Multi-module combined aquaculture water quality purification method and system

Abstract

This application discloses a multi-module combined aquaculture water purification method and system, relating to the field of water purification technology. The method includes: acquiring the rated aquaculture load and module distribution information of multiple aquaculture modules; determining the initial connection topology between the multiple water purification modules through a priori empirical model; collecting real-time monitoring data from the multiple aquaculture modules and calculating the real-time water quality load; optimizing water purification parameters based on simulation analysis; and controlling the aquaculture water purification in the target scenario based on the optimized water purification parameter results. This solves the technical problem of traditional aquaculture water purification methods being unable to dynamically adjust according to the actual load and distribution characteristics of different aquaculture modules, leading to low purification efficiency.

Description

Technical Field

[0001] This application relates to the field of water purification technology, specifically to a multi-module combined method and system for purifying aquatic aquaculture water. Background Technology

[0002] With the large-scale and intensive development of aquaculture, the accumulation of organic matter such as uneaten feed and feces in aquaculture water, as well as the discharge of metabolic products from aquaculture organisms, has led to increasingly prominent water quality deterioration problems. Traditional aquaculture water purification methods mostly adopt single-module or fixed combination models, which are difficult to dynamically adjust according to the actual load and distribution characteristics of different aquaculture modules, resulting in waste of purification resources or insufficient purification capacity.

[0003] Meanwhile, although some aquaculture water purification methods attempt to combine multiple modules for purification, they lack scientific planning of the connection topology between the aquaculture load and the purification modules. They often rely on experience for configuration, resulting in low purification efficiency and difficulty in coping with the real-time changes in water quality load during the aquaculture process. They cannot achieve precise and intelligent water quality control, which in turn affects the growth environment of aquaculture organisms and the aquaculture benefits. Summary of the Invention

[0004] This application provides a multi-module combined aquaculture water purification method and system, solving the technical problem of low purification efficiency caused by the difficulty of dynamically adjusting the traditional aquaculture water purification method according to the actual load and distribution characteristics of different aquaculture modules. It achieves the technical effect of dynamically planning the initial connection topology of the water purification modules based on the rated aquaculture load and distribution information of the aquaculture modules, and combining this with simulation optimization based on real-time water quality load, thereby improving the water purification efficiency and intelligence level.

[0005] The technical solution to the above-mentioned technical problems in this application is as follows: Firstly, this application provides a multi-module combined aquaculture water purification method, the method comprising: Interact with the target scenario to obtain the rated aquaculture load and module distribution information of multiple aquaculture modules; Based on the rated aquaculture load and the module distribution information, the initial connection topology between multiple water purification modules is determined through a preset prior experience model, wherein the initial connection topology includes at least one combination of water purification modules. Collect real-time monitoring data from multiple aquaculture modules and calculate real-time water quality load based on the real-time monitoring data; Based on the real-time water quality load and the initial connection topology, water quality purification parameters are optimized based on simulation analysis, and the water quality purification of the target scenario is controlled based on the optimization results of the water quality purification parameters.

[0006] Secondly, this application provides a multi-module combined aquaculture water purification system, including: The information acquisition module is used to interact with the target scenario and acquire the rated aquaculture load and module distribution information of multiple aquaculture modules; The data processing module is used to determine the initial connection topology between multiple water purification modules based on the rated aquaculture load and the module distribution information through a preset prior experience model, wherein the initial connection topology includes at least one combination of water purification modules. The load calculation module is used to collect real-time monitoring data from multiple aquaculture modules and calculate real-time water quality load based on the real-time monitoring data. The water purification module is used to optimize water purification parameters based on simulation analysis according to the real-time water quality load and the initial connection topology, and to control the water purification of aquaculture in the target scenario based on the optimized water purification parameters.

[0007] This application provides one or more technical solutions, which have at least the following technical effects or advantages: This application provides a multi-module combined aquaculture water purification method and system. First, by interacting with a target scenario, the rated aquaculture load and module distribution information of multiple aquaculture modules are obtained, clarifying the potential water purification needs and spatial layout of different modules. Second, a pre-set empirical model is used to determine the initial connection topology between the multiple water purification modules, initially constructing a purification system framework that meets the general needs of the target scenario, allowing for a scientific preliminary plan of the combination and connection methods of the water purification modules. Subsequently, real-time monitoring data from multiple aquaculture modules is collected, and real-time water quality load is calculated accordingly, ensuring that the water purification process closely matches the actual conditions of the current aquaculture water body, avoiding potential lags caused by relying solely on initial settings. Finally, water purification parameters are optimized based on simulation analysis, and the aquaculture water purification in the target scenario is controlled according to the optimization results. By constructing a simulation analysis environment, combining purification performance parameters, pre-set purification constraints, and defined parameter evaluation functions, the water purification parameters are iteratively optimized, minimizing purification costs while ensuring water quality meets standards, achieving a balance between purification efficiency and economy.

