An aquaculture multi-parameter intelligent monitoring system and method based on the Internet of Things
Through the Internet of Things technology combined with sensing and prediction models, multi-parameters and animal behavior status of aquaculture areas are monitored, and the monitoring intensity and management order are dynamically adjusted, which solves the problem that existing systems cannot effectively monitor and manage, and improves the monitoring of aquaculture Accuracy and efficiency.
Patent Information
- Application Number
- CN202411169986.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-08-26
AI Technical Summary
The existing aquaculture monitoring system cannot effectively monitor and warn of minor abnormal behaviors of aquatic animals and the deterioration of the breeding environment, which has affected aquaculture production and economic benefits. The unified management method has led to excessive or under-monitoring monitoring in certain areas, reducing Management effect.
Using a multi-parameter intelligent monitoring system based on the Internet of Things, multiple parameters in the breeding area are monitored through sensing equipment, combined with prediction models and cameras to obtain the behavioral status of aquatic animals, generate status scores and classify them, and dynamically adjust the monitoring intensity and management order. Generate control strategies based on environment and behavioral state, and perform regional sorting and management optimization.
It realizes personalized monitoring, early warning and management of aquaculture areas, improves the monitoring accuracy and management effect of the breeding environment, avoids stress response and weakening of the immune system of aquatic animals, optimizes resource allocation, and improves breeding efficiency and economic benefits. .
Smart Images

Figure CN118672228B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of aquaculture monitoring, and in particular to an aquaculture multi-parameter intelligent monitoring system and method based on the Internet of Things. Background Art
[0002] The aquaculture monitoring system is a comprehensive technical solution for real-time monitoring and management of the aquaculture environment. The system helps farmers optimize the breeding environment, ensure the healthy growth of aquatic animals, and improve breeding efficiency and productivity by integrating sensor technology, the Internet of Things (IoT), data analysis and automated control.
[0003] The prior art has the following defects:
[0004] 1. Existing monitoring systems usually monitor and regulate the aquaculture environment during aquaculture. However, in the actual aquaculture process, when aquatic animals have slightly abnormal behaviors and the aquaculture environment deteriorates (monitoring parameters are close to the corresponding thresholds), the monitoring system cannot monitor and warn, which may have a serious impact on the output and economic benefits of aquaculture (for example, causing a stress response in aquatic animals and weakening the immune system of aquatic animals, etc.);
[0005] 2. In the actual aquaculture process, there are usually multiple breeding areas. The existing monitoring system adopts a unified monitoring intensity for all breeding areas. This may waste monitoring resources and may cause insufficient monitoring of some breeding areas, resulting in poor monitoring effects. In addition, when all breeding areas are managed uniformly, the monitoring system also randomly gives the management order of the breeding areas, which will reduce the management effect of the breeding areas (breeding areas with higher attention may not receive priority management).
[0006] Based on this, the present invention proposes an IoT-based aquaculture multi-parameter intelligent monitoring system and method, which can monitor and warn based on the behavioral status of aquatic animals and the environmental status of the breeding area, and dynamically optimize the monitoring intensity of all breeding areas and then manage and sort all breeding areas to improve the management effect. Summary of the invention
[0007] The purpose of the present invention is to provide an aquaculture multi-parameter intelligent monitoring system and method based on the Internet of Things to solve the shortcomings of the background technology.
[0008] In order to achieve the above object, the present invention provides the following technical solution: a multi-parameter intelligent monitoring system method for aquaculture based on the Internet of Things, the monitoring method comprising the following steps:
[0009] The monitoring system monitors multiple parameters of the breeding area through sensor equipment, analyzes multiple parameters based on the prediction model, divides the state of the breeding area environment, obtains the behavioral state of aquatic animals based on the camera, and generates a state score of aquatic animals based on the behavioral state. Based on the state score, the state of aquatic animals is classified through a clustering algorithm;
[0010] The environmental status of the breeding area is combined with the behavioral status of aquatic animals to comprehensively analyze the overall status of the breeding area, and the corresponding control strategy is generated based on the results of environmental status division, the behavioral status of aquatic animals and the overall status of the breeding area;
[0011] Based on the overall status analysis results, all breeding areas are sorted and a regional list is generated. The monitoring intensity of all breeding areas is dynamically adjusted according to the regional list, and the management order of all breeding areas is generated in combination with the regional list.
