquaculture cage includes the following steps:

[0035] S1 uses a gateway to simulate and calculate the material properties of the cages, collecting relevant structural parameters such as the elastic modulus of the main frame, the weaving density of the netting, the shear strength of the connectors, the buoyancy coefficient of the float, the anchorage stiffness, and the draft of the cage.

[0036] Specifically, step S1 involves parameter acquisition via a specially constructed gateway for simulating the material properties of the net cage. This gateway integrates multiple types of sensors and data transmission modules, enabling it to simultaneously acquire multi-dimensional structural parameters. The acquired parameters cover key structural components of the boat-shaped aquaculture net cage. These include the main frame's elastic modulus, which falls within the common engineering range of 190-210 GPa; the netting weaving density, precisely calculated at 30-80 strands per square meter; the shear strength of connectors, collected separately for different locations, with values ​​concentrated between 350-550 MPa; the buoyancy coefficient, determined based on the float material and structural design, ranging from 0.85 to 0.98; and the anchorage stiffness, calculated based on the anchor chain diameter and embedment depth, with a value of 1.2 × 10⁻⁶. 5 -3.5×10 5 The draft of the net cage is monitored in real time using underwater pressure sensors, with an accuracy of ±0.05 meters. During implementation, the gateway uses distributed sensor nodes to collect data at key sections of the net cage frame, different areas of the netting, connector interfaces, floating hull installation points, and anchorage connections. The collection frequency is set to 10Hz, and the continuous collection time is no less than 30 minutes to ensure sufficient sample size of parameter data. These parameters directly reflect the basic characteristics of the net cage structure and are the core data support for subsequent model building and structural optimization. The accuracy and completeness of the data collection directly determine the reliability of subsequent optimization analysis, providing comprehensive and accurate initial data input for the entire optimization method.

[0037] S2. Based on the collected structural parameters, a wave-current coupled cage vibration attenuation model is constructed. This model is used to analyze the vibration displacement, vibration frequency, and vibration propagation characteristics of different parts of the cage under the combined action of waves and current.

[0038] Specifically, step S2, based on all structural parameters such as the elastic modulus of the main frame and the mesh weaving density collected in step S1, constructs a wave-current coupled cage vibration attenuation model using finite element analysis. During model construction, the cage structure is first modularly disassembled into components such as the frame, mesh, floats, and anchorages. Each module is assigned corresponding collected parameter values. Then, a coupled algorithm of fluid mechanics and structural dynamics is used to establish the interaction between the wave-current field and the cage structure. In implementation, boundary conditions for the combined wave-current action are first set, including common marine environmental ranges such as wave-current velocity 0.5-2.5 m / s, wave height 0.3-3.0 m, and wave period 3-12 s. The model then simulates the vibration response of the cage under different wave-current combination conditions. The analysis focuses on the vibration displacement, vibration frequency, and vibration propagation characteristics of different parts of the cage. The vibration displacement monitoring accuracy reaches ±0.1 mm, the vibration frequency analysis range is 0.1-10 Hz, and the vibration propagation characteristics are characterized by the vibration phase difference and amplitude attenuation rate of adjacent structural components. This step quantifies the combined effect of wave and current on the vibration of the cage, clearly presenting the vibration patterns of various parts of the cage, providing accurate vibration data support for subsequent anti-overturning risk assessment. Its core significance lies in breaking the limitations of single load analysis, comprehensively reflecting the dynamic response characteristics of the cage in complex marine environments, and laying the foundation for the targeted formulation of optimization schemes.

[0039] S3 calls the ship-shaped cage anti-overturning early warning model, and combines the vibration analysis results with wave velocity, wave height, wave period and flow direction angle parameters to obtain the cage anti-overturning stability coefficient and potential overturning risk points.

[0040] Specifically, step S3 calls upon a pre-built anti-overturning early warning model for the ship-shaped gabion to conduct an anti-overturning performance assessment. During implementation, the vibration displacement, vibration frequency, and vibration propagation characteristics data of the gabion obtained in step S2 are first fused with wave and current parameters collected by external wave and current monitoring equipment. These wave and current parameters specifically include wave and current velocities of 0.5-2.5 m / s, wave heights of 0.3-3.0 m, wave periods of 3-12 s, and flow angles of 0-180°. The data fusion employs a time-series alignment algorithm to ensure the time synchronization of data from different sources. Subsequently, the model uses a load decomposition algorithm to transform the combined wave and current loads into transverse, longitudinal, and vertical component loads of the gabion. Combined with the gabion structural parameters, the anti-overturning stability coefficient is calculated. This coefficient is set to a range of 0-2.5, with values ​​less than 1.0 indicating a risk of overturning. Simultaneously, the model uses a risk point identification algorithm to locate key areas of the gabion prone to overturning under different wave and current conditions, based on vibration characteristics and load distribution patterns. These areas are typically concentrated at the bow and stern ends and the middle of the sides of the gabion. This step combines real-time calculation with offline analysis, updating the overturning stability coefficient and risk point data every 5 minutes. Its core significance lies in accurately quantifying the overturning resistance of the cages, identifying potential risks, providing clear target guidance for subsequent adaptive regulation, and ensuring that regulation measures can specifically address the weak links in the overturning resistance.