[0008] The above technical solutions effectively solve the problem of the difficulty in dynamic adjustment of traditional methods, improve the level of intelligence and actual operation efficiency of aquaculture water purification, and ensure that farmed organisms can grow in a more stable and suitable water environment, thereby helping to improve aquaculture efficiency. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a schematic flowchart of the multi-module combined aquaculture water purification method provided in the embodiments of this application; Figure 2 This is a schematic diagram of the structure of the multi-module combined aquaculture water purification system provided in the embodiments of this application.

[0011] The components represented by each number in the attached diagram are explained below: Information acquisition module 11, data processing module 12, load calculation module 13, water purification module 14. Detailed Implementation

[0012] This application provides a multi-module combined aquaculture water purification method and system to address the technical problem that traditional aquaculture water purification methods are difficult to dynamically adjust according to the actual load and distribution characteristics of different aquaculture modules, resulting in low purification efficiency.

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0015] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid unnecessarily obscuring the description of this application. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0016] Example 1, as Figure 1 As shown in the embodiments of this application, a multi-module combined aquaculture water purification method is provided, including: S10: Interact with the target scenario to obtain the rated aquaculture load and module distribution information of multiple aquaculture modules; In this embodiment, the target scenario is an aquaculture farm of different sizes, such as a pond aquaculture scenario or a factory-style recirculating aquaculture scenario. When interacting with the target scenario, the rated aquaculture load and module distribution information of multiple aquaculture modules can be obtained by exchanging information with the farm management personnel or by retrieving relevant data from the farm's existing management system.

[0017] Among them, the rated aquaculture load refers to the maximum amount of aquaculture biomass that each aquaculture module can bear when it is designed; the module distribution information covers the geographical location, relative positional relationship, and positional connection of each aquaculture module in the target scenario with key facilities such as water source and drainage outlet.

[0018] By acquiring the rated aquaculture load and module distribution information of multiple aquaculture modules, basic data support is provided for determining the initial connection topology of the water purification module, making the planning of the initial connection topology more in line with the actual situation of the target scenario.

[0019] Specifically, step S10 in the method includes: Obtain the aquaculture planning parameters and spatial location information of the aquaculture module in the target scenario; Based on the aquaculture planning parameters, the rated aquaculture load of the aquaculture module is determined, wherein the rated aquaculture load includes aquaculture capacity information, aquaculture target information, and associated aquaculture category information; Based on the spatial location information of multiple aquaculture modules, output module distribution information.

[0020] In this embodiment, firstly, an on-site survey of the target scene is conducted or planning drawings of the aquaculture farm are retrieved to obtain the aquaculture planning parameters and spatial location information of the aquaculture module. The aquaculture planning parameters include the design area, water depth, and expected stocking density of each aquaculture module; the spatial location information is determined through coordinate positioning, distance measurement, etc. For example, in a pond aquaculture scenario, the specific coordinates of each aquaculture pond and the distance between them are determined.

[0021] Secondly, the rated aquaculture load is determined based on the aquaculture planning parameters. The aquaculture capacity information can be calculated from the design area and the expected aquaculture density. The aquaculture target information includes the planned aquaculture output, such as the individual weight of the fish when aquaculture is completed, which determines the intensity of pollutants generated. The associated aquaculture category information clarifies the specific species of fish, shrimp, etc., to be farmed. Different aquaculture categories have different water quality requirements, and the rated aquaculture load is also different.

[0022] Finally, the spatial location information of multiple aquaculture modules is integrated and output in the form of charts or coordinate sets to show the layout of each module in the target scene, that is, to determine how to group and divide them.

[0023] S20: Based on the rated aquaculture load and the module distribution information, the initial connection topology between multiple water purification modules is determined through a preset prior experience model, wherein the initial connection topology includes at least one combination of water purification modules. In this embodiment, the pre-defined prior experience model is constructed based on practical experience and historical data in aquaculture water purification engineering. This model includes corresponding rules between different rated aquaculture load ranges, different module distribution characteristics, and the connection topology of water purification modules. For example, when the sum of the rated aquaculture loads of multiple aquaculture modules in a certain area is high and relatively concentrated, the corresponding output includes a combination of multiple series-connected water purification modules to enhance the water purification capacity of that area; while for cases where the modules are more dispersed, the corresponding output is a combination of multiple independent water purification modules, each serving aquaculture modules in different areas.

[0024] Secondly, the initial connection topology is determined by inputting the obtained rated aquaculture load and module distribution information into a preset prior experience model. The model matches and calculates according to its internal corresponding rules to generate the initial connection topology between multiple water purification modules.

[0025] For example, the water purification module combination can be a combination of different types of water purification modules such as physical filtration module, biological purification module, and chemical treatment module. Different combination methods are suitable for different water purification needs.

[0026] By using the rated aquaculture load and module distribution information, the initial connection topology is determined using a pre-set a priori experience model, so that the combination and connection of water purification modules can be preliminarily planned, avoiding the subjectivity and blindness that may result from relying entirely on human experience.

