Deep-sea fish culture netting damage detection method and related equipment

Abstract

The invention discloses a method for detecting damage of a deep-sea fish culture netting and related equipment. The method comprises the following steps: acquiring net rope initial tension of each connecting position after a net cage is arranged; establishing a gravity distribution model of the netting on the basis of the initial tension of the net rope; and periodically collecting real-time tension of the net rope at each connection position and combining the real-time tension with the gravity distribution model to analyze and predict whether the netting is damaged or not. The problems that netting damage may occur at any position, and initial damage is often small and is difficult to find in time can be solved. When the damage is found, the damage may be enlarged, and even the breeding object escapes.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computers, and more specifically, the present invention relates to a method for detecting damage to deep-sea fish farming nets and related equipment. Background Art

[0002] Net damage is a common problem in marine aquaculture, especially in deep-sea aquaculture and harsh marine environments. Net materials will gradually age, lose strength and become easily damaged under long-term ultraviolet radiation, seawater corrosion and mechanical wear. Nets soaked in seawater for a long time will attract various marine organisms to attach, such as barnacles, oysters and other shellfish. After these organisms attach to the net, they will continue to grow and secrete sticky substances, causing the net wires to be worn off or the mesh to be blocked. When the net is damaged, the aquaculture objects may escape, resulting in a decrease in aquaculture density, which in turn affects the aquaculture benefits. The escaped aquaculture objects may pollute the environment, such as destroying the ecological balance and spreading diseases. The damaged nets need to be repaired or replaced in time, which will increase the aquaculture cost. At the same time, the escaped aquaculture objects will also cause economic losses. Net damage may occur at any location, and the initial damage is often small and difficult to be discovered in time. By the time it is discovered, the damage may have expanded and even caused the aquaculture objects to escape. Summary of the invention

[0003] A series of simplified concepts are introduced in the Summary of the Invention, which will be further described in detail in the Detailed Description of the Invention. The Summary of the Invention does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0004] In order to solve the problem that the net damage may occur at any position, and the initial damage is often small and difficult to be discovered in time. By the time it is discovered, the damage may have expanded and even caused the farmed objects to escape, in the first aspect, the present invention proposes a method for detecting the damage of deep-sea fish farming nets, which is applied to gravity cages, wherein the net rope of the net is connected to the bottom of the floating frame of the cage, and the connection positions of the net rope and the cage are evenly distributed on the bottom of the floating frame, and the above method comprises:

[0005] Obtaining the initial tension of the net rope at each connection position after the net cage is set;

[0006] Establishing a gravity distribution model of the net based on the initial tension of the net rope;

[0007] The real-time tension of the net rope at each connection position is periodically collected and combined with the gravity distribution model to analyze and predict whether the net is damaged.

[0008] Specifically, the periodic collection of the real-time tension of the net rope at each connection position and the combination with the gravity distribution model to analyze and predict whether the net is damaged include:

[0009] Periodically collect the real-time tension of the net rope at each connection position and combine it with the gravity distribution model to analyze the abnormal tension;

[0010] Based on the abnormal tension situation, it is predicted whether the net is damaged.

[0011] Specifically, the periodic collection of the real-time tension of the net rope at each connection position is combined with the gravity distribution model to analyze and predict the attachment of marine organisms to the net, including:

[0012] Periodically collect the real-time tension of the net rope at each connection position and combine it with the gravity distribution model to analyze the abnormal tension;

[0013] The marine biological attachment condition of the net is predicted based on the abnormal tension condition.

[0014] Specifically, it also includes:

[0015] In case of predicting whether the net is damaged based on the abnormal distribution of tension, analyzing the abnormal distribution of tension;

[0016] The damaged position of the net is predicted according to the abnormal distribution of the tension.

[0017] Specifically, it also includes:

[0018] Obtain theoretical mesh distribution information of nets in the sea;

[0019] The damage size and shape of the damaged position of the net clothing are predicted according to the abnormal tension distribution and theoretical mesh distribution information.

[0020] Specifically, it also includes:

[0021] Predicting the marine biological attachment of the net based on the abnormal tension and analyzing the abnormal distribution of tension;

[0022] The marine organism attachment concentration area of ​​the net is predicted according to the abnormal tension distribution.

[0023] Specifically, it also includes:

[0024] The marine organism attachment concentration area and mesh blockage condition of the net are predicted based on the abnormal tension distribution.

[0025] In a second aspect, the present invention further proposes a deep-sea fish farming net damage detection device, which is applied to a gravity cage, wherein the net rope of the net is connected to the bottom of the floating frame of the cage, and the connection positions of the net rope and the cage are evenly distributed at the bottom of the floating frame, and the above-mentioned device comprises:

[0026] An acquisition unit, used for acquiring the initial tension of the net rope at each connection position after the net cage is set;

[0027] A modeling unit, used for establishing a gravity distribution model of the net based on the initial tension of the net rope;

[0028] The monitoring unit is used to periodically collect the real-time tension of the net rope at each connection position and combine it with the gravity distribution model to analyze and predict whether the net is damaged.