[0041] S4 employs a wave energy buffer adaptive control algorithm to dynamically adjust the distribution position of the cage floats, the tension of the netting, and the anchorage pulling angle based on the anti-overturning stability coefficient and risk points.

[0042] Specifically, step S4 employs a wave energy buffer adaptive control algorithm to perform dynamic control operations, based on the anti-overturning stability coefficient and risk point data obtained in step S3. During implementation, a correlation model between the control parameters and the anti-overturning stability coefficient is first established to clarify the quantitative relationship between the adjustment of the float distribution location, netting tension, and anchor pulling angle and the improvement of the stability coefficient. Regarding the adjustment of the float distribution location, the floats are redistributed on both sides and at the beginning and end of the net cage according to the risk point distribution, with the adjustment spacing controlled within the range of 0.8-2.0 meters to ensure more sufficient buoyancy coverage in the risk areas. The netting tension is achieved through a hydraulic control device; based on the vibration intensity and risk level of different areas, the netting tension is adjusted to 1.1-1.5 times the initial value, with a higher value used in the risk point areas. The anchor pulling angle is adjusted based on the flow direction angle and the risk point location, dynamically correcting the pulling angle within the range of 30°-60° to ensure that the anchor tension can effectively counteract the lateral load of the wave current. During the control process, the algorithm iterates and calculates parameters every 2 minutes, adjusting the control amplitude based on real-time feedback of the cage's attitude data to ensure precise and controllable control. This step maximizes the wave energy buffering effect by actively intervening in the cage's key structural parameters. Its core significance lies in transforming the risk of overturning from passive early warning to active prevention and control. By dynamically adapting to changes in the wave and current environment, it continuously optimizes the cage's stress state, significantly improving the cage's stability in complex environments.

[0043] S5 simulates and calculates the stress distribution, fatigue damage accumulation, and structural deformation of the cage material after real-time feedback and adjustment by the gateway through cage material performance simulation calculation.

[0044] Specifically, step S5 uses a wire mesh cage material performance simulation calculation gateway to complete the performance feedback after regulation. This gateway integrates four major functional modules: stress monitoring, fatigue damage calculation, deformation monitoring, and data processing. During implementation, the stress monitoring module is first activated. Distributed strain gauges, placed at 12-18 key sections of the cage frame, 20-30 monitoring points on the mesh, and all interfaces of the connectors, collect real-time stress data at a sampling frequency of 5Hz and a data accuracy of ±5MPa, generating a global stress distribution cloud map. Subsequently, the fatigue damage calculation module calls the material's preset SN curve and, based on the stress distribution data and control time, uses Miner's linear cumulative damage theory to calculate the cumulative fatigue damage value at each location, with a calculation step size set to 1 hour. The deformation monitoring module uses laser ranging technology to set monitoring targets at 8-10 feature points of the cage frame and 4-6 key areas of the mesh, measuring linear deformation and in-plane deformation with a measurement accuracy of ±0.1mm. Finally, the gateway performs format standardization conversion and lossless compression on the above three types of data, controlling the compression ratio within 10:1, and transmits the data in real-time to the structural optimization decision module via wired transmission. The core significance of this step lies in capturing the mechanical response and structural state changes of the cage material in real time after regulation, providing accurate performance feedback data for subsequent structural optimization, ensuring that the optimization scheme can be dynamically adjusted based on actual working conditions, and verifying the effectiveness of the previous regulation measures, thus forming a closed-loop logic of "regulation-feedback".

[0045] S6 optimizes the structural parameters of the boat-shaped aquaculture cage in multiple dimensions, based on stress distribution, fatigue damage accumulation and structural deformation data, including frame cross-sectional dimensions, mesh size, number of floats and anchorage spacing.

[0046] Specifically, step S6, based on the stress distribution, fatigue damage accumulation, and structural deformation data fed back from step S5, conducts multi-dimensional structural parameter optimization. During implementation, an optimization objective function is first established, with the core objectives being stress distribution uniformity, minimum fatigue damage accumulation, and structural deformation controlled within allowable ranges. Constraints are set as follows: material performance parameters do not exceed design limits, and manufacturing cost increases do not exceed 15%. The optimization parameters include the cross-sectional dimensions of the gabion frame, the size of the mesh, the number of floats, and the spacing of the anchorages. The frame cross-sectional dimensions are adjusted based on stress distribution data, increasing the cross-sectional area of ​​stress-concentrated areas by 10%-25%, while maintaining or appropriately reducing the cross-sectional dimensions in areas with lower stress. The cross-sectional width ranges from 0.15-0.35 meters, and the height from 0.2-0.4 meters. The mesh size is adjusted based on the stress and deformation data of the mesh, reducing the mesh size to 5-10 cm in high-risk areas and 10-20 cm in other areas. The number of floats is adjusted according to buoyancy requirements and fatigue damage, with an adjustment range of ±20% of the original number. The anchorage spacing is optimized based on anchorage stress and gabion deformation data, with a spacing of 8-15 meters. The optimization process uses a multi-objective genetic algorithm, with 50-100 iterations. After each iteration, the optimization effect is verified by simulating the material properties of the gabion until all performance indicators meet the design requirements. This step achieves optimal matching between the cage structure and the marine environment and material properties by systematically adjusting the core structural parameters. Its core significance lies in fundamentally improving the structural stability, material durability and service safety of the cage, while also taking into account economic efficiency, and forming an optimized solution that can be directly applied to engineering practice.

