Group collaboration and environment perception method of lifting type culture net cage

Abstract

The invention relates to a group collaboration and environment perception method for a lifting type culture net cage, and belongs to the technical field of lifting type culture net cages. An underwater communication local area network is configured and optimized, and a plurality of environment monitoring buoys are arranged in a culture area; environment monitoring data in the current culture area is monitored through an environment monitoring buoy, a three-dimensional water body environment model is constructed, a fish growth adaptability prediction model is constructed based on a deep neural network, and adaptability data of each depth layer in the current three-dimensional water body environment model is predicted; and finally, selecting an optimal water layer according to the adaptability data of each depth layer in the current three-dimensional water body environment model, and controlling the depth area position of the lifting type culture net cage based on the optimal water layer control cluster. Lifting is adjusted according to habits of fishes, and all the net cages can be instructed to synchronously dive to a proper water layer below a thermocline when the water temperature of the surface layer is too high after the afternoon in summer, so that the fishes are bred in a more excellent environment.

Description

Technical Field

[0001] This invention relates to the field of technology, and in particular to a method for group coordination and environmental perception in a lifting aquaculture cage. Background Technology

[0002] Gravity-type deep-sea cages are low-cost and technologically mature, and will remain an important facility supporting the development of deep-sea aquaculture for some time to come. However, as cage aquaculture expands to the open sea, extreme weather events such as large waves, strong currents, and especially typhoons will seriously affect the safety of the facilities. Among related technologies, gravity-type deep-sea cages cannot cope with large waves, strong currents, or extreme weather events such as typhoons. They can only rely on "hard-hitting" to cope with extreme weather, threatening the safety of the cage facilities. Even if the facilities are not damaged, the survival of farmed organisms under extreme weather conditions remains highly risky. Lift-type aquaculture cages, with their lifting and lowering functions, can submerge the entire cage body before the arrival of extreme sea conditions such as typhoons, achieving the purpose of typhoon resistance and disaster avoidance. However, current lift-type cages cannot adjust their lifting and lowering according to the habits of fish. They cannot simultaneously command all cages to submerge to the cooler water layer below the thermocline when the surface water temperature is too high in the summer afternoon, preventing fish from reproducing in a more favorable environment. Summary of the Invention

[0003] This invention overcomes the shortcomings of the prior art and provides a method for group coordination and environmental perception in lifting aquaculture cages.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of this invention provides a method for group coordination and environmental perception in a lifting aquaculture cage, comprising the following steps:

[0006] Communication equipment is configured in all the lifting cages to form an underwater communication local area network, and the underwater communication local area network is configured and optimized.

[0007] Several environmental monitoring buoys are deployed in the aquaculture area, and environmental monitoring data in the current aquaculture area are monitored through the environmental monitoring buoys to construct a three-dimensional aquatic environment model;

[0008] A fish growth adaptation prediction model was constructed based on a deep neural network, and the adaptation data of each depth layer in the current three-dimensional aquatic environment model were predicted.

[0009] The optimal water layer is selected based on the adaptive data of each depth layer in the current three-dimensional water environment model, and the depth region position of the lifting aquaculture cage is controlled by the control cluster based on the optimal water layer.

[0010] Furthermore, in the method for group coordination and environmental perception of elevating aquaculture cages, communication equipment is configured in all elevating cages to form an underwater communication local area network, specifically:

[0011] Configure communication devices in all lifting cages, obtain the predetermined sensing range of the communication devices, initialize the setting position of the first lifting cage, and configure the setting positions of all lifting cages according to the predetermined sensing range of the communication devices.

[0012] Calculate the sensing overlap area of ​​two adjacent lifting cages, set a sensing overlap area threshold, and determine whether the sensing overlap area of ​​the two adjacent lifting cages is greater than the sensing overlap area threshold.

[0013] When the overlapping sensing areas of two adjacent lifting cages are both greater than the threshold of the overlapping sensing area, the underwater communication local area network is completed and configured according to the current set position of each lifting cage.

[0014] When the overlapping areas of two adjacent lifting cages are not both greater than the threshold value of the overlapping area, the set position of the lifting cage is reset until the overlapping areas of the two adjacent lifting cages are both greater than the threshold value of the overlapping area.

