A method for preventing typhoon disaster and quickly recovering after disaster of deep-sea net cage culture

Abstract

The application discloses a method for typhoon disaster prevention and rapid recovery after disaster in deep-sea net cage culture, which comprises the following steps: before the disaster, an unmanned aerial vehicle is used to take aerial photos of the water surface structure of the net cage by carrying a high-definition camera, and an underwater robot is used to collect underwater images by layer scanning through a sonar, so that structure data and fish school data before the disaster are generated; weak points such as framework, netting and anchor chain are analyzed and repaired and reinforced through three-dimensional modeling, the stocking density is optimized in combination with typhoon information, the risk of facility damage and fish loss is reduced, and after the disaster, the structure data and fish school data are repeated, the degree of framework damage, netting damage, anchor chain breakage and fish escape or death is compared and evaluated by taking the data before the disaster as a reference, and a grading repair scheme and disaster relief plan are generated. Through the cooperation of multiple devices and data fusion, the detection accuracy and evaluation efficiency are improved, the damaged parts are quickly located, and the recovery strategy is optimized, so that an efficient disaster prevention and reduction and rapid recovery solution after disaster is provided for the deep-sea net cage culture.

Description

Technical Field

[0001] This invention relates to the fields of deep-sea aquaculture and typhoon disaster prevention and mitigation, and in particular to a method for typhoon disaster prevention and rapid post-disaster recovery in deep-sea cage aquaculture. Background Technology

[0002] Deep-sea cage aquaculture, as an important development direction of modern aquaculture, has been widely promoted globally due to its advantages such as high stocking density, high-quality water conditions, and distance from nearshore pollution. However, it still faces many challenges when encountering extreme weather disasters such as typhoons, mainly including: 1. Infrastructure damage: Strong winds, high waves, and torrential rains caused by typhoons directly damage cage aquaculture facilities. The cage frames, nets, and anchoring systems are easily deformed, broken, detached, or drift under the impact of violent waves, leading to mass fish deaths or escapes and causing huge economic losses to farmers. 2. Water quality deterioration: Heavy rainfall and seawater disturbance brought by typhoons can cause rapid deterioration of water quality. The large influx of freshwater into the aquaculture area causes a sharp drop in salinity. At the same time, typhoons also stir up bottom sediments, increasing suspended particles, decreasing dissolved oxygen, and increasing harmful substances such as ammonia nitrogen and nitrates. In addition, torrential rains and floods bring large amounts of silt and pollutants into the coastal and aquaculture waters, all of which lead to a rapid deterioration of water quality. 3. Post-disaster disease outbreaks: Typhoons, rainstorms, and other events cause drastic environmental changes (such as sudden changes in water temperature, dissolved oxygen, and salinity), which can produce strong stress responses in farmed fish, including decreased immunity, metabolic disorders, and abrasion infections. This can easily lead to large-scale outbreaks of fish diseases, further exacerbating post-disaster losses.

[0003] Currently, deep-sea aquaculture still relies mainly on experience and traditional methods for typhoon prevention and post-disaster recovery. This has many technical and operational limitations, such as delayed response and slow post-disaster recovery. For example, the traditional method of manually inspecting each net cage is inefficient and has limited coverage, making it easy to miss potential hazards. Other problems include inaccurate fish population statistics, a lack of systematic post-disaster loss assessment, and a lack of targeted post-disaster recovery measures. These issues make it difficult to meet the high-efficiency, precise, and intelligent aquaculture needs of deep-sea aquaculture. Summary of the Invention

[0004] To address the aforementioned problems, this invention proposes a method for typhoon disaster prevention and rapid post-disaster recovery in deep-sea cage aquaculture, primarily resolving the issues raised in the background technology.

[0005] To address the aforementioned technical problems, the first aspect of this invention proposes a method for preventing typhoon disasters in deep-sea cage aquaculture, comprising the following steps:

[0006] Unmanned detectors were used to acquire pre-disaster structural data about the cages;

[0007] A risk assessment is conducted on the pre-disaster structural data and typhoon information, and a first structural repair plan and an aquaculture adjustment plan are generated based on the assessment results.

