An intelligent control system for aquaculture environment based on environmentally responsive photosensitizer

Abstract

The invention relates to an intelligent control system for aquaculture environment based on an environment-responsive photosensitizer, and relates to the field of aquaculture, comprising: a sensor network deployment module for deploying sensors in a target aquaculture space; a time series data acquisition module for acquiring time series sensor data with sensor position marks; an indicator distribution prediction module for predicting the distribution of multiple key control indicators of the target aquaculture space according to the time series sensor data, and obtaining a predicted indicator field; a combination matching module for screening and determining multiple delivery points according to the predicted indicator field, and matching the target photosensitizer combination of each delivery point in a photosensitizer library of a target scene according to the characteristic indicator label groups corresponding to the multiple delivery points; a dynamic update module for iteratively updating the predicted indicator field; and an adaptive adjustment module for adaptively adjusting the photosensitizer combination according to the dynamic predicted indicator field and intelligently controlling the aquaculture environment.

Description

Technical Field

[0001] The present invention relates to the field of aquaculture, and in particular to an intelligent control system for aquaculture environment based on an environment-responsive photosensitizer. Background Art

[0002] In modern aquaculture environment management, the ecological environment has an important impact on aquaculture efficiency and output quality. Traditional aquaculture environment control methods mostly rely on fixed manual adjustments or simple automation methods, which are inefficient when facing complex environmental variables and difficult to respond quickly to environmental changes. With the emergence of new materials such as photosensitizers, the potential for intelligent control of aquaculture environments has been greatly enhanced.

[0003] At present, there are some methods for monitoring and controlling the aquaculture environment based on photosensitizers. However, these technologies often only focus on a single or a few parameters and lack the ability to comprehensively predict multidimensional environmental data. In addition, the use of photosensitizers has not yet formed an efficient dynamic management system. Existing methods mostly use fixed doses and delivery point designs, which makes it difficult to achieve precise control.

[0004] In summary, the existing technologies have the technical problems of single environmental factors, lack of flexibility and dynamic regulation of photosensitizer delivery, and impact on resource utilization and control effect. Summary of the invention

[0005] The present invention aims to solve the technical problems in the prior art, such as single environmental factors, lack of flexibility and dynamic regulation of photosensitizer delivery, and impact on resource utilization and control effect, by providing an intelligent control system for aquaculture environment based on environment-responsive photosensitizers.

[0006] The technical solution of the present invention to solve the above technical problems is as follows:

[0007] A sensor network deployment module is used to deploy sensors in a target breeding space and obtain a sensor network.

[0008] A time series data acquisition module, wherein the time series data acquisition module is used to acquire time series sensing data, wherein the time series sensing data has a sensing position mark.

[0009] An indicator distribution prediction module is used to perform distribution prediction of multiple key control indicators of the target breeding space according to the time series sensor data to obtain a predicted indicator field.

[0010] A combination matching module is used to screen and determine multiple delivery points according to the predicted indicator field, and match the target photosensitizer combination of each delivery point in the photosensitizer library of the target scene according to the characteristic indicator label group corresponding to the multiple delivery points, wherein the target photosensitizer combination includes multiple photosensitizer identification codes and corresponding delivery concentrations and delivery rates.

[0011] A dynamic update module is used to continuously update and collect the target breeding space through the sensor network, and iteratively update the prediction index field to obtain a dynamic prediction index field.

[0012] An adaptive adjustment module is used to perform adaptive adjustment of the target photosensitizer combination according to the dynamic prediction index field, including combination adjustment and point adjustment, and to perform intelligent control of the breeding environment based on the adjustment result.

[0013] The beneficial effects of the present invention are as follows: through the sensor network deployment module, sensors are deployed in the target breeding space to obtain the sensor network; the time series data acquisition module collects the time series sensor data, wherein the time series sensor data has a sensor position mark; the index distribution prediction module predicts the distribution of multiple key control indicators of the target breeding space according to the time series sensor data, and obtains the prediction index field; the combination matching module screens and determines multiple delivery points according to the prediction index field, and matches the target photosensitizer combination of each delivery point in the photosensitizer library of the target scene according to the characteristic index label group corresponding to the multiple delivery points, wherein the target photosensitizer combination includes multiple photosensitizer identification codes and corresponding delivery concentrations and delivery rates; the dynamic update module continuously updates and collects the target breeding space through the sensor network, and iteratively updates the prediction index field to obtain the dynamic prediction index field; the adaptive adjustment module performs adaptive adjustment of the target photosensitizer combination according to the dynamic prediction index field, including combination adjustment and point adjustment, and performs intelligent control of the breeding environment based on the adjustment result. Thereby achieving the technical effect of improving the richness of environmental data call and the level of intelligent regulation of photosensitizers, improving resource utilization and control accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A schematic diagram of the structure of an intelligent control system for aquaculture environment based on an environment-responsive photosensitizer provided by the present invention;

[0015] Figure 2 A schematic diagram of a process for obtaining a prediction index field in an intelligent control system for aquaculture environment based on an environment-responsive photosensitizer provided by the present invention;

[0016] Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention;

[0017] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0018] In the accompanying drawings, the components represented by the reference numerals are listed as follows:

[0019] Sensor network deployment module 11, time series data collection module 12, indicator distribution prediction module 13, combination matching module 14, dynamic update module 15, adaptive adjustment module 16, electronic device 500, memory 510, processor 520, computer program 511, computer readable storage medium 600, computer program 611. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0021] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0022] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0023] Embodiment 1:

[0024] like Figure 1 As shown, an embodiment of the present invention provides an intelligent control system for aquaculture environment based on an environment-responsive photosensitizer.

