Optimization control method and system for intelligent breeding environment

Abstract

The invention relates to the technical field of environment control, and provides an optimization control method and system for an intelligent breeding environment. The method comprises the following steps: executing field digital twin modeling of an intelligent breeding environment, and distributing environment control equipment; fitting a control intensity field in the digital twinborn model, and constructing a grid topological graph in combination with the behavior heat map; arranging monitoring sensors in each grid region, establishing an environment data set, and collecting behavior characteristics to construct a behavior characteristic set; fusing the two sets to evaluate a health risk level; performing control strategy optimization based on the risk level to generate a local strategy set; and performing global coordination fitting based on the coordination scheduling identifier, and executing optimization control according to the global coordination fitting. According to the method, the technical problems of resource waste and health risk early warning lag caused by low matching degree of environmental parameter regulation and control and biological behavior requirements and lack of global coordination of a local control strategy in an existing breeding environment control method are solved, and the technical effect of improving the intelligence and refinement level of breeding environment control is achieved.

Description

Technical Field

[0001] The present application relates to the field of environmental control technology, and specifically to an optimization control method and system for a smart breeding environment. Background Art

[0002] In modern farm management, precise control of the breeding environment has a decisive impact on animal health, breeding efficiency, and economic benefits. Existing technologies often rely on static threshold control of single environmental parameters (such as temperature, humidity, and ammonia concentration), lacking in-depth perception of the dynamic behavioral needs of farmed organisms, resulting in a disconnect between environmental control and biological physiological needs. For example, fixed ventilation strategies may ignore real-time changes in hot spots where animals gather, causing local overload or energy waste. At the same time, existing systems often adopt a "single-point monitoring-independent control" model, lacking coordination between devices and prone to control conflicts (such as humidification and cooling equipment running simultaneously). Although IoT technology has improved data collection capabilities, the separation of environmental data and biological behavioral data makes it difficult to achieve early warning of health risks, and delayed control often leads to outbreaks of stress-related diseases.

[0003] In addition, the application of digital twin technology in the aquaculture field is still in its early stages. Existing models mostly focus on physical field simulation (such as temperature field distribution) and do not integrate biological behavioral characteristics (such as activity heat maps and feeding patterns) into control decisions, resulting in deviations between virtual models and actual biological responses. Multi-objective optimization in environmental control is often limited to the balance between energy consumption and comfort. It does not include biological indicators such as health risk level and behavioral delayed response into the optimization objectives, making it difficult to achieve precise intervention. Therefore, there is an urgent need for a smart aquaculture environment optimization control method and system based on the integration of digital twins, behavioral perception and multi-objective optimization to achieve in-depth perception of the environment and animal status in the farm, dynamic assessment of health risks, adaptive generation of regional control strategies and global coordinated control, so as to improve the level of intelligent aquaculture and overall operational efficiency. Summary of the Invention

[0004] This application provides an optimization control method and system for a smart aquaculture environment, aiming to solve the technical problems in existing aquaculture environment control methods, such as the low matching degree between environmental parameter regulation and biological behavior requirements, the lack of global coordination of local control strategies leading to resource waste and delayed health risk warning, so as to achieve the technical effect of realizing refined assessment of health risks by integrating behavioral perception and environmental perception, constructing a local control and global coordination mechanism under multi-objective optimization, and improving the intelligence and refinement level of aquaculture environment control.

[0005] The first aspect disclosed in the present application provides an optimization control method for a smart breeding environment, the method comprising: executing site digital twin modeling of the smart breeding environment and distributing environmental control equipment; executing control intensity field fitting of the environmental control equipment in the digital twin model, and constructing a grid topology map using the fitting results and the behavior heat map of the farmed animals, wherein the grid topology map is provided with a collaborative scheduling association identifier; deploying monitoring sensors in each grid area, using the monitoring sensors to perform environmental monitoring of the grid area, establishing a grid environment data set, and using biosensors to collect behavioral characteristics of the farmed animals to establish a grid behavior feature set; using the grid behavior feature set and the grid environment data set to evaluate the health risk level of the farmed animals in each grid; optimizing the control strategy for each grid area according to the health risk level based on a multi-objective optimization channel, and establishing a local control strategy set; using the collaborative scheduling association identifier of the network topology map to perform global coordinated fitting of the local control strategy set, and performing optimization control using the global coordinated fitting result.

[0006] Another aspect disclosed in the present application provides an optimization control system for a smart breeding environment, the system comprising: a twin modeling module: executing digital twin modeling of the site of the smart breeding environment and distributing environmental control equipment; a topology map construction module: executing control intensity field fitting of the environmental control equipment in the digital twin model, and constructing a grid topology map using the fitting results and the behavior heat map of the farmed objects, wherein the grid topology map is provided with a collaborative scheduling association identifier; a feature acquisition module: deploying monitoring sensors in each grid area, using the monitoring sensors to perform environmental monitoring of the grid area, establishing a grid environment data set, and using biosensors to collect behavioral characteristics of the farmed objects, and establishing a grid behavior feature set; a risk level assessment module: using the grid behavior feature set and the grid environment data set to assess the health risk level of the farmed objects in each grid; a strategy optimization module: performing control strategy optimization for each grid area according to the health risk level based on a multi-objective optimization channel, and establishing a local control strategy set; an optimization control module: using the collaborative scheduling association identifier of the network topology map to perform global coordinated fitting of the local control strategy set, and performing optimization control using the global coordinated fitting result.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The aforementioned optimization and control method for a smart aquaculture environment constructs a digital twin model of the aquaculture site, simultaneously deploys environmental control equipment, and dynamically integrates equipment control intensity fields with animal behavior heat maps to create a gridded space with collaborative scheduling indicators. Each grid integrates environmental monitoring sensors and biosensors to collect real-time environmental parameters (such as temperature, humidity, and gas concentrations) and animal behavioral characteristics (such as activity distribution and feeding frequency), generating a multidimensional data set. Subsequently, through correlation analysis of environmental and biological data, the health risk level of the animals within each grid is assessed. Based on different risk levels, a multi-objective optimization algorithm is used to generate local control strategies that balance energy consumption, response speed, and health requirements. Finally, collaborative indicators within the grid topology coordinate regional strategies, eliminate equipment conflicts, and achieve global resource optimization. This allows for dynamic adjustment of environmental control parameters, achieving the combined goals of precise regulation, risk warning, and efficient resource utilization.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 The figure is a flow chart of an optimization control method for a smart farming environment in one embodiment.