[0012] In a preferred embodiment, the monitoring system monitors multiple parameters of the breeding area through sensor equipment and analyzes the multiple parameters based on the prediction model, including the following steps:
[0013] The monitoring system uses sensor equipment to monitor multiple parameters in the breeding area, including water quality discrete values, redox potential values, and water temperature deviation growth rate;
[0014] The water quality discrete value, redox potential value and water temperature deviation growth rate are calculated comprehensively to obtain the environmental state coefficient, which is expressed as follows: , where is the environmental state coefficient, Assign discrete values to water quality. is the redox potential value, is the water temperature deviation growth rate, , , are the adjustment coefficients of water quality discrete value, redox potential value and water temperature deviation growth rate, respectively, and , , Both are greater than 1.
[0015] In a preferred embodiment, the state division of the environment of the breeding area includes the following steps:
[0016] After obtaining the environmental state coefficient, the environmental state coefficient is compared with a preset first coefficient threshold and a second coefficient threshold, the second coefficient threshold is used to determine whether there is an abnormality in the environmental state of the breeding area, and the first coefficient threshold is used to determine the severity of the abnormality in the environmental state of the breeding area;
[0017] If the environmental state coefficient is greater than or equal to the second coefficient threshold, it is judged that there is no abnormality in the environmental state of the breeding area, and the environmental state of the breeding area is classified as a normal state; if the environmental state coefficient is less than the second coefficient threshold, and the environmental state coefficient is greater than or equal to the first coefficient threshold, it is judged that there is a slight abnormality in the environmental state of the breeding area, and the environmental state of the breeding area is classified as a slight abnormal state;
[0018] If the environmental state coefficient is less than the first coefficient threshold, it is determined that there is a serious abnormality in the environmental state of the breeding area, and the environmental state of the breeding area is classified as a serious abnormal state.
[0019] In a preferred embodiment, the behavior status of aquatic animals is acquired based on a camera, and a status score of the aquatic animals is generated according to the behavior status, including the following steps:
[0020] The behavioral status of aquatic animals including the activity deviation amplitude and feeding behavior change rate of aquatic animals are obtained based on the camera. The activity deviation amplitude and feeding behavior change rate are normalized so that the value range of the activity deviation amplitude and feeding behavior change rate is mapped to [0,1], and the normalized value of the activity deviation amplitude and the normalized value of the feeding behavior change rate are obtained. The normalized value of the activity deviation amplitude and the normalized value of the feeding behavior change rate are summed to obtain the status score.
[0021] In a preferred embodiment, the status of aquatic animals is classified by a clustering algorithm based on the status score, comprising the following steps:
[0022] Randomly generate K initial cluster centers, and multiply the number of all aquatic animals in the breeding area by the K value to obtain the maximum number of aquatic animals in the cluster;
[0023] Assign the status score of each aquatic animal to the nearest cluster center. The number of aquatic animals in each cluster is less than or equal to the maximum number of aquatic animals. After the first allocation of aquatic animals is completed, calculate the average status score of each cluster, use the average status score as the new cluster center of the cluster and iterate in a loop. When the change of a cluster center is less than the change threshold, exit the iteration and output all clusters.
[0024] The clusters whose status scores are greater than or equal to the second scoring threshold are marked as warning clusters, the clusters whose status scores are less than the second scoring threshold and whose status scores are greater than or equal to the first scoring threshold are marked as abnormal clusters, and the clusters whose status scores are less than the first scoring threshold are marked as normal clusters.
[0025] In a preferred embodiment, the environmental status of the breeding area is combined with the behavioral status of aquatic animals to comprehensively analyze the overall status of the breeding area, and a corresponding control strategy is generated according to the environmental status division results, the behavioral status of aquatic animals and the overall status of the breeding area, including the following steps:
[0026] If the environmental status coefficient of the breeding area and the average status score of aquatic animals are combined to comprehensively analyze the overall status of the breeding area, the expression is:
[0027] , where is the overall status index, is the average status score, is the environmental state coefficient;
[0028] If the environmental status classification result is a serious abnormal state, there is any warning cluster in the aquatic animals, or the overall status index is less than the index threshold, a control strategy is generated to send a warning signal to the management personnel;
[0029] If the environmental state classification result is a slightly abnormal state and there is any abnormal cluster among the aquatic animals, a control strategy is generated to send a prompt signal to the management personnel.