[0025] The system comprises:

[0026] The sensor network deployment module 11 is used to deploy sensors in the target breeding space and obtain the sensor network.

[0027] Specifically, the sensor network collects environmental data in real time through multiple sensors deployed in the target breeding space, thereby providing data support for the control of the breeding environment. The target breeding space refers to the physical space used in the breeding process that requires environmental control, which includes pig houses, chicken houses, fish ponds, greenhouses, etc. The environmental conditions of the target breeding space directly affect the breeding effect and the health of the animals.

[0028] Specifically, the sensor network is composed of multiple sensor nodes deployed in the target breeding space. Multiple sensor nodes are connected through wired or wireless connections to form a sensor network. By deploying sensors in the target breeding space and acquiring the sensor network, the environmental changes of the breeding space can be monitored in real time, which will help to achieve subsequent precise management, optimize resource allocation and improve breeding efficiency.

[0029] In some embodiments, sensors are deployed in the target breeding space to obtain a sensor network, and the execution steps of the sensor network deployment module 11 include:

[0030] A key control indicator set of a target breeding space is obtained, wherein the key control indicator set includes multiple key control indicators; according to a predetermined sensor deployment strategy, multiple environmental sampling points are determined in the target breeding space; according to the environmental zoning characteristics of the target breeding space, a sampling indicator set of multiple environmental sampling points is matched, wherein the sampling indicator set includes multiple key control indicators that need to be collected at the corresponding environmental sampling points, and the sampling indicator set is a subset of the key control indicator set; according to the multiple sampling indicator sets, sensors are deployed at multiple environmental sampling points to assemble the sensor network, wherein the sensor network includes multiple sensors corresponding to multiple environmental control indicators.

[0031] Specifically, key control indicators refer to key environmental parameters that directly affect animal health, growth and production efficiency in the breeding environment, including but not limited to temperature, humidity, light, gas concentration, oxygen concentration, water quality parameters such as pH value, dissolved oxygen, ammonia nitrogen, air pressure, concentration of harmful substances, etc. Key control indicators can help to fully understand the environmental conditions of the breeding space.

[0032] Specifically, the sensor deployment strategy defines how to plan the layout of sensors to maximize their monitoring effect. The influencing factors of the sensor deployment strategy include: the geometric shape of the breeding space (such as long, square, circular, etc.) and the distribution of different internal areas (such as animal activity areas, ventilation areas, drainage areas, etc.); the spatial distribution patterns of different environmental parameters; the energy efficiency of sensors, signal coverage range, and the construction of communication networks.

[0033] Specifically, in the target breeding space, multiple environmental sampling points are determined according to the sensor layout strategy. Multiple environmental sampling points cover key areas of the breeding space, including, for example, animal concentration areas, environmental fluctuation areas (such as high and low temperature distribution areas of the breeding space or areas with large changes in light intensity), near air circulation and ventilation systems (to ensure that gas concentration sensors can effectively capture gas changes), resource usage peak areas (such as feed feeding or excretion areas, monitoring parameters that may affect the environment); by scientifically deploying sampling points, all key control indicators can be effectively monitored.

[0034] Specifically, according to the environmental zoning characteristics of the target breeding space, the sampling index sets of multiple environmental sampling points are matched to ensure the accuracy and comprehensiveness of the environmental data, wherein the environmental zoning characteristics of the breeding space refer to the environmental characteristics of different areas in the space, and the division methods of the environmental zoning characteristics include: based on functional division, such as feeding area, excretion area, rest area, etc., different areas have different environmental requirements; based on climate division, such as high temperature area, low temperature area, etc., especially the distribution differences of environmental factors such as temperature and humidity; based on equipment division, such as the location of heating equipment, ventilation system, etc., preferably, the environmental sampling point is selected at the position corresponding to the photodynamic sterilization chamber / area / channel in the water body.

[0035] Specifically, for each environmental sampling point, the key control indicators that need to be collected at the point are defined. Different regional environmental conditions determine the control indicators that need to be collected, where the sampling indicator set of each environmental sampling point is a subset of the key control indicator set; for example, the animal activity area mainly collects temperature, humidity, gas concentration (such as carbon dioxide, ammonia, etc.), light intensity, etc.; the ventilation area focuses on monitoring air flow, gas concentration and humidity; the aquaculture area collects water quality indicators, such as pH value, dissolved oxygen, ammonia nitrogen concentration, etc.; the breeding area looks at temperature, humidity, gas concentration, oxygen concentration, etc.

[0036] Furthermore, at each environmental sampling point, according to the requirements of the sampling indicator set, appropriate types of sensors are selected and deployed, including temperature and humidity sensors, gas sensors (such as harmful gas sensors such as carbon dioxide, ammonia, hydrogen sulfide, etc., water quality sensors (used in aquaculture to monitor water quality parameters such as pH value, ammonia nitrogen, dissolved oxygen, etc.), oxygen sensors (used for monitoring oxygen concentration in aquaculture or breeding space); light sensors (used to monitor light intensity); and then, through wired or wireless communication technology (such as Wi-Fi, LoRa, ZigBee, etc.), the sensors at each environmental sampling point are connected to form an interconnected sensor network.

