Intelligent lifting and mooring method and system applied to offshore combined net cage

Abstract

The application discloses an intelligent lifting and mooring method and system applied to offshore combined net cages, and the method comprises the following steps: setting underwater image and environment monitoring devices according to the distribution of the combined net cages to collect image data and environment data; in the lifting and mooring process, the horizontal and vertical deviations of reference points of the net cages are analyzed in combination with the underwater image data, and deviation vectors are generated; the clustering algorithm is used to screen the points with consistent deviation characteristics and large proportion, the cluster with the largest number of points is marked, and the deviation characteristic points are obtained by mapping the reference point classification; the first stress distribution information closest to the deviation characteristic points is extracted by acquiring the cable stress distribution data; double risk assessment is carried out in combination with the expected stress distribution and environment data, early warning information and net cage control regulation information are generated. Through the application, the stability, safety and intelligent level of the net cage lifting and mooring can be improved, the complex offshore environment can be adapted, and the loss of net cage operation can be reduced.

Description

Technical Field

[0001] This invention relates to the field of intelligent offshore operations, and more specifically, to an intelligent lifting and mooring method and system for offshore modular cages. Background Technology

[0002] As marine aquaculture develops towards large-scale and deep-sea operations, modular cages have become one of the mainstream equipment for marine aquaculture due to their advantages such as flexible assembly, large aquaculture capacity, and adaptability to different marine environments. Modular cages are typically composed of multiple individual cages assembled with connectors, allowing for scale adjustments based on aquaculture needs. They are widely used in fish and shellfish farming, playing a crucial role in ensuring aquaculture yields and expanding aquaculture space. However, the marine environment is highly random, complex, and uncertain; environmental factors such as wind, waves, and ocean currents are constantly changing, placing extremely high demands on the raising, lowering, and mooring safety of modular cages.

[0003] Currently, the lifting and mooring of marine modular cages mostly adopt traditional manual control or simple automated control methods, which have many technical defects. Traditional technologies often rely on single experience or simple environmental factors to determine whether cage lifting, moving, or mooring operations can be carried out. They lack multi-dimensional data fusion analysis, dynamic prediction, and control and regulation optimization. They cannot achieve coordinated control and adaptive adjustment of lifting and mooring installation, and it is difficult to judge potential risk factors and comprehensive stress trends during real-time movement. This leads to problems such as splicing misalignment and uneven mooring stress. Furthermore, there is a lack of targeted analysis and adjustment methods. When problems occur, operations can only be stopped or waiting for a safe opportunity can be waited for, resulting in poor practicality. Summary of the Invention

[0004] This invention overcomes the shortcomings of the prior art and proposes an intelligent lifting and mooring method and system for marine modular cages.

[0005] The first aspect of this invention provides an intelligent lifting and mooring method for offshore modular cages, comprising: S1: Based on the distribution of the modular cages, set up underwater imaging devices and environmental monitoring devices to collect underwater image data and environmental data of the modular cages through the devices; S2: During the lifting and mooring of the combined cage, the deviations in the horizontal and vertical dimensions of different reference points are analyzed in real time using the reference points of the cage and underwater image data, and a deviation vector is generated. S3: Cluster the deviation vectors of all combined cages, label the clusters with the most numbers, and map them to the classification of the reference site to obtain the deviation feature points; S4: Obtain the cable force distribution data of the combined cage, extract the force information closest to the deviation feature point, and obtain the first force distribution information; S5: Conduct a preliminary risk assessment by combining the expected force distribution information and the first force distribution information, and conduct a real-time control risk assessment by combining environmental data. Based on the horizontal and vertical deviation characteristics of the deviation point and the first force distribution information, generate early warning information and cage control and regulation information.

[0006] In this solution, S1 specifically refers to: A modular wire mesh cage consists of multiple individual wire mesh cages, which are spliced ​​together by rigid connectors. The modular cages consist of multiple units. Based on the location distribution of the modular cages, multiple underwater imaging devices are installed, ensuring that each modular cage includes one or more underwater imaging devices. Underwater imaging devices are used to acquire underwater image data of the modular cage, covering the four corners and the center of the cage.