[0029] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the method for detecting damage to deep-sea fish farming nets as described in any one of the first aspects above when executing the computer program stored in the memory.

[0030] In a fourth aspect, the present invention further proposes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for detecting damage to deep-sea fish farming nets according to any one of the above items in the first aspect is implemented.

[0031] In summary, the deep-sea fish farming net damage detection method proposed in this application is applied to gravity-type cages, wherein the net rope of the net is connected to the bottom of the floating frame of the cage, and the connection positions of the net rope and the cage are evenly distributed at the bottom of the floating frame, by obtaining the initial tension of the net rope at each of the connection positions after the cage is set up; establishing the gravity distribution model of the net based on the initial tension of the net rope; periodically collecting the real-time tension of the net rope at each of the connection positions combined with the gravity distribution model, analyzing and predicting whether the net is damaged. In this way, automated and remote monitoring of net damage is achieved, reducing the frequency of manual inspections. Even if the initial damage is small, it can be discovered in time to avoid expansion. Timely repair of damaged areas to prevent the escape of farmed objects. Reduce indirect losses caused by ecological damage and disease transmission. Real-time monitoring ensures the overall safety of the farming cages, and can respond to emergencies even in the harsh environment of the deep sea.

[0032] The deep-sea fish farming net damage detection method of the present invention, other advantages, objectives and features of the present invention will be reflected in part through the following description, and in part will be understood by technicians in this field through research and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0034] Figure 1 A schematic diagram of a process for detecting damage to deep-sea fish farming nets provided in an embodiment of the present application;

[0035] Figure 2 A schematic diagram of the structure of a deep-sea fish farming net damage detection device provided in an embodiment of the present application;

[0036] Figure 3 A schematic diagram of the structure of an electronic device for detecting damage to deep-sea fish farming nets provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0038] To solve the problem that the net may be damaged at any position, and the initial damage is often small and difficult to detect in time. By the time it is discovered, the damage may have expanded and even caused the farmed animals to escape, please refer to Figure 1 , is a schematic flow chart of a method for detecting damage to deep-sea fish farming nets provided in an embodiment of the present application, which may specifically include: steps S110 to S130.

[0039] S110, obtaining the initial tension of the net rope at each connection position after the net cage is set up.

[0040] Applicable to a gravity-type net cage, wherein the net rope of the net is connected to the bottom of the floating frame of the net cage, and the connection positions of the net rope and the net cage are evenly distributed on the bottom of the floating frame.

[0041] S120, establishing a gravity distribution model of the net garment based on the initial tension of the net rope.

[0042] S130, periodically collecting the real-time tension of the net rope at each connection position and combining it with the gravity distribution model to analyze and predict whether the net is damaged.

[0043] For example, the core principle of the deep-sea aquaculture net damage detection solution is to reflect the state of the net through the change of the net rope tension. The net bears a variety of complex loads such as farmed fish, attached organisms, and marine fluid dynamics. Under these loads, the tension distribution of the net rope will change. The tension sensor is used to periodically monitor the tension of the net rope, and combined with the established gravity distribution model, it is possible to identify abnormal tension changes and locate potential damage points. Based on the initial tension and the geometric structure of the net, a tension distribution model under normal working conditions can be established. By collecting the tension value of the net rope in real time, it is determined whether it exceeds the expected range. Combined with the model calculation, the location of the abnormal point and the damage trend are obtained.

[0044] For example, to obtain the initial tension of the net rope, a tension sensor can be installed at each connection point of the net rope after the net box is installed. Under static conditions, the tension value of each point is collected and recorded as the initial tension T0. The initial tension reflects the force of the net under normal conditions and serves as the benchmark data. For example, assuming that the net has 10 connection points, the initial tension values ​​are [T 0,1 ,T 0,2 ,…,T 0,10 ] These values ​​are affected by factors such as net geometry, aquaculture volume, and buoyancy. Based on the shape of the net, fish distribution, seawater buoyancy, etc., a gravity balance model of the net is established to predict the theoretical tension value distribution of each connection point. Net force calculation formula: T i =F g +F b -F h Where: T i is the tension at the connection point iii; F g is the gravity of the net and the cultured organisms; F b is the buoyancy of seawater; F h is the horizontal thrust of the ocean current on the net. Finite element analysis (FEM) software can be used to simulate the stress distribution of the net. Input the initial tension T0 and the material parameters of the net to obtain the normal tension distribution at each point. For example, if the net is designed as a rectangle, the theoretical tension distribution of 10 connection points may be [T th,1 ,T th,2 ,…,T th,10 ]. Each sensor collects the current tension T in real time realThe data is transmitted to the monitoring system through wireless transmission or data acquisition module. For example, in one day, the collected tension value is [T real,1(t) ,T real,2(t) ,…,T real,10(t) ]. Compare the real-time tensile force T real and theoretical tension T th Difference: ΔTi = |T real,i -T th,i | If the difference ΔT i If the threshold is exceeded, it means there may be an abnormality. Based on the strength of the net material and environmental data, a tolerance range is set, such as a 10% deviation, and an alarm is triggered when the threshold is exceeded. For example, at a certain moment, it is found that ΔT3>threshold, then it is determined that there may be damage near connection point 3. Based on multiple sampling data, trend analysis (such as time series analysis) is used to predict the trend of damage expansion. If multiple abnormalities or rapidly increasing ΔT are found, it is recommended to check and repair them in time. The ΔT of a net rope increased from 5% to 20%, and the system issued a high-priority maintenance prompt.