[0011] Figure 2 This is a diagram of the architecture of an optimized control system for a smart farming environment in one embodiment.

[0012] Explanation of the accompanying drawings: twin modeling module 11, topology map construction module 12, feature collection module 13, risk level assessment module 14, strategy optimization module 15, optimization control module 16. DETAILED DESCRIPTION

[0013] The embodiments of the present application provide an optimization and control method and system for a smart aquaculture environment to solve the technical problems in existing aquaculture environment control methods, such as the low matching degree between environmental parameter regulation and biological behavior requirements, the lack of global coordination of local control strategies, which leads to resource waste and delayed health risk warning. The invention achieves the technical effect of realizing refined assessment of health risks by integrating behavioral perception and environmental perception, constructing a local control and global coordination mechanism under multi-objective optimization, and improving the intelligence and refinement level of aquaculture environment control.

[0014] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0015] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0016] Example 1, as Figure 1 As shown, the present application provides a method for optimizing and controlling a smart farming environment, the method comprising: Perform site digital twin modeling of smart farming environments and distribute environmental control equipment.

[0017] In this embodiment, a virtual site framework is first constructed based on the site's environmental data (e.g., the topography and regional distribution of the aquaculture area) and the structure of the aquaculture facilities (e.g., feeding areas and drainage areas). This creates a preliminary physical model, which includes the geometric parameters of each area (e.g., area, shape, and layout) and the connectivity between facilities (e.g., pipe connections and electrical wiring). Subsequently, boundary conditions and constraints related to the aquaculture environment (e.g., ambient temperature range, humidity control target, and air circulation requirements) are input. These conditions define the modeling parameter range and control analysis dimensions (e.g., temperature and humidity regulation, air quality control), thereby providing a precise basis for simulation control. All collected parameters are then transferred to a digital twin simulation platform (e.g., a BIM platform or CFD simulation tool) for boundary initialization and physical modeling, resulting in a complete digital twin model. This model provides the spatial foundation for subsequent digital twin analysis and control strategies. During the model construction process, environmental control devices (e.g., fans, heaters, air conditioners, etc.) are also arranged in the virtual space based on their location information to simulate their operating states and interactions under different environmental conditions. In this way, the prediction of environmental changes and dynamic monitoring of equipment operation can be achieved in the digital model, providing data support for precise control of the environment.

[0018] The control intensity field fitting of the environmental control equipment is performed in the digital twin model, and a grid topology map is constructed using the fitting results and the behavior heat map of the farmed animals, wherein the grid topology map is provided with a collaborative scheduling association identifier.

[0019] In one embodiment, a digital twin model simulates and quantifies the control capabilities of environmental control devices (such as fans, heaters, and air conditioners) at different locations (e.g., the adjustment range and intensity of factors like temperature and humidity). This generates a control intensity dataset, and based on this dataset, generates a control intensity field fitting result. This control intensity field fitting result describes the control effectiveness of the devices at each location, helping to determine which areas require more or less environmental adjustment. Subsequently, a behavioral heat map of the farmed animals is obtained. This behavior heat map shows the activity frequency and behavior distribution of the animals in different areas. By combining the control intensity field fitting result with the behavior heat map, a complementary index is calculated for each location. This complementary index enables the system to better understand the interaction between the animals and the environment, providing a more accurate basis for the delineation of each area. Based on the calculated complementary index, the farm is then divided into multiple grids through cluster reconstruction, with each grid representing an independent control unit. By splicing these grids according to their location, a grid topology is constructed. Each grid in this grid topology has a collaborative scheduling association identifier based on boundary interference sensitivity, which represents the relationship and scheduling priority between different grids, thereby achieving collaborative operation and optimized resource allocation among the grids.

[0020] Furthermore, the present application provides the control intensity field fitting of the environmental control device executed in the digital twin model, including: Obtain the device control gear of the environmental control device and establish a distance attenuation function mapped to the environmental control device; in the digital twin model, use the distance attenuation function to perform device control gear simulation of the environmental control device and establish a control intensity data set of the location point; use the control intensity data set to generate a fitting result of the control intensity field.

[0021] Preferably, for each environmental control device (such as a fan, heater, air conditioner, etc.), its control gear parameter is obtained. The control gear parameter refers to the different power or working intensity levels that the device can adjust. For example, a fan may have low, medium, and high gears, and an air conditioner may have different temperature setting gears. By combining the device control gear with physical characteristics, a distance decay function is established to show that its control intensity decays with spatial distance. The distance decay function is as follows: ;in, is the control intensity at distance d, is the baseline strength of the device in the current gear (such as the maximum wind speed), k is the attenuation coefficient, which is calibrated by the device type and environmental characteristics, and d is the Euclidean distance from the spatial position to the device. Subsequently, in the digital twin model, the established distance attenuation function is used to simulate the impact of different gears of the device in space. That is, according to the position of the device, the position of the target area and the simulated gear, the control strength of each location point is calculated, and then these control strength data are added to a set in sequence to obtain the control strength data set of all location points. Afterwards, the control strength data set is divided according to the gear, and the control strength field of each gear at different positions is used as the fitting result to show the control effect of different areas under different parameters, helping to determine which areas require more control resources (such as increasing the power of the equipment or adjusting the position of the equipment) and which areas do not require too much adjustment, thereby providing a basis for subsequent control strategies.