[0007] In this solution, S1 further includes: Based on the distribution of the modular cages, multiple environmental monitoring devices are set up, ensuring that each location of a modular cage corresponds to one environmental monitoring device; Environmental data is collected at the corresponding location of each modular cage through environmental monitoring devices. The environmental data includes wind speed, wind direction, water temperature, salinity, water flow velocity, and water flow direction.

[0008] In this solution, S2 specifically refers to: During the lifting and mooring of the modular cage, underwater image data is acquired for image noise reduction and enhancement preprocessing. By using an edge detection operator, the preprocessed underwater image data is converted to grayscale and edge features are extracted to obtain real-time edge features at different locations in the image. The real-time edge features are compared with the preset edge features to determine the actual location of the reference point. Based on the operational requirements, calculate the horizontal and vertical deviations between the actual location point and the ideal moving point, and generate a two-dimensional deviation vector. ; Multiple deviation vectors are generated based on multiple reference points.

[0009] In this solution, S3 specifically refers to: Calculate the deviation vectors of all combined cages and form a sample set; K-medoids clustering is introduced, and the deviation vectors corresponding to the center points of the K combined cages are selected as the initial cluster centers; Calculate the distance between all data points corresponding to non-cluster centers and each initial cluster center, and classify the non-cluster centers based on the shortest distance to form K clusters; Within each cluster, the cluster centers are cyclically changed, and the total dissimilarity of the clusters is calculated after each change of cluster centers; The clustering state is updated cyclically until the preset number of iterations is reached, and the clustering state with the lowest total dissimilarity is recorded. The largest cluster is selected based on the clustering state. The corresponding reference sites are extracted as deviation feature points based on the deviation vectors in the largest cluster.

[0010] In this solution, S4 specifically refers to: By using a stress monitoring device, the stress data and time information of the stress records of the combined cage in various directions are obtained, and stress distribution data are generated. Calculate the straight-line distance between each deviation feature point and the corresponding cage cable, and select the cable with the smallest distance as the associated cable corresponding to that deviation feature point; By extracting the tension value, direction of force, rate of change of force, frequency of force, and duration of force of the associated cable from the force distribution data, the first force distribution information is obtained.

[0011] In this solution, S5 specifically refers to; By comparing the expected force distribution information with the first force distribution information in multiple dimensions and conducting a risk assessment, the force risk status is obtained. By combining environmental data, real-time environmental risk and control risk assessments are conducted to obtain the environmental risk status. Based on the deviation vector corresponding to the deviation feature point, the horizontal and vertical deviation characteristics of the force are analyzed. The current early warning status is comprehensively assessed by combining the force risk status and the environmental risk status, and cage control and regulation information is generated. The current early warning status and generated cage control and regulation information are then sent to a preset terminal device.

[0012] A second aspect of the present invention also provides an intelligent lifting and mooring system for offshore modular cages. The system includes a memory, a processor, and an interface. The memory includes an intelligent lifting and mooring program for offshore modular cages. When executed by the processor, the intelligent lifting and mooring program for offshore modular cages performs the following steps: S1: Based on the distribution of the modular cages, set up underwater imaging devices and environmental monitoring devices to collect underwater image data and environmental data of the modular cages through the devices; S2: During the lifting and mooring of the combined cage, the deviations in the horizontal and vertical dimensions of different reference points are analyzed in real time using the reference points of the cage and underwater image data, and a deviation vector is generated. S3: Cluster the deviation vectors of all combined cages, label the clusters with the most numbers, and map them to the classification of the reference site to obtain the deviation feature points; S4: Obtain the cable force distribution data of the combined cage, extract the force information closest to the deviation feature point, and obtain the first force distribution information; S5: Conduct a preliminary risk assessment by combining the expected force distribution information and the first force distribution information, and conduct a real-time control risk assessment by combining environmental data. Based on the horizontal and vertical deviation characteristics of the deviation point and the first force distribution information, generate early warning information and cage control and regulation information.