[0015] Furthermore, in the group coordination and environmental perception method for lifting aquaculture cages, several environmental monitoring buoys are deployed within the aquaculture area, and environmental monitoring data within the current aquaculture area is monitored through these buoys to construct a three-dimensional aquatic environment model, specifically including:

[0016] Several environmental monitoring buoys are deployed in the aquaculture area to monitor the environmental monitoring data in the current aquaculture area. Based on the environmental monitoring data in the current aquaculture area, environmental monitoring data for each depth gradient is obtained.

[0017] A virtual space is constructed, and the depth of the virtual space is set according to the depth location of the breeding area. Environmental monitoring data of each depth gradient is mapped to the virtual space.

[0018] Several rendering layers are constructed based on depth gradients. Each rendering layer is rendered based on the environmental monitoring data of each depth gradient to construct an initial three-dimensional water environment model and obtain the initial three-dimensional water environment model at each time point.

[0019] The initial three-dimensional water environment model is integrated from each time stamp to form a three-dimensional water environment model.

[0020] Furthermore, in the group coordination and environmental perception methods for elevating aquaculture cages, a fish growth adaptation prediction model is constructed based on deep neural networks, specifically including:

[0021] A fish growth adaptability prediction model is constructed based on a deep neural network. Fish growth adaptability characteristic data under different environmental data are obtained, and the fish growth adaptability characteristic data under different environmental data are input into the fish growth adaptability prediction model for training.

[0022] Different environmental data are used as model inputs, and fish growth adaptation characteristic data are used as model outputs. The contribution of different environmental data types to the prediction of the fish growth adaptation characteristic data is calculated.

[0023] Obtain environmental data types with a contribution greater than a preset contribution threshold, input the environmental data types with a contribution greater than the preset contribution threshold into the attention mechanism, and focus attention on environmental data types with a contribution greater than the preset contribution threshold;

[0024] The training of the fish growth adaptation prediction model is complete when the prediction accuracy of the model exceeds the preset prediction accuracy threshold.

[0025] Furthermore, in the group coordination and environmental perception method for elevating aquaculture cages, the adaptive data of each depth layer in the current three-dimensional aquatic environment model are predicted, specifically:

[0026] Obtain environmental data for each depth layer in the current three-dimensional aquatic environment model, and input the environmental data for each depth layer in the current three-dimensional aquatic environment model into the fish growth adaptability prediction model for prediction;

[0027] By prediction, adaptive data for each depth layer in the current three-dimensional water environment model is obtained, and the adaptive data for each depth layer in the current three-dimensional water environment model is output.

[0028] Furthermore, in the group coordination and environmental perception method for lifting aquaculture cages, the optimal water layer is selected based on the adaptive data of each depth layer in the current three-dimensional water environment model, and the depth region position of the lifting aquaculture cage is controlled by the control cluster based on the optimal water layer, specifically as follows:

[0029] Construct a sorting table, input the adaptive data of each depth layer in the current three-dimensional water environment model into the sorting table for sorting, and obtain adaptive data sorted from largest to smallest;

[0030] The maximum adaptive data is obtained based on the adaptive data sorted from largest to smallest, and the water layer corresponding to the maximum adaptive data is obtained. The depth region position of the lifting aquaculture cage is controlled based on the optimal water layer cluster.

[0031] Obtain meteorological characteristic data of the current aquaculture area, and assess the probability of sudden disasters occurring in the depth area of ​​the lifting aquaculture cage based on the meteorological characteristic data of the current aquaculture area;

[0032] When the probability of a sudden disaster occurring in the depth region of the lifting aquaculture cage is greater than a preset threshold for the probability of a sudden disaster, the depth region with the lowest probability of a sudden disaster is evaluated, and the depth region with the lowest probability of a sudden disaster is used as the final depth region configuration position of the lifting aquaculture cage.

[0033] A second aspect of the present invention provides a group coordination and environmental perception system for a liftable aquaculture cage, including a memory and a processor. The memory includes a method program for group coordination and environmental perception of the liftable aquaculture cage. When the processor executes the method program for group coordination and environmental perception of the liftable aquaculture cage, it implements the steps of the method for group coordination and environmental perception of the liftable aquaculture cage as described in any one of the present invention.