[0045] Exemplarily, in order to realize the damage detection of deep-sea aquaculture nets, using experimental simulation and training models is an effective way. By simulating different environmental conditions and net stress conditions, a model can be trained to predict the damage of nets in the marine environment, the concentrated area of ​​attached organisms and the blockage of meshes. In order to verify the relationship between the change of tension and the damage of nets, attached organisms, and mesh blockage, it is necessary to construct a simulation experiment adapted to the deep-sea aquaculture environment. Nets of different specifications and materials (such as nylon nets, PE nets, etc.) can be simulated. A simulated environment for deep-sea aquaculture can be constructed, including factors such as water flow velocity, ocean temperature, and salinity. Different load conditions can be set, such as the weight of the cultured (fish), the attachment load of marine organisms, and the hydrodynamic force of seawater (waves, flow rate, etc.). Tension sensors can be arranged on the nets, and the sensors need to be installed at different connection points of the net rope to monitor the tension changes of the net rope. The tension data of each connection point will be collected and compared with the theoretical tension value. Different load conditions can be simulated, for example, the load of aquaculture, by simulating the weight of aquaculture (such as fish), the load imposed on the net; the attached organism load, simulating the attachment of different types and quantities of attached organisms (such as barnacles, oysters, etc.) on the net, and observing their effects on the tension of the net; water flow simulation, by controlling the flow rate, waves and other marine environmental factors through water flow simulation equipment, and observing the effects of water flow on the net. Simulate the damage of the net by artificial destruction or simulating the excessive force on the net. Record the tension data under different damage states and mark the damage location. Record the tension data of each connection point in real time. The collection includes tension data under normal conditions, tension changes caused by attachments, and tension changes caused by damage or deformation of the net. Use experimental data to build a training data set. Each sample can include the following information: for example, the initial state of the net: the specifications, materials, mesh size, connection point layout of the net; experimental conditions: the load of the aquaculture, the number of attachments, the flow rate of seawater, etc.; tension data: real-time tension data of each connection point and its abnormal conditions; attachment and mesh blockage annotation: the distribution area of ​​the attachments in the labeled data, and whether the mesh is blocked or deformed. The prediction model is trained using a machine learning algorithm to identify the relationship between tension anomalies, attachments, and mesh blockage. Common training methods include: the labeled data set can be used for training, and the model learns how to predict the attachment area and mesh blockage from tension anomalies. For the tension data of each connection point, a regression model can be used to predict the load of attachments, the degree of mesh blockage, etc. The effect of the model is evaluated using indicators such as cross-validation, confusion matrix, and accuracy to ensure that the model can accurately predict the damage, attachment, and mesh blockage of the net under new data. The parameters of the model are adjusted according to the evaluation results to optimize the model performance. Therefore, through experimental simulation and training, the feasibility of the deep-sea aquaculture net damage detection scheme can be efficiently verified. The specific implementation steps include experimental simulation, data collection and cleaning, feature extraction, model training and evaluation.The experimental simulation provides a variety of environmental factors, which enables the training model to have strong generalization ability and can accurately predict the damage of nets, the distribution of attached organisms and the blockage of meshes in real environments.

[0046] In summary, the deep-sea fish farming net damage detection method provided in the embodiment of the present application is applied to a gravity-type net cage, wherein the net rope of the net is connected to the bottom of the floating frame of the net cage, and the connection positions of the net rope and the net cage are evenly distributed at the bottom of the floating frame, by obtaining the initial tension of the net rope at each of the connection positions after the net cage is set up; establishing a gravity distribution model of the net based on the initial tension of the net rope; periodically collecting the real-time tension of the net rope at each of the connection positions combined with the gravity distribution model, analyzing and predicting whether the net is damaged. In this way, automated and remote net damage monitoring is achieved, reducing the frequency of manual inspections. Even if the initial damage is small, it can be discovered in time to avoid expansion. Timely repair of damaged areas to prevent the escape of farmed objects. Reduce indirect losses caused by ecological damage and disease transmission. Real-time monitoring ensures the overall safety of the farming net cage, and can respond to emergencies even in the harsh environment of the deep sea.