[0037] Through the above steps, comprehensive monitoring of the target breeding space can be achieved. Through real-time collection and transmission of environmental data, data basis can be provided for breeding management, thereby improving breeding efficiency and environmental control capabilities.

[0038] The time series data acquisition module 12 is used to acquire time series sensing data, wherein the time series sensing data has a sensing position mark.

[0039] Specifically, in the scenario of the target breeding space, the collection of time-series sensor data is the basis for environmental management and optimization decisions. Time-series sensor data refers to data collected by sensors within a specific time interval, that is, time-series data of multiple key control indicators in the target breeding environment, such as water temperature, pH value, dissolved oxygen, ammonia nitrogen concentration, etc. The time series of the data means that each data point corresponds to a specific timestamp to reflect the dynamic changes of parameters over time, among which the data collection frequency is adjusted according to the rate of change of the breeding environment.

[0040] Specifically, in order to improve the effectiveness and availability of time series sensor data, the acquired time series sensor data has a corresponding sensor position mark as an additional dimension, that is, the position of the sensor corresponding to each group of continuous time series data. The sensor position mark helps to locate and associate sensor data at different positions, helping to achieve more refined monitoring and control.

[0041] The indicator distribution prediction module 13 is used to perform distribution prediction of multiple key control indicators of the target breeding space according to the time series sensor data to obtain a predicted indicator field.

[0042] Specifically, within the target breeding space, distribution predictions of multiple key control indicators are carried out, aiming to accurately predict environmental parameters at different locations and time points based on real-time time series sensor data, thereby providing more precise data support for breeding management.

[0043] Specifically, the prediction indicator field is used to reflect the changes in various environmental control indicators (such as temperature, humidity, gas concentration, etc.) in the breeding space within a certain period of time in the future. In other words, the prediction indicator field is the predicted value of the multi-dimensional space, covering the multi-dimensional environmental parameters of each sampling point or area in the breeding space. Optionally, the prediction indicator field may include temperature field, water body substance concentration field (for aquaculture space, by predicting the concentration distribution of dissolved oxygen, ammonia nitrogen and other substances in the water body, a water quality concentration field map is generated to better manage water quality), etc.

[0044] In some embodiments, Figure 2 As shown, according to the time series sensor data, the distribution prediction of multiple key control indicators of the target breeding space is performed to obtain the predicted indicator field. The execution steps of the indicator distribution prediction module 13 include:

[0045] The target breeding space is adaptively gridded to generate an adaptive grid space; the adaptive grid space is merged and optimized to merge multiple adjacent grids of the same type into a larger grid area; historical sensor data is used as sample data to construct a regression analysis model for each merged grid area, and multiple key control indicator values ​​of multiple environmental sampling points are predicted to generate distribution prediction results; based on the distribution prediction results, spatial fitting based on the interpolation method is performed to form the prediction indicator field of the target breeding space.

[0046] Specifically, first, according to the physical layout and control requirements of the target breeding space, the target breeding space is adaptively gridded to obtain an adaptive grid space, in which each grid corresponds to a monitoring point or a prediction point. Through adaptive grid division, the divided adaptive grid space can better adapt to the changing characteristics of the target breeding space.

[0047] Optionally, a spatial partitioning algorithm based on environmental characteristics (such as temperature change, humidity distribution, etc.), such as a K-means clustering algorithm, a DBSCAN density clustering algorithm, etc., is used to perform adaptive grid division.

[0048] Specifically, merging adjacent grids refers to merging and optimizing the grids after adaptive division, merging multiple adjacent grids of the same type into a larger area to reduce the number of grids that need to be processed, and simplifying the spatial prediction task while maintaining the representativeness and accuracy of the data. The principle of merging involves the similarity or consistency of environmental parameters within the grid.

[0049] Exemplarily, similarity metrics such as the mean or standard deviation of environmental parameters are used to calculate the differences in environmental parameters between adjacent grids (such as temperature differences, humidity differences, etc.) to determine which grids can be merged. Grid areas with smaller differences can be merged into a large grid area, which can reduce the amount of calculation and improve the efficiency of subsequent modeling and prediction.

[0050] Furthermore, taking the historical sensor data as sample data, a regression analysis model is established for each merged grid area. The regression analysis model establishes the relationship between the key control indicator values ​​of the environmental sampling points and time. For example, the concentration of water substances is affected by factors such as free diffusion and water flow state, and thus has the characteristic of changing over time.

[0051] Optionally, the regression model can be a model based on linear regression, support vector machine regression (SVR), random forest regression, etc. Through the regression analysis model, the changing trend and distribution law of environmental control indicators can be understood, and then the key control indicator values ​​in each grid area can be accurately predicted, helping the system to perform spatial interpolation and fitting at multiple sampling points.