[0008] According to the first structural repair plan, maintenance personnel were dispatched to repair and reinforce the cages before the typhoon, and the aquaculture density was reduced according to the aquaculture adjustment plan.

[0009] Unmanned detectors were used to obtain pre-disaster fish population data within the net cage area after the reduction of aquaculture density.

[0010] In some implementations, the typhoon information includes at least the typhoon path and wind speed.

[0011] In some embodiments, the unmanned detector includes a drone and an underwater robot, the drone being equipped with a high-definition camera and the underwater robot being equipped with a high-definition camera and sonar equipment.

[0012] In some implementations, the process of acquiring the pre-disaster structural data includes:

[0013] The underwater robot uses sonar to scan the part of the cage below the sea surface in layers according to the preset scanning path, obtains the first real-time image and structural outline, and extracts the netting, anchor chain, frame bottom and / or binding force points from the first real-time image.

[0014] The drone acquires a second real-time image of the cage above the sea surface based on preset positioning coordinates, and extracts the frame connection points from the second real-time image;

[0015] By combining the first real-time image, the structural outline, and the second real-time image, 3D modeling is used to analyze the defects in the cage morphology and generate the pre-disaster structural data.

[0016] In some implementations, the process of acquiring the pre-disaster fish population data includes:

[0017] Feeding is carried out at fixed points, and images of fish schools on the surface of the net cages are taken using drones. The number of fish schools in the surface fish school images is counted to generate surface fish school quantity data.

[0018] The underwater robot uses its onboard sonar equipment to perform layered scanning of the net cages during feeding, obtaining spatial distribution data of fish at different depths;

[0019] The underwater robot uses a high-definition camera to capture images of the fish school during feeding. It then uses a target detection algorithm to count the number of fish in the images, generating underwater fish school quantity data. The spatial distribution data is then verified and corrected based on the underwater fish school quantity data.

[0020] Based on the amount of bait consumed and the average amount of food consumed by fish during the predetermined time period;

[0021] The data on the number of surface fish, the spatial distribution data, and the number of underwater fish are combined when feeding to generate the pre-disaster fish population data. The number of fish in the pre-disaster fish population data is then corrected by the amount of feed consumed and the average amount of feed consumed by the fish.

[0022] The second aspect of this invention proposes a method for rapid recovery of deep-sea cage aquaculture after a disaster, based on the above-mentioned method for preventing typhoon disasters in deep-sea cage aquaculture, including the following steps:

[0023] Unmanned detectors were used to obtain post-disaster structural data about the fish cages and post-disaster fish population data within the cages, following the same pre-disaster paths.

[0024] Based on the pre-disaster structural data, the post-disaster structural data is compared and analyzed through three-dimensional modeling. A second structural repair plan and vulnerable structures are generated based on the assessment results. The repair priority is determined based on the second structural repair plan and the vulnerable structures. Maintenance personnel are dispatched to carry out repair work and optimize the cage structure.

[0025] The fish population loss is calculated based on the pre-disaster and post-disaster fish population data, and the health status of the fish population is analyzed based on the post-disaster fish population data. Based on the health status, prevention and control and feeding suggestions are generated.

[0026] The beneficial effects of this invention are as follows: By collaboratively inspecting the key structures of the cages before a disaster using multiple devices, hidden dangers can be accurately identified and reinforced in a timely manner, reducing the risk of facility damage and fish escape during typhoons; after a disaster, the damage can be quickly and comprehensively assessed, generating repair and disaster relief plans. Compared with traditional methods, this solution significantly improves the coverage and accuracy of detection, overcoming the limitations of isolated surface and underwater detection; through real-time data integration and intelligent analysis, the post-disaster assessment time is significantly shortened, and damaged parts can be located in a timely manner, allowing for restoration operations to be carried out according to priority, providing a comprehensive, accurate, and efficient solution for disaster prevention and post-disaster reconstruction in deep-sea cage aquaculture. Attached Figure Description

[0027] Figure 1 This is a flowchart of a method for preventing typhoon disasters in deep-sea cage aquaculture, as disclosed in Embodiment 1 of the present invention.