[0047] According to some embodiments, the periodic collection of the real-time tension of the net rope at each connection position combined with the gravity distribution model to analyze and predict whether the net is damaged includes:

[0048] Periodically collect the real-time tension of the net rope at each connection position and combine it with the gravity distribution model to analyze the abnormal tension;

[0049] Based on the abnormal tension situation, it is predicted whether the net is damaged.

[0050] It is understandable that in a cylindrical net box, the net connection points are distributed around the annular floating frame, the distance between each point is uniform, and the net is in a bell-shaped hanging state. In a cylindrical net box, the force on each net rope connection point mainly comes from: vertical component force F v , vertical loads such as the weight of the net, the weight of the fish school and the attached organisms; horizontal component force F h , horizontal thrust caused by water flow pressure, wave action, etc.; neighborhood pull affects F adj Due to the tensile force transmission of the net, the net rope near the damaged point will redistribute part of the stress originally borne by the damaged point. Assume that the radius of the cylindrical net cage floating frame is R, the number of net rope connection points is N, and the total tension of the i-th connection point is T i , then:

[0051]

[0052] In the initial state, the gravity distribution model can be described as:

[0053]

[0054] Where G is the total weight of the net and fish, W is the additional weight of the attached organisms, Cd is the drag coefficient, and A is i is the net projection area corresponding to the connection point, ρ is the water density, and V is the water flow velocity. When the net is damaged, the tension of the net rope at the damaged point is reduced, and its force is shared by the net ropes in the adjacent area. This transfer effect causes the tension near the damaged point to be abnormally high, while the tension away from the damaged point changes little.

[0055] For example, a tension sensor can be used to collect the tension T of all connection points every Δt time. i (t), generate time series T i (t1), T i (t2), .... Calculate the theoretical tension T by combining the gravity distribution model th,i (t), and compared with the collected value, the deviation is obtained: ΔT i =|T i (t)-T th，i (t)|, if ΔTi>threshold, it is considered that the tension at the connection point i is abnormal. Calculate the tension change gradient between the abnormal point and its neighboring points: Among them, the area with a significant increase in gradient may be the center of damage or its range of influence. Combine the spatial distribution of tension anomalies with the temporal trend to predict the damage point and damage extension of the net. Specifically, spatial interpolation methods, such as spline interpolation or Kriging, can be used to convert the distribution of tension anomalies at discrete connection points into a continuous field. Possible damage points are located through the abnormal peak area. Trend fitting is performed on the change of tension at the abnormal point over time, such as using an exponential model or time series analysis to predict the trend of damage expansion. Use probability-based models, such as Bayesian networks, to combine historical data with current abnormal conditions to calculate the probability of damage.

[0056] In some examples, the periodic collection of the real-time tension of the net rope at each of the connection positions is combined with the gravity distribution model to analyze and predict the attachment of marine organisms to the net, including:

[0057] Periodically collect the real-time tension of the net rope at each connection position and combine it with the gravity distribution model to analyze the abnormal tension;

[0058] The marine biological attachment condition of the net is predicted based on the abnormal tension condition.

[0059] It is understandable that the attachment of marine organisms (such as barnacles, oysters, etc.) is one of the main problems that lead to the degradation of net performance in deep-sea aquaculture. Changes in the tension of the net rope can not only reflect damage, but also the degree and distribution of marine organism attachment. The cumulative weight of marine organisms increases the tension near the attachment area. The attached organisms change the smoothness of the net surface, increase the resistance of the water flow, and cause an increase in the horizontal tension near the attachment area. Due to the attachment of organisms, the tension at the connection point is unevenly distributed in space. Combined with these characteristics, the real-time tension of the net rope can be periodically collected, and the gravity distribution model and tension anomaly analysis can be used to predict the attachment situation.

[0060] For example, a tension sensor is installed at each connection point of the cage floating frame to regularly collect the real-time tension T of each connection point. i (t). Generate time series tension data for each connection point [T i (t1),T i (t2),…,T i (tn)] The theoretical tension T is calculated using the gravity distribution model. th,i , including: initial tension T0 under normal conditions, that is, after the initial setting of the cage, the theoretical distribution is obtained based on the weight of the net, the shape of the cage, the distribution of the fish school, etc. The theoretical tension value is corrected according to the tidal speed, water density changes, etc. The corrected theoretical tension: T th,i =f(G,V,ρ,C d ). Where G is the total weight of the net and the fish school, V is the water velocity, ρ is the water density, C d is the resistance coefficient. Compare the collected real-time tension with the theoretical tension and calculate the tension anomaly ΔT i :ΔT i =T i -T th,i , then if ΔTi>0, there may be biological attachment or increased external resistance. The larger the anomaly, the more serious the attachment may be. The spatial distribution and temporal variation trend of the tension anomaly can be used to infer the location and severity of marine biological attachment. For example, the distribution of the attachment area can be plotted through the tension anomalies of multiple connection points. Or analyze the ΔT at a certain point i Predict the attachment trend over time. Therefore, the concentrated area of ​​attachment or the overall attachment distribution of the cage can be accurately located through the abnormal tension spatial distribution. Combined with the tension anomaly and gravity distribution model, the weight and growth rate of the attachment are estimated to provide a basis for cleaning decisions. Detect and deal with attachments in advance to avoid cage blockage, increased fluid resistance, reduced stocking density, or stress on farmed fish. Automated monitoring and early warning of attachment conditions in farms can be achieved through periodic collection and abnormal analysis.