[0052] Specifically, spatial interpolation methods such as Kriging, inverse distance weighted (IDW), spline interpolation, etc. are used to perform spatial fitting of the target breeding space according to the prediction results of the regression analysis model, thereby realizing the prediction of control indicators in unsampled areas in the space and improving the coverage and accuracy of spatial prediction. The generated prediction indicator field of the target breeding space is a complete spatial data set, which contains the estimated values ​​of multiple control indicators (such as temperature, humidity, etc.) at different locations in the entire breeding space, and can comprehensively reflect the environmental conditions of each location in the breeding space, thereby providing more complete data support for intelligent breeding management and decision-making.

[0053] The combination matching module 14 is used to screen and determine multiple delivery points according to the predicted indicator field, and match the target photosensitizer combination of each delivery point in the photosensitizer library of the target scene according to the characteristic indicator label group corresponding to the multiple delivery points, wherein the target photosensitizer combination includes multiple photosensitizer identification codes and corresponding delivery concentrations and delivery rates.

[0054] Specifically, by analyzing the spatial distribution of the predicted control index fields (such as temperature, humidity, gas concentration, etc.), multiple placement points suitable for the placement of photosensitizers are screened out. These placement points are key areas where the predicted index values ​​change significantly or have a greater impact on the breeding environment under specific conditions.

[0055] Specifically, the characteristic indicator label group includes the numerical values ​​and predicted trends of various control indicators (such as temperature, humidity, gas concentration, etc.). The characteristic indicator label group provides comprehensive environmental characteristic data for each placement point, which facilitates the precise matching of subsequent photosensitizers.

[0056] Specifically, according to the characteristic indicator label group of each delivery point, it is matched with the entries in the photosensitizer library to match the most suitable photosensitizer combination for each delivery point, wherein the matching is based on the key control indicators that need to be adjusted at the delivery point, as well as the properties of the photosensitizer such as efficacy, concentration and delivery rate. The photosensitizer library contains information such as different photosensitizer types and performance characteristics. In other words, each photosensitizer has a different scope of application and efficacy. Through precise photosensitizer matching, it is ensured that each delivery point obtains the most suitable photosensitizer combination, thereby maximizing the efficacy of the photosensitizer.

[0057] By screening delivery points from the prediction index field, extracting feature labels, matching the optimal photosensitizer combination in the photosensitizer library, and ultimately determining the delivery concentration and rate of each delivery point, the accuracy of photosensitizer delivery can be effectively improved, resource waste can be avoided, and optimal control of the target environment can be achieved, achieving the goals of energy saving, environmental protection, and maximum efficiency.

[0058] In some embodiments, based on the prediction index field, multiple delivery points are screened and determined, and the execution steps of the combination matching module 14 include:

[0059] 1PASS screening is performed according to the concentration control limits of multiple characteristic indicator labels in the characteristic indicator label group to determine multiple single target points and obtain an initial single target point set; based on the interaction relationship of multiple characteristic indicator labels, the multi-target weighted concentration of the prediction indicator field is calculated, and multiple composite target points are determined according to the multi-target weighted concentration to obtain a composite target point set; based on the composite target point set and the initial single target point set, point matching is performed, and based on the matching result, the repeated single target points in the initial single target point set are eliminated to obtain a standard single target point set; based on the standard single target point set and the composite target point set, a plurality of the delivery points are defined.

[0060] Specifically, each placement point has a set of characteristic indicator labels to describe the characteristics of the point. At the same time, each characteristic indicator label has a concentration control limit, which is used to specify the acceptable range of the characteristic indicator label in the target breeding space scenario. Exceeding this range may have an adverse effect on biological growth.

[0061] Specifically, 1PASS screening refers to traversing the characteristic indicator label groups of multiple points in the prediction indicator field according to the concentration control limit of each characteristic indicator label, and screening out the points that exceed the concentration control limit of a single characteristic indicator label, thereby obtaining multiple single-target points to form an initial single-target point set; that is, 1PASS screening is a single-target rapid screening of the prediction indicator field, and each point only checks a single characteristic indicator label, while ignoring the superposition or compound effect between different characteristic indicator labels, to ensure that all points that exceed the concentration control limit are screened out.

[0062] Specifically, characteristic indicator labels are multiple independent environmental monitoring data. In the actual environment, indicators do not exist in isolation, but rather have a certain interactive relationship, that is, changes in different indicators may produce synergistic effects or mutual interference on the same target.

[0063] Specifically, based on the interaction relationship among multiple characteristic indicator labels, the multi-target weighted concentrations of multiple prediction indicator fields are calculated, and multiple composite target points are determined according to the concentration to obtain a composite target point set, wherein the interaction relationship among multiple characteristic indicator labels can be based on correlation analysis, regression analysis or graph network construction. Preferably, the interaction relationship among multiple characteristic indicator labels is obtained by collecting existing research data through big data.

[0064] Optionally, based on the relative importance of the indicator to the system goal and combined with the interaction relationship of multiple characteristic indicator labels, the concentrations of all characteristic indicators are weighted and summed, and the weighted concentrations of multiple characteristic indicator labels are calculated. By considering the interaction relationship between multiple indicators, the multi-target weighted concentrations are calculated and the composite target points are determined. This allows for more accurate selection of release points based on the multiple control requirements of the breeding environment, thereby improving the accuracy of release and avoiding the limitations of a single indicator.