[0013] A third aspect of the present invention also provides a computer-readable storage medium including an intelligent lifting and mooring program for offshore modular cages, wherein when the intelligent lifting and mooring program for offshore modular cages is executed by a processor, it implements the steps of the intelligent lifting and mooring method for offshore modular cages as described in any of the preceding claims.

[0014] This invention discloses an intelligent lifting and mooring method and system for offshore modular cages. The method includes: setting up underwater image and environmental monitoring devices according to the distribution of the modular cages to collect image data and environmental data; during lifting and mooring, combining cage reference points and underwater image data to analyze the horizontal and vertical deviations of each reference point and generate a deviation vector; using a clustering algorithm to select points with consistent deviation characteristics and a large proportion, marking the cluster with the largest number, and mapping the reference points to obtain deviation feature points; acquiring cable force distribution data and extracting the first force distribution information closest to the deviation feature point; combining the expected force distribution and environmental data to perform a dual risk assessment, generating early warning information and cage control and regulation information. This invention can improve the stability, safety, and intelligence level of cage lifting and mooring, adapt to complex marine environments, and reduce losses in cage operations. Attached Figure Description

[0015] Figure 1 A flowchart of an intelligent lifting and mooring method for offshore modular cages according to the present invention is shown; Figure 2 The flowchart of the deviation vector analysis of the present invention is shown; Figure 3 A block diagram of an intelligent lifting and mooring system for offshore modular cages is shown. Detailed Implementation

[0016] To better understand the above-mentioned objects, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It will be understood that, unless otherwise specified, the embodiments and features described in the embodiments of this application can be combined with each other.

[0017] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0018] Figure 1 The flowchart illustrates an intelligent lifting and mooring method for marine modular cages according to the present invention.

[0019] like Figure 1 As shown, the first aspect of the present invention provides an intelligent lifting and mooring method for offshore modular cages, comprising: S1: Based on the distribution of the modular cages, set up underwater imaging devices and environmental monitoring devices to collect underwater image data and environmental data of the modular cages through the devices; S2: During the lifting and mooring of the combined cage, the deviations in the horizontal and vertical dimensions of different reference points are analyzed in real time using the reference points of the cage and underwater image data, and a deviation vector is generated. S3: Cluster the deviation vectors of all combined cages, label the clusters with the most numbers, and map them to the classification of the reference site to obtain the deviation feature points; S4: Obtain the cable force distribution data of the combined cage, extract the force information closest to the deviation feature point, and obtain the first force distribution information; S5: Conduct a preliminary risk assessment by combining the expected force distribution information and the first force distribution information, and conduct a real-time control risk assessment by combining environmental data. Based on the horizontal and vertical deviation characteristics of the deviation point and the first force distribution information, generate early warning information and cage control and regulation information.

[0020] According to an embodiment of the present invention, S1 specifically includes: A modular wire mesh cage consists of multiple individual wire mesh cages, which are spliced ​​together by rigid connectors. The modular cages consist of multiple units. Based on the location distribution of the modular cages, multiple underwater imaging devices are installed, ensuring that each modular cage includes one or more underwater imaging devices. Underwater imaging devices are used to acquire underwater image data of the modular cage, covering the four corners and the center of the cage.

[0021] As can be understood from the embodiments, the modular cages can generally form rectangular or polygonal structures, and multiple modular cages are generally placed in a grid-like manner. Through lifting and mooring control, they provide intelligent, safe and efficient aquaculture services.

[0022] The underwater imaging device includes a wireless communication module and a camera unit, used to acquire underwater images in real time and transmit them to the system terminal. The shooting ranges of two adjacent underwater cameras can be set to have a 10%-15% overlap area to avoid blind spots in monitoring, and the sampling frame rate of the underwater cameras is set to 10-20 frames / second to ensure that the real-time positional changes of the cage can be captured.