[0061] In some examples, this also includes:

[0062] In case of predicting whether the net is damaged based on the abnormal distribution of tension, analyzing the abnormal distribution of tension;

[0063] The damaged position of the net is predicted according to the abnormal distribution of the tension.

[0064] For example, in deep-sea aquaculture, net damage is usually caused by long-term exposure to seawater, ultraviolet rays, mechanical wear, or biological adhesion. By periodically collecting the tension of the net rope and combining it with the analysis of abnormal tension distribution, the damaged position of the net can be predicted and measures can be taken to prevent more serious damage.

[0065] It is understandable that a damaged net will cause a sudden decrease in tension in the damaged area, but due to the tension transfer effect between the net ropes, the change in tension near the damaged point will affect the tension distribution of adjacent net ropes. Specifically, the tension at the damaged point usually drops significantly because the net loses some of its structural strength. The load at the damaged point will be transferred to the adjacent net ropes, resulting in an increase in tension at these locations. Due to the transfer of force, the tension anomaly near the damaged point usually presents a symmetrical distribution, especially in symmetrical net cage structures. By performing anomaly analysis on the tension data of each connection point and combining it with a theoretical model, the damaged location and its impact range can be predicted. The distribution pattern and change trend of the tension anomaly can help us identify possible damaged locations, especially in areas where the tension anomaly is concentrated.

[0066] For example, tension sensors are installed at multiple connection points of the cage to periodically collect the real-time tension T at each point. i (t). Record the tension change data of each connection point and establish a time series of real-time tension data. Combine the gravity distribution model, cage structure and environmental factors (such as water flow, marine biological attachment, etc.) to calculate the theoretical tension T of each connection point. th,i These theoretical values ​​reflect the tension that the net rope should withstand under normal conditions. By using the difference between the theoretical value and the actual tension, the tension anomaly at each connection point is calculated: ΔT i =T i (t)-T th,i. The size and direction (increase or decrease) of the anomaly can reflect the possible damaged area of ​​the net. Observe the change of tension at each connection point and look for the area where the anomaly increases. Usually, these places may be the precursor of damage. The abnormal tension at the damaged point usually affects the change of tension at the surrounding connection points. Therefore, by analyzing the spatial distribution of the abnormal tension, it can be determined that the damaged point may be located in the area with large abnormal changes. Calculate the difference in tension between each connection point and its adjacent points. If the tension of a connection point is significantly abnormal, while the tension of its neighboring connection points is normal, it means that the damage may have occurred at this location. When the gradient exceeds the set threshold, the location can be identified as a possible damage point. If the tension of multiple connection points of a certain section of net rope is abnormal, and the distribution of the anomaly is coherent, it can be inferred that the area is a high-risk area for damage. The extension of the damage can be inferred by the time evolution trend of the abnormal tension. If the abnormal tension in a certain area continues to increase, it indicates that the damage may have expanded and may even lead to complete breakage. Therefore, by analyzing the distribution of the abnormal tension, the damaged location of the net can be accurately predicted, especially the possible weak points or stress concentration areas in the cage structure can be found. It can issue an early warning through the change trend of abnormal tension before damage occurs, avoiding economic losses caused by the expansion of damage. By accurately locating the damaged area, targeted repairs and reinforcements can be carried out, thereby reducing maintenance costs. Combined with abnormal tension analysis, it can not only predict damage, but also avoid problems such as escape of aquaculture objects and environmental pollution caused by damage.

[0067] In some examples, this also includes:

[0068] Obtain theoretical mesh distribution information of nets in the sea;

[0069] The damage size and shape of the damaged position of the net clothing are predicted according to the abnormal tension distribution and theoretical mesh distribution information.