[0047] Preferably, the expression for the wave-current coupled cage vibration attenuation model is:

[0048] ,

[0049] in, This is the vibration attenuation of the cage. The vibration attenuation coefficient is... The elastic modulus of the main frame. For the mesh weave density, The weighting factor for the influence of flow velocity. For wave velocity, The wave height influence weighting coefficient. For wave height, To ensure the rigidity of the anchorage, This is the buoyancy coefficient of the floating body.

[0050] Specifically, the wave-current coupled cage vibration attenuation model is constructed based on the synergistic effect of the cage structure's core parameters and wave-current environmental parameters, used to accurately quantify the vibration attenuation effect of the cage under the combined action of waves and currents. The implementation of this model requires first obtaining basic parameters such as the elastic modulus of the main frame, the mesh weaving density, the anchorage fixing stiffness, and the buoyancy coefficient of the float through cage material performance simulation calculations. The vibration attenuation coefficient is preset to a reasonable range of 0.02-0.08 based on the cage structure type. The influence weighting coefficients of flow velocity and wave height are determined through fitting of a large amount of wave-current experimental data, with values ​​of 0.3-0.7 and 0.5-0.9, respectively. During implementation, the model first receives wave-current velocity and wave height data collected by wave-current monitoring equipment, characterizes the dynamic changes of wave-current loads through trigonometric function calculations, and then combines the product and square root calculations of the cage structure parameters to comprehensively reflect the synergistic contribution of frame stiffness, mesh density, anchorage fixing capacity, and float buoyancy to vibration attenuation. This model breaks through the limitations of traditional single-factor analysis, achieving a deep integration of wave-current coupling effect and cage structure characteristics. Its calculation results can accurately present the quantitative law of cage vibration attenuation under different wave-current conditions, providing reliable vibration characteristic data for subsequent anti-overturning risk assessment, ensuring that anti-overturning analysis can fully consider the impact of vibration propagation on cage stability, and making the initial analysis stage of the entire structural optimization process more in line with the actual marine environment.

[0051] Preferably, the expression for the ship-shaped cage anti-overturning early warning model is:

[0052] ,

[0053] in, This refers to the overturning stability coefficient of the cage. This is the overturning resistance correction factor. For the draft of the net cage, For the shear strength of the connector, For the flow direction angle, For wave period, The wave-current direction and period coupling function, This is the vibration attenuation of the cage. To ensure the rigidity of the anchorage.

[0054] Specifically, the ship-type gabion anti-capsulation early warning model is designed to quantify the anti-capsulation capability of gabions under the combined action of waves and currents and to identify risk points. Its implementation relies on the collaborative input and comprehensive calculation of multi-source data. During model implementation, the anti-capsulation correction coefficient is preset to 0.8-1.2 based on the gabion ship design parameters. First, wave direction angle and wave period data are acquired through wave and current monitoring equipment. A wave-current direction and period coupling function is constructed to characterize the impact of different wave-current and period combinations on the gabion. Then, combined with the buoyancy coefficient of the floating body, the draft of the gabion, and the shear strength of the connecting parts collected in step S1, fractional calculations are used to demonstrate the fundamental role of buoyancy support, draft, and connecting part strength in preventing capsulation. Simultaneously, the model incorporates the gabion vibration attenuation and anchorage stiffness calculated in step S2, and quantifies the synergistic effect of vibration attenuation and anchorage fixation on improving anti-capsulation performance through logarithmic calculations. During implementation, the model receives updated wave-current parameters and vibration data every 3 minutes, and calculates the overturning stability coefficient in real time. The reasonable range for this coefficient is set at 1.0-2.5. When the coefficient is below 1.2, risk point identification is initiated. This model establishes a correlation between vibration characteristics, wave-current environment, and cage structure parameters, enabling quantitative assessment of overturning performance and precise risk location. This provides a clear target for subsequent adaptive control, ensuring that control measures can specifically address weak points in overturning resistance and avoiding the inaccuracy issues caused by traditional assessment methods relying on experience.

[0055] Preferably, the expression for the wave energy buffer adaptive control algorithm is:

[0056] ,

[0057] in, This is the amount of adjustment for the anchorage pulling angle. To adjust the gain coefficient, This refers to the overturning stability coefficient of the cage. The elastic modulus of the main frame. For the mesh weave density, The buoyancy coefficient of the floating body. The number of segments for the net cage. Let i be the vibration attenuation of the i-th segment of the cage. For the flow direction angle, The interval is the segmented angle.