[0023] According to an embodiment of the present invention, step S1 further includes: Based on the distribution of the modular cages, multiple environmental monitoring devices are set up, ensuring that each location of a modular cage corresponds to one environmental monitoring device; Environmental data is collected at the corresponding location of each modular cage through environmental monitoring devices. The environmental data includes wind speed, wind direction, water temperature, salinity, water flow velocity, and water flow direction.

[0024] As can be understood from the embodiments, the environmental data may include other underwater or surface environments besides those mentioned above, depending on the analysis requirements.

[0025] Figure 2 A flowchart of the deviation vector analysis of the present invention is shown.

[0026] According to an embodiment of the present invention, step S2 specifically includes: During the lifting and mooring of the modular cage, underwater image data is acquired for image noise reduction and enhancement preprocessing. By using an edge detection operator, the preprocessed underwater image data is converted to grayscale and edge features are extracted to obtain real-time edge features at different locations in the image. The real-time edge features are compared with the preset edge features to determine the actual location of the reference point. Based on the operational requirements, calculate the horizontal and vertical deviations between the actual location point and the ideal moving point, and generate a two-dimensional deviation vector. ; Multiple deviation vectors are generated based on multiple reference points.

[0027] As can be understood in this embodiment, the reference points can be set based on the characteristics of the cage. For example, reference points can be set at the connection points between two individual cages in a modular cage to analyze the movement deviation at the connection points during movement, and to comprehensively analyze the overall movement deviation. This allows for the analysis of potential deviation trends and movement anomalies based on image features. The default reference points can be the four corners and the center point. Edge detection operators can employ LBP mode operators or Sobel operators, etc., to extract contour features from the image. The center position of the cage can be determined by identifying the center point based on the overall contour edge.

[0028] The preset edge features are the preset edge features of the reference points, used for feature comparison and confirmation of the reference point's location. The operational requirements include information such as the expected movement position, distance, and time of the reference points during the lifting and mooring of the cage, used to analyze the offset. The two-dimensional deviation vector is represented as follows: (V1, V2), where V1 and V2 represent the horizontal and vertical deviation distances, specifically calculated based on the positional deviation of the image recognition, with the unit of the deviation vector being meters.

[0029] Each modular cage has multiple deviation vectors, and each deviation vector corresponds to a reference point. In subsequent calculations, clustering is performed based on all deviation vectors of multiple modular cages to analyze deviation characteristics and potential risk trends.

[0030] According to an embodiment of the present invention, step S3 specifically includes: Calculate the deviation vectors of all combined cages and form a sample set; K-medoids clustering is introduced, and the deviation vectors corresponding to the center points of the K combined cages are selected as the initial cluster centers; Calculate the distance between all data points corresponding to non-cluster centers and each initial cluster center, and classify the non-cluster centers based on the shortest distance to form K clusters; Within each cluster, the cluster centers are cyclically changed, and the total dissimilarity of the clusters is calculated after each change of cluster centers; The clustering state is updated cyclically until the preset number of iterations is reached, and the clustering state with the lowest total dissimilarity is recorded. The largest cluster is selected based on the clustering state. The corresponding reference sites are extracted as deviation feature points based on the deviation vectors in the largest cluster.

[0031] As can be understood in the embodiments, the largest cluster is the cluster with the largest deviation vector.

[0032] According to an embodiment of the present invention, step S4 specifically includes: By using a stress monitoring device, the stress data and time information of the stress records of the combined cage in various directions are obtained, and stress distribution data are generated. Calculate the straight-line distance between each deviation feature point and the corresponding cage cable, and select the cable with the smallest distance as the associated cable corresponding to that deviation feature point; By extracting the tension value, direction of force, rate of change of force, frequency of force, and duration of force of the associated cable from the force distribution data, the first force distribution information is obtained.

[0033] As can be understood in the embodiments, the force monitoring device uses tension sensors for data acquisition. At least one tension sensor is installed on each cable, with the sensors positioned at the connection points between the cable and the gabion and between the cable and the anchor, ensuring comprehensive monitoring of the cable's stress state and recording of data. The modular gabion comprises multiple cables securing the gabion, each cable representing a different force direction, thereby obtaining force data in each direction.