[0070] It is understandable that in deep-sea aquaculture, the damage of nets not only affects the aquaculture density and benefits, but may also cause the escape of aquaculture and even pollute the environment. Combining the abnormal distribution of tension with the theoretical mesh distribution information of the net, the location, size and shape of the damage can be accurately predicted, thus providing a scientific basis for timely repair. The mesh distribution of the net is closely related to the distribution of tension. The size, shape and spacing of the mesh affect the carrying capacity of the net. The theoretical mesh distribution model takes into account the following factors: the mesh shape, usually hexagonal, square or rectangular, determines the rigidity of the net; the mesh size, the size of the mesh determines the load capacity of the net; the mesh distribution, the uniformity and size changes of the mesh determine the force distribution of the net. By establishing the theoretical mesh distribution model of the net, the theoretical size and shape information of the mesh can be provided for each connection point. If the tension in a certain area increases abnormally, it means that the mesh at that location may be subjected to additional tension, and may be deformed or partially damaged. If the tension in a certain area decreases abnormally, it may be due to uneven load distribution caused by mesh deformation, or damage in that area. Changes in mesh shape (such as stretching, deformation, and breakage) are associated with abnormal changes in tension. By combining the tension anomaly with theoretical mesh distribution information, the location, size, and shape of the damage in the net can be inferred.

[0071] For example, first, the theoretical distribution of meshes needs to be obtained based on the design and installation information of the net. The size of the net box (such as diameter, height, etc.) and the thickness, mesh size and shape of the net are determined. The influence of factors such as seawater velocity, salinity, and ultraviolet rays on the net may cause the morphology of the mesh to change. Based on these parameters, a theoretical distribution model of the mesh is constructed. The theoretical mesh distribution information provides the ideal size S for each mesh. i Ideally, the shape and size of all meshes should be consistent. Periodically collect the real-time tension T of each connection point of the net rope i (t), and the theoretical tensile force T th,i Compare and calculate the tensile force anomaly ΔT i :ΔT i =T i (t)-T th,i. By analyzing the abnormal distribution of tension at all connection points, determine which areas have abnormal tension. By analyzing the spatial characteristics of the abnormal distribution of tension and combining it with the theoretical mesh distribution, identify possible damaged areas. If the tension of a certain section of the net rope increases abnormally, it means that the mesh in this area may be stretched or deformed, which leads to a decrease in local bearing capacity. By analyzing the abnormal strength and distribution of tension in this area and combining it with the theoretical mesh model, the size and shape of the mesh deformation or damage can be inferred. According to the distribution of abnormal tension and the theoretical mesh distribution information, the location, size and shape of the net damage are predicted. Areas with large abnormal tension usually correspond to the damaged points of the net. Especially in areas with prominent abnormal changes, the probability of damage is predicted to be high. By calculating the abnormal gradient of tension and combining it with the size change of the mesh, the area and shape of the damaged area can be inferred. For example, if the abnormal change in a certain area is large and the surrounding mesh is severely deformed, the damaged area in this area may be large. According to the damage prediction, provide priority repair areas and recommended repair methods. For example, if the damaged area is small and localized, it can be repaired by local reinforcement or patching; if the damaged area is large, the net may need to be replaced. Based on the trend of abnormal tension, the expansion of net damage can be predicted, and maintenance and repair time can be planned in advance to avoid the escape of aquaculture or environmental pollution caused by damage.

[0072] In some examples, this also includes:

[0073] Predicting the marine biological attachment of the net based on the abnormal tension and analyzing the abnormal distribution of tension;

[0074] The marine organism attachment concentration area of ​​the net is predicted according to the abnormal tension distribution.

[0075] It is understandable that in deep-sea aquaculture, the attachment of marine organisms (such as barnacles, oysters, seaweed, etc.) is one of the important factors for the damage of nets. Biological attachment not only increases the load on the net, but also causes wear, clogging of the mesh, and even rupture of the net. By periodically monitoring the changes in the tension of the net rope and combining the abnormal distribution of tension, the attachment of marine organisms on the net can be effectively predicted, especially the concentrated areas of attachment. The attachment of marine organisms will produce additional loads on the net, which is manifested in the following aspects: the attachments increase the weight of the net, resulting in an increase in the tension of the net rope; since the attachments are usually unevenly distributed on the net, the abnormal changes in tension will show obvious local concentrated areas, especially in areas with heavier biological attachment, the tension of the net rope will increase significantly; the attachments increase the resistance of the mesh, resulting in poor water flow, thereby affecting the force distribution of the net. In some areas, there are more attached organisms, which will increase the local tension, making the tension in the area significantly higher than the normal value. The size, quantity and distribution characteristics of the attachments will affect the intensity and distribution range of the abnormal tension. For example, when multiple attachments are concentrated in a certain area, the tension anomaly will be more concentrated and may be accompanied by local mesh deformation. The seasonal changes in marine biological attachment and water flow changes will affect the temporal and spatial distribution of the attachment amount, which will be reflected in the dynamic changes of the tension anomaly.