[0027] Specifically, step S20 in the method includes: Historical water quality records of the aquaculture module are obtained, and combined with preset water quality indicator intervals, the typical water quality probability distribution of the aquaculture module is analyzed and obtained. The number of merges in the aquaculture module is a variable. The joint probability set under multiple merge numbers is calculated by iterating through the set of joint probability and the probability distribution of merged water quality under multiple merge numbers is obtained based on the joint probability set. Calculate the expected value of water quality indicators and the standard deviation of water quality fluctuation for the typical water quality probability distribution and the multiple merged water quality probability distributions respectively; By combining the elbow method with the calculated standard deviations of multiple water quality fluctuations, the optimal number of samples to be merged was determined.

[0028] In this embodiment, firstly, water quality parameter data for each aquaculture module over a period of time, such as a farming cycle or a year, is retrieved from the historical water quality monitoring database of the target scenario. This data includes, but is not limited to, dissolved oxygen, ammonia nitrogen, nitrite, pH, and turbidity. The preset water quality indicator range is determined based on the suitable growth environment of the farmed organisms and relevant industry water quality standards. For example, for a specific farmed species, the suitable range for dissolved oxygen is 5-8 mg / L, and the safe range for ammonia nitrogen is 0-0.5 mg / L.

[0029] Secondly, by comparing and analyzing historical water quality data with preset water quality indicator ranges, the frequency of each water quality parameter occurring in different ranges is statistically analyzed, thereby constructing a typical water quality probability distribution for each aquaculture module. This distribution reflects the variation patterns and probabilistic characteristics of water quality parameters under conventional aquaculture conditions. For example, the probability of ammonia nitrogen concentration occurring in the 0-0.3 mg / L range for a certain aquaculture module is 70%, and the probability of occurring in the 0.3-0.5 mg / L range is 25%.

[0030] Secondly, the number of merged aquaculture modules is a variable, for example, starting from 1 and gradually increasing to different merge numbers. For each merge number, the aquaculture modules are merged according to certain rules, such as merging based on the geographical proximity principle in the module distribution information. Then, the overall water quality parameter data after merging is calculated, thereby obtaining the joint probability set under that merge number. The joint probability set refers to the probability combination of the common occurrence of each water quality parameter in different intervals after merging. Based on this joint probability set, the merged water quality probability distribution can be obtained.

[0031] Then, for the typical water quality probability distribution of each aquaculture module and the merged water quality probability distribution under different merging numbers, the expected value of water quality indicators and the standard deviation of water quality fluctuation are calculated respectively. The expected value of water quality indicators is the average value of water quality parameters under their probability distribution, representing the average level of water quality; the standard deviation of water quality fluctuation reflects the dispersion of water quality parameters over a certain period of time. The smaller the standard deviation, the more stable the water quality.

[0032] Finally, the elbow method was used to analyze the calculated standard deviations of water quality fluctuations. The elbow method states that as the number of merged samples increases, the standard deviation of water quality fluctuations gradually decreases, but when the number of merged samples reaches a certain value, the rate of decrease in standard deviation becomes very slow, forming an inflection point. The number of merged samples corresponding to this inflection point is the optimal number of merged samples. Furthermore, by determining the optimal number of merged samples, the aquaculture module is grouped while ensuring water quality stability. This provides a basis for the subsequent combination and connection of water purification modules, avoiding situations where too many merged samples lead to excessive complexity in the purification system, or too few merged samples fail to meet water purification requirements.

[0033] Furthermore, based on the rated aquaculture load and the module distribution information, the initial connection topology between multiple water purification modules is determined through a preset prior experience model, including: Input the rated aquaculture load into the pre-constructed water quality mapping model to obtain the expected water quality load of the aquaculture module; Based on the preset optimal merging quantity, and combined with the module distribution information, multiple aquaculture modules are divided into zones. Taking any aquaculture module combination in the zoning results as the analysis target, the equivalent water quality load is calculated and obtained in combination with the expected water quality load. By combining the equivalent water quality load and the prior experience model, a water quality purification assessment is conducted to determine the initial connection topology between multiple water quality purification modules.

[0034] In this embodiment, the rated aquaculture load is first input into a pre-constructed water quality mapping model. This model is trained based on a large amount of historical aquaculture data and water quality change patterns, and can predict the corresponding expected water quality load based on the aquaculture load. The expected water quality load refers to the expected range of changes in the types and concentrations of pollutants and water quality parameters that the aquaculture module may generate under the current rated aquaculture load. For example, as the aquaculture biomass increases, the emissions of pollutants such as ammonia nitrogen and organic matter will also increase accordingly, and the expected water quality load quantifies this relationship.

[0035] Secondly, based on the previously determined optimal number of merges, and combined with the geographical location and relative positional relationships in the module distribution information, the multiple aquaculture modules are divided into zones. For example, aquaculture modules that are geographically adjacent and have a significant mutual impact on water quality are divided into one region, forming several relatively independent aquaculture zones, with each zone managed as a whole for water quality purification.

[0036] Then, taking any combination of aquaculture modules in the partitioning results, i.e. a partition, as the analysis target, and combining the expected water quality load of each aquaculture module in the partition, the equivalent water quality load of the partition is obtained by weighted summation calculation.