[0028] Figure 2 This is a flowchart of a method for rapid post-disaster recovery of deep-sea cages disclosed in Embodiment 2 of the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this invention clearer and more explicit, the content of this invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to this invention are shown in the accompanying drawings, not all of them.

[0030] Example 1

[0031] This embodiment proposes a method for preventing typhoon disasters in deep-sea cage aquaculture, such as... Figure 1 As shown, it includes the following steps:

[0032] S1 uses an unmanned detector to acquire pre-disaster structural data about the cage.

[0033] In this embodiment, the aforementioned unmanned detector may include drones and underwater robots. The drones are equipped with high-definition cameras, and the underwater robots are equipped with high-definition cameras and sonar equipment. By using drones and underwater robots equipped with high-resolution cameras and multimodal sensors, a comprehensive inspection of key structures such as the cage frame, netting, and anchoring system can be carried out. Loose or damaged parts can be found and repaired or reinforced in a timely manner, reducing the risk of facility damage and fish escape during typhoons.

[0034] Specifically, the process of acquiring pre-disaster structural data includes:

[0035] S101, the underwater robot uses sonar to scan the subsurface portion of the net cage according to a preset scanning path, acquiring a first real-time image and structural outline, and extracting the netting, anchor chains, frame bottom, and / or mooring stress points from the first real-time image. The primary object of this first real-time image capture is the underwater structural part of the net cage, used to detect the frame, netting, and anchoring system, etc.

[0036] S102, the drone acquires a second real-time image of the net cage above the sea surface based on preset positioning coordinates, and extracts the frame connection points from the second real-time image. The main focus of this second real-time image is the above-water structure of the net cage, such as the frame structure and the frame mooring stress points, which are the key areas for inspection.

[0037] S103, combining the first real-time image, structural outline, and second real-time image, uses 3D modeling to analyze the defects in the cage morphology and generate pre-disaster structural data.

[0038] S2 conducts risk assessments on pre-disaster structural data and typhoon information, and generates a first structural repair plan and an aquaculture adjustment plan based on the assessment results.

[0039] In S2, the pre-disaster structural data includes a real-time model of the net cages, which can provide managers with intuitive and detailed identification of net cage defects. After conducting a risk assessment on the pre-disaster structural data, users can preset corresponding primary structural repair plans and aquaculture adjustment plans.

[0040] Typhoon information includes at least the typhoon's path and wind speed. Combining typhoon information with optimal stocking density is a preventative aquaculture management strategy aimed at balancing the risks of typhoons with the production benefits of aquaculture. Reasonable stocking density can effectively reduce fish mortality caused by typhoons and maximize aquaculture benefits after a typhoon. By combining different typhoon wind speed forecasts and flexibly adjusting stocking density before a typhoon, existing aquaculture resources can be protected, and the long-term survival and development of aquaculture enterprises can be ensured with minimal losses after a disaster. (See Table 1.)

[0041] Table 1. Typhoon Wind Force Level and Stocking Density Adjustment Table (Taking Golden Pomfret as an Example)

[0042]

[0043]

[0044] S3, in accordance with the first structural repair plan, dispatch maintenance personnel to carry out cage repair and reinforcement work before the typhoon, and reduce the breeding density according to the aquaculture adjustment plan.

[0045] In S3, managers can promptly repair or reinforce critical structures such as defective cage frames, netting, and anchoring systems according to the guidance of the first structural repair plan, reducing the risk of facility damage and fish escape during typhoons. Additionally, by following the guidance of the aquaculture adjustment plan (such as separating cages or early harvesting), the stocking density of fish in the cages can be reduced, minimizing the risk of abrasions and oxygen depletion caused by water disturbance and reducing potential losses. The specific density reduction ratio can be determined based on the specific destructive force of the typhoon and the wind and wave resistance level of the cages.

[0046] S4 uses unmanned detectors to acquire pre-disaster fish population data within the cage area after reducing the stocking density.