[0034] A third aspect of the present invention provides a computer-readable storage medium including a method program for group coordination and environmental perception of a lifting aquaculture cage, wherein when the method program is executed by a processor, it implements the steps of the method program for group coordination and environmental perception of a lifting aquaculture cage as described in any one of the present invention.

[0035] This invention addresses the shortcomings of the prior art and has the following beneficial effects:

[0036] This invention configures communication devices in all lifting cages to form an underwater communication local area network (LAN). This LAN is then configured and optimized. Several environmental monitoring buoys are deployed within the aquaculture area to monitor environmental data, constructing a three-dimensional aquatic environment model. Based on this model, a fish growth adaptability prediction model is built using a deep neural network. The model predicts the adaptability data for each depth layer within the three-dimensional aquatic environment model. Finally, the optimal water layer is selected based on the adaptability data for each depth layer in the model, and the depth position of the lifting cages is controlled by a cluster based on this optimal water layer. By adjusting the lifting and lowering according to fish habits, this invention can instruct all cages to simultaneously descend to a cooler water layer below the thermocline when the surface water temperature is too high in the summer afternoons, allowing fish to reproduce in a more favorable environment. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained from these drawings without creative effort.

[0038] Figure 1 A flowchart illustrating the overall process of group collaboration and environmental perception methods for lifting aquaculture cages is shown.

[0039] Figure 2 A system block diagram of the group coordination and environmental perception system of the lifting aquaculture cage is shown. Detailed Implementation

[0040] To better understand the above-mentioned objectives, 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 should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0041] 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.

[0042] like Figure 1 As shown, the first aspect of the present invention provides a method for group coordination and environmental perception in a lifting aquaculture cage, comprising the following steps:

[0043] Configure communication equipment in all the lifting cages to form an underwater communication local area network, and configure and optimize the underwater communication local area network.

[0044] Several environmental monitoring buoys are deployed in the aquaculture area, and environmental monitoring data in the current aquaculture area is monitored through the environmental monitoring buoys to construct a three-dimensional aquatic environment model;

[0045] A fish growth adaptation prediction model was constructed based on a deep neural network, and the adaptation data of each depth layer in the current three-dimensional aquatic environment model were predicted.

[0046] The optimal water layer is selected based on the adaptive data of each depth layer in the current three-dimensional water environment model, and the depth region position of the lifting aquaculture cage is controlled by the control cluster based on the optimal water layer.

[0047] It should be noted that this invention adjusts the raising and lowering of the cages according to the habits of fish, and can instruct all cages to simultaneously descend to a cool water layer below the thermocline when the surface water temperature is too high in the summer afternoon, so that the fish can reproduce in a more favorable environment.

[0048] Furthermore, in the method for group coordination and environmental perception of elevating aquaculture cages, communication equipment is configured in all elevating cages to form an underwater communication local area network, specifically:

[0049] Configure communication devices in all lifting cages, obtain the predetermined sensing range of the communication devices, initialize the setting position of the first lifting cage, and configure the setting positions of all lifting cages according to the predetermined sensing range of the communication devices.

[0050] Calculate the sensing overlap area of ​​two adjacent lifting cages, set a sensing overlap area threshold, and determine whether the sensing overlap area of ​​two adjacent lifting cages is greater than the sensing overlap area threshold.

[0051] When the overlapping sensing areas of two adjacent lifting cages are both greater than the threshold of the overlapping sensing area, the underwater communication local area network is completed and configured according to the current set position of each lifting cage.

[0052] When the overlapping areas of two adjacent lifting cages are not both greater than the threshold for overlapping areas, the set position of the lifting cage is reset until the overlapping areas of the two adjacent lifting cages are both greater than the threshold for overlapping areas.