[0034] The cable force distribution data also includes the cable force frequency and force duration, where the force frequency refers to the number of times the cable force changes per unit time, and the force duration refers to the duration for which the cable is in a certain force range.

[0035] Here, the initial force distribution information can be organized to form a force distribution matrix, which facilitates subsequent comparison and analysis with the expected force distribution information.

[0036] According to an embodiment of the present invention, step S5 specifically includes: By comparing the expected force distribution information with the first force distribution information in multiple dimensions and conducting a risk assessment, the force risk status is obtained. By combining environmental data, real-time environmental risk and control risk assessments are conducted to obtain the environmental risk status. Based on the deviation vector corresponding to the deviation feature point, the horizontal and vertical deviation characteristics of the force are analyzed. The current early warning status is comprehensively assessed by combining the force risk status and the environmental risk status, and the cage control and regulation information is generated.

[0037] As can be understood in the embodiments, the multi-dimensional parameter analysis includes information on tensile force, force direction, force change rate, force frequency, and force duration. The force risk status is used to reflect the comprehensive deviation of the multi-dimensional parameters. The greater the deviation, the greater the force risk.

[0038] Risk status can be set with multiple levels of risk labels based on the deviation between actual and expected levels.

[0039] The expected stress distribution information is based on the structural parameters, lifting height, mooring method, and pre-set cable stress standards for different sea state levels of the modular cage. These standards include the maximum allowable tensile force, minimum allowable tensile force, normal stress range, stress direction range, and stress change rate threshold for each cable, and are used to conduct stress risk assessment.

[0040] Here, environmental data is mainly analyzed to assess the risk impact of wind speed and direction on the raising, lowering, mooring, and control of the cages.

[0041] Specifically, the multi-dimensional force parameter comparison covers a comprehensive comparison of core force parameters, including the tension value, force direction, force change rate, force frequency, and force duration of each associated cable. The actual parameters in the first force distribution information are compared with the standard parameters in the expected force distribution information, and the deviation value and deviation percentage of each parameter are calculated. At the same time, combined with the force imbalance degree (the ratio of the standard deviation to the average value of the force values ​​of each associated cable), the force risk is graded and assessed, and finally the force risk status is obtained.

[0042] Secondly, the impact of environmental parameters on the raising, lowering, and mooring of the cages is analyzed to assess the environmental risk level. Simultaneously, considering the stress risk status, the adaptability of the cage control strategy under the current environment is analyzed to complete the control risk assessment, ultimately integrating the results to obtain the environmental risk status. Specifically, the assessment can be as follows: when the water flow velocity > 2 m / s or the wind speed > 15 m / s, the environmental risk is determined to be medium risk, and the control risk is simultaneously increased, requiring adjustments to the control strategy to adapt to severe sea conditions; when the water flow velocity > 3 m / s or the wind speed > 20 m / s, the environmental risk is determined to be high risk, and the control risk level is simultaneously increased to high risk, requiring the implementation of stricter control measures, etc. Finally, based on the deviation vector corresponding to the deviation feature point, the horizontal and vertical deviation characteristics of the stress are analyzed. Combining the stress risk status and the environmental risk status, the current warning status is comprehensively assessed, and cage control and regulation information is generated. Specifically, this includes obtaining information based on the first stress distribution information. The deviation vectors corresponding to multiple reference points are analyzed one by one. The horizontal deviation characteristics (magnitude and direction) and vertical deviation characteristics (magnitude and direction) of each deviation point are analyzed. The deviation characteristics of all deviation points are integrated to clarify the overall offset trend of one or more cages. For example, most deviation points are offset to the right, with horizontal deviation values ​​between 0.3-0.5m; most deviation points are below the standard position, with vertical deviation values ​​between 0.2-0.4m. Based on this analysis, it is concluded that the right side of the cage is vertically lower and horizontally offset to the right, indicating an uneven stress on the cables in the corresponding area. Subsequently, the stress risk status, environmental risk status, and the above deviation characteristics are comprehensively assessed. Combining the risk status and level superposition rules, the overall warning status is upgraded to high risk. Based on the comprehensive assessment results, targeted cage control and regulation information is generated, along with corresponding high-risk early warning information. The early warning information can indicate the risk level (high risk), the specific location of the reference point, and the stress status of the associated cables (overloaded cable number, stress deviation value). The cage control and regulation information is divided into lifting and lowering regulation information and mooring regulation and other optimized regulation information. During the regulation process, the real-time stress and environmental risk status can be combined to predict the subsequent displacement trend of the cage and adjust the pre-tension of the cables in each area in advance to achieve proactive prevention and control, and reduce the risk of cage displacement and cable overload.