[0047] In this embodiment, fish stock data is acquired after the stocking density is reduced. This pre-disaster fish stock data includes fish location, size, distribution, and quantity, providing data support for subsequent post-disaster recovery. Optionally, the process of acquiring pre-disaster fish stock data includes:

[0048] S401, feeding at fixed points, using drones to capture images of fish on the surface of the net cages, counting the number of fish in the surface fish images, and generating surface fish quantity data;

[0049] S402, the underwater robot uses its onboard sonar equipment to perform layered scanning of the net cage during feeding, obtaining spatial distribution data of fish at different depths. Optionally, the underwater robot's sonar equipment records spatial distribution data every 2-3 meters of water depth, and the scanning path is set to descend spirally along the inner wall of the net cage, sequentially performing sonar scanning at each depth layer to obtain the fish density distribution at each depth layer.

[0050] S403, an underwater robot, uses its onboard high-definition camera to capture images of fish schools during feeding. It then employs a target detection algorithm to count the number of fish in the images, generating underwater fish population data. This data is used to verify and correct spatial distribution data. In one example, the YOLO algorithm, based on deep learning, is used to process the fish school images, identifying and counting fish at different depths. This data is used to correct the spatial distribution data obtained from sonar layered scanning (the YOLO algorithm uses a pre-trained fish detection model to automatically identify and count fish schools).

[0051] S404, based on the amount of bait consumed and the average amount of fish consumed during a predetermined time period;

[0052] S405 integrates surface fish population data, spatial distribution data, and underwater fish population data during feeding to generate pre-disaster fish population data. The pre-disaster fish population data is corrected by the amount of feed consumed and the average amount of feed consumed by fish. The total number of fish in the net cages is evaluated through comprehensive analysis of multi-source data to reduce statistical errors.

[0053] In this embodiment, when fish are fed at fixed points, they quickly rise to the surface. At this time, a drone is used to capture the surface distribution of the fish and count their numbers. Combined with the depth distribution data of the fish generated by sonar equipment, the total number of fish is estimated. At the same time, the fish consumption is used to correct the statistical error of the fish population and establish an accurate benchmark for the number of fish, providing reliable benchmark data for post-disaster assessment and recovery.

[0054] Example 2

[0055] This embodiment proposes a method for rapid post-disaster recovery of deep-sea cage aquaculture, based on the typhoon disaster prevention method for deep-sea cage aquaculture described in Embodiment 1, such as... Figure 2 As shown, it includes the following steps:

[0056] S1 uses an unmanned detector to obtain post-disaster structural data about the fish cages and post-disaster fish population data within the fish cages, following the same path as before the disaster.

[0057] The methods for obtaining post-disaster structural data and post-disaster fish population data in this embodiment can refer to S1 and S4 in Embodiment 1, and will not be repeated here.

[0058] S2 uses pre-disaster structural data as a benchmark, compares and analyzes the post-disaster structural data through 3D modeling, generates a second structural repair plan and vulnerable structures based on the assessment results, determines the repair priority based on the second structural repair plan and vulnerable structures, and dispatches maintenance personnel to carry out repair work and optimize the cage structure.

[0059] In this embodiment, the post-disaster structural data can be a 3D structural model of the fish cage. Based on a comparison of pre-disaster and post-disaster structural data, the extent of facility damage is accurately assessed, providing support for repair decisions and automatically generating a second structural repair plan and vulnerable structures. The second structural repair plan is used for loss assessment, insurance claims, and restocking decisions, facilitating managers to quickly locate damaged areas and formulate repair plans, ensuring efficient repair processes and optimal resource utilization. The aforementioned vulnerable structures can be used to simulate the damage process of typhoons to the fish cage structure and fish populations, analyze weak points, and optimize future disaster prevention plans.

[0060] S3 calculates fish losses based on pre-disaster and post-disaster fish population data, analyzes the health status of fish populations based on post-disaster fish population data, and generates prevention and feeding recommendations based on the health status.