[0030] In a preferred embodiment, the calculation logic of the water quality discrete assignment is: monitoring the ammonia nitrogen concentration and nitrite concentration in the breeding area through a multi-parameter water quality analyzer set at multiple monitoring points in the breeding area;
[0031] The ammonia nitrogen concentration and the nitrite concentration are normalized so that the value range of the ammonia nitrogen concentration and the nitrite concentration is mapped to [0,1], and the normalized value of the ammonia nitrogen concentration and the normalized value of the nitrite concentration are obtained. The water quality index is obtained by summing the normalized value of the ammonia nitrogen concentration and the normalized value of the nitrite concentration. After obtaining the water quality index at multiple monitoring points, the average water quality index and the water quality standard deviation are calculated, and the water quality discrete assignment is obtained according to the average water quality index and the water quality standard deviation;
[0032] If the average water quality index is less than or equal to the water quality threshold, and the water quality standard deviation is less than or equal to the standard deviation threshold, the water quality discrete assignment ; If the average water quality index is less than or equal to the water quality threshold, and the water quality standard deviation is greater than the standard deviation threshold, the water quality discrete assignment ; If the average water quality index is greater than the water quality threshold, and the water quality standard deviation is less than or equal to the standard deviation threshold, the water quality discrete assignment ; If the average water quality index is greater than the water quality threshold, and the water quality standard deviation is less than or equal to the standard deviation threshold, the water quality discrete assignment .
[0033] An aquaculture multi-parameter intelligent monitoring system based on the Internet of Things, including a data analysis module, a fusion module, and a region list generation module;
[0034] Data analysis module: monitors multiple parameters of the breeding area through sensor equipment, analyzes multiple parameters based on the prediction model, divides the state of the breeding area environment, obtains the behavioral state of aquatic animals based on the camera, and generates a state score of aquatic animals based on the behavioral state. Based on the state score, the state of aquatic animals is classified through a clustering algorithm;
[0035] Fusion module: Combines the environmental status of the breeding area with the behavioral status of aquatic animals to comprehensively analyze the overall status of the breeding area, and generates corresponding control strategies based on the results of environmental status division, the behavioral status of aquatic animals and the overall status of the breeding area;
[0036] Area list generation module: sort all breeding areas based on the overall status analysis results, generate an area list, dynamically adjust the monitoring intensity of all breeding areas according to the area list, and generate the management order of all breeding areas based on the area list.
[0037] In the above technical solution, the technical effects and advantages provided by the present invention are:
[0038] After analyzing multiple parameters based on the prediction model, the present invention divides the state of the environment of the breeding area, obtains the behavioral state of aquatic animals based on the camera, and generates the state score of aquatic animals according to the behavioral state, combines the environmental state of the breeding area with the behavioral state of aquatic animals to comprehensively analyze the overall state of the breeding area, and generates corresponding control strategies according to the environmental state division results, the behavioral state of aquatic animals and the overall state of the breeding area. The monitoring system can monitor and warn in combination with the behavioral state of aquatic animals and the environmental state of the breeding area, and dynamically optimizes the monitoring strength of all breeding areas and manages and sorts all breeding areas to improve the management effect.
[0039] The present invention sorts all breeding areas based on the overall status analysis results, generates a regional list, dynamically adjusts the monitoring intensity of all breeding areas according to the regional list, and generates the management order of all breeding areas in combination with the regional list. After dynamically optimizing the monitoring intensity of all breeding areas, all breeding areas are sorted for management to improve the management effect. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0041] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION
[0042] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0043] Example 1: Please refer to Figure 1 As shown, the multi-parameter intelligent monitoring method for aquaculture based on the Internet of Things described in this embodiment includes the following steps:
[0044] The monitoring system monitors multiple parameters of the breeding area through sensor equipment, analyzes multiple parameters based on the prediction model, divides the state of the environment of the breeding area, obtains the behavioral state of aquatic animals based on the camera, and generates a state score of aquatic animals based on the behavioral state. Based on the state score, the state of aquatic animals is classified through a clustering algorithm, and the environmental state of the breeding area is combined with the behavioral state of aquatic animals to comprehensively analyze the overall state of the breeding area. The corresponding control strategy is generated based on the results of the environmental state division, the behavioral state of aquatic animals and the overall state of the breeding area. All breeding areas are sorted based on the overall state analysis results, and a regional list is generated. The monitoring intensity of all breeding areas is dynamically adjusted according to the regional list, and the management order of all breeding areas is generated in combination with the regional list.