[0053] It should be noted that the communication equipment includes acoustic communication equipment, optical communication equipment, etc. When constructing the underwater communication local area network (LAN), the LAN is completed when the overlapping sensing areas of two adjacent lifting cages are both greater than the threshold. It is then configured according to the current set position of each lifting cage. If the overlapping sensing areas of two adjacent lifting cages are not both greater than the threshold, the set position of the lifting cage is reset until the overlapping sensing areas of two adjacent lifting cages are both greater than the threshold, enabling communication between adjacent lifting aquaculture cages and thus completing the cluster control of the lifting aquaculture cages. This method allows multiple cages in a region to form an intelligent cluster, coordinating their lifting and lowering based on large-scale marine environmental data to jointly find the optimal water layer and improve overall aquaculture efficiency.

[0054] Furthermore, in the group collaboration and environmental perception method for lifting aquaculture cages, several environmental monitoring buoys are deployed within the aquaculture area. These buoys monitor environmental data within the aquaculture area, and a three-dimensional aquatic environment model is constructed. Specifically, this includes:

[0055] Several environmental monitoring buoys are deployed in the aquaculture area to monitor the environmental data in the current aquaculture area. Based on the environmental monitoring data in the current aquaculture area, environmental monitoring data for each depth gradient is obtained.

[0056] A virtual space is constructed, and the depth of the virtual space is set according to the depth location of the breeding area. Environmental monitoring data of each depth gradient is mapped to the virtual space.

[0057] Several rendering layers are constructed based on depth gradients. Each rendering layer is rendered based on the environmental monitoring data of each depth gradient to construct an initial three-dimensional water environment model and obtain the initial three-dimensional water environment model at each time point.

[0058] The initial three-dimensional water environment model is integrated from each time stamp to form a three-dimensional water environment model.

[0059] It should be noted that environmental monitoring data includes data such as temperature and salinity. This method can be used to construct a three-dimensional water environment model, thereby enabling the visualization of environmental monitoring data at different depth gradients and making the data more intuitive.

[0060] Furthermore, in the group coordination and environmental perception methods for elevating aquaculture cages, a fish growth adaptation prediction model is constructed based on deep neural networks, specifically including:

[0061] A fish growth adaptability prediction model is constructed based on a deep neural network. Fish growth adaptability characteristic data under different environmental data are obtained, and the fish growth adaptability characteristic data under different environmental data are input into the fish growth adaptability prediction model for training.

[0062] Different environmental data are used as model inputs, and fish growth adaptation characteristic data are used as model outputs. The contribution of different environmental data types to the prediction of fish growth adaptation characteristic data is calculated.

[0063] Get the environmental data types whose contribution is greater than the preset contribution threshold, input the environmental data types whose contribution is greater than the preset contribution threshold into the attention mechanism, and focus attention on the environmental data types whose contribution is greater than the preset contribution threshold;

[0064] The training of the fish growth adaptation prediction model is complete when the prediction accuracy of the model exceeds the preset prediction accuracy threshold.

[0065] It should be noted that inputting environmental data types with a contribution value greater than a preset contribution threshold into the attention mechanism, and focusing attention on environmental data types with a contribution value greater than the preset contribution threshold, can improve the training speed and prediction accuracy of the fish growth adaptation prediction model. Adaptive feature data includes the adaptation states of fish under different environments, such as low adaptation, moderate adaptation, high adaptation, and perfect adaptation.

[0066] Furthermore, in the group coordination and environmental perception method for elevating aquaculture cages, the adaptive data of each depth layer in the current three-dimensional aquatic environment model are predicted, specifically:

[0067] Obtain environmental data for each depth layer in the current three-dimensional aquatic environment model, and input the environmental data for each depth layer in the current three-dimensional aquatic environment model into the fish growth adaptability prediction model for prediction.

[0068] By predicting, we obtain adaptive data for each depth layer in the current three-dimensional water environment model, and output the adaptive data for each depth layer in the current three-dimensional water environment model.

[0069] Furthermore, in the group coordination and environmental perception method for lifting aquaculture cages, the optimal water layer is selected based on the adaptive data of each depth layer in the current three-dimensional water environment model, and the depth region position of the lifting aquaculture cage is controlled by the cluster based on the optimal water layer. Specifically:

[0070] Construct a sorting table, input the adaptive data of each depth layer in the current three-dimensional water environment model into the sorting table and sort it to obtain adaptive data sorted from largest to smallest;

[0071] The maximum adaptive data is obtained by sorting the adaptive data from largest to smallest, and the water layer corresponding to the maximum adaptive data is obtained. The depth region of the lifting aquaculture cage is controlled based on the optimal water layer cluster.