[0061] The above-mentioned prevention and feeding recommendations are shown in Table 2 below. These recommendations mainly include the post-disaster assessment phase and the post-disaster fish population recovery phase. During the post-disaster assessment phase, repair resources are rationally allocated based on the extent of damage and its impact on the overall stability of the net cages and the survival of the fish population. Priority is given to restoring key facilities. This tiered repair strategy efficiently utilizes limited manpower and resources, quickly mitigates losses, and lays the foundation for subsequent fish population management. During the post-disaster fish population recovery phase, drones and underwater robots work together, and the feeding amount is adjusted based on real-time fish population distribution and behavioral data to reduce the feed conversion ratio and improve aquaculture efficiency. Additionally, high-definition cameras and acoustic data are used to monitor the health status of the fish population, quickly identify potential diseases, and provide prevention and control recommendations to reduce the risk of post-disaster disease outbreaks. Through health monitoring and management measures, the survival rate of fish is maximized, their growth is promoted, and secondary losses caused by post-disaster diseases and environmental degradation are prevented.

[0062] Table 2 Priority Table for Cage Structure Repair and Fish Management After Typhoon Disaster

[0063]

[0064]

[0065] The above embodiments are merely illustrative of the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and implement it accordingly. They should not be construed as limiting the scope of protection of the present invention. All equivalent changes or modifications made based on the essence of the content of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A method for preventing typhoon disasters in deep-sea cage aquaculture, characterized in that, Includes the following steps: Unmanned detectors are used to acquire pre-disaster structural data about the cages; the unmanned detectors include drones and underwater robots, the drones are equipped with high-definition cameras, and the underwater robots are equipped with high-definition cameras and sonar equipment; The process of acquiring the pre-disaster structural data includes: the underwater robot using sonar to scan the part of the cage below the sea surface according to a preset scanning path, acquiring a first real-time image and structural outline, and extracting the netting, anchor chains, frame bottom and / or binding stress points from the first real-time image; the UAV acquiring a second real-time image of the cage above the sea surface according to preset positioning coordinates, and extracting frame connection points from the second real-time image; combining the first real-time image, the structural outline and the second real-time image, using three-dimensional modeling to analyze the morphological defects of the cage, generating the pre-disaster structural data; A risk assessment is conducted on the pre-disaster structural data and typhoon information, and a first structural repair plan and an aquaculture adjustment plan are generated based on the assessment results; the typhoon information includes at least the typhoon path and wind force. According to the first structural repair plan, maintenance personnel were dispatched to repair and reinforce the cages before the typhoon, and the aquaculture density was reduced according to the aquaculture adjustment plan. Unmanned detectors are used to acquire pre-disaster fish population data within the net cage area after reducing the stocking density. The acquisition process includes: when feeding at fixed points, using a drone to capture images of fish on the surface of the net cage, counting the number of fish in the surface images, and generating surface fish population data; an underwater robot using its onboard sonar equipment to perform layered scanning of the net cage during feeding, acquiring spatial distribution data of fish at different depths; the underwater robot using its onboard high-definition camera to capture images of fish during feeding, using a target detection algorithm to count the number of fish in the images, generating underwater fish population data, verifying and correcting the spatial distribution data based on the underwater fish population data; based on the feed intake and average fish intake within a predetermined time period; fusing the surface fish population data, the spatial distribution data, and the underwater fish population data during feeding to generate the pre-disaster fish population data, and correcting the pre-disaster fish population data based on the feed intake and average fish intake.

2. A method for rapid post-disaster recovery of deep-sea cage aquaculture, based on the typhoon disaster prevention method for deep-sea cage aquaculture as described in claim 1, characterized in that, Includes the following steps: Unmanned detectors were used to obtain post-disaster structural data about the fish cages and post-disaster fish population data within the cages, following the same pre-disaster paths. Based on the pre-disaster structural data, the post-disaster structural data is compared and analyzed through three-dimensional modeling. A second structural repair plan and vulnerable structures are generated based on the assessment results. The repair priority is determined based on the second structural repair plan and the vulnerable structures. Maintenance personnel are dispatched to carry out repair work and optimize the cage structure. The fish population loss is calculated based on the pre-disaster and post-disaster fish population data, and the health status of the fish population is analyzed based on the post-disaster fish population data. Based on the health status, prevention and control and feeding suggestions are generated.

Images