[0022] Table 1: Environmental control equipment parameters: ; Table 2: Position point control strength calculation table (Example: Position point P(12,16)): ; Table 1 above is a table of environmental control equipment parameters. It shows the basic parameters of three types of environmental control equipment (fan, heater, and humidifier), including equipment type, control gear, baseline intensity, attenuation coefficient, and the equipment's location coordinates in the aquaculture environment. The control intensity of each device is related to its gear, operating conditions (such as temperature, humidity, etc.), and attenuation coefficient, which in turn affects its control effect in the space.

[0023] Table 2 above is a table for calculating the control strength of a location point. This table shows the distance from the device to the control point (unit: m) and the control strength data at that location. The table lists each device's ID, the distance to the specified point, and the corresponding control strength data (such as wind speed, temperature, and humidity). This is used to calculate the control effect of the device at different locations and optimize the control strategy.

[0024] Furthermore, the present application provides a method for constructing a grid topology map using the fitting results and the behavior heat map of the cultivated object, including: Perform a joint analysis of the fitting results and the behavior heat map to calculate the behavior-control complementarity index, which is calculated as follows: ;in, Characterization location The behavior-control complementarity index, is the location activity generated based on the behavior heat map, Characterize the position gradient of the control intensity field generated based on the fitting result; divide the smart farming environment into regular grids to form a basic grid set; calculate the internal area mean of each basic grid using the behavior-control complementarity index; and perform cluster reconstruction using the internal area mean to generate a grid topology map.

[0025] Preferably, after obtaining the fitting results, the behavior heat map is combined with the control intensity field of the environmental control device to calculate the behavior-control complementarity index, which is calculated as follows: ;in, Characterization location The behavior-control complementarity index is used to measure the match between behavior and control, reflecting the complementarity between environmental control and animal behavior in a specific location. A high behavior-control complementarity index indicates that the location has both high animal activity and suitable environmental control, while a low value indicates insufficient control or a mismatch between animal activity and control effects. is the location activity extracted from the behavior heat map, The position gradient of the control intensity field generated based on the fitting results is characterized by calculating the rate of change of the control intensity with position, reflecting the spatial variation of the environmental control device's intensity. In a smart farming environment, the entire site is divided into regular grid cells, forming a basic grid set. Each basic grid in the basic grid set represents an independent area. The grid division can be a uniform rectangular or square grid, and the size of each grid can be customized according to actual needs (e.g., 1m or 2m). The purpose of this step is to discretize the farming environment, allowing independent behavior and control analysis for each grid. For each basic grid, the behavior-control complementarity index is averaged across all locations within the grid to obtain the internal region mean of each basic grid, providing the basis for subsequent grid clustering and topology map generation. Subsequently, all grids are clustered and reconstructed using the calculated internal region mean. Specifically, internal deviation analysis of each basic grid is performed based on the internal region mean to assess the degree of behavior and control match within each grid. This helps identify grid areas with significant discrepancies between behavior and control, and these areas are then demarcated. Next, based on the partitioning results, the mean values ​​of the divided areas are recalculated, and the different areas are clustered and reconstructed to generate a new grid topology. Finally, the boundary interference sensitivity of the clusters is calculated to assess the degree of interference between adjacent areas. This sensitivity information is used to construct collaborative scheduling association identifiers to ensure coordination and optimization between areas. Through these steps, the generated grid topology not only reflects which areas have a high degree of match between environmental control and animal behavior, but also guides subsequent control strategies and resource allocation.

[0026] Furthermore, the present application provides the method of performing cluster reconstruction using the internal region mean to generate a grid topology map, including: The internal area mean is used to perform deviation analysis within the basic grid and construct internal split areas. After recalculating the regional mean of the internal split areas, cluster merging evaluation of adjacent areas is performed, cluster reconstruction is completed using the cluster evaluation results, and the boundary interference sensitivity of the cluster cluster is calculated. The boundary interference sensitivity is used to establish a collaborative scheduling association identifier.

[0027] Optionally, for each base grid, an internal deviation analysis is performed based on the internal regional mean. Specifically, the deviation of the behavior-control complementarity index of its internal points from the internal regional mean of the grid is calculated and compared with a deviation threshold. This deviation is used to identify points that differ significantly from the regional mean. These points with significant deviations may indicate a mismatch between behavior and control. These points are removed from the base grid, and internal split regions are constructed based on these points. Subsequently, a new internal regional mean is calculated for each split region. This mean represents the average of the behavior-control complementarity of all points within the split region. If the deviation of the behavior-control complementarity of all points within the split region from this new internal regional mean does not exceed the deviation threshold, the control of this internal split region is relatively consistent. This internal split region and the corresponding base grid are then clustered separately. Otherwise, the evaluation continues with the next level of adjacent regions (split regions within the internal split region) until the deviation of the internal regional mean of the split region does not exceed the deviation threshold. After completing the cluster merging evaluation, the resulting cluster evaluation results are used to reconstruct the basic grid set. Specifically, the basic grid set is repartitioned according to the clusters identified in the cluster evaluation results, and a grid topology is constructed based on these partitioned grids to reflect a more refined regional division. Next, for each grid in the grid topology, the gradient change in the control intensity field of adjacent regions is calculated to quantify the boundary interference sensitivity between adjacent regions (this gradient change can be directly used as the boundary interference sensitivity). If the control intensity between two adjacent regions changes dramatically (i.e., the gradient is large), it indicates that the boundary interference sensitivity between the two adjacent regions is relatively high, and therefore, more coordinated adjustments are required. Finally, based on the calculated boundary interference sensitivity, a coordinated scheduling association flag is established for the boundary region between each cluster. This flag indicates that coordinated scheduling is required between adjacent regions to ensure a smooth transition of control strategies and optimal resource allocation, thereby improving the overall management efficiency of the aquaculture environment.