[0072] Obtain meteorological characteristic data of the current aquaculture area, and assess the probability of sudden disasters occurring in the depth area of ​​the lifting aquaculture cage based on the meteorological characteristic data of the current aquaculture area;

[0073] When the probability of a sudden disaster occurring in the depth area of ​​the lifting aquaculture cage is greater than the preset threshold for the probability of a sudden disaster, the depth area with the lowest probability of a sudden disaster is evaluated, and the depth area with the lowest probability of a sudden disaster is used as the final depth area configuration position of the lifting aquaculture cage.

[0074] It should be noted that the probability of sudden disasters occurring in the depth area of ​​the lifting aquaculture cages is assessed based on the meteorological characteristics data of the current aquaculture area. For example, the probability of sudden disasters is assessed using historical meteorological data. If a red tide risk is detected in a local area, all cages are instructed to coordinate to avoid the polluted water mass. This collective intelligence behavior far exceeds the decision-making ability of a single cage.

[0075] In addition, this method also includes:

[0076] Inclination sensors and stress strain gauges were installed at key nodes of the cage frame, and tension sensors were installed on the mooring line. An underwater acoustic Doppler current profiler was used to monitor the surrounding flow velocity and direction.

[0077] The system learns the correspondence between historical ocean currents, wave data and cage attitude and anchor cable tension based on long short-term memory neural network, and obtains the learned long short-term memory neural network model.

[0078] The data collected by the tilt sensor and the strain gauge, the tension data collected by the tension sensor, the surrounding flow velocity and the flow direction are input into the long short-term memory neural network model that has been learned.

[0079] Predicting abnormal tilting of the cage or overload of the anchor cable force, when the overload of the anchor cable force exceeds the safety threshold, the center of gravity is adjusted by adjusting the draft of the cage to avoid the strong current layer, or by using the active balancing tank in control scheme five to counteract the overturning moment.

[0080] It should be noted that combining multi-source sensor data with AI algorithms not only enables real-time monitoring but also predicts the risks of cage posture imbalance and netting stress concentration, achieving early warning and adaptive adjustment.

[0081] like Figure 2 As shown, a second aspect of the present invention provides a group coordination and environmental perception system for a lifting aquaculture cage, including a memory and a processor. The memory includes a method program for group coordination and environmental perception of the lifting aquaculture cage. When the processor executes the method program for group coordination and environmental perception of the lifting aquaculture cage, it performs the following steps:

[0082] Configure communication equipment in all the lifting cages to form an underwater communication local area network, and configure and optimize the underwater communication local area network.

[0083] Several environmental monitoring buoys are deployed in the aquaculture area, and environmental monitoring data in the current aquaculture area is monitored through the environmental monitoring buoys to construct a three-dimensional aquatic environment model;

[0084] A fish growth adaptation prediction model was constructed based on a deep neural network, and the adaptation data of each depth layer in the current three-dimensional aquatic environment model were predicted.

[0085] The optimal water layer is selected based on the adaptive data of each depth layer in the current three-dimensional water environment model, and the depth region position of the lifting aquaculture cage is controlled by the control cluster based on the optimal water layer.

[0086] It should be noted that this invention adjusts the raising and lowering of the cages according to the habits of fish, and can instruct all cages to simultaneously descend to a cool water layer below the thermocline when the surface water temperature is too high in the summer afternoon, so that the fish can reproduce in a more favorable environment.

[0087] Furthermore, in the group coordination and environmental sensing system of the lifting aquaculture cages, communication equipment is configured in all lifting cages to form an underwater communication local area network, specifically:

[0088] Configure communication devices in all lifting cages, obtain the predetermined sensing range of the communication devices, initialize the setting position of the first lifting cage, and configure the setting positions of all lifting cages according to the predetermined sensing range of the communication devices.

[0089] Calculate the sensing overlap area of ​​two adjacent lifting cages, set a sensing overlap area threshold, and determine whether the sensing overlap area of ​​two adjacent lifting cages is greater than the sensing overlap area threshold.