[0045] This application divides the state of the environment of the breeding area after analyzing multiple parameters based on the prediction model, obtains the behavioral state of aquatic animals based on the camera, and generates the state score of aquatic animals based on the behavioral state, combines the environmental state of the breeding area with the behavioral state of aquatic animals to comprehensively analyze the overall state of the breeding area, and generates corresponding control strategies based on the environmental state division results, the behavioral state of aquatic animals and the overall state of the breeding area. The monitoring system can monitor and warn in combination with the behavioral state of aquatic animals and the environmental state of the breeding area, and dynamically optimize the monitoring strength of all breeding areas and manage and sort all breeding areas to improve management results.
[0046] This application sorts all breeding areas based on the overall status analysis results, generates a regional list, dynamically adjusts the monitoring intensity of all breeding areas according to the regional list, and generates the management order of all breeding areas in combination with the regional list. After dynamically optimizing the monitoring intensity of all breeding areas, all breeding areas are sorted for management to improve management effectiveness.
[0047] Embodiment 2: The monitoring system monitors multiple parameters of the breeding area through sensor equipment, analyzes multiple parameters based on the prediction model, and divides the state of the environment of the breeding area, including the following steps:
[0048] The monitoring system uses sensor equipment to monitor multiple parameters in the breeding area, including water quality discrete values, redox potential values, and water temperature deviation growth rate;
[0049] The water quality discrete value, redox potential value and water temperature deviation growth rate are calculated comprehensively to obtain the environmental state coefficient, which is expressed as follows: , where is the environmental state coefficient, Assign discrete values to water quality. is the redox potential value, is the water temperature deviation growth rate, , , are the adjustment coefficients of water quality discrete value, redox potential value and water temperature deviation growth rate, respectively, and , , Both are greater than 1.
[0050] The larger the environmental state coefficient is, the better the environmental state of the breeding area is. After obtaining the environmental state coefficient, the environmental state coefficient is compared with the preset first coefficient threshold and second coefficient threshold. The second coefficient threshold is used to determine whether there is an abnormality in the environmental state of the breeding area, and the first coefficient threshold is used to determine the severity of the abnormality in the environmental state of the breeding area.
[0051] If the environmental state coefficient is greater than or equal to the second coefficient threshold, it is judged that there is no abnormality in the environmental state of the breeding area, and the environmental state of the breeding area is classified as a normal state; if the environmental state coefficient is less than the second coefficient threshold, and the environmental state coefficient is greater than or equal to the first coefficient threshold, it is judged that there is a slight abnormality in the environmental state of the breeding area, and the environmental state of the breeding area is classified as a slight abnormal state;
[0052] If the environmental state coefficient is less than the first coefficient threshold, it is determined that there is a serious abnormality in the environmental state of the breeding area, and the environmental state of the breeding area is classified as a serious abnormal state.
[0053] The calculation logic of the water quality discrete assignment is as follows: the ammonia nitrogen concentration and nitrite concentration in the aquaculture area are monitored by the Hach-HQ40d multi-parameter water quality analyzer installed at multiple monitoring points in the aquaculture area;
[0054] The ammonia nitrogen concentration and the nitrite concentration are normalized to map the value range of the ammonia nitrogen concentration and the nitrite concentration to [0,1], and the normalized value of the ammonia nitrogen concentration and the normalized value of the nitrite concentration are obtained. The water quality index is obtained by summing the normalized value of the ammonia nitrogen concentration and the normalized value of the nitrite concentration. After obtaining the water quality index at multiple monitoring points, the average water quality index and the water quality standard deviation are calculated. The expression is: , where is the average water quality index, is the water quality standard deviation, For the The water quality index at each monitoring point is Indicates the number of monitoring points;
[0055] Obtain water quality discrete values based on the average water quality index and water quality standard deviation;
[0056] If the average water quality index is less than or equal to the water quality threshold, and the water quality standard deviation is less than or equal to the standard deviation threshold, the overall water quality of the aquaculture area is good, and the water quality discrete assignment ;
[0057] If the average water quality index is less than or equal to the water quality threshold, and the water quality standard deviation is greater than the standard deviation threshold, the overall water quality in the aquaculture area is good (that is, the average water quality index at some monitoring points is greater than the water quality threshold), and the water quality is discretely assigned. ;
[0058] If the average water quality index is greater than the water quality threshold, and the water quality standard deviation is less than or equal to the standard deviation threshold, the overall water quality in the aquaculture area is considered to be medium (i.e., the average water quality index at some monitoring points is less than or equal to the water quality threshold), and the water quality is discretely assigned. ;
[0059] If the average water quality index is greater than the water quality threshold, and the water quality standard deviation is less than or equal to the standard deviation threshold, the overall water quality of the aquaculture area is poor, and the water quality is discretely assigned. .