[0043] According to an embodiment of the present invention, the current early warning status and generated cage control and regulation information are sent to a preset terminal device.

[0044] In this embodiment, the preset terminal devices include mobile terminals and computer terminals.

[0045] It is worth noting that traditional lifting and mooring technologies often rely on single experiences or simple environmental factors to determine whether cage lifting, moving, or mooring operations can be carried out. They lack multi-dimensional data fusion analysis, dynamic prediction, and control optimization, making it impossible to achieve coordinated control and adaptive adjustment of lifting and mooring installations. Furthermore, they struggle to assess potential risk factors and comprehensive stress trends during real-time movement. This invention, however, utilizes cage reference points and underwater image data to analyze vertical and horizontal deviations from an image perspective. It then clusters these deviations based on their characteristics, analyzing the characteristic points within each cluster (reflecting reference points where risks accumulate). Combined with the stress distribution at these reference points, it precisely analyzes risk states across different dimensions, effectively achieving comprehensive and multi-dimensional risk assessment for cage operations. This constructs an intelligent, precise, and efficient early warning mechanism, ensuring operational stability, safety, and intelligence, adapting to complex marine environments, and reducing aquaculture losses.

[0046] According to an embodiment of the present invention, it further includes: Multiple time points are set during the lifting and mooring of the modular cage; Select a set of deviation feature points of the combined cage, and in each node, extract the vertical deviation and horizontal deviation corresponding to a set of deviation feature points and average them to obtain the vertical mean deviation and the horizontal mean deviation. Based on multiple time points, the vertical mean deviation and the horizontal mean deviation are serialized to obtain the vertical deviation sequence and the horizontal deviation sequence. By using univariate linear regression, the vertical deviation sequence and the horizontal deviation sequence are fitted, and the correlation between the two sequences is determined by the linear coefficient. If a correlation exists, the risk of cage control in the next period is predicted and fed back to the early warning information in real time.

[0047] It is worth mentioning that modular cages require a certain amount of vertical and horizontal movement during relocation. In complex sea conditions, the deviation characteristics and trends during the lifting, raising, and mooring processes need to be analyzed in real time to assess and control risks. However, existing technologies often rely on human experience for judgment, resulting in low early warning capabilities.

[0048] Based on this, this invention analyzes the linear correlation between the horizontal and vertical deviation sequences according to deviation characteristic points. If the linear coefficients are all positive or negative and the difference is <= 0.2, a correlation is identified, and the deviation characteristic correlation is marked, indicating a control risk. The control status is further evaluated; the stronger the correlation, the higher the control risk, and this is fed back to the early warning information in real time. This improves operational stability, safety, and intelligence, adapts to complex marine environments, and reduces aquaculture losses.

[0049] As can be understood in the embodiments, the set of deviation feature points here can be deviation feature points of one or more selected combined cages. Vertical and horizontal deviation serialization is used to analyze the correlation between linear changes and common trends, and to set control risk warnings.

[0050] Figure 3 A block diagram of an intelligent lifting and mooring system for offshore modular cages is shown.