[0037] Specifically, the equivalent water quality load comprehensively considers the impact of all aquaculture modules within the zone on water quality, transforming it into a comprehensive indicator that can characterize the overall water quality purification needs of the zone.

[0038] For example, the formula for calculating the equivalent water quality load can be expressed as: Equivalent water quality load = Σ (Expected water quality load of a single aquaculture module × Weighting coefficient of the module). The weighting coefficient is determined based on the proportion of the rated aquaculture load of each module to the total rated aquaculture load of the zone. For example, if the rated aquaculture load of a certain aquaculture module within a zone is 30% of the total rated aquaculture load of the zone, then its weighting coefficient is 0.3.

[0039] Finally, the calculated equivalent water quality load is input into a pre-defined empirical model. The model assesses water purification capacity and matches purification schemes based on factors such as the magnitude of the equivalent water quality load, pollutant type, and the size of the zone. The empirical model stores information on the optimal combination, connection sequence, and operating parameter range of water purification modules under different equivalent water quality loads. Through evaluation, the initial connection topology between multiple water purification modules that can meet the water purification needs of the zone is determined. For example, for zones with high equivalent water quality loads, the initial connection topology may include a series combination of physical filtration modules, biological purification modules, and chemical treatment modules to ensure strong purification capacity.

[0040] Specifically, the multi-module combined aquaculture water purification method of this application also includes: Based on the rated aquaculture load, extract aquaculture category information, and initialize the water quality mapping model based on the aquaculture category information, wherein the water quality mapping model is a mathematical model; Analyze the rated aquaculture load, obtain the most unfavorable aquaculture load for the target scenario, and extract its features; Input the feature extraction results into the initialized water quality mapping model to obtain the desired water quality load.

[0041] In this embodiment, firstly, because different aquaculture species exhibit significant differences in their sensitivity to water quality and the amount of pollutants they generate, the water quality mapping model is initialized based on the aquaculture species information. For example, high-density cultured carnivorous fish and low-density cultured filter-feeding shellfish produce significantly different amounts of pollutants such as ammonia nitrogen and organic matter under the same aquaculture load. The parameters of the water quality mapping model need to be adjusted according to these differences to ensure the accuracy of the expected water quality load prediction. The water quality mapping model is a mathematical model built on a neural network, and its parameters are determined through training with historical data.

[0042] Secondly, the rated aquaculture load is analyzed to identify the most unfavorable aquaculture load conditions that may occur in the target scenario. The most unfavorable aquaculture load typically refers to the load state during the aquaculture process where the pressure on water purification is greatest due to factors such as the highest stocking density, the largest feeding amount, and the most vigorous biological metabolism. For example, in the middle and late stages of the aquaculture cycle, the cultured organisms reach their maximum size, and the rated aquaculture load at this time is often the highest value of the entire cycle, i.e., the most unfavorable aquaculture load. Feature extraction is performed on the most unfavorable aquaculture load, and the extracted features include, but are not limited to, indicators such as the cultured biomass, daily feeding amount, and expected metabolic waste discharge under this load.

[0043] Finally, the feature extraction results of the most unfavorable aquaculture load are input into the water quality mapping model, which has been initialized based on the aquaculture species information. Based on the input feature data, and combined with its internal mathematical algorithms and parameter settings, the model calculates and predicts the types of pollutants that may be generated by the aquaculture module under the most unfavorable aquaculture load conditions, their concentration trends, and their impact on various water quality parameters such as dissolved oxygen and pH. This allows the model to obtain the desired water quality load, for example, mapping the chemical oxygen demand (COD) production to 100 mg / h.

[0044] By considering the most unfavorable aquaculture load, the design of water purification solutions can be more forward-looking and reliable, ensuring that the purification system can operate effectively and maintain water quality stability even under the greatest water quality pressure.

[0045] Specifically, water quality purification assessment is conducted by combining the equivalent water quality load and the prior experience model to determine the initial connection topology between multiple water quality purification modules, including: Obtain the purification performance parameters of the water purification module, and calculate the initial number of modules to be used in combination based on the purification performance parameters and the equivalent water quality load; By combining the initial number of combined water purification modules, the purification performance parameters, and the prior experience model, the purification performance of the initial number of combined water purification modules is verified. The initial combined dosage was randomly fluctuated, and the purification performance was iteratively verified. Multiple initial combined quantities that meet the preset purification constraints are selected, and the one with the highest matching degree between purification performance and purification constraints is selected as the target combined quantity. Based on the target number of combined applications, multiple water purification modules are grouped and divided to obtain the initial connection topology.

[0046] In this embodiment, firstly, the purification performance parameters of various types of water purification modules are obtained from the technical parameter manual or performance test report of the water purification modules. These parameters include, for example, the filtration rate, interception efficiency, and maximum treatment capacity of physical filtration modules; the ammonia nitrogen removal rate, dissolved oxygen enhancement capacity, and hydraulic retention time of biological purification modules; and the dosage and pollutant degradation rate of chemical treatment modules. The purification performance parameters are then matched with the equivalent water load of each zone to preliminarily determine the initial number of various types of water purification modules required for each zone.