[0090] When the overlapping sensing areas of two adjacent lifting cages are both greater than the threshold of the overlapping sensing area, the underwater communication local area network is completed and configured according to the current set position of each lifting cage.

[0091] When the overlapping areas of two adjacent lifting cages are not both greater than the threshold for overlapping areas, the set position of the lifting cage is reset until the overlapping areas of the two adjacent lifting cages are both greater than the threshold for overlapping areas.

[0092] It should be noted that the communication equipment includes acoustic communication equipment, optical communication equipment, etc. When constructing the underwater communication local area network (LAN), the LAN is completed when the overlapping sensing areas of two adjacent lifting cages are both greater than the threshold. It is then configured according to the current set position of each lifting cage. If the overlapping sensing areas of two adjacent lifting cages are not both greater than the threshold, the set position of the lifting cage is reset until the overlapping sensing areas of two adjacent lifting cages are both greater than the threshold, enabling communication between adjacent lifting aquaculture cages and thus completing the cluster control of the lifting aquaculture cages. This method allows multiple cages in a region to form an intelligent cluster, coordinating their lifting and lowering based on large-scale marine environmental data to jointly find the optimal water layer and improve overall aquaculture efficiency.

[0093] Furthermore, in the group coordination and environmental perception system of the lifting aquaculture cage, several environmental monitoring buoys are deployed within the aquaculture area. These buoys monitor environmental data within the aquaculture area, constructing a three-dimensional aquatic environment model, specifically including:

[0094] Several environmental monitoring buoys are deployed in the aquaculture area to monitor the environmental data in the current aquaculture area. Based on the environmental monitoring data in the current aquaculture area, environmental monitoring data for each depth gradient is obtained.

[0095] A virtual space is constructed, and the depth of the virtual space is set according to the depth location of the breeding area. Environmental monitoring data of each depth gradient is mapped to the virtual space.

[0096] Several rendering layers are constructed based on depth gradients. Each rendering layer is rendered based on the environmental monitoring data of each depth gradient to construct an initial three-dimensional water environment model and obtain the initial three-dimensional water environment model at each time point.

[0097] The initial three-dimensional water environment model is integrated from each time stamp to form a three-dimensional water environment model.

[0098] It should be noted that environmental monitoring data includes data such as temperature and salinity. This method can be used to construct a three-dimensional water environment model, thereby enabling the visualization of environmental monitoring data at different depth gradients and making the data more intuitive.

[0099] Furthermore, in the group coordination and environmental perception system of the lifting aquaculture cage, a fish growth adaptability prediction model is constructed based on a deep neural network, specifically including:

[0100] A fish growth adaptability prediction model is constructed based on a deep neural network. Fish growth adaptability characteristic data under different environmental data are obtained, and the fish growth adaptability characteristic data under different environmental data are input into the fish growth adaptability prediction model for training.

[0101] Different environmental data are used as model inputs, and fish growth adaptation characteristic data are used as model outputs. The contribution of different environmental data types to the prediction of fish growth adaptation characteristic data is calculated.

[0102] Get the environmental data types whose contribution is greater than the preset contribution threshold, input the environmental data types whose contribution is greater than the preset contribution threshold into the attention mechanism, and focus attention on the environmental data types whose contribution is greater than the preset contribution threshold;

[0103] The training of the fish growth adaptation prediction model is complete when the prediction accuracy of the model exceeds the preset prediction accuracy threshold.

[0104] It should be noted that inputting environmental data types with a contribution value greater than a preset contribution threshold into the attention mechanism, and focusing attention on environmental data types with a contribution value greater than the preset contribution threshold, can improve the training speed and prediction accuracy of the fish growth adaptation prediction model. Adaptive feature data includes the adaptation states of fish under different environments, such as low adaptation, moderate adaptation, high adaptation, and perfect adaptation.

[0105] Furthermore, in the group coordination and environmental perception system of the lifting aquaculture cage, the adaptive data of each depth layer in the current three-dimensional aquatic environment model are predicted, specifically:

[0106] Obtain environmental data for each depth layer in the current three-dimensional aquatic environment model, and input the environmental data for each depth layer in the current three-dimensional aquatic environment model into the fish growth adaptability prediction model for prediction.