[0058] Specifically, the wave energy buffer adaptive control algorithm is the core technology for dynamically adapting the net cage structure to the wave and current environment. Its implementation revolves around improving the anti-overturning stability coefficient and eliminating risk points. Active control is achieved through precise calculation of adjustments to key control parameters. During algorithm implementation, the control gain coefficient is set to 0.1-0.3 based on the net cage size and aquaculture scale. First, the anti-overturning stability coefficient and risk point data from step S3 are extracted. Combined with the elastic modulus of the main frame, netting weaving density, and buoyancy coefficient of the float from step S1, a correlation between structural parameters and control effects is established through fractional calculations. Simultaneously, the algorithm divides the net cage into 3-8 segments along its length, setting the segment angle interval to 15°-30°. By summing operations, the coupling effect of vibration attenuation and flow angle in each segment is integrated to precisely calculate the adjustment amount of the anchor pull angle. During implementation, the algorithm iterates every 2 minutes, dynamically adjusting the control parameters based on changes in the anti-overturning stability coefficient. It simultaneously outputs the incremental adjustments to the floating body distribution position (0.5-2.0 meters), the netting tension adjustment ratio (10%-50%), and the anchorage traction angle range (5°-20°), and sends the control commands to the actuators. This algorithm achieves adaptive and precise control measures. By responding in real-time to changes in the wave and current environment and the net cage's state feedback, it overcomes the limitations of traditional fixed structural parameters that are difficult to adapt to complex environments, maximizing the wave energy buffering effect, continuously optimizing the net cage's stress state, and significantly improving anti-overturning stability.

[0059] Preferably, the parameter output model of the cage material performance simulation calculation gateway is as follows:

[0060] ,

[0061] in, Output parameter values ​​for the gateway. For gateway conversion coefficients, This represents the stress distribution value of the material. This represents the amount of structural deformation. This represents the cumulative fatigue damage value. The elastic modulus of the main frame. The weave density of the mesh garment.

[0062] Specifically, the parameter output model of the cage material performance simulation calculation gateway is used to integrate multi-dimensional material performance data collected by the gateway and generate standardized parameter values ​​that can be directly used for subsequent optimization. During model implementation, the gateway conversion coefficient is preset to 0.9-1.1 based on the sensor type and data transmission protocol. First, the gateway's stress monitoring module collects real-time stress data (range 0-500MPa) of the cage frame, mesh, and connectors, generating a global stress distribution cloud map. Then, the fatigue damage calculation module calculates the cumulative fatigue damage value (0-1.0) for each part based on the stress data and the material SN curve. Simultaneously, the deformation monitoring module obtains the linear deformation of the frame (0-50mm) and the in-plane deformation of the mesh (0-100mm). The model couples the stress distribution value, structural deformation, and cumulative fatigue damage value through multiplication and square root operations, and then combines this with the ratio of the main frame's elastic modulus to the mesh weaving density to comprehensively reflect the synergistic relationship between material mechanical properties and structural state. During implementation, the model processes data collected by the gateway every minute, with data processing latency controlled within 0.5 seconds. The output parameter values ​​are set to a range of 0-100, with higher values ​​indicating better material properties and structural state. This model integrates and standardizes material performance data, providing unified and accurate feedback indicators for subsequent structural optimization. It avoids the inefficiency of optimization decisions caused by scattered multi-source data, ensuring that the optimization process can make precise parameter adjustments based on comprehensive material performance feedback.

[0063] Preferably, the parameter matching model for optimizing the boat-shaped aquaculture cage structure is as follows:

[0064] ,

[0065] in, To optimize the matching degree of the structure, To optimize the weighting coefficients, For the allowable stress of the material, To allow for cumulative fatigue damage, This represents the actual stress distribution value of the material. This represents the actual cumulative fatigue damage value. To design the elastic modulus, This is the actual elastic modulus. To design the mesh weave density, This refers to the actual mesh weave density.

[0066] Specifically, the parameter matching model for optimizing the structure of boat-shaped aquaculture cages is used to quantify the degree of fit between actual structural parameters and design objectives, providing a basis for judgment in multi-dimensional structural optimization. During model implementation, the optimization weight coefficient is set to 0.6-0.8 based on safety and economic requirements. First, design indicators such as allowable material stress (300-500MPa) and allowable cumulative fatigue damage (0.6-0.8) are defined. Then, the actual material stress distribution, actual cumulative fatigue damage, actual elastic modulus, and actual netting weaving density are obtained through a netting material performance simulation calculation gateway. The model compares the differences between actual performance parameters and design indicators through fractional operations, and then integrates the ratio of the design value to the actual value of the elastic modulus and netting weaving density through square root operations to comprehensively calculate the structural optimization matching degree. During implementation, the model receives updated actual performance data every 5 minutes and calculates the optimization matching degree in real time. This matching degree ranges from 0 to 1.0. When the value is below 0.7, the structural parameter optimization process is triggered, clarifying the adjustment direction and magnitude of the frame cross-sectional dimensions, netting mesh size, number of floats, and anchor spacing. This model establishes a quantitative correlation between structural parameters, material properties, and design objectives, providing objective and accurate judgment criteria for optimization decisions. It avoids the problem of insufficient parameter matching caused by traditional optimization relying on experience, ensuring that the optimized structural parameters can simultaneously meet the requirements of safety, durability, and economy.

[0067] Preferred, such as Figure 2 As shown, step S3 includes the following sub-steps: S31, the vibration displacement and vibration frequency data of the net cage obtained in S2 are time-aligned with the wave velocity, wave height, wave period and flow direction angle parameters collected by the wave and current monitoring equipment to form a multi-dimensional input dataset; S32, the dataset is input into the ship-type net cage anti-overturning early warning model, and the wave and current loads in different directions are decomposed by the wave and current force calculation module inside the model to determine the difference in lateral thrust, longitudinal tension and vertical buoyancy force on the net cage; S33, based on the wave and current load decomposition results, combined with the net cage's center of gravity height, buoyancy center position and metacentric radius parameters, the anti-overturning stability coefficient of the net cage under different working conditions is calculated; S34, by judging the stability coefficient threshold, the risk points where the net cage is prone to overturning under the combined action of waves and current are located, forming a risk point coordinate dataset.