[0060] In summary, the larger the discrete value of water quality, the better the overall water quality of the aquaculture area.
[0061] Ammonia nitrogen: Ammonia nitrogen is a product of the decomposition of aquatic animal excrement and feed residues. It is highly toxic. High concentrations of ammonia nitrogen can cause poisoning in aquatic animals, affect the normal function of gills, and even cause death. Increased ammonia nitrogen concentrations are a direct indicator of water quality deterioration. If the safety threshold is exceeded, aquatic animals may exhibit behaviors such as floating heads and abnormal swimming.
[0062] Nitrite: Nitrite is an intermediate product in the nitrogen cycle and is toxic to aquatic animals. Long-term exposure to high concentrations of nitrite can cause poisoning of aquatic animals. Increased nitrite concentrations indicate problems with the nitrogen cycle in the biofilter or aquaculture system, which may lead to further deterioration of water quality.
[0063] The calculation expression of the redox potential value is: , where is the redox potential, is the standard electrode potential, is the gas constant (8.314 J / (mol·K)), is the absolute temperature (K), is the number of moles of electrons transferred, is the Faraday constant (96485C / mol), , are the concentrations of oxidized and reduced species, respectively;
[0064] The redox potential value is a comprehensive reflection of the oxidation and reduction reactions in the water body, reflecting the self-purification ability of the water body. Low redox potential values usually indicate that the water body is lacking oxygen or polluted. Lower redox potential values may indicate that the water body is beginning to lack oxygen or that organic pollutants are increasing, which is an early warning signal of environmental deterioration.
[0065] The logic for obtaining the water temperature deviation growth rate is: first calculate the water temperature deviation in the breeding area, the expression is: , where is the water temperature deviation, is the real-time water temperature, is the lower limit of the preset water temperature stability range. is the upper limit of the preset water temperature stability range. The water temperature deviation growth rate is calculated based on the water temperature deviation. The expression is:
[0066] , where For the moment The water temperature deviation, For the moment The water temperature deviation, For the current moment, is the previous moment; the greater the growth rate of water temperature deviation, the faster the real-time water temperature approaches the upper and lower limits of the water temperature stability range. Water temperature is an important factor affecting the metabolism, feeding and growth of aquatic animals. Different aquatic animals have different adaptability to water temperature. Too high or too low water temperature can lead to stress response, reduced feeding and even death.
[0067] Acquiring the behavior status of aquatic animals based on a camera and generating a status score of the aquatic animals according to the behavior status includes the following steps:
[0068] Based on the camera, the behavioral status of aquatic animals including the activity deviation amplitude and the feeding behavior change rate of the aquatic animals are obtained, the activity deviation amplitude and the feeding behavior change rate are normalized so that the value range of the activity deviation amplitude and the feeding behavior change rate is mapped to [0,1], the normalized value of the activity deviation amplitude and the normalized value of the feeding behavior change rate are obtained, and the normalized value of the activity deviation amplitude and the normalized value of the feeding behavior change rate are summed to obtain the status score;
[0069] The calculation expression of active deviation amplitude is:
[0070] , where For active deviation, is the real-time movement rate of aquatic animals, The larger the active deviation amplitude is, the more the real-time movement rate of aquatic animals deviates from the stable range of movement rate, which is manifested as the movement rate of aquatic animals being too large or too small. The following abnormalities may exist:
[0071] Movement rate is too high: When the water environment changes suddenly (such as increased water temperature, decreased dissolved oxygen), aquatic animals may swim faster. This is a manifestation of coping with environmental pressure. External emergencies such as noise and vibration may cause aquatic animals to swim suddenly faster to escape potential threats. When toxic substances appear in the water (such as high concentrations of ammonia nitrogen and nitrite), aquatic animals may swim abnormally fast due to poisoning. When the dissolved oxygen concentration in the water is too low, aquatic animals may swim faster in an attempt to find an area with sufficient oxygen.
[0072] Slow movement speed: When aquatic animals are infected with diseases, they often swim slowly or stagnate. This is because their physical strength decreases or they feel unwell. Long-term malnutrition or poor food quality may cause aquatic animals to lose their physical strength, which manifests as a slower swimming speed. When water quality deteriorates and harmful substances accumulate in the water, the body functions of aquatic animals may be affected, resulting in a slower movement speed. Water temperatures that are too low or too high will reduce the metabolic rate of aquatic animals, resulting in a slower swimming speed.