[0028] Monitoring sensors are deployed in each grid area, and the monitoring sensors are used to monitor the environment of the grid area to establish a grid environment data set. Biosensors are used to collect behavioral characteristics of farmed animals to establish a grid behavioral feature set.

[0029] In one embodiment, in a smart farming environment, monitoring sensors are installed in each grid area to collect environmental data specifically for that area. These sensors can monitor and record key environmental parameters such as temperature, humidity, light, and air quality in real time. The data collected by these sensors will form a detailed grid environmental dataset containing information about the environmental status within each grid area, enabling real-time assessment of environmental changes and making corresponding adjustments. Simultaneously, biosensors will be deployed to monitor the behavioral characteristics of farmed animals. Biosensors can capture animal activity information in various ways, such as using video surveillance to track animal movements, using sound sensors to detect animal call frequency, or using pressure sensors to monitor animal activity density. This behavioral data will form a grid behavioral feature set, which includes activity density, clustering status, call frequency, and more for each grid area. These behavioral features enable real-time understanding of animal behavior patterns within each grid area, and dynamic adjustment of environmental control strategies based on this data to ensure the health and productivity of farmed animals.

[0030] The grid behavior feature set and the grid environment data set are used to evaluate the health risk level of the cultured animals in each grid.

[0031] In one embodiment, after obtaining the grid behavior feature set and the grid environment data set, the activity density, clustering state, and chirping frequency in the grid behavior feature set, and the temperature, humidity, air quality, and other data in the grid environment data set are standardized so that these data are in the same dimension. Subsequently, these data are weighted according to the weights predetermined by domain experts to quantify a health risk indicator. Based on these indicators, the health risk of each grid is divided into different levels, such as low risk, medium risk, and high risk, to help the system promptly identify high-risk areas and adjust the breeding environment based on the assessment results, so as to intervene at the earliest stage and ensure that the breeding environment and animal health are effectively managed.

[0032] Furthermore, the present application provides the method of using the grid behavior feature set and the grid environment data set to assess the health risk level of each grid culture, including: A health risk feature vector is constructed by integrating the grid behavior feature set and the grid environment data set; after normalizing the health risk feature vector, a health risk index is calculated using a weighted scoring function; and the health risk level of each grid culture is generated using the health risk index.

[0033] Preferably, after obtaining the grid behavior feature set and the grid environment data set, each data point in the grid behavior feature set and the grid environment data set will be combined to form a unified health risk feature vector. The elements of each feature vector represent the health risk-related information of the farmed animals in the grid. In this health risk feature vector, the dimensions and value ranges of different features may be different. For example, the ambient temperature may range from 0 to 50°C, and the behavioral feature value of the farmed animals may be a standardized percentage. Therefore, these features need to be normalized to ensure that the influence of each feature is balanced when calculating health risks. Common normalization methods include minimum-maximum normalization, Z-score normalization, etc. Through normalization, all feature values ​​in the health risk feature vector are standardized to the same scale, making them comparable in the subsequent calculation of health risk indicators. After the normalization process is completed, the preset weighted scoring function will be activated. This weighted scoring function records the weight value corresponding to each feature. Through this weighted scoring function, the normalized features can be multiplied by the corresponding weights and then summed to obtain the health risk index of each grid. The higher the health risk index, the greater the health risk of the farmed animals in the area. The specific form of the weighted scoring function is: , R is the health risk index; n is the dimension of the feature vector, that is, the total number of features; is the weight corresponding to the i-th feature. Initially, it is usually determined by domain experts (such as veterinarians and environmental control engineers) based on practical experience. Later, when a large amount of historical data is available, it can be determined based on the Pearson correlation coefficient between each feature and the historical health risk results. That is, it is calculated using the ratio of the Pearson correlation coefficient of each feature to the total Pearson correlation coefficient; is the normalized ith eigenvalue. Finally, the calculated health risk index is compared with multiple preset risk intervals to determine the health risk level of the farmed animals in each grid. For example, the multiple risk intervals can be low risk: [0, 0.3), medium risk: [0.3, 0.7), and high risk [0.7, 1]. In summary, through the above process, the system can calculate the health risk index of farmed animals in each grid area based on behavioral characteristics and environmental data, and further divide them into different health risk levels. According to these health risk levels, the health status of farmed animals can be finely managed, and timely measures such as adjusting environmental controls and improving animal behavior can be taken to ensure the optimization of the breeding environment.

[0034] Furthermore, the present application provides the method of generating the health risk level of each grid culture using the health risk index, including: A multi-scale sliding window is configured; a time series analysis is performed on the grid behavior feature set under the multi-scale sliding window to generate an enhanced health risk vector; and the enhanced health risk vector is used to compensate for the health risk level.