[0107] By predicting, we obtain adaptive data for each depth layer in the current three-dimensional water environment model, and output the adaptive data for each depth layer in the current three-dimensional water environment model.

[0108] Furthermore, in the group coordination and environmental perception system of the lifting aquaculture cage, the optimal water layer is selected based on the adaptive data of each depth layer in the current three-dimensional water environment model, and the depth region position of the lifting aquaculture cage is controlled by the control cluster based on the optimal water layer, specifically:

[0109] Construct a sorting table, input the adaptive data of each depth layer in the current three-dimensional water environment model into the sorting table and sort it to obtain adaptive data sorted from largest to smallest;

[0110] The maximum adaptive data is obtained by sorting the adaptive data from largest to smallest, and the water layer corresponding to the maximum adaptive data is obtained. The depth region of the lifting aquaculture cage is controlled based on the optimal water layer cluster.

[0111] Obtain meteorological characteristic data of the current aquaculture area, and assess the probability of sudden disasters occurring in the depth area of ​​the lifting aquaculture cage based on the meteorological characteristic data of the current aquaculture area;

[0112] When the probability of a sudden disaster occurring in the depth area of ​​the lifting aquaculture cage is greater than the preset threshold for the probability of a sudden disaster, the depth area with the lowest probability of a sudden disaster is evaluated, and the depth area with the lowest probability of a sudden disaster is used as the final depth area configuration position of the lifting aquaculture cage.

[0113] It should be noted that the probability of sudden disasters occurring in the depth area of ​​the lifting aquaculture cages is assessed based on the meteorological characteristics data of the current aquaculture area. For example, the probability of sudden disasters is assessed using historical meteorological data. If a red tide risk is detected in a local area, all cages are instructed to coordinate to avoid the polluted water mass. This collective intelligence behavior far exceeds the decision-making ability of a single cage.

[0114] A third aspect of the present invention provides a computer-readable storage medium including a method program for group coordination and environmental perception of a lifting aquaculture cage, wherein when the method program for group coordination and environmental perception of a lifting aquaculture cage is executed by a processor, it implements any of the steps of the method program for group coordination and environmental perception of a lifting aquaculture cage.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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 of 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.

[0120] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for group coordination and environmental perception in a lifting aquaculture cage, characterized in that, Includes the following steps: Communication equipment is configured in all the lifting cages to form an underwater communication local area network, and the underwater communication local area network is configured and optimized. Several environmental monitoring buoys are deployed in the aquaculture area, and environmental monitoring data in the current aquaculture area are monitored through the environmental monitoring buoys to construct a three-dimensional aquatic environment model; A fish growth adaptation prediction model was constructed based on a deep neural network, and the adaptation data of each depth layer in the current three-dimensional aquatic environment model were predicted. The optimal water layer is selected based on the adaptive data of each depth layer in the current three-dimensional water environment model, and the depth region position of the lifting aquaculture cage is controlled by the control cluster based on the optimal water layer.

2. The method for group coordination and environmental perception of a lifting aquaculture cage according to claim 1, characterized in that, Communication equipment is installed in all the lifting cages to form an underwater communication local area network, specifically as follows: Configure communication devices in all lifting cages, obtain the predetermined sensing range of the communication devices, initialize the setting position of the first lifting cage, and configure the setting positions of all lifting cages according to the predetermined sensing range of the communication devices. Calculate the sensing overlap area of ​​two adjacent lifting cages, set a sensing overlap area threshold, and determine whether the sensing overlap area of ​​the two adjacent lifting cages is greater than the sensing overlap area threshold. When the sensing overlap area of ​​two adjacent lifting cages is greater than the sensing overlap area threshold, the underwater communication local area network is completed and configured according to the current set position of each lifting cage. When the overlapping areas of two adjacent lifting cages are not both greater than the threshold value of the overlapping area, the set position of the lifting cage is reset until the overlapping areas of the two adjacent lifting cages are both greater than the threshold value of the overlapping area.