[0047] For example, if the ammonia nitrogen concentration in the equivalent water load of a certain zone is 1.2 mg / L, and the selected biological purification module has an ammonia nitrogen removal rate of 80% under specific operating conditions, and the designed effluent ammonia nitrogen concentration needs to be controlled below 0.5 mg / L, then according to the material balance formula "ammonia nitrogen removal amount = influent ammonia nitrogen concentration × treated water volume × removal rate", it can be preliminarily calculated that at least two biological purification modules of this type need to be used in series to meet the ammonia nitrogen removal requirements. This number is the initial number of biological purification modules used in series.

[0048] Secondly, the calculated initial number of combined water purification modules, corresponding purification performance parameters, and equivalent water quality load of each zone are input into a pre-defined prior experience model. This prior experience model is a calculation model related to water purification obtained from an expert system. Based on the combined module effects under similar water purification requirements in historical engineering cases, the purification performance of the initial number of combined water purification modules is verified. The verification includes whether the combined purification modules can stably control various water quality parameters within the preset water quality indicator range under continuous input of equivalent water quality load.

[0049] For example, after combined treatment by the physical filtration module and the biological purification module, can the turbidity of the effluent be reduced to below 5 NTU, and can the dissolved oxygen be maintained above 6 mg / L? Simulate different operating conditions, such as fluctuations in influent load and adjustments to module operating parameters, to evaluate the stability and reliability of the purification effect of the initial number of modules used in combination under various conditions.

[0050] Then, the initial combined dosage is randomly fluctuated, for example, adjusted by ±1 or ±2 based on the initial dosage, generating multiple different combined dosage schemes. For each adjusted combined dosage scheme, the above purification performance verification process is repeated, that is, the water purification effect under that dosage is simulated and calculated using a priori empirical model, including indicators such as expected value of water quality indicators and standard deviation of water quality fluctuation. Through multiple iterations of verification, purification performance data corresponding to different combined dosage schemes are obtained, forming a set of results for comparison.

[0051] Finally, from the multiple combined treatment schemes obtained through iterative verification, the scheme whose purification performance meets the preset purification constraints is selected. These preset purification constraints typically include minimum standards that water quality parameters must meet, upper limits on the energy consumption of the purification system, and a budgeted treatment cost. For example, it may require that all parameters of the effluent water quality meet 100% of the suitable water quality range for the aquaculture species, and that the energy consumption per unit of water treatment does not exceed 0.5 kWh / m³. 3 Among the schemes that meet the constraints, the matching degree between the purification performance and the purification constraints of each scheme is calculated. For example, factors such as water quality compliance rate, water quality stability, and operating costs are comprehensively considered, and the number of modules with the highest matching degree is selected as the target number of modules to be used. Based on the target number of modules to be used, multiple water purification modules are grouped according to the connection order recommended by the prior experience model, such as physical filtration module first, biological purification module in the middle, and chemical treatment module last. The connection mode of series, parallel, or series-parallel hybrid connection between each module is determined, thereby finally obtaining the initial connection topology between multiple water purification modules.

[0052] S30: Collect real-time monitoring data from multiple aquaculture modules and calculate real-time water quality load based on the real-time monitoring data; In this embodiment, dynamic water quality information of the aquaculture module is obtained through real-time monitoring and converted into real-time water quality load that can be used for subsequent purification and control.

[0053] First, determine the types of real-time monitoring data to be collected, including real-time values ​​of key water quality parameters such as dissolved oxygen, pH, ammonia nitrogen, nitrite nitrogen, nitrate nitrogen, chemical oxygen demand (COD), biochemical oxygen demand (BOD), turbidity, water temperature, and salinity, as well as operational data related to aquaculture activities, such as real-time feeding amount, feeding frequency, water exchange rate, and aeration equipment operating power. Data collection points should be distributed in representative locations within the aquaculture module, such as inlets, outlets, the middle and bottom of the aquaculture water body, to ensure data accuracy and comprehensiveness.

[0054] Then, the received real-time monitoring data is preprocessed, including data cleaning to remove outliers and noise data caused by sensor malfunctions, signal interference, etc. Based on the preprocessed real-time monitoring data, the real-time water quality load is calculated. The calculation method for the real-time water quality load is similar to that of the equivalent water quality load mentioned above, but the input data is replaced with the real-time monitoring values ​​at the current moment.

[0055] Specifically, step S30 in the method includes: Based on the preset collection interval and collection window, N aquaculture modules are randomly selected for sequence data collection to obtain real-time monitoring data, where N is greater than or equal to 2. The real-time monitoring data is traversed, and the average water quality value of the acquisition window is calculated for N sets of sequence data to obtain the real-time water quality load.