[0035] Optionally, a multi-scale sliding window can be configured based on actual needs. This method analyzes time series data at different time scales, with window sizes ranging from short-term (e.g., 5 minutes), medium-term (e.g., 3 minutes), and long-term (e.g., 1 hour). The grid behavior feature set is then sorted by timestamp to obtain a grid behavior feature sequence set. Then, based on each window scale defined in the multi-scale sliding window, the behavior data for each sliding window is extracted, sliding at a fixed time step (e.g., once per minute) from the starting point of the grid behavior feature sequence set. The mean of each behavior feature within the window is then calculated. The mean values ​​of the behavior features at the same window scale are then combined to form an enhanced health risk vector for each window scale. The compensation coefficient for each window scale is then calculated by weighting each normalized mean feature in the enhanced health risk vector. The compensation coefficients corresponding to these enhanced health risk vectors are then used to compensate for the current health risk level. During this process, the preset window weights for each window scale are multiplied by the corresponding compensation coefficients, and then accumulated to obtain a comprehensive compensation coefficient. This compensation coefficient is then multiplied by the health risk indicator corresponding to the current health risk level to dynamically adjust the health risk level and make the health risk level assessment more accurate. In summary, this dynamic compensation mechanism can effectively cope with fluctuations in behavioral patterns and ensure that health risk assessments can respond to actual changes in a timely manner.

[0036] Based on the multi-objective optimization channel, the control strategy of each grid area is optimized according to the health risk level, and a local control strategy set is established.

[0037] In one embodiment, control strategies are optimized based on the health risk level of each grid area. The health risk level reflects the health status of the aquaculture in that area; higher risk levels indicate a more refined control strategy is required. To ensure effective environmental control, a multi-objective optimization channel is used to balance multiple optimization objectives, including control energy efficiency, health response matching, and response delay. During the optimization process, the health risk level is synchronized with the multi-objective optimization function of the multi-objective optimization channel, and the weights of the multi-objective optimization function are dynamically adjusted. After the multi-objective optimization function is adjusted, local control strategies are generated based on the adjusted multi-objective optimization function. For high-risk areas, health response matching and rapid response are prioritized to ensure timely adjustment of environmental conditions. For low-risk areas, energy efficiency optimization is prioritized to reduce energy consumption. Based on this optimization process, a local control strategy suitable for each grid area is generated and stored in a set, resulting in a local control strategy set. In summary, as the health risk level changes, the local control strategy set is dynamically adjusted to ensure that the environment in each area is always optimal for the health of the aquaculture, thereby achieving refined management and intelligent optimization of the aquaculture environment.

[0038] Furthermore, the present application provides the method of optimizing the control strategy for each grid area according to the health risk level based on the multi-objective optimization channel to establish a local control strategy set, including: A multi-objective optimization function is established, wherein the control objectives of the multi-objective optimization function include energy consumption control objectives, health response matching objectives, and behavioral response delay objectives; the health risk level is synchronized to the multi-objective optimization function, and the weight factor of the multi-objective optimization function is dynamically updated; the multi-objective optimization function with the updated weight factor is used to optimize the control strategy for each grid area and establish a local control strategy set.

[0039] Preferably, the multi-objective optimization channel has a pre-built multi-objective optimization function, which can simultaneously optimize multiple control objectives, namely, the control energy consumption target, the health response matching target, and the behavior response delay target, to ensure the best overall effect in the breeding environment. The calculation method of the multi-objective optimization function is to weight the control energy consumption target, 1 minus the health response matching target, and the behavior response delay target. The specific form is: ,in, The final multi-objective optimization function value, the optimization goal is to minimize the function; To control energy consumption targets, used to minimize energy consumption, for example, reducing the power use of air conditioners, heaters, fans and other equipment, while ensuring that the breeding environment meets health requirements; The health response matching goal aims to optimize the farming environment so that it matches the health needs of the cultured animals as closely as possible; The behavioral response delay goal is to reduce the response delay of the aquaculture environment to changes in the behavior of the cultured animals. For example, if the activity pattern of the cultured animals changes (such as a decrease or increase in activity), the environmental conditions (such as temperature, humidity, ventilation, etc.) should be able to be adjusted quickly to respond to the behavioral changes in a timely manner; 、 、 The weight coefficients corresponding to the three objectives are derived from a risk-weight mapping table (pre-constructed by domain experts). Subsequently, the health risk level of each grid area is matched to the risk-weight mapping table to obtain the control objective weights corresponding to each health risk level. For example, when the health risk level is high, the control objective weights may be 0.2 (control energy consumption target), 0.5 (health response matching target), and 0.3 (behavior response delay target). When the health risk level is low, the control objective weights may be 0.5 (control energy consumption target), 0.3 (health response matching target), and 0.2 (behavior response delay target). The matched control objective weights are then synchronized with the multi-objective optimization function to replace the original weight factors of each control objective in the multi-objective optimization function. The updated weighting factors are then used to optimize the control strategy for each grid zone using a pre-set optimization algorithm, such as particle swarm optimization or genetic algorithm. The goal is to find the most appropriate control strategy combination based on each grid zone's control objectives (energy consumption, health response, behavioral response delay, etc.). Each resulting control strategy combination is simulated using the digital twin model to obtain the corresponding control energy consumption target, health response matching target, and behavioral response delay target. This strategy is then evaluated using a multi-objective optimization function until the result of the multi-objective optimization function is less than or equal to the optimization threshold. This results in a local control strategy set that includes adjustments to the health risks, environmental conditions, and behavioral changes in that area, such as the temperature setting of the air conditioner and the operating status of the humidity control device. In summary, by establishing a multi-objective optimization function, it is possible to balance energy consumption, health response matching, and behavioral response delay to generate optimal control strategies for different grid zones. Dynamically adjusting the weighting factors of the optimization function enables the system to respond in real time to changes in health risk levels. A corresponding local control strategy set is generated for each zone, ensuring energy efficiency optimization and minimization of response delay while ensuring animal health.