[0073] The calculation expression of the change rate of feeding behavior is: , where is the feeding behavior change rate, For aquatic animals in time The amount of food intake at For aquatic animals in time The amount of food intake at , are the start and end time of the observation period, respectively;
[0074] A large change in feeding behavior indicates that the food intake of aquatic animals fluctuates significantly over a short period of time. Such fluctuations may appear as sudden increases or decreases in food intake.
[0075] Possible causes:
[0076] Environmental stress: Sudden changes in the environment, such as changes in water temperature, light, and oxygen concentration, may cause stress responses in aquatic animals, leading to drastic changes in feeding behavior.
[0077] Disease: Certain diseases can cause loss of appetite or fluctuations in feeding behavior in aquatic animals. When a disease begins or becomes severe, the rate of change in feeding behavior can increase rapidly.
[0078] Changes in food quality: If the quality of the food provided changes suddenly (such as switching from old to new feed), it may also cause fluctuations in the feeding behavior of aquatic animals.
[0079] Based on the status score, the status of aquatic animals is classified by clustering algorithm, including the following steps:
[0080] By calculating the sum of squared clustering errors (SSE) under different K values, drawing an elbow diagram, and determining the optimal K value, that is, the K value where the error drops significantly in the diagram;
[0081] Randomly generate K initial cluster centers (i.e., randomly select the state score as the initial cluster center), and divide the number of all aquatic animals in the breeding area by the K value to obtain the maximum number of aquatic animals in the cluster;
[0082] Assign the status score of each aquatic animal to the nearest cluster center. The number of aquatic animals in each cluster is less than or equal to the maximum number of aquatic animals. After the first allocation of aquatic animals is completed, calculate the average status score of each cluster, use the average status score as the new cluster center of the cluster and iterate in a loop. When the change of a cluster center is less than the change threshold, exit the iteration and output all clusters.
[0083] The clusters whose status scores are greater than or equal to the second scoring threshold are marked as warning clusters, the clusters whose status scores are less than the second scoring threshold and whose status scores are greater than or equal to the first scoring threshold are marked as abnormal clusters, and the clusters whose status scores are less than the first scoring threshold are marked as normal clusters.
[0084] The overall status of the breeding area is analyzed by combining the environmental status of the breeding area with the behavioral status of aquatic animals, including the following steps:
[0085] If the environmental status coefficient of the breeding area and the average status score of aquatic animals are combined to comprehensively analyze the overall status of the breeding area, the expression is:
[0086] , where is the overall status index, is the average status score, is the environmental state coefficient.
[0087] Generate corresponding control strategies based on the environmental status division results, the behavior status of aquatic animals and the overall status of the breeding area, including the following steps:
[0088] If the environmental status classification result is a serious abnormal state, there is any warning cluster in the aquatic animals, or the overall status index is less than the index threshold, a control strategy is generated to send a warning signal to the management personnel;
[0089] If the environmental state classification result is a slightly abnormal state and there is any abnormal cluster among the aquatic animals, a control strategy is generated to send a prompt signal to the management personnel.
[0090] Based on the overall status analysis results, all breeding areas are sorted to generate a regional list. The monitoring intensity of all breeding areas is dynamically adjusted according to the regional list. The management order of all breeding areas is generated in combination with the regional list, including the following steps:
[0091] Sort all breeding areas from small to large according to the overall status index to generate a regional list. The higher the breeding area is ranked in the regional list, the more attention it needs. Therefore, the regional list is divided into the first list, the second list and the third list in positive order. The number of breeding areas in the first list, the second list and the third list is obtained by dividing the number of all breeding areas by 3. Among them, the data collection frequency of the breeding areas in the third list is the initial data collection frequency, the data collection frequency of the breeding areas in the second list is 10% higher than the initial data collection frequency, and the data collection frequency of the breeding areas in the first list is 20% higher than the initial data collection frequency.
[0092] When all breeding areas are managed regularly, the management order of the breeding areas is selected according to the positive order of the area list.