[0056] In this embodiment, a preset data collection interval is first set, such as collecting data once per hour. Simultaneously, a data collection window is set, such as continuously collecting data for 4 or 8 hours, forming a data collection cycle. Within each collection cycle, N (N≥2) aquaculture modules are randomly selected from all aquaculture modules as samples, and continuous sequence data is collected from them. Choosing random sampling avoids data bias that might occur from fixed collection of certain modules, ensuring the representativeness of the samples. Furthermore, the value of N must meet statistical requirements to ensure the reliability of subsequent calculation results. For example, if there are 50 aquaculture modules, 5 modules can be randomly selected within each collection window for monitoring data collection, obtaining continuous change sequence data of parameters such as dissolved oxygen and ammonia nitrogen within the collection window.

[0057] Secondly, the N sets of collected sequence data are traversed, and for each set of sequence data, the average water quality value within the entire collection window is calculated. Specifically, for each water quality parameter, such as ammonia nitrogen concentration, the monitoring values ​​of the parameter at each time point within the collection window are arithmetically averaged to obtain the average value of the parameter within the collection window.

[0058] For example, if the ammonia nitrogen concentrations of a certain aquaculture module within a 4-hour sampling window are 0.8 mg / L, 0.9 mg / L, 0.7 mg / L, and 1.0 mg / L, then the average ammonia nitrogen concentration within that sampling window is (0.8 + 0.9 + 0.7 + 1.0) / 4 = 0.85 mg / L. By summing the average values ​​of various water quality parameters from the sampling windows of N aquaculture modules, the overall water quality status of the monitored modules under the current sampling window is comprehensively characterized. Furthermore, the average data is integrated and processed to obtain the real-time water quality load, which reflects the real-time water quality pressure of the current aquaculture system.

[0059] S40: Based on the real-time water quality load and the initial connection topology, optimize the water quality purification parameters based on simulation analysis, and control the aquaculture water quality purification in the target scenario based on the water quality purification parameter optimization results.

[0060] The water purification parameters include at least one of the water distribution ratio of each water purification module in the water purification module assembly and the return ratio between water purification modules.

[0061] In this embodiment, the operating parameters of the water purification system are dynamically adjusted through simulation analysis to cope with changes in real-time water quality load and ensure stable and efficient purification effect.

[0062] Specifically, firstly, based on the acquired real-time water quality load and the established initial connection topology, a dynamic simulation model of the water purification system is constructed. This simulation model can simulate the flow process of water between different water purification modules, the migration and transformation patterns of pollutants within each module, and the impact of module operating parameters on the purification effect.

[0063] Secondly, real-time water quality load data is input into the dynamic simulation model. The model performs simulations across multiple scenarios based on the combination of water purification modules and the range of operating parameters in the initial connection topology. During the simulation, the focus is on the water purification parameters, specifically the impact of the water distribution ratio flowing into each purification module and the recirculation ratio between modules on the final effluent quality. The water distribution ratio refers to the percentage of the total influent volume allocated to each module when water flows into multiple parallel purification modules of the same or different types. The recirculation ratio refers to the percentage of the effluent from a particular purification module that is redirected back to the preceding module for further treatment, relative to the total effluent from that module.

[0064] Then, based on the simulation results, optimization algorithms, such as genetic algorithms and particle swarm optimization, are used to optimize the water distribution ratio and recirculation ratio. The optimization goal is to achieve the best overall performance of the purification system while meeting preset purification constraints, such as meeting effluent quality standards, minimizing energy consumption, and minimizing cost. The optimization algorithm calculates the fitness values ​​of different parameter combinations based on the water quality, energy consumption, and cost indicators output by the simulation model, and finds the parameter combination with the highest fitness value, i.e., the optimal water distribution ratio and recirculation ratio, through iterative search.

[0065] Finally, the optimized water purification parameters are sent to the control system of the water purification system. The control system then adjusts the corresponding actuators in real time, such as adjusting the opening of the inlet valves of each module to change the water distribution ratio, or adjusting the operating frequency of the return pump to change the return ratio. Through closed-loop control, the water purification system can dynamically respond to changes in real-time water quality load, always maintaining optimal operating conditions, thereby achieving precise and efficient purification of water quality in the target aquaculture scenario.

[0066] For example, when the optimization algorithm determines that the optimal water inlet ratio of the biological purification module is 60%, the control system will automatically adjust the corresponding valve to the appropriate opening degree to ensure that 60% of the water flow enters the biological purification module in order to achieve the best biodegradation effect.

[0067] The optimization of water purification parameters based on simulation analysis, according to the real-time water quality load and the initial connection topology, includes: A physical model of the water purification module is constructed, and multiple physical models are connected to generate a simulation analysis environment based on the initial connection topology. By combining the purification performance parameters of the water purification module with the preset purification constraints of the target scenario, the boundary conditions of the simulation analysis environment are defined, and the simulation analysis environment is initialized according to the real-time water quality load. A parameter evaluation function is defined, including purification cost factor and water quality compliance factor, and iterative simulation analysis is performed in the simulation analysis environment with water purification parameters as the optimization objective. The water purification parameter corresponding to the parameter with the largest value in the iterative simulation analysis results is selected as the optimized water purification parameter.