[0040] The collaborative scheduling association identifier of the network topology graph is used to perform global coordinated fitting of the local control strategy set, and the global coordinated fitting result is used to perform optimal control.

[0041] In one embodiment, after obtaining a set of local control strategies, the local control strategies of each grid area are evaluated, the adjustment costs are calculated, and adjustment penalties are generated. These penalties reflect the potential costs of the adjustment process and aim to avoid over-adjustment or ineffective intervention, thereby ensuring the rationality of the control strategy adjustment. Subsequently, the consistency between the control strategies of different grid areas is analyzed through collaborative scheduling association identification. This analysis helps identify which areas' control strategies need to be adjusted synchronously to avoid conflicts or incoordination between local strategies. On this basis, the results of the control consistency analysis and the adjustment penalties are used to perform a global adjustment optimization process. This process aims to optimize the global strategy, ensure that the control effects between the various grid areas are coordinated and consistent, and maximize the performance of the overall system. Finally, based on the global coordinated fitting results, the optimized control strategy is executed. This result not only takes into account the needs of each grid area, but also adjusts the environmental control strategy of each area according to the requirements of coordination and optimization to ensure the overall efficiency and stability of environmental regulation.

[0042] Furthermore, the present application provides the method of performing global coordinated fitting of a local control strategy set using the collaborative scheduling association identifier of the network topology graph, and performing optimized control using the global coordinated fitting result, including: The adjustment cost of the corresponding local control strategy set is calculated for each grid area to generate an adjustment penalty term; the control consistency analysis of the local control strategy set is performed using the collaborative scheduling association identifier, and an adjustment optimization is performed from a global perspective based on the control consistency analysis results and the adjustment penalty term to establish a global coordinated fitting result.

[0043] Preferably, after obtaining the set of local control strategies, a digital twin model is used to simultaneously simulate the local control strategies for each grid region. During the simulation, the energy efficiency cost, health response cost, and response delay cost for each grid region are recorded. The energy efficiency cost is the product of the actual power consumption of the control device during the simulation (which may be affected by adjacent grid regions) and the device's operating time. The health response cost is a weighted sum of the deviations between the actual temperature and the optimal temperature and humidity required for plant health during the simulation. The response delay cost is the actual time delay between the occurrence of a behavioral change in the simulation and the response of the control strategy. Subsequently, the energy efficiency cost, health response cost, and response delay cost are normalized and weighted and summed to obtain the adjustment penalty term for each grid region. The coordinated scheduling association identifier is then used to determine the relationship between adjacent regions, that is, whether there is significant interference between adjacent regions. The coordinated scheduling association identifiers of adjacent regions are compared with a coordination threshold. If they are greater than or equal to the coordination threshold, the two adjacent regions need to be controlled synchronously; otherwise, they can be controlled independently. Then, based on the results of the consistency analysis, the adjustment penalty items of the grid areas that require coordinated control are introduced to perform adjustment optimization from a global perspective. In this process, it will be judged whether the adjustment cost of the local control strategy involved is too high. If there is a penalty tolerance greater than or equal to the penalty tolerance, the adjustment range of the strategy will be reduced to reduce the overall negative impact of the system. After the adjustment is completed, the simulation will be performed again until there are no local control strategies with a penalty tolerance greater than or equal to the penalty tolerance. Finally, the adjusted local control strategies are summarized to establish a global coordinated fitting result. This global coordinated fitting result includes the control strategy of the entire breeding environment, ensuring that the control strategy of each grid area can not only achieve the optimal state, but also be coordinated with the control strategies of adjacent areas.

[0044] Furthermore, the present application provides that after performing the optimization control using the global coordinated fitting result, the method includes: A response cycle is established, and environmental response monitoring of the smart farming environment is performed during the response cycle to generate a cycle response result; abnormality identification is controlled for the cycle response result and the global coordinated fitting result, and an abnormality warning is reported based on the abnormality identification.

[0045] Preferably, a response cycle is established to periodically monitor the environmental response within the smart farming environment. This response cycle can be set to a specific time period, for example, once per hour or once per day, as needed. During each response cycle, various data from the farming environment, such as temperature, humidity, air flow, and light intensity, are collected and analyzed. This data generates a cycle response result, which reflects the actual environmental conditions during that cycle. The cycle response result is then compared with the expected control effect from the global coordinated fitting results to determine whether any environmental parameters experience significant fluctuations—that is, whether any environmental parameter's deviation exceeds the fluctuation tolerance range. If a significant deviation is detected between the actual environment and the expected effect during the comparison, this indicates an abnormality in the current environment, such as equipment failure or environmental control failure. Based on the abnormality identification results, an immediate abnormality warning is issued to alert management personnel. In this way, the control effect of the farming environment can be monitored in real time, potential problems can be promptly identified, and the health of the farmed animals and the stability of the environment can be ensured.