[0093] Embodiment 3: The multi-parameter intelligent monitoring system for aquaculture based on the Internet of Things described in this embodiment includes a data analysis module, a fusion module, and a region list generation module;
[0094] Data analysis module: monitors multiple parameters of the breeding area through sensor equipment, analyzes multiple parameters based on the prediction model, divides the state of the breeding area environment, obtains the behavioral state of aquatic animals based on the camera, and generates a state score of aquatic animals based on the behavioral state. Based on the state score, the state of aquatic animals is classified through a clustering algorithm. The results of the environmental state division of the breeding area and the state classification results of aquatic animals are sent to the fusion module;
[0095] Fusion module: Combines the environmental status of the breeding area with the behavioral status of aquatic animals to comprehensively analyze the overall status of the breeding area, and generates corresponding control strategies based on the environmental status division results, the behavioral status of aquatic animals and the overall status of the breeding area. The overall status of the breeding area is sent to the area list generation module;
[0096] Area list generation module: sort all breeding areas based on the overall status analysis results, generate an area list, dynamically adjust the monitoring intensity of all breeding areas according to the area list, and generate the management order of all breeding areas based on the area list.
[0097] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0098] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0099] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.
Claims
1. A multi-parameter intelligent monitoring method for aquaculture based on the Internet of Things, characterized by: The monitoring method comprises the following steps: The monitoring system monitors multiple parameters of the breeding area through sensor equipment, analyzes multiple parameters based on the prediction model, divides the state of the breeding area environment, obtains the behavioral state of aquatic animals based on the camera, and generates a state score of aquatic animals based on the behavioral state. Based on the state score, the state of aquatic animals is classified through a clustering algorithm; The environmental status of the breeding area is combined with the behavioral status of aquatic animals to comprehensively analyze the overall status of the breeding area, and the corresponding control strategy is generated based on the results of environmental status division, the behavioral status of aquatic animals and the overall status of the breeding area; Based on the overall status analysis results, all breeding areas are sorted and a regional list is generated. The monitoring intensity of all breeding areas is dynamically adjusted according to the regional list, and the management order of all breeding areas is generated in combination with the regional list; The monitoring system monitors multiple parameters of the breeding area through sensor equipment and analyzes multiple parameters based on the prediction model, including the following steps: The monitoring system uses sensor equipment to monitor multiple parameters in the breeding area, including water quality discrete values, redox potential values, and water temperature deviation growth rate; The water quality discrete value, redox potential value and water temperature deviation growth rate are calculated comprehensively to obtain the environmental state coefficient, which is expressed as follows: , where is the environmental state coefficient, Assign discrete values to water quality, is the redox potential value, is the water temperature deviation growth rate, , , are the adjustment coefficients of water quality discrete value, redox potential value and water temperature deviation growth rate, respectively, and , , All greater than 1; The state classification of the environment of the breeding area includes the following steps: After obtaining the environmental state coefficient, the environmental state coefficient is compared with a preset first coefficient threshold and a second coefficient threshold, the second coefficient threshold is used to determine whether there is an abnormality in the environmental state of the breeding area, and the first coefficient threshold is used to determine the severity of the abnormality in the environmental state of the breeding area; If the environmental state coefficient is greater than or equal to the second coefficient threshold, it is judged that there is no abnormality in the environmental state of the breeding area, and the environmental state of the breeding area is classified as a normal state; if the environmental state coefficient is less than the second coefficient threshold, and the environmental state coefficient is greater than or equal to the first coefficient threshold, it is judged that there is a slight abnormality in the environmental state of the breeding area, and the environmental state of the breeding area is classified as a slight abnormal state; If the environmental state coefficient is less than the first coefficient threshold, it is determined that there is a serious abnormality in the environmental state of the breeding area, and the environmental state of the breeding area is classified as a serious abnormal state; Acquiring the behavior status of aquatic animals based on a camera and generating a status score of the aquatic animals according to the behavior status includes the following steps: Based on the camera, the behavioral status of aquatic animals including the activity deviation amplitude and the feeding behavior change rate of the aquatic animals are obtained, the activity deviation amplitude and the feeding behavior change rate are normalized so that the value range of the activity deviation amplitude and the feeding behavior change rate is mapped to [0,1], the normalized value of the activity deviation amplitude and the normalized value of the feeding behavior change rate are obtained, and the normalized value of the activity deviation amplitude and the normalized value of the feeding behavior change rate are summed to obtain the status score; The calculation expression of active deviation amplitude is: , where For active deviation, is the real-time movement rate of aquatic animals, is the stable