[0076] Exemplarily, similar to the prediction of damage, the tension of each connection point of the net rope is periodically collected and compared with the theoretical tension value to calculate the tension anomaly. According to the structure and environmental conditions of the net cage, data of a certain period is collected to record the tension change of each connection point. By analyzing the tension data, the local tension anomaly value is found to determine whether there is biological attachment in the area. Areas with larger tension anomaly values ​​usually correspond to areas with more or heavier attachments. Areas with biological attachment usually show a certain distribution pattern. For areas with more marine organisms, the tension anomaly will form a local concentrated high value. If the tension in a certain area increases abnormally and the mesh in the area is small or blocked, it may be due to the obstruction of water flow caused by the attached organisms, thereby increasing the local tension. Areas with more biological attachment may cause the mesh to stretch or deform, change the bearing capacity of the net, and thus affect the distribution of tension. According to the distribution of tension anomaly, combined with the theoretical mesh model, the concentrated area of ​​marine biological attachment is predicted: at certain connection points or net rope areas, if there is a continuous increase in tension anomaly, it indicates that there are more biological attachments in the area; through the distribution pattern of tension anomaly, the concentrated area of ​​attachment is identified. For example, if the tension anomaly forms a concentrated elevated area at the front end of the cage or a specific section, it may be because the water flow in this area is slow or there is a lot of accumulation of attachments. In addition, biological attachment has seasonal fluctuations. By monitoring the changes in tension data in different seasons, the peak period and concentrated area of ​​biological attachment can be dynamically predicted. For example, there are fewer seaweeds in winter, while barnacles and oysters are attached in large quantities. Changes in water flow may also affect the distribution of attached organisms. Areas with slower flow rates may be hot spots for biological attachment. Therefore, by combining tension anomalies and mesh distribution, the concentrated areas of biological attachment on the net can be accurately identified, providing guidance for subsequent cleaning and maintenance. Predicting the biological attachment area helps to clean and reinforce before the attachment grows excessively, reduce the load on the net, and avoid damage. By periodically collecting tension data, the changes in attachments can be dynamically monitored and countermeasures can be taken in a timely manner. Reduce the damage to the net caused by biological attachment, ensure the stability of the aquaculture environment, and improve the aquaculture efficiency.

[0077] In some examples, this also includes:

[0078] The marine organism attachment concentration area and mesh blockage condition of the net are predicted based on the abnormal tension distribution.

[0079] It is understandable that in deep-sea aquaculture, marine organisms attached to nets (such as barnacles, oysters, seaweed, etc.) not only increase the load on the nets, but may also cause mesh blockage, affecting water flow and the force distribution of the nets. By periodically monitoring the tension changes of the net ropes and combining the abnormal distribution of tension, it is possible to effectively predict the concentrated areas of marine organism attachment on the nets and the risk of mesh blockage.

[0080] For example, the attachment of marine organisms will cause an increase in the local load of the net, which is manifested as an increase in the tension in the area. The attachments are usually distributed locally, so the abnormal change of tension will show significant local abnormalities, especially in areas where the attached organisms are concentrated, the tension will increase significantly. The attached organisms may cause the mesh to be blocked and the water flow to be sluggish, which will affect the force distribution of the net, especially in areas with slower water flow and more attachments, the tension abnormality will be more obvious. The attachment of attached organisms to the net will not only cause changes in the mesh size, but also cause the mesh to be completely blocked. After the mesh is blocked, the water flow is reduced or stopped, and the tension abnormality will become more obvious in these areas. By analyzing the tension abnormality area, it can be inferred which areas the mesh may have been blocked or deformed. Areas with higher tension abnormality values ​​are usually areas with more biological attachment. These areas may be accompanied by mesh blockage or slow water flow. Mesh blockage will cause poor water flow, causing abnormal tension distribution in the area. By analyzing the tension data, the distribution of mesh blockage can be predicted and cleaning measures can be taken in time.

[0081] See also Figure 2 An embodiment of the deep-sea fish farming net damage detection device in the embodiment of the present application is applied to a gravity cage, wherein the net rope of the net is connected to the bottom of the floating frame of the cage, and the connection positions of the net rope and the cage are evenly distributed at the bottom of the floating frame, and may include:

[0082] An acquisition unit 21 is used to acquire the initial tension of the net rope at each connection position after the net cage is set;

[0083] A modeling unit 22, used for establishing a gravity distribution model of the net based on the initial tension of the net rope;

[0084] The monitoring unit 23 is used to periodically collect the real-time tension of the net rope at each connection position and combine it with the gravity distribution model to analyze and predict whether the net is damaged.