[0046] In summary, the embodiments of the present application have at least the following technical effects: The embodiment of the present application first performs site digital twin modeling of the smart farming environment and distributes environmental control equipment; then, the control intensity field fitting of the environmental control equipment is performed in the digital twin model, and a grid topology map is constructed using the fitting results and the behavioral heat map of the farmed animals, wherein the grid topology map is provided with a collaborative scheduling association identifier; thereafter, monitoring sensors are deployed in each grid area, and the monitoring sensors are used to perform environmental monitoring of the grid area to establish a grid environment data set, and the behavioral characteristics of the farmed animals are collected using biosensors to establish a grid behavior feature set; further, the grid behavior feature set and the grid environment data set are used to evaluate the health risk level of the farmed animals in each grid; then, based on the multi-objective optimization channel, the control strategy of each grid area is optimized according to the health risk level to establish a local control strategy set; finally, the collaborative scheduling association identifier of the network topology map is used to perform global coordinated fitting of the local control strategy set, and the global coordinated fitting result is used to perform optimization control. These technical effects jointly solve the technical problems in existing aquaculture environment control methods, such as the low matching degree between environmental parameter regulation and biological behavior requirements, the lack of global coordination of local control strategies leading to resource waste and delayed health risk warning, and achieve the technical effect of realizing refined assessment of health risks by integrating behavioral perception and environmental perception, building a local control and global coordination mechanism under multi-objective optimization, and improving the intelligence and refinement of aquaculture environment control.

[0047] Example 2, based on the same inventive concept as the optimization control method of a smart farming environment in the above embodiment, Figure 2As shown, the present application provides an optimization control system for a smart farming environment, the system comprising: a twin modeling module 11: executing digital twin modeling of the site of the smart farming environment and distributing environmental control equipment; a topology map construction module 12: executing control intensity field fitting of the environmental control equipment in the digital twin model, and constructing a grid topology map using the fitting results and the behavior heat map of the farmed objects, wherein the grid topology map is provided with a collaborative scheduling association identifier; a feature acquisition module 13: deploying monitoring sensors in each grid area, using the monitoring sensors to perform environmental monitoring of the grid area, establishing a grid environment data set, and using biosensors to collect behavioral characteristics of farmed objects to establish a grid behavior feature set; a risk level assessment module 14: using the grid behavior feature set and the grid environment data set to assess the health risk level of each grid farmed object; a strategy optimization module 15: performing control strategy optimization for each grid area according to the health risk level based on a multi-objective optimization channel, and establishing a local control strategy set; an optimization control module 16: using the collaborative scheduling association identifier of the network topology map to perform global coordinated fitting of the local control strategy set, and performing optimization control using the global coordinated fitting result.

[0048] Furthermore, the topology map construction module 12 is further configured to execute the following method: Obtain the device control gear of the environmental control device and establish a distance attenuation function mapped to the environmental control device; in the digital twin model, use the distance attenuation function to perform device control gear simulation of the environmental control device and establish a control intensity data set of the location point; use the control intensity data set to generate a fitting result of the control intensity field.

[0049] Furthermore, the topology map construction module 12 is further configured to execute the following method: Perform a joint analysis of the fitting results and the behavior heat map to calculate the behavior-control complementarity index, which is calculated as follows: ;in, Characterization location The behavior-control complementarity index, is the location activity generated based on the behavior heat map, Characterize the position gradient of the control intensity field generated based on the fitting result; divide the smart farming environment into regular grids to form a basic grid set; calculate the internal area mean of each basic grid using the behavior-control complementarity index; and perform cluster reconstruction using the internal area mean to generate a grid topology map.

[0050] Furthermore, the topology map construction module 12 is further configured to execute the following method: The internal area mean is used to perform deviation analysis within the basic grid and construct internal split areas. After recalculating the regional mean of the internal split areas, cluster merging evaluation of adjacent areas is performed, cluster reconstruction is completed using the cluster evaluation results, and the boundary interference sensitivity of the cluster cluster is calculated. The boundary interference sensitivity is used to establish a collaborative scheduling association identifier.

[0051] Furthermore, the risk level assessment module 14 is further configured to perform the following method: A health risk feature vector is constructed by integrating the grid behavior feature set and the grid environment data set; after normalizing the health risk feature vector, a health risk index is calculated using a weighted scoring function; and the health risk level of each grid culture is generated using the health risk index.

[0052] Furthermore, the risk level assessment module 14 is further configured to perform the following method: A multi-scale sliding window is configured; a time series analysis is performed on the grid behavior feature set under the multi-scale sliding window to generate an enhanced health risk vector; and the enhanced health risk vector is used to compensate for the health risk level.

[0053] Furthermore, the strategy optimization module 15 is also used to perform the following method: A multi-objective optimization function is established, wherein the control objectives of the multi-objective optimization function include energy consumption control objectives, health response matching objectives, and behavioral response delay objectives; the health risk level is synchronized to the multi-objective optimization function, and the weight factor of the multi-objective optimization function is dynamically updated; the multi-objective optimization function with the updated weight factor is used to optimize the control strategy for each grid area and establish a local control strategy set.

[0054] Furthermore, the optimization control module 16 is further configured to execute the following method: The adjustment cost of the corresponding local control strategy set is calculated for each grid area to generate an adjustment penalty term; the control consistency analysis of the local control strategy set is performed using the collaborative scheduling association identifier, and an adjustment optimization is performed from a global perspective based on the control consistency analysis results and the adjustment penalty term to establish a global coordinated fitting result.

[0055] Furthermore, the optimization control module 16 is further configured to execute the following method: A response cycle is established, and environmental response monitoring of the smart farming environment is performed during the response cycle to generate a cycle response result; abnormality identification is controlled for the cycle response result and the global coordinated fitting result, and an abnormality warning is reported based on the abnormality identification.