[0068] Specifically, step S3 achieves accurate assessment of overturning risk through four sub-steps. S31 first aligns the vibration displacement and frequency data of the net cage obtained in step S2 with the parameters collected by the wave and current monitoring equipment. The vibration data sampling frequency is 10Hz, and the wave and current parameters include a flow velocity of 0.5-2.5m / s, a wave height of 0.3-3.0m, a wave period of 3-12s, and a flow direction angle of 0-180°. A timestamp synchronization algorithm is used to ensure that the data time error does not exceed 0.1 seconds, forming a multi-dimensional input dataset including vibration and wave and current information. S32 inputs the dataset into the ship-type net cage overturning early warning model. The wave and current force calculation module inside the model uses a vector decomposition algorithm to decompose the combined wave and current load into lateral, longitudinal, and... Vertical load decomposition clarifies the differences in lateral thrust, longitudinal tension, and vertical buoyancy experienced by various parts of the cage, with a decomposition accuracy of 0.01 kN. Based on the load decomposition results, and combined with structural geometric parameters such as the cage's center of gravity height, center of buoyancy position, and epicenter radius, S33 uses static equilibrium equations to calculate the cage's overturning stability coefficient under different wave and current conditions, with a calculation step size set at 0.5 seconds to ensure real-time results. S34 presets a stability coefficient threshold of 1.2. When the calculated result is lower than this value, a risk point identification algorithm, combined with load distribution and vibration characteristic data, locates key areas of the cage prone to overturning, generating a risk point dataset including coordinate information. This summary, through step-by-step refinement, ensures the entire process of overturning assessment—from data preparation and load decomposition to coefficient calculation and risk location—is precise and controllable, providing a clear basis for subsequent regulation.

[0069] Preferred, such as Figure 3 As shown, S4 includes the following sub-steps: S41, extract the anti-overturning stability coefficient and risk point coordinate data output by S3, and establish a mapping relationship model between the control parameters and the stability coefficient; S42, based on the mapping relationship model, calculate the adjustment increment of the floating body distribution position, the adjustment ratio of the net tension, and the change range of the anchor pulling angle through the wave energy buffer adaptive control algorithm; S43, move the floating body installation position according to the calculated adjustment increment, change the extension and retraction of the net tensioning mechanism through the hydraulic control device, and adjust the length of the anchor pulling rope to change the pulling angle; S44, collect the net cage attitude data after control in real time, and feed it back to the wave energy buffer adaptive control algorithm to form a closed-loop control logic.

[0070] Specifically, step S4 achieves adaptive and precise control of wave energy buffering through four sub-steps. S31 first extracts the anti-overturning stability coefficient and risk point coordinate data output from step S3. A multivariate regression analysis algorithm is used to establish a mapping relationship model between control parameters such as the floating body distribution position, netting tension, and anchorage pulling angle and the stability coefficient. The model fit is no less than 0.95 to ensure accurate correlation. S42, based on this mapping relationship model, calls the wave energy buffering adaptive control algorithm, inputting the stability coefficient, risk points, and netting structure parameters. It calculates the adjustment increment of the floating body distribution position (range 0.5-2.0 meters), the adjustment ratio of the netting tension (10%-50%), and the change range of the anchorage pulling angle (5°-20°), and calculates the iteration cycle. The control period is 2 seconds, adapting to dynamic changes in the wave and current environment. S43 executes control operations according to the calculation results, moving the floating body's installation position via an electric translation device with a translation accuracy of 0.05 meters, adjusting the extension and retraction of the netting tensioning mechanism via a hydraulic control device with an adjustment accuracy of 0.1 millimeters, and adjusting the length of the anchorage traction rope via a winch device to achieve precise correction of the traction angle. S44 collects attitude data such as the net cage's tilt angle, pitch angle, and draft in real time using attitude sensors at a sampling frequency of 5Hz, feeding the data back to the wave energy buffer adaptive control algorithm, forming a closed-loop logic of "calculation-control-feedback-iteration" to ensure continuous optimization of the control effect. This approach, implemented step-by-step, automates the entire control process from model establishment and parameter calculation to execution feedback, improving the net cage's adaptability to complex wave and current environments.

[0071] Preferred, such as Figure 4 As shown, step S5 includes the following sub-steps: S51, activating the stress monitoring module of the cage material performance simulation calculation gateway, collecting real-time stress data of the cage frame, netting, and connectors through distributed sensors, and generating a stress distribution cloud map; S52, using the fatigue damage calculation module of the gateway, calculating the cumulative fatigue damage value of the material in each part of the cage based on the stress distribution data and the material SN curve; S53, using the deformation monitoring module of the gateway, acquiring the linear deformation of the main frame of the cage and the in-plane deformation of the netting using laser ranging technology; S54, converting and compressing the stress distribution cloud map, cumulative fatigue damage value, and deformation data, and transmitting them to the structural optimization decision module.