[0085] In summary, the deep-sea fish farming net damage detection device provided in the embodiment of the present application is applied to a gravity-type net cage, wherein the net rope of the net is connected to the bottom of the floating frame of the net cage, and the connection positions of the net rope and the net cage are evenly distributed at the bottom of the floating frame, by obtaining the initial tension of the net rope at each of the connection positions after the net cage is set up; establishing a gravity distribution model of the net based on the initial tension of the net rope; periodically collecting the real-time tension of the net rope at each of the connection positions combined with the gravity distribution model, analyzing and predicting whether the net is damaged. In this way, automated and remote net damage monitoring is achieved, reducing the frequency of manual inspections. Even if the initial damage is small, it can be discovered in time to avoid expansion. Timely repair of damaged areas to prevent the escape of farmed objects. Reduce indirect losses caused by ecological damage and disease transmission. Real-time monitoring ensures the overall safety of the farming net cage, and can respond to emergencies even in the harsh environment of the deep sea.

[0086] like Figure 3 As shown, the embodiment of the present application further provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any one of the above-mentioned methods for detecting damage to deep-sea fish farming nets are implemented:

[0087] Obtaining the initial tension of the net rope at each connection position after the net cage is set;

[0088] Establishing a gravity distribution model of the net based on the initial tension of the net rope;

[0089] The real-time tension of the net rope at each connection position is periodically collected and combined with the gravity distribution model to analyze and predict whether the net is damaged.

[0090] Since the electronic device introduced in this embodiment is a device used to implement a deep-sea fish farming net damage detection device in the embodiment of the present application, based on the method introduced in the embodiment of the present application, the technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by the technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0091] In the specific implementation process, when the computer program 311 is executed by the processor, it can achieve Figure 1 Any implementation method in the corresponding embodiment:

[0092] Obtaining the initial tension of the net rope at each connection position after the net cage is set;

[0093] Establishing a gravity distribution model of the net based on the initial tension of the net rope;

[0094] The real-time tension of the net rope at each connection position is periodically collected and combined with the gravity distribution model to analyze and predict whether the net is damaged.

[0095] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0096] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0097] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0098] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0100] The present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device is caused to execute the following Figure 1 The process of deep-sea fish farming net damage detection in the corresponding embodiment.

[0101] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0102] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0103] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0106] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0107] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting damage to deep-sea fish farming nets, characterized in that: Applied to a gravity-type net cage, wherein the net rope of the net is connected to the bottom of the floating frame of the net cage, and the connection positions of the net rope and the net cage are evenly distributed at the bottom of the floating frame, the method comprises: Obtaining the initial tension of the net rope at each connection position after the net cage is set; Establishing a gravity distribution model of the net based on the initial tension of the net rope; The real-time tension of the net rope at each connection position is periodically collected and combined with the gravity distribution model to analyze and predict whether the net is damaged.

2. The method according to claim 1, characterized in that The periodic collection of the real-time tension of the net rope at each connection position is combined with the gravity distribution model to analyze and predict whether the net is damaged, including: Periodically collect the real-time tension of the net rope at each connection position and combine it with the gravity distribution model to analyze the abnormal tension; Based on the abnormal tension situation, it is predicted whether the net is damaged.

3. The method according to claim 1, characterized in that The periodic collection of the real-time tension of the net rope at each connection position is combined with the gravity distribution model to analyze and predict the attachment of marine organisms to the net, including: Periodically collect the real-time tension of the net rope at each connection position and combine it with the gravity distribution model to analyze the abnormal tension; The marine biological attachment condition of the net is predicted based on the abnormal tension condition.

4. The method according to claim 2, characterized in that Also includes: In case of predicting whether the net is damaged based on the abnormal distribution of tension, analyzing the abnormal distribution of tension; The damaged position of the net is predicted according to the abnormal distribution of the tension.

5. The method according to claim 4, characterized in that Also includes: Obtain theoretical mesh distribution information of nets in the sea; The damage size and shape of the damaged position of the net clothing are predicted according to the abnormal tension distribution and theoretical mesh distribution information.

6. The method according to claim 3, characterized in that Also includes: Predicting the marine biological attachment of the net based on the abnormal tension and analyzing the abnormal distribution of tension; The marine organism attachment concentration area of ​​the net is predicted according to the abnormal tension distribution.

7. The method according to claim 6, characterized in that Also includes: The marine organism attachment concentration area and mesh blockage condition of the net are predicted based on the abnormal tension distribution.

8. A deep-sea fish farming net damage detection device, characterized in that: Applied to a gravity-type net cage, wherein the net rope of the net is connected to the bottom of the floating frame of the net cage, and the connection positions of the net rope and the net cage are evenly distributed at the bottom of the floating frame, and the device comprises: An acquisition unit, used for acquiring the initial tension of the net rope at each connection position after the net cage is set; A modeling unit, used for establishing a gravity distribution model of the net based on the initial tension of the net rope; The monitoring unit is used to periodically collect the real-time tension of the net rope at each connection position and combine it with the gravity distribution model to analyze and predict whether the net is damaged.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the method for detecting damage to deep-sea fish farming nets as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for detecting damage to deep-sea fish farming nets as described in any one of claims 1 to 7 is implemented.

Images