[0065] Specifically, a match is performed between the composite target point set and the initial single target point set to determine which single target points have already appeared in the composite target, and duplicate points are removed. For example, when a point in the composite target point set is repeated with a point in the initial single target point set, the point will be removed from the initial single target point set to obtain a standardized and unique single target point set, thereby avoiding repeated use of each point in the final delivery process and ensuring efficient use of each delivery point.

[0066] Optionally, the point matching between the composite target point set and the initial single target point set is achieved through set operations, nearest neighbor algorithms, or distance measurement methods (such as Euclidean distance, Manhattan distance, etc.).

[0067] Through the above steps, the overall system can accurately screen out the most suitable release points based on the interaction relationship between multiple characteristic indicators, improve the scientificity and accuracy of the release strategy, and effectively enhance the intelligence and refinement level of aquaculture environment control.

[0068] In some embodiments, according to the characteristic index tag groups corresponding to the plurality of delivery points, the target photosensitizer combination of each delivery point is matched in the photosensitizer library of the target scene, and the execution steps of the combination matching module 14 include:

[0069] Parse multiple characteristic indicator labels in the characteristic indicator label group to obtain qualitative indicator labels and characteristic indicator values; use the qualitative indicator label as an index parameter to traverse the photosensitizer library for label matching to obtain multiple optimal photosensitizers corresponding to each delivery point; perform quantitative calculations based on the physical property equations of the multiple optimal photosensitizers in combination with the characteristic indicator values ​​to obtain delivery concentrations and delivery flow rates of the multiple optimal photosensitizers; extract photosensitizer identification codes of the multiple optimal photosensitizers, associate the corresponding delivery concentrations and delivery flow rates, and output them as the target photosensitizer combination.

[0070] Specifically, first parse multiple characteristic indicator labels in the characteristic indicator label group, extract multiple groups of qualitative indicator labels and characteristic indicator values, wherein the qualitative indicator label is used to describe the category information of the characteristic indicator label, that is, to determine whether the characteristic indicator label is a temperature characteristic, a dissolved oxygen characteristic, a COD characteristic, ammonia nitrogen characteristic, etc.; the characteristic indicator value is a specific numerical data, such as the dissolved oxygen concentration is 8 mg / L, the temperature is 25°C, etc.

[0071] Specifically, the qualitative tags are used for preliminary matching with photosensitizers in the photosensitizer library, while the characteristic index values ​​are used for subsequent quantitative calculations.

[0072] Exemplarily, first, taking the qualitative indicator label as the index parameter, the photosensitizer that meets the requirements is screened out by matching the qualitative indicator label with the photosensitizer label in the photosensitizer library, so as to obtain the optimal photosensitizer combination corresponding to each delivery point, wherein the photosensitizer library is a collection of multiple photosensitizers, and each photosensitizer has multiple attribute labels, such as chemical properties, reactivity, applicable scope, concentration, etc.; then, based on the physical property equation of the selected photosensitizer and combined with the characteristic indicator value, quantitative calculation is performed to determine the delivery concentration and delivery flow rate of each optimal photosensitizer, wherein the physical property equation of the photosensitizer involves the behavior and properties of the photosensitizer under different conditions, and different types of photosensitizers have different physical property equations.

[0073] Optionally, the physical property equation of the photosensitizer may include the following aspects: light absorption characteristics, which can be described by the Beer-Lambert law; the reaction rate of the photosensitizer under light, which can be described by a kinetic equation; the quantum efficiency (Quantum Efficiency, QE, i.e., the number of reactions caused by each photon) of the photosensitizer; and the thermodynamic properties of the photosensitizer (such as Gibbs free energy change), which can be described by the reaction free energy under standard conditions.

[0074] Through the above-mentioned qualitative matching and quantitative calculation, the concentration and flow rate of each photosensitizer can be accurately determined according to the environmental characteristics and physical property equations, thereby ensuring the optimization of the photosensitizer effect under different environmental conditions.

[0075] Furthermore, the photosensitizer identification code of each optimal photosensitizer is extracted, and its corresponding delivery concentration and delivery flow rate are associated, and finally output as a target photosensitizer combination, wherein the photosensitizer identification code is used to accurately identify the photosensitizer in the database, so that obtaining the target photosensitizer combination can clarify the photosensitizer type, delivery concentration and flow rate required for each delivery point, which is convenient for subsequent automated delivery or manual intervention.

[0076] The above steps accurately analyze the characteristic indicator label group, match the photosensitizer library, quantitatively calculate the photosensitizer delivery parameters, and finally output the target photosensitizer combination to ensure the accurate delivery of the photosensitizer. This process effectively improves the intelligence level of the system, reduces resource waste, and improves the efficiency and accuracy of environmental control.

[0077] In some implementations, the qualitative indicator label is used as an index parameter, the photosensitizer library is traversed to perform label matching, and multiple optimal photosensitizers corresponding to each of the delivery points are obtained, and then the method further includes:

[0078] The multiple optimal photosensitizers corresponding to each of the delivery points are defined as an exclusion discrimination group; based on the photosensitizer knowledge graph, exclusion analysis of the multiple exclusion discrimination groups is performed; if it is determined that there are excluded photosensitizer pairs, any photosensitizer is randomly selected from the photosensitizer pairs, and replacement matching is performed again in the photosensitizer library until there are no excluded photosensitizer pairs in the multiple exclusion discrimination groups.