[0072] Specifically, step S5 achieves comprehensive real-time feedback on the performance of the cage material through four sub-steps. S51 activates the stress monitoring module of the cage material performance simulation calculation gateway, arranging distributed strain gauges at 12-18 key sections of the cage frame, 20-30 monitoring points on the mesh, and all connector interfaces. The strain gauge accuracy is ±2με, and the sampling frequency is set to 5Hz. Real-time stress data for each location is collected, and a global stress distribution cloud map is generated using a data visualization algorithm, clearly showing the stress concentration areas. S52 utilizes the gateway's fatigue damage calculation module, calling the preset SN curve of the cage material. Based on the stress distribution data collected in S51 and the control time, the cumulative fatigue damage value of the material at each location is calculated using Miner's linear cumulative damage theory. The calculation time interval is... Within one hour, the damage assessment is ensured to accurately reflect actual service conditions. The S53 module, through the gateway's deformation monitoring module, sets laser ranging targets at 8-10 feature points on the cage frame and 4-6 key areas on the mesh, achieving a laser ranging accuracy of ±0.1 mm. It measures the linear deformation of the frame and the in-plane deformation of the mesh in real time, with a data update frequency of 10 Hz. The S54 module employs a standardized data format conversion algorithm to convert the pixel information of the stress distribution cloud map, cumulative fatigue damage values, and deformation data into a unified format. A lossless compression algorithm is used to control the data compression ratio to within 10:1, and then the data is transmitted in real time to the structural optimization decision module via wired transmission, with a transmission delay of no more than 0.5 seconds. This approach, by refining the monitoring, calculation, measurement, and transmission processes step by step, ensures that the material performance feedback data is comprehensive, accurate, and real-time, providing reliable support for subsequent structural optimization.

[0073] like Figure 5 As shown, a method for optimizing the structure of a boat-shaped aquaculture cage is proposed. This method is implemented through different units, including: a structural parameter acquisition unit, a wave-current coupling vibration analysis unit, an anti-overturning risk assessment unit, a wave energy buffering and control unit, a material performance feedback unit, and a multi-dimensional optimization decision-making unit.

[0074] The structural parameter acquisition unit establishes a data transmission connection with the cage material performance simulation calculation gateway to collect the elastic modulus of the main frame and the structural parameters of the netting weave density of the boat-shaped aquaculture cage and transmit them to the wave-current coupled vibration analysis unit. After receiving the structural parameters, the wave-current coupled vibration analysis unit analyzes the vibration characteristics of the cage through its built-in wave-current coupled cage vibration attenuation model and sends the vibration analysis results to the anti-overturning risk assessment unit. The anti-overturning risk assessment unit calls the boat-shaped cage anti-overturning early warning model, calculates the anti-overturning stability coefficient and risk points in combination with wave-current parameters, and outputs them to the wave energy buffer control unit. The wave energy buffer control unit adopts a wave energy buffer adaptive control algorithm to dynamically adjust the distribution of the cage float, the tension of the netting, and the anchor pull angle, while feeding back the control commands to the material performance feedback unit. The material performance feedback unit obtains the stress distribution, fatigue damage accumulation, and structural deformation data after control through the cage material performance simulation calculation gateway and transmits them to the multi-dimensional optimization decision unit. The multi-dimensional optimization decision unit optimizes the cage frame cross-sectional dimensions and netting mesh size parameters based on the received data to form the final optimization scheme.

[0075] The formula in this invention can integrate different scalar and vector parameters for unified calculation. Through scientific parameter normalization and physical meaning correlation modeling, it eliminates calculation conflicts caused by differences in parameter types. Scalar parameters, such as the elastic modulus of the main frame, the mesh weaving density, and the buoyancy coefficient of the float, have clear numerical quantification attributes and can be directly converted into a unified dimension suitable for formula calculation through magnitude calibration. Vector parameters, such as wave velocity, flow direction angle, and vibration displacement, are decomposed into components along the coordinate system of the net cage structure (such as transverse, longitudinal, and vertical vector components), converting directional characteristics into quantifiable numerical indicators, and then establishing correlations with the physical action mechanisms corresponding to the parameters. For example, in the wave-current coupled cage vibration attenuation model, the wave velocity (vector) and wave height (scalar) are related through trigonometric functions. The directional characteristics of the velocity are transformed into numerical effects through weighting coefficients related to the flow direction angle. It is integrated with the elastic modulus (scalar) and anchorage stiffness (scalar) through operations such as product and square root. Essentially, it is based on the joint action mechanism of wave and current on cage vibration, transforming the directional effect of the vector and the magnitude effect of the scalar into a unified vibration attenuation quantification index, ensuring that different types of parameters form a logical closed loop at the physical meaning level.