3. The method for group coordination and environmental perception of a lifting aquaculture cage according to claim 1, characterized in that, Several environmental monitoring buoys are deployed within the aquaculture area, and environmental monitoring data within the current aquaculture area is monitored through these buoys to construct a three-dimensional aquatic environment model, specifically including: Several environmental monitoring buoys are deployed in the aquaculture area to monitor the environmental monitoring data in the current aquaculture area. Based on the environmental monitoring data in the current aquaculture area, environmental monitoring data for each depth gradient is obtained. A virtual space is constructed, and the depth of the virtual space is set according to the depth location of the breeding area. Environmental monitoring data of each depth gradient is mapped to the virtual space. Several rendering layers are constructed based on depth gradients. Each rendering layer is rendered based on environmental monitoring data of each depth gradient to construct an initial three-dimensional water environment model and obtain the initial three-dimensional water environment model at each time point. The initial three-dimensional water environment model at each time point is integrated to form a three-dimensional water environment model.

4. The method for group coordination and environmental perception of a lifting aquaculture cage according to claim 1, characterized in that, A fish growth adaptation prediction model based on deep neural networks is constructed, specifically including: A fish growth adaptability prediction model is constructed based on a deep neural network. Fish growth adaptability characteristic data under different environmental data are obtained, and the fish growth adaptability characteristic data under different environmental data are input into the fish growth adaptability prediction model for training. Different environmental data are used as model inputs, and fish growth adaptation characteristic data are used as model outputs. The contribution of different environmental data types to the prediction of the fish growth adaptation characteristic data is calculated. Obtain environmental data types with a contribution greater than a preset contribution threshold, input the environmental data types with a contribution greater than the preset contribution threshold into the attention mechanism, and focus attention on environmental data types with a contribution greater than the preset contribution threshold; The training of the fish growth adaptation prediction model is complete when the prediction accuracy of the model exceeds the preset prediction accuracy threshold.

5. The method for group coordination and environmental perception of a lifting aquaculture cage according to claim 1, characterized in that, Predict adaptive data for each depth layer in the current 3D aquatic environment model, specifically: Obtain environmental data for each depth layer in the current three-dimensional aquatic environment model, and input the environmental data for each depth layer in the current three-dimensional aquatic environment model into the fish growth adaptability prediction model for prediction; By prediction, adaptive data for each depth layer in the current three-dimensional water environment model is obtained, and the adaptive data for each depth layer in the current three-dimensional water environment model is output.

6. The method for group coordination and environmental perception of a lifting aquaculture cage according to claim 1, characterized in that, The optimal water layer is selected based on the adaptive data of each depth layer in the current three-dimensional aquatic environment model, and the depth region position of the lifting aquaculture cage is controlled by the control cluster based on the optimal water layer, specifically as follows: Construct a sorting table, input the adaptive data of each depth layer in the current three-dimensional water environment model into the sorting table for sorting, and obtain adaptive data sorted from largest to smallest; The maximum adaptive data is obtained based on the adaptive data sorted from largest to smallest, and the water layer corresponding to the maximum adaptive data is obtained. The depth region position of the lifting aquaculture cage is controlled based on the optimal water layer cluster. Obtain meteorological characteristic data of the current aquaculture area, and assess the probability of sudden disasters occurring in the depth area of ​​the lifting aquaculture cage based on the meteorological characteristic data of the current aquaculture area; When the probability of a sudden disaster occurring in the depth region of the lifting aquaculture cage is greater than a preset threshold for the probability of a sudden disaster, the depth region with the lowest probability of a sudden disaster is evaluated, and the depth region with the lowest probability of a sudden disaster is used as the final depth region configuration position of the lifting aquaculture cage.

7. A group coordination and environmental perception system for a lifting aquaculture cage, characterized in that, The device includes a memory and a processor. The memory includes a program for a group coordination and environmental perception method for a liftable aquaculture cage. When the processor executes the program for the group coordination and environmental perception method for a liftable aquaculture cage, it implements the steps of the group coordination and environmental perception method for a liftable aquaculture cage as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, The method includes a group coordination and environmental perception method program for lifting aquaculture cages. When the program is executed by a processor, it implements the steps of the group coordination and environmental perception method for lifting aquaculture cages as described in any one of claims 1-6.

Images