[0051] A second aspect of the present invention also provides an intelligent lifting and mooring system 3 for offshore modular cages. The system includes a memory, a processor, and an interface. The memory includes an intelligent lifting and mooring program for offshore modular cages. When executed by the processor, the intelligent lifting and mooring program for offshore modular cages performs the following steps: S1: Based on the distribution of the modular cages, set up underwater imaging devices and environmental monitoring devices to collect underwater image data and environmental data of the modular cages through the devices; S2: During the lifting and mooring of the combined cage, the deviations in the horizontal and vertical dimensions of different reference points are analyzed in real time using the reference points of the cage and underwater image data, and a deviation vector is generated. S3: Cluster the deviation vectors of all combined cages, label the clusters with the most numbers, and map them to the classification of the reference site to obtain the deviation feature points; S4: Obtain the cable force distribution data of the combined cage, extract the force information closest to the deviation feature point, and obtain the first force distribution information; S5: Conduct a preliminary risk assessment by combining the expected force distribution information and the first force distribution information, and conduct a real-time control risk assessment by combining environmental data. Based on the horizontal and vertical deviation characteristics of the deviation point and the first force distribution information, generate early warning information and cage control and regulation information.

[0052] A third aspect of the present invention also provides a computer-readable storage medium including an intelligent lifting and mooring program for offshore modular cages, wherein when the intelligent lifting and mooring program for offshore modular cages is executed by a processor, it implements the steps of the intelligent lifting and mooring method for offshore modular cages as described in any of the preceding claims.

[0053] This invention effectively enables early warning of the stress distribution of the cage during movement, assessment of the consistency between the control movement process and the expected outcome, and dynamic prediction and optimization of the lifting and mooring system. It assesses potential risk factors instead of simply relying on a single environmental state or single stress data to evaluate the risk of the lifting and mooring system, thus effectively improving the coordinated control and adaptive adjustment capabilities of the lifting and mooring installation.

[0054] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0055] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0056] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0057] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0058] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0059] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligent lifting and mooring of marine modular cages, characterized in that, include: S1: Based on the distribution of the modular cages, set up underwater imaging devices and environmental monitoring devices to collect underwater image data and environmental data of the modular cages through the devices; S2: During the lifting and mooring of the combined cage, the deviations in the horizontal and vertical dimensions of different reference points are analyzed in real time using the reference points of the cage and underwater image data, and a deviation vector is generated. S3: Cluster the deviation vectors of all combined cages, label the clusters with the most numbers, and map them to the classification of the reference site to obtain the deviation feature points; S4: Obtain the cable force distribution data of the combined cage, extract the force information closest to the deviation feature point, and obtain the first force distribution information; S5: Conduct a preliminary risk assessment by combining the expected force distribution information and the first force distribution information, and conduct a real-time control risk assessment by combining environmental data. Based on the horizontal and vertical deviation characteristics of the deviation point and the first force distribution information, generate early warning information and cage control and regulation information.

2. The intelligent lifting and mooring method for offshore modular cages according to claim 1, characterized in that, Specifically, S1 is: A modular wire mesh cage consists of multiple individual wire mesh cages, which are spliced ​​together by rigid connectors. The modular cages consist of multiple units. Based on the location distribution of the modular cages, multiple underwater imaging devices are installed, ensuring that each modular cage includes one or more underwater imaging devices. Underwater imaging devices are used to acquire underwater image data of the modular cage, covering the four corners and the center of the cage.

3. The intelligent lifting and mooring method for offshore modular cages according to claim 1, characterized in that, S1 further includes: Based on the distribution of the modular cages, multiple environmental monitoring devices are set up, ensuring that each location of a modular cage corresponds to one environmental monitoring device; Environmental data is collected at the corresponding location of each modular cage through environmental monitoring devices. The environmental data includes wind speed, wind direction, water temperature, salinity, water flow velocity, and water flow direction.