[0056] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0057] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0058] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A method for optimizing and controlling a smart breeding environment, characterized in that: The method comprises: Implement site digital twin modeling of smart farming environments and distribute environmental control equipment; Performing control intensity field fitting of the environmental control device in the digital twin model, and constructing a grid topology map using the fitting results and the behavior heat map of the cultivated animals, wherein the grid topology map is provided with a collaborative scheduling association identifier; Deploy monitoring sensors in each grid area, use the monitoring sensors to monitor the environment of the grid area, establish a grid environment data set, and use biosensors to collect behavioral characteristics of farmed animals to establish a grid behavioral feature set; Using the grid behavior feature set and the grid environment data set, the health risk level of the cultured animals in each grid is evaluated; Based on the multi-objective optimization channel, the control strategy of each grid area is optimized according to the health risk level, and a local control strategy set is established; The collaborative scheduling association identifier of the network topology graph is used to perform global coordinated fitting of the local control strategy set, and the global coordinated fitting result is used to perform optimal control.

2. The optimization control method of a smart breeding environment according to claim 1, characterized in that: The performing of control intensity field fitting of the environmental control device in the digital twin model includes: Obtaining a device control gear of an environmental control device and establishing a distance attenuation function mapped to the environmental control device; In the digital twin model, the distance decay function is used to perform a device control gear simulation of the environmental control device to establish a control intensity data set of the location point; The control intensity data set is used to generate a fitting result of the control intensity field.

3. The optimization control method of a smart breeding environment according to claim 1, characterized in that: The method of constructing a grid topology map using the fitting results and the behavior heat map of the cultivated animals includes: Perform a joint analysis of the fitting results and the behavior heat map to calculate the behavior-control complementarity index, which is calculated as follows: ； in, Characterization location The behavior-control complementarity index, is the location activity generated based on the behavior heat map, characterize the position gradient of the control intensity field generated based on the fitting results; Dividing the smart farming environment into regular grids to form a basic grid set; Calculating the internal region mean for each basic grid using the behavior-control complementarity index; Cluster reconstruction is performed using the internal region mean to generate a grid topology map.

4. The optimization control method of a smart breeding environment according to claim 3, characterized in that: The clustering reconstruction using the internal area mean to generate a grid topology map includes: Using the internal region mean value to perform deviation analysis inside the basic grid and construct an internal split region; After recalculating the regional mean of the internal split area, the cluster merging evaluation of the adjacent areas is performed, the clustering evaluation results are used to complete the cluster reconstruction, and the boundary interference sensitivity of the cluster cluster is calculated, and the boundary interference sensitivity is used to establish the collaborative scheduling association identifier.

5. The optimization control method of a smart breeding environment according to claim 1, characterized in that: The method of evaluating the health risk level of each grid cultured animal using the grid behavior feature set and the grid environment data set includes: Constructing a health risk feature vector that integrates the grid behavior feature set and the grid environment data set; After normalizing the health risk feature vector, a health risk index is calculated using a weighted scoring function; The health risk index is used to generate a health risk level for each grid culture.

6. The optimization control method of a smart breeding environment according to claim 5, characterized in that: The step of generating the health risk level of each grid cultured animal using the health risk indicator includes: Configure multi-scale sliding windows; Performing a time series analysis on the grid behavior feature set under a multi-scale sliding window to generate an enhanced health risk vector; The enhanced health risk vector is used to perform health risk level compensation.

7. The optimization control method for a smart breeding environment according to claim 1, characterized in that: The multi-objective optimization channel is used to optimize the control strategy for each grid area according to the health risk level, and establish a local control strategy set, including: Establishing a multi-objective optimization function, wherein the control objectives of the multi-objective optimization function include controlling energy consumption objectives, health response matching objectives, and behavior response delay objectives; Synchronizing the health risk level to the multi-objective optimization function, and dynamically updating the weight factor of the multi-objective optimization function; The multi-objective optimization function after updating the weight factors is used to optimize the control strategy of each grid area and establish a local control strategy set.

8. The optimization control method for a smart breeding environment according to claim 1, characterized in that: The method of performing global coordinated fitting of a local control strategy set using the collaborative scheduling association identifier of the network topology graph and performing optimized control using the global coordinated fitting result includes: Calculate the adjustment cost of the corresponding local control strategy set for each grid area and generate the adjustment penalty term; The collaborative scheduling association identifier is used to perform control consistency analysis of the local control strategy set, and based on the control consistency analysis result and the adjustment penalty item, an adjustment optimization is performed from a global perspective to establish a global coordinated fitting result.

9. The optimization control method for a smart breeding environment according to claim 1, characterized in that: After the optimization control is performed using the global coordinated fitting result, the method includes: Establishing a response cycle, performing environmental response monitoring of the smart farming environment during the response cycle, and generating a cycle response result; Anomaly identification is performed on the periodic response result and the global coordinated fitting result, and an anomaly warning is issued based on the anomaly identification.

10. An optimization control system for a smart farming environment, characterized in that: The system is used to execute the optimization control method of a smart farming environment according to any one of claims 1 to 9, and the system comprises: Twin modeling module: performs site digital twin modeling of the smart farming environment and distributes environmental control equipment; Topology construction module: performs control intensity field fitting of environmental control equipment in the digital twin model, and uses the fitting results and the behavior heat map of the farmed animals to construct a grid topology map, wherein the grid topology map is provided with a collaborative scheduling association identifier; Feature collection module: Deploy monitoring sensors in each grid area, use the monitoring sensors to monitor the environment of the grid area, establish a grid environment data set, and use biosensors to collect behavioral characteristics of farmed animals to establish a grid behavior feature set; Risk level assessment module: using the grid behavior feature set and the grid environment data set to assess the health risk level of each grid culture; Strategy optimization module: Based on the multi-objective optimization channel, the control strategy of each grid area is optimized according to the health risk level, and a local control strategy set is established; Optimization control module: Use the collaborative scheduling association identifier of the network topology graph to perform global coordination fitting of the local control strategy set, and use the global coordination fitting results to perform optimization control.

Images