[0076] Meanwhile, the formula achieves coordinated calculation of scalar and vector parameters by introducing targeted correction coefficients and coupling functions. Correction coefficients, such as vibration attenuation coefficients and anti-overturning correction coefficients, are calibrated based on extensive experimental data, compensating for dimensional differences in different types of parameters and ensuring the calculation results conform to actual physical laws. Coupling functions, such as wave-current direction and period coupling functions, are specifically used to integrate the directional characteristics of vector parameters with the magnitude characteristics of scalar parameters, establishing a quantitative correlation between their physical effects. Taking the anti-overturning early warning model of a ship-shaped gabion as an example, the flow angle (vector) and wave period (scalar) are transformed into a unified load influence factor through the coupling function. This factor is then combined with the buoyancy coefficient (scalar) of the floating body and the draft of the gabion (scalar) through fractional and logarithmic operations. This retains the influence of the flow angle direction on overturning risk while quantifying the structure's own anti-overturning fundamental capability through scalar parameters, ultimately outputting a unified anti-overturning stability coefficient. This design respects the physical nature of different parameters and achieves organic integration between them through mathematical modeling, enabling the formula to comprehensively reflect the multi-factor coupling effects of gabion structures in complex marine environments.

[0077] A method for optimizing the structure of a boat-shaped aquaculture cage has been developed, constructing a multi-model collaborative and closed-loop technical system to achieve precise, dynamic, and comprehensive structural optimization. Through a dedicated material performance simulation gateway, the system collects structural and performance parameters of key components such as the cage frame, netting, and connectors. Combined with a wave-current coupled vibration attenuation model, it overcomes the limitations of traditional single-load analysis, deeply analyzing the vibration patterns of the cage under the combined action of waves and currents, providing precise data support for subsequent optimization. An anti-capsulation early warning model accurately locates risk points, and a wave energy buffer adaptive control algorithm dynamically adjusts relevant parameters of the float, netting, and anchorage, forming a targeted control logic that effectively improves the cage's adaptability to complex marine environments. Through real-time material performance feedback and multi-dimensional parameter optimization, a direct correlation is established between structural parameters and stress, fatigue damage, and deformation, ensuring that the optimized scheme possesses both stability and durability.

[0078] This method addresses the lack of deep integration between wave-current coupling and structural characteristics in traditional technologies. By synergistically applying a wave-current coupling vibration attenuation model and an anti-overturning early warning model, it comprehensively captures the combined effects of wave and current on the vibration and anti-overturning performance of the cage, making the optimization scheme more aligned with the actual marine environment. Furthermore, it addresses the shortcomings of existing technologies, such as lagging material performance monitoring and reliance on empirical parameters. A material performance simulation calculation gateway enables real-time feedback of stress, fatigue damage, and deformation. Combined with a wave energy buffer adaptive control algorithm, a closed-loop control mechanism is constructed to replace empirical parameter settings, driving dynamic iteration of the optimization scheme. This not only solves the problem of insufficient structural adaptability but also extends the service life of the cage material, achieving a dual improvement in safety and economy.

[0079] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and alterations 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 method for optimizing a structure of a net cage for fish farming, characterized in that, Includes the following steps: S1. Using a network gateway, structural parameters related to the main frame elastic modulus, netting weaving density, shear strength of connectors, buoyancy coefficient of the float, anchorage stiffness, and draft of the ship-shaped aquaculture cage are collected through material performance simulation calculations. S2. Based on the collected structural parameters, a wave-current coupled cage vibration attenuation model is constructed. This model is used to analyze the vibration displacement, vibration frequency, and vibration propagation characteristics of different parts of the cage under the combined action of waves and currents. S3. The ship-shaped cage anti-overturning early warning model is invoked. Combining the vibration analysis results with wave and current velocity, wave height, wave period, and flow direction angle parameters, the anti-overturning early warning parameters of the cage are obtained. S4. Using a wave energy buffer adaptive control algorithm, the distribution position of the cage floats, the tension of the netting, and the anchorage pulling angle are dynamically adjusted according to the anti-overturning stability coefficient and the risk points; S5. The stress distribution, fatigue damage accumulation, and structural deformation of the cage material after real-time feedback control are calculated through cage material performance simulation; S6. Based on the stress distribution, fatigue damage accumulation, and structural deformation data, the frame cross-sectional dimensions, netting mesh size, number of floats, and anchorage spacing of the boat-shaped aquaculture cage are optimized in multiple dimensions.

2. The method for optimizing the structure of a boat-shaped aquaculture cage according to claim 1, characterized in that, The expression for the vibration attenuation model of the wave-current coupled cage is as follows: ， in, This is the vibration attenuation of the cage. The vibration attenuation coefficient is... The elastic modulus of the main frame. For the mesh weave density, The weighting factor for the influence of flow velocity. For wave velocity, The wave height influence weighting coefficient. For wave height, To ensure the rigidity of the anchorage, This is the buoyancy coefficient of the buoyant body.

3. The method for optimizing the structure of a boat-shaped aquaculture cage according to claim 1, characterized in that, The expression for the anti-overturning early warning model of the ship-shaped cage is: ， in, The overturning stability coefficient of the cage. This is the overturning correction factor. For the draft of the net cage, For the shear strength of the connector, For the flow direction angle, For wave period, The wave-current direction and period coupling function, This is the vibration attenuation of the cage. To ensure the rigidity of the anchorage.

4. The method for optimizing the structure of a boat-shaped aquaculture cage according to claim 1, characterized in that, The expression for the wave energy buffer adaptive control algorithm is as follows: ， in, This is the amount of adjustment for the anchorage pulling angle. To adjust the gain coefficient, The overturning stability coefficient of the cage. The elastic modulus of the main frame. For the mesh weave density, The buoyancy coefficient of the floating body. The number of segments for the net cage. Let i be the vibration attenuation of the i-th segment of the cage. For the flow direction angle, The interval is the segmented angle.