4. The intelligent lifting and mooring method for offshore modular cages according to claim 1, characterized in that, Specifically, S2 is: During the lifting and mooring of the modular cage, underwater image data is acquired for image noise reduction and enhancement preprocessing. By using an edge detection operator, the preprocessed underwater image data is converted to grayscale and edge features are extracted to obtain real-time edge features at different locations in the image. The real-time edge features are compared with the preset edge features to determine the actual location of the reference point. Based on the operational requirements, calculate the horizontal and vertical deviations between the actual location point and the ideal moving point, and generate a two-dimensional deviation vector. ; Multiple deviation vectors are generated based on multiple reference points.

5. The intelligent lifting and mooring method for offshore modular cages according to claim 1, characterized in that, Specifically, S3 is: Calculate the deviation vectors of all combined cages and form a sample set; K-medoids clustering is introduced, and the deviation vectors corresponding to the center points of the K combined cages are selected as the initial cluster centers; Calculate the distance between all data points corresponding to non-cluster centers and each initial cluster center, and classify the non-cluster centers based on the shortest distance to form K clusters; Within each cluster, the cluster centers are cyclically changed, and the total dissimilarity of the clusters is calculated after each change of cluster centers; The clustering state is updated cyclically until the preset number of iterations is reached, and the clustering state with the lowest total dissimilarity is recorded. The largest cluster is selected based on the clustering state. The corresponding reference sites are extracted as deviation feature points based on the deviation vectors in the largest cluster.

6. The intelligent lifting and mooring method for offshore modular cages according to claim 1, characterized in that, Specifically, S4 is: By using a stress monitoring device, the stress data and time information of the stress records of the combined cage in various directions are obtained, and stress distribution data are generated. Calculate the straight-line distance between each deviation feature point and the corresponding cage cable, and select the cable with the smallest distance as the associated cable corresponding to that deviation feature point; By extracting the tension value, direction of force, rate of change of force, frequency of force, and duration of force of the associated cable from the force distribution data, the first force distribution information is obtained.

7. The intelligent lifting and mooring method for offshore modular cages according to claim 1, characterized in that, Specifically, S5 is: By comparing the expected force distribution information with the first force distribution information in multiple dimensions and conducting a risk assessment, the force risk status is obtained. By combining environmental data, real-time environmental risk and control risk assessments are conducted to obtain the environmental risk status. Based on the deviation vector corresponding to the deviation feature point, the horizontal and vertical deviation characteristics of the force are analyzed. The current early warning status is comprehensively assessed by combining the force risk status and the environmental risk status, and the cage control and regulation information is generated.

8. The intelligent lifting and mooring method for offshore modular cages according to claim 7, characterized in that, The current early warning status and generated cage control and regulation information are sent to the preset terminal device.

9. An intelligent lifting and mooring system for offshore modular cages, characterized in that, The system includes: a memory, a processor, and an interaction interface. The memory includes an intelligent lifting and mooring program for offshore modular cages. When the processor executes the intelligent lifting and mooring program for offshore modular cages, it performs the following steps: S1: Based on the distribution of the modular cages, set up underwater imaging devices and environmental monitoring devices to collect underwater image data and environmental data of the modular cages through the devices; S2: During the lifting and mooring of the combined cage, the deviations in the horizontal and vertical dimensions of different reference points are analyzed in real time using the reference points of the cage and underwater image data, and a deviation vector is generated. S3: Cluster the deviation vectors of all combined cages, label the clusters with the most numbers, and map them to the classification of the reference site to obtain the deviation feature points; S4: Obtain the cable force distribution data of the combined cage, extract the force information closest to the deviation feature point, and obtain the first force distribution information; S5: Conduct a preliminary risk assessment by combining the expected force distribution information and the first force distribution information, and conduct a real-time control risk assessment by combining environmental data. Based on the horizontal and vertical deviation characteristics of the deviation point and the first force distribution information, generate early warning information and cage control and regulation information.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes an intelligent lifting and mooring program for offshore modular cages. When the intelligent lifting and mooring program for offshore modular cages is executed by a processor, it implements the steps of the intelligent lifting and mooring method for offshore modular cages as described in any one of claims 1 to 8.

Images