range of moving speed; The calculation expression of the change rate of feeding behavior is: , where is the feeding behavior change rate, For aquatic animals in time The amount of food intake at For aquatic animals in time The amount of food intake at , are the start and end time of the observation period, respectively; Based on the status score, the status of aquatic animals is classified by clustering algorithm, including the following steps: Randomly generate K initial cluster centers, and multiply the number of all aquatic animals in the breeding area by the K value to obtain the maximum number of aquatic animals in the cluster; Assign the status score of each aquatic animal to the nearest cluster center. The number of aquatic animals in each cluster is less than or equal to the maximum number of aquatic animals. After the first allocation of aquatic animals is completed, calculate the average status score of each cluster, use the average status score as the new cluster center of the cluster and iterate in a loop. When the change of a cluster center is less than the change threshold, exit the iteration and output all clusters. Mark the clusters whose status scores are greater than or equal to the second scoring threshold as warning clusters, mark the clusters whose status scores are less than the second scoring threshold and whose status scores are greater than or equal to the first scoring threshold as abnormal clusters, and mark the clusters whose status scores are less than the first scoring threshold as normal clusters; The environmental status of the breeding area and the behavioral status of aquatic animals are combined to comprehensively analyze the overall status of the breeding area, and the corresponding control strategy is generated according to the environmental status division results, the behavioral status of aquatic animals and the overall status of the breeding area, including the following steps: If the environmental status coefficient of the breeding area and the average status score of aquatic animals are combined to comprehensively analyze the overall status of the breeding area, the expression is: , where is the overall status index, is the average status score, is the environmental state coefficient; If the environmental status classification result is a serious abnormal state, there is any warning cluster in the aquatic animals, or the overall status index is less than the index threshold, a control strategy is generated to send a warning signal to the management personnel; If the environmental state classification result is a slightly abnormal state and there is any abnormal cluster among the aquatic animals, a control strategy is generated to send a prompt signal to the management personnel.
2. The multi-parameter intelligent monitoring method for aquaculture based on the Internet of Things according to claim 1 is characterized in that: The calculation logic of the water quality discrete assignment is: monitor the ammonia nitrogen concentration and nitrite concentration in the breeding area through the multi-parameter water quality analyzer set at multiple monitoring points in the breeding area; The ammonia nitrogen concentration and the nitrite concentration are normalized so that the value range of the ammonia nitrogen concentration and the nitrite concentration is mapped to [0,1], and the normalized value of the ammonia nitrogen concentration and the normalized value of the nitrite concentration are obtained. The water quality index is obtained by summing the normalized value of the ammonia nitrogen concentration and the normalized value of the nitrite concentration. After obtaining the water quality index at multiple monitoring points, the average water quality index and the water quality standard deviation are calculated, and the water quality discrete assignment is obtained according to the average water quality index and the water quality standard deviation; If the average water quality index is less than or equal to the water quality threshold, and the water quality standard deviation is less than or equal to the standard deviation threshold, the water quality discrete assignment ; If the average water quality index is less than or equal to the water quality threshold, and the water quality standard deviation is greater than the standard deviation threshold, the water quality discrete assignment ; If the average water quality index is greater than the water quality threshold, and the water quality standard deviation is greater than the standard deviation threshold, the water quality discrete assignment ; If the average water quality index is greater than the water quality threshold, and the water quality standard deviation is less than or equal to the standard deviation threshold, the water quality discrete assignment .
3. An aquaculture multi-parameter intelligent monitoring system based on the Internet of Things, used to implement the monitoring method according to any one of claims 1-2, characterized in that: Includes data analysis module, fusion module, and region list generation module; Data analysis module: monitors multiple parameters of the breeding area through sensor equipment, analyzes multiple parameters based on the prediction model, divides the state of the breeding area environment, obtains the behavioral state of aquatic animals based on the camera, and generates a state score of aquatic animals based on the behavioral state. Based on the state score, the state of aquatic animals is classified through a clustering algorithm; Fusion module: Combines the environmental status of the breeding area with the behavioral status of aquatic animals to comprehensively analyze the overall status of the breeding area, and generates corresponding control strategies based on the results of environmental status division, the behavioral status of aquatic animals and the overall status of the breeding area; Area list generation module: sort all breeding areas based on the overall status analysis results, generate an area list, dynamically adjust the monitoring intensity of all breeding areas according to the area list, and generate the management order of all breeding areas based on the area list.
Citation Information
Patent Citations
Fish behavior analysis method and system based on dynamic convolutional graph neural network
CN117058757A
Remote video monitoring system for aquaculture farm
CN117579784A
Benthic organism breeding monitoring system based on Internet of Things
CN118489597A