[0079] Specifically, based on the photosensitizer conflict characteristics in the photosensitizer knowledge graph, it is determined whether there is any exclusion or conflict between the multiple optimal photosensitizers corresponding to each delivery point, so as to ensure that they can work together at the same delivery point without adverse chemical reactions or mutual interference. Specifically, multiple optimal photosensitizers are defined into an exclusion discrimination group, with the aim of isolating and analyzing the photosensitizer set at each delivery point to ensure the compatibility between different photosensitizers.

[0080] Specifically, the photosensitizer knowledge graph is a graphical structure containing information about the interactions between photosensitizers. Each photosensitizer node is connected to other nodes, and the connecting edges are used to represent the relationship between photosensitizers, such as "mutually exclusive", "mutually reinforcing" or "no interaction". The photosensitizer knowledge graph can be established through chemical reaction data, experimental research or chemical engineering manuals.

[0081] Optionally, a graph query analysis method is used to obtain the interaction information between photosensitizers to determine whether any pair of photosensitizers has an exclusion relationship. If an exclusion relationship is found between the photosensitizer pairs in the exclusion analysis, a photosensitizer is randomly selected from the excluded photosensitizer pair, removed from the photosensitizer pair, and re-matched in the photosensitizer library based on the qualitative indicator label and the characteristic indicator value to determine a new compatible photosensitizer for replacement. The above steps are repeated until all the excluded photosensitizer pairs are resolved, that is, there are no more incompatible photosensitizer pairs.

[0082] Through exclusion analysis and substitution matching, the system can ensure that there is no chemical conflict between the photosensitizer combinations at each placement point. By introducing a random substitution matching mechanism, it can flexibly deal with the exclusion problem between different photosensitizers and automatically optimize the photosensitizer combination, thereby ensuring the safety, stability and efficiency of the environmental control system.

[0083] In some implementations, the qualitative indicator label is used as an index parameter, the photosensitizer library is traversed to perform label matching, and multiple optimal photosensitizers corresponding to each of the delivery points are obtained, and then the method further includes:

[0084] If there are still excluded photosensitizer pairs after the preset number of replacement matches, the optimal photosensitizer whose corresponding characteristic index value exceeds the concentration control limit the least is excluded; based on the exclusion result, the multiple optimal photosensitizers corresponding to the multiple delivery points are updated.

[0085] Specifically, in the photosensitizer matching process, if there are still excluded photosensitizer pairs after multiple (preset number of) replacement matching, it means that the current photosensitizer combination may not meet all compatibility requirements, and the photosensitizer whose corresponding characteristic index value exceeds the concentration control limit the least is excluded. In other words, the photosensitizer corresponding to the characteristic index label with little impact on the target breeding space (the index value exceeds the limit less) in the excluded photosensitizer pairs is preferentially excluded, thereby minimizing the impact of reducing the number of photosensitizer types on the control ability of the target breeding space.

[0086] When there is still an exclusion relationship after multiple replacements of photosensitizer matching, the system can improve the compatibility and stability of the photosensitizer combination while maintaining the environmental control capability as much as possible by updating the most suitable photosensitizer set and excluding the photosensitizer with the least impact on the control effect. This improves the actual effect of the photosensitizer combination, ensures that the target environment can be controlled efficiently and safely, and enhances the intelligence and adaptability of the system.

[0087] The dynamic update module 15 is used to continuously update and collect the target breeding space through the sensor network, and iteratively update the prediction index field to obtain a dynamic prediction index field.

[0088] Specifically, based on the preset data collection frequency, the target breeding space is continuously monitored through the sensor network, and the latest dynamic information of the target breeding space can be obtained in real time; then, the collected data is iteratively updated for the prediction index field, and the iteratively updated prediction index field is a dynamic environmental prediction model that reflects the changes in the target breeding space, which helps to make more accurate and continuous decisions.

[0089] The adaptive adjustment module 16 is used to perform adaptive adjustment of the target photosensitizer combination according to the dynamic prediction index field, including combination adjustment and point adjustment, and perform intelligent control of the breeding environment based on the adjustment result.

[0090] Furthermore, based on the dynamic prediction index field, iterative decisions are made on the target photosensitizer combination, including adjusting the photosensitizer category composition in the target photosensitizer combination, changing the photosensitizer delivery points, etc., so as to cope with changes in the breeding environment and ensure that the breeding environment and resource utilization efficiency remain in the optimal state, while reducing human intervention and improving the overall breeding efficiency.

[0091] Optionally, intelligent control of the breeding environment is performed based on the adjustment results, including configuring a photosensitizer concentration sensor to monitor the release of the photosensitizer in real time, wherein the photosensitizer concentration sensor includes a front photosensitizer concentration sensor and a rear photosensitizer concentration sensor, the front photosensitizer concentration sensor is used to monitor whether the photosensitizer concentration of the configured photosensitizer solution to be released meets the expected release concentration, and can also be combined with the integral method to measure the total amount of photosensitizer released, the rear photosensitizer concentration sensor is used to monitor the concentration and concentration change of the photosensitizer at the corresponding release point after the photosensitizer is released; the monitoring data obtained by the photosensitizer concentration sensor is helpful for feedback control of photosensitizer release to ensure that the control effect meets expectations.