[0068] In this embodiment, firstly, a physical model of each water purification module is constructed based on its type and structural characteristics. For example, for a physical filtration module, the physical model needs to include structural parameters such as the material, particle size distribution, porosity, and filter layer thickness of the filter media, as well as equations for water flow resistance and suspended solids retention kinetics within the filter layer. The physical model of a biological purification module needs to consider the thickness, specific surface area, and microbial community composition of the biofilm, as well as mass transfer rate equations for pollutants and biochemical reaction kinetic equations (such as the Monod equation). The physical model of a chemical treatment module needs to cover the structure of the reagent dosing device, reagent diffusion coefficient, and chemical reaction rate constant. By converting physical properties and mathematical equations into computer-recognizable model parameters and code, a physical model that accurately reflects the internal physical, chemical, and biological processes of the module is formed.

[0069] Secondly, based on the grouping and connection methods of each water purification module in the initial connection topology, such as series, parallel, or a combination of series and parallel, the constructed individual physical models are connected and combined in the simulation platform to generate a complete simulation analysis environment. For example, if the initial connection topology is "physical filtration module (2 in parallel) → biological purification module (3 in series) → chemical treatment module (1)," then in the simulation analysis environment, the physical models of the two physical filtration modules are first set to be connected in parallel, and their common outlet is connected to the inlet of the physical models of the three series-connected biological purification modules. Finally, the outlets of the three biological purification modules are merged and connected to the physical model of the chemical treatment module, thus completely reproducing the actual connection structure of the water purification system.

[0070] Furthermore, considering the purification performance parameters of each water purification module, such as the maximum processing capacity of the physical filtration module, the ammonia nitrogen removal rate of the biological purification module, and the dosage range of the chemical treatment module, as well as the preset purification constraints of the target scenario, such as effluent COD ≤ 50 mg / L, dissolved oxygen ≥ 6 mg / L, and unit water treatment cost ≤ 0.3 yuan / m³, the system is optimized. 3 Define the boundary conditions of the simulation analysis environment. Boundary conditions include inlet water boundary, outlet water boundary, module operating parameter boundary, such as the adjustable range of water distribution ratio (0%-100%), the adjustable range of reflux ratio (0%-50%), and environmental parameter boundary, such as constant values ​​or variation ranges of water temperature and pH.

[0071] Then, the calculated real-time water quality load data is used as the initial condition and input into the inlet boundary of the simulation analysis environment to complete the initialization of the simulation environment, so that the model can start the simulation operation based on the current actual water quality load.

[0072] Next, a parameter evaluation function is defined, which comprehensively considers the purification cost factor and the water quality compliance factor. The purification cost factor can be obtained by weighted summing of energy consumption cost, reagent cost, and maintenance cost; the water quality compliance factor is determined by calculating the degree of matching between the effluent water quality parameters and the preset purification constraints.

[0073] For example, if a water quality parameter meets the standard, it is counted as 1; if it exceeds the standard, it is counted as a value between 0 and 1 depending on the degree of exceedance. A weighted average is then applied to all the parameters' compliance values. The parameter evaluation function can be expressed as: Evaluation function value = α × Water quality compliance factor + β × (1 - Normalized value of purification cost factor), where α and β are weighting coefficients, adjusted according to the actual optimization focus. For example, if more emphasis is placed on water quality compliance, α is taken as a larger value; if more emphasis is placed on cost control, β is taken as a larger value. Using water purification parameters as the optimization target variable, multiple iterative simulation analyses are performed in the simulation analysis environment by changing the parameter values. In each iteration, the simulation model simulates the water purification process based on the current parameter combination and outputs the corresponding effluent water quality data, energy consumption data, and cost data, thereby calculating the parameter evaluation function value under that parameter combination.

[0074] Finally, after completing a preset number of iterative simulation analyses, all iteration results are traversed, and the set of water purification parameters with the largest parameter evaluation function value is selected as the optimization result. The water distribution ratio and recirculation ratio corresponding to this set of parameters can achieve the best balance between water purification effect and operating cost while meeting the preset purification constraints.

[0075] For example, after 100 iterations, if the water distribution ratio of a certain set of parameters is 40% for physical module A and 60% for physical module B, and the return ratio is 20% for the effluent from biological module C returning to the influent of physical module C, and the corresponding parameter evaluation function value is the highest, then this is determined as the final optimized result of the water quality purification parameters.

[0076] In summary, compared with existing technologies, this application achieves precision and efficiency in aquaculture water purification by dynamically combining and intelligently controlling multiple water purification modules.