5. The method for optimizing the structure of a boat-shaped aquaculture cage according to claim 1, characterized in that, The parameter output model of the gateway for simulating and calculating the material properties of the wire mesh cage is as follows: ， in, Output parameter values ​​for the gateway. For gateway conversion coefficients, This represents the stress distribution value of the material. This represents the amount of structural deformation. This represents the cumulative fatigue damage value. The elastic modulus of the main frame. The weave density of the mesh garment.

6. The method for optimizing the structure of a boat-shaped aquaculture cage according to claim 1, characterized in that, The parameter matching model for optimizing the boat-shaped aquaculture cage structure is as follows: ， in, To optimize the matching degree of the structure, To optimize the weighting coefficients, For the allowable stress of the material, To allow for cumulative fatigue damage, This represents the actual stress distribution value of the material. This represents the actual cumulative fatigue damage value. To design the elastic modulus, This is the actual elastic modulus. To design the mesh weave density, This refers to the actual mesh weave density.

7. The method for optimizing the structure of a boat-shaped aquaculture cage according to claim 1, characterized in that, S3 includes the following sub-steps: S31, the vibration displacement and vibration frequency data of the net cage obtained in S2 are time-series aligned with the wave velocity, wave height, wave period and flow direction angle parameters collected by the wave and current monitoring equipment to form a multi-dimensional input dataset; S32, the dataset is input into the ship-type net cage anti-overturning early warning model, and the wave and current loads in different directions are decomposed by the wave and current force calculation module inside the model to determine the difference in lateral thrust, longitudinal tension and vertical buoyancy force on the net cage; S33, based on the wave and current load decomposition results, combined with the net cage's center of gravity height, buoyancy center position and metacentric radius parameters, the anti-overturning stability coefficient of the net cage under different working conditions is calculated; S34, by judging the stability coefficient threshold, the risk points where the net cage is prone to overturning under the combined action of waves and current are located, forming a risk point coordinate dataset.

8. The method for optimizing the structure of a boat-shaped aquaculture cage according to claim 1, characterized in that, S4 includes the following sub-steps: S41, extract the anti-overturning stability coefficient and risk point coordinate data output from S3, and establish a mapping relationship model between the control parameters and the stability coefficient; S42, based on the mapping relationship model, calculate the adjustment increment of the floating body distribution position, the adjustment ratio of the net tension, and the change range of the anchor pulling angle through the wave energy buffer adaptive control algorithm; S43, move the floating body installation position according to the calculated adjustment increment, change the extension and retraction of the net tensioning mechanism through the hydraulic control device, and adjust the length of the anchor pulling rope to change the pulling angle; S44, collect the net cage attitude data after control in real time, and feed it back to the wave energy buffer adaptive control algorithm to form a closed-loop control logic.

9. The method for optimizing the structure of a boat-shaped aquaculture cage according to claim 1, characterized in that, S5 includes the following steps: S51, activating the stress monitoring module of the cage material performance simulation calculation gateway, collecting real-time stress data of the cage frame, netting, and connectors through distributed sensors, and generating a stress distribution cloud map; S52, using the fatigue damage calculation module of the gateway, calculating the cumulative fatigue damage value of the material in each part of the cage based on the stress distribution data and the material SN curve; S53, using the deformation monitoring module of the gateway, acquiring the linear deformation of the main frame of the cage and the in-plane deformation of the netting using laser ranging technology; S54, converting and compressing the stress distribution cloud map, cumulative fatigue damage value, and deformation data, and transmitting them to the structural optimization decision module.

10. A method for optimizing the structure of a boat-shaped aquaculture cage according to any one of claims 1-9, characterized in that, This method is implemented through different units, including: a structural parameter acquisition unit, a wave-current coupling vibration analysis unit, an overturning risk assessment unit, a wave energy buffering and control unit, a material performance feedback unit, and a multi-dimensional optimization decision-making unit; The structural parameter acquisition unit establishes a data transmission connection with the cage material performance simulation calculation gateway to collect the elastic modulus of the main frame and the structural parameters of the netting weave density of the boat-shaped aquaculture cage and transmit them to the wave-current coupled vibration analysis unit. After receiving the structural parameters, the wave-current coupled vibration analysis unit analyzes the vibration characteristics of the cage through its built-in wave-current coupled cage vibration attenuation model and sends the vibration analysis results to the anti-overturning risk assessment unit. The anti-overturning risk assessment unit calls the boat-shaped cage anti-overturning early warning model, calculates the anti-overturning stability coefficient and risk points in combination with wave-current parameters, and outputs them to the wave energy buffer control unit. The wave energy buffer control unit adopts a wave energy buffer adaptive control algorithm to dynamically adjust the distribution of the cage float, the tension of the netting, and the anchor pull angle, while feeding back the control commands to the material performance feedback unit. The material performance feedback unit obtains the stress distribution, fatigue damage accumulation, and structural deformation data after control through the cage material performance simulation calculation gateway and transmits them to the multi-dimensional optimization decision unit. The multi-dimensional optimization decision unit optimizes the cage frame cross-sectional dimensions and netting mesh size parameters based on the received data to form the final optimization scheme.

Images