[0092] Furthermore, the execution steps of the system also include:

[0093] The photosensitizer library is interacted with to obtain the performance decay characteristics of multiple photosensitizers, and utility correction models of the multiple photosensitizers are correspondingly constructed; environmental data of multiple delivery points are obtained, input into the utility correction model, and delivery correction coefficients of multiple delivery points are obtained; and the target photosensitizer combination is adjusted based on the delivery correction coefficient for control correction.

[0094] Specifically, first, the performance decay characteristics of each photosensitizer are obtained from the photosensitizer library. The performance decay characteristics describe the attenuation of the photosensitizer's effectiveness during use, and optionally include factors such as time decay, environmental impact, and frequency of use. Then, based on the above performance decay characteristics, a utility correction model is constructed for each photosensitizer. The utility correction model analyzes the performance changes of the photosensitizer under different environmental conditions and establishes a corresponding mathematical model (such as a decay function) to describe the photosensitizer's effectiveness decay process.

[0095] Specifically, the correction coefficient of each placement point is calculated based on the environmental data of multiple placement points in combination with the utility correction model. The correction coefficient reflects the actual efficacy of the photosensitizer under specific conditions, such as a decrease or increase compared to the standard efficacy.

[0096] Furthermore, the photosensitizer combination is adjusted according to the correction coefficient of different delivery points, including increasing / decreasing the concentration of the photosensitizer, optimizing the delivery amount and delivery method. Through the adjustment based on the delivery correction coefficient, the system can accurately control the delivery strategy of the photosensitizer to ensure the optimal control of the breeding environment, while reducing the excessive use of photosensitizers, saving resources and improving economic benefits.

[0097] The embodiment of the present invention provides an intelligent control system for aquaculture environment based on an environment-responsive photosensitizer, which has at least the following technical effects:

[0098] By laying out sensors in the target breeding space and establishing a sensor network, time-series sensor data are collected, which contain sensor position tags; based on the time-series sensor data, the distribution of multiple key control indicators in the target breeding space is predicted to generate a prediction indicator field; according to the prediction indicator field, multiple delivery points are screened and determined, and the characteristic indicator label group of each delivery point is combined to match a suitable target photosensitizer combination from the photosensitizer library, and the target photosensitizer combination includes a photosensitizer identification code and the corresponding delivery concentration and rate; the target breeding space is continuously collected through the sensor network, and the prediction indicator field is dynamically updated according to the collected data to generate a dynamic prediction indicator field; based on the dynamic prediction indicator field, the target photosensitizer combination is adaptively adjusted, including adjusting the photosensitizer combination and delivery point, and the breeding environment is intelligently controlled according to the adjustment results. Thus, the technical effect of improving the richness of environmental data call and the level of photosensitizer intelligent regulation, improving resource utilization and control accuracy is achieved.

[0099] Embodiment 2:

[0100] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, the following steps are implemented: deploying sensors in the target breeding space to obtain a sensor network; collecting time-series sensor data, wherein the time-series sensor data has a sensor position mark; predicting the distribution of multiple key control indicators of the target breeding space based on the time-series sensor data to obtain a predicted indicator field; screening and determining based on the predicted indicator field A plurality of delivery points, and according to the characteristic indicator label groups corresponding to the plurality of delivery points, a target photosensitizer combination of each delivery point is matched in the photosensitizer library of the target scene, wherein the target photosensitizer combination includes a plurality of photosensitizer identification codes and corresponding delivery concentrations and delivery rates; the target breeding space is continuously updated and collected through the sensor network, and the prediction indicator field is iteratively updated to obtain a dynamic prediction indicator field; according to the dynamic prediction indicator field, the target photosensitizer combination is adaptively adjusted, including combination adjustment and point adjustment, and the breeding environment is intelligently controlled based on the adjustment result.

[0101] Embodiment three:

[0102] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600 on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the following steps are implemented: xxxx.

[0103] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0104] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0105] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0106] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0108] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0109] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. An intelligent control system for aquaculture environment based on an environment-responsive photosensitizer, characterized in that: The system comprises: A sensor network deployment module, which is used to deploy sensors in a target breeding space and obtain a sensor network; A time series data acquisition module, the time series data acquisition module is used to collect time series sensor data, wherein the time series sensor data has a sensor position mark; An indicator distribution prediction module, which is used to predict the distribution of multiple key control indicators of the target breeding space according to the time series sensor data and obtain a predicted indicator field; A combination matching module, the combination matching module is used to screen and determine multiple delivery points according to the prediction index field, and match the target photosensitizer combination of each delivery point in the photosensitizer library of the target scene according to the characteristic index label group corresponding to the multiple delivery points, wherein the target photosensitizer combination includes multiple photosensitizer identification codes and corresponding delivery concentrations and delivery rates; A dynamic update module, the dynamic update module is used to continuously update and collect the target breeding space through the sensor network, and iteratively update the prediction index field to obtain a dynamic prediction index field; An adaptive adjustment module, the adaptive adjustment module is used to perform adaptive adjustment of the target photosensitizer combination according to the dynamic prediction index field, including combination adjustment and point adjustment, and perform intelligent control of the breeding environment based on the adjustment result; Among them, according to the time series sensor data, the distribution prediction of multiple key control indicators of the target breeding space is carried out to obtain the predicted indicator field, including: Adaptively grid the target breeding space to generate an adaptive grid space; Merging and optimizing the adaptive grid space to merge multiple adjacent grids of the same type into a larger grid area; Using historical sensor data as sample data, a regression analysis model is constructed for each merged grid area, and multiple key control indicator values ​​of multiple environmental sampling points are predicted to generate distribution prediction results. Based on the distribution prediction results, spatial fitting based on an interpolation method is performed to form the prediction index field of the target breeding space; Among them, according to the predicted indicator field, multiple delivery points are screened and determined, including: Performing 1PASS screening according to the concentration control limits of multiple characteristic indicator labels in the characteristic indicator label group, determining multiple single target points, and obtaining an initial single target point set; Based on the interaction relationship of multiple characteristic indicator labels, a multi-target weighted concentration of the prediction indicator field is calculated, and multiple composite target points are determined according to the multi-target weighted concentration to obtain a composite target point set; Based on the composite target point set and the initial single target point set, point matching is performed, and based on the matching result, repeated single target points are eliminated from the initial single target point set to obtain a standard single target point set; A plurality of the delivery points are defined according to the standard single target point set and the compound target point set.

2. The intelligent control system for aquaculture environment based on an environment-responsive photosensitizer according to claim 1, characterized in that: Deploy sensors in the target breeding space to obtain a sensor network, including: Acquire a key control indicator set of a target breeding space, wherein the key control indicator set includes a plurality of key control indicators; According to the predetermined sensor deployment strategy, multiple environmental sampling points are determined in the target breeding space; According to the environmental zoning characteristics of the target breeding space, a sampling indicator set of a plurality of the environmental sampling points is matched, wherein the sampling indicator set includes a plurality of the key control indicators that need to be collected at the corresponding environmental sampling points, and the sampling indicator set is a subset of the key control indicator set; According to the plurality of sampling index sets, sensors are deployed at the plurality of environmental sampling points to form the sensor network, wherein the sensor network includes a plurality of sensors corresponding to the plurality of environmental control indexes.

3. The intelligent control system for aquaculture environment based on an environment-responsive photosensitizer according to claim 2, characterized in that: According to the characteristic index tag groups corresponding to the plurality of delivery points, the target photosensitizer combination of each delivery point is matched in the photosensitizer library of the target scene, including: Parsing multiple characteristic indicator labels in the characteristic indicator label group to obtain qualitative indicator labels and characteristic indicator values; Using the qualitative indicator label as an index parameter, traversing the photosensitizer library to perform label matching, and obtaining a plurality of optimal photosensitizers corresponding to each of the delivery points; According to the physical property equations of the multiple optimal photosensitizers, quantitative calculation is performed in combination with the characteristic index values ​​to obtain the delivery concentration and delivery flow rate of the multiple optimal photosensitizers; The photosensitizer identification codes of the plurality of the optimal photosensitizers are extracted, and the corresponding delivery concentrations and delivery flow rates are associated, and the codes are output as the target photosensitizer combination.

4. The intelligent control system for aquaculture environment based on an environment-responsive photosensitizer according to claim 3, characterized in that: Taking the qualitative index label as the index parameter, traversing the photosensitizer library for label matching, and obtaining a plurality of optimal photosensitizers corresponding to each of the delivery points, and then further comprising: Defining the plurality of optimal photosensitizers corresponding to each delivery point as an exclusion discrimination group; According to the photosensitizer knowledge graph, performing rejection analysis of the rejection discrimination groups; If it is determined that there is an excluded photosensitizer pair, any one of the photosensitizers is randomly selected from the photosensitizer pair, and replacement matching is performed again in the photosensitizer library until there is no excluded photosensitizer pair in the plurality of the excluded judgment groups.

5. The intelligent control system for aquaculture environment based on an environment-responsive photosensitizer according to claim 4, characterized in that: Taking the qualitative index label as the index parameter, traversing the photosensitizer library for label matching, and obtaining a plurality of optimal photosensitizers corresponding to each of the delivery points, and then further comprising: If there are still excluded photosensitizer pairs after the preset number of replacement matches, the optimal photosensitizer whose corresponding characteristic index value exceeds the least concentration control limit is excluded; Based on the elimination result, the multiple optimal photosensitizers corresponding to the multiple delivery points are updated.

6. The intelligent control system for aquaculture environment based on an environment-responsive photosensitizer according to claim 5, characterized in that: The execution steps of the system also include: Interacting the photosensitizer library to obtain the performance decay characteristics of multiple photosensitizers, and correspondingly constructing utility correction models of multiple photosensitizers; Obtaining environmental data of the plurality of delivery points, inputting the data into the utility correction model, and obtaining delivery correction coefficients of the plurality of delivery points; The target photosensitizer combination is adjusted based on the dosage correction coefficient to perform control correction.

7. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby realizing an intelligent control system for aquaculture environment based on an environment-responsive photosensitizer as described in any one of claims 1 to 6.

8. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, it implements an intelligent control system for aquaculture environment based on an environment-responsive photosensitizer as described in any one of claims 1 to 6.

Images