[0077] In summary, the embodiments of this application have at least the following technical effects: This application provides a multi-module combined aquaculture water purification method. First, by interacting with a target scenario, the rated aquaculture load and module distribution information of multiple aquaculture modules are obtained, clarifying the potential water purification needs and spatial layout of different modules. Second, a pre-set empirical model is used to determine the initial connection topology between the multiple water purification modules, initially constructing a purification system framework that meets the general needs of the target scenario, allowing for a scientific preliminary plan of the combination and connection methods of the water purification modules. Subsequently, real-time monitoring data from multiple aquaculture modules is collected, and real-time water quality load is calculated accordingly, ensuring that the water purification process closely matches the actual conditions of the current aquaculture water body, avoiding potential lags caused by relying solely on initial settings. Finally, water purification parameters are optimized based on simulation analysis, and the aquaculture water purification in the target scenario is controlled according to the optimization results. By constructing a simulation analysis environment, combining purification performance parameters, pre-set purification constraints, and defined parameter evaluation functions, the water purification parameters are iteratively optimized, minimizing purification costs while ensuring water quality meets standards, achieving a balance between purification efficiency and economy. The above technical solutions effectively solve the problem of the difficulty in dynamic adjustment of traditional methods, improve the level of intelligence and actual operation efficiency of aquaculture water purification, and ensure that farmed organisms can grow in a more stable and suitable water environment, thereby helping to improve aquaculture efficiency.

[0078] Example 2, as Figure 2 As shown, based on the same inventive concept as the multi-module combined aquaculture water purification method provided in Embodiment 1, this application also provides a multi-module combined aquaculture water purification system, including: Information acquisition module 11 is used to interact with the target scene and acquire the rated aquaculture load and module distribution information of multiple aquaculture modules; The data processing module 12 is used to determine the initial connection topology between multiple water purification modules based on the rated aquaculture load and the module distribution information through a preset prior experience model, wherein the initial connection topology includes at least one combination of water purification modules. The load calculation module 13 is used to collect real-time monitoring data from multiple aquaculture modules and calculate real-time water quality load based on the real-time monitoring data. The water purification module 14 is used to optimize the water purification parameters based on simulation analysis according to the real-time water quality load and the initial connection topology, and to control the water purification of aquaculture in the target scenario based on the water purification parameter optimization results.

[0079] In one embodiment, the information acquisition module 11 is specifically used for: Obtain the aquaculture planning parameters and spatial location information of the aquaculture module in the target scenario; Based on the aquaculture planning parameters, the rated aquaculture load of the aquaculture module is determined, wherein the rated aquaculture load includes aquaculture capacity information, aquaculture target information, and associated aquaculture category information; Based on the spatial location information of multiple aquaculture modules, output module distribution information.

[0080] In one embodiment, the data processing module 12 is specifically used for: Historical water quality records of the aquaculture module are obtained, and combined with preset water quality indicator intervals, the typical water quality probability distribution of the aquaculture module is analyzed and obtained. The number of merges in the aquaculture module is a variable. The joint probability set under multiple merge numbers is calculated by iterating through the set of joint probability and the probability distribution of merged water quality under multiple merge numbers is obtained based on the joint probability set. Calculate the expected value of water quality indicators and the standard deviation of water quality fluctuation for the typical water quality probability distribution and the multiple merged water quality probability distributions respectively; By combining the elbow method with the calculated standard deviations of multiple water quality fluctuations, the optimal number of samples to be merged was determined.

[0081] Furthermore, in one embodiment, based on the rated aquaculture load and the module distribution information, the initial connection topology between multiple water purification modules is determined through a preset prior experience model, including: Input the rated aquaculture load into the pre-constructed water quality mapping model to obtain the expected water quality load of the aquaculture module; Based on the preset optimal merging quantity, and combined with the module distribution information, multiple aquaculture modules are divided into zones. Taking any aquaculture module combination in the zoning results as the analysis target, the equivalent water quality load is calculated and obtained in combination with the expected water quality load. By combining the equivalent water quality load and the prior experience model, a water quality purification assessment is conducted to determine the initial connection topology between multiple water quality purification modules.

[0082] Furthermore, in one embodiment of the application, the multi-module combined aquaculture water purification method further includes: Based on the rated aquaculture load, extract aquaculture category information, and initialize the water quality mapping model based on the aquaculture category information, wherein the water quality mapping model is a mathematical model; Analyze the rated aquaculture load, obtain the most unfavorable aquaculture load for the target scenario, and extract its features; Input the feature extraction results into the initialized water quality mapping model to obtain the desired water quality load.

[0083] Furthermore, in one embodiment, water quality purification assessment is performed by combining the equivalent water quality load and the prior experience model to determine the initial connection topology between multiple water quality purification modules, including: Obtain the purification performance parameters of the water purification module, and calculate the initial number of modules to be used in combination based on the purification performance parameters and the equivalent water quality load; By combining the initial number of combined water purification modules, the purification performance parameters, and the prior experience model, the purification performance of the initial number of combined water purification modules is verified. The initial combined dosage was randomly fluctuated, and the purification performance was iteratively verified. Multiple initial combined quantities that meet the preset purification constraints are selected, and the one with the highest matching degree between purification performance and purification constraints is selected as the target combined quantity. Based on the target number of combined applications, multiple water purification modules are grouped and divided to obtain the initial connection topology.

[0084] In one embodiment, the load calculation module 13 is specifically used for: Based on the preset collection interval and collection window, N aquaculture modules are randomly selected for sequence data collection to obtain real-time monitoring data, where N is greater than or equal to 2. The real-time monitoring data is traversed, and the average water quality value of the acquisition window is calculated for N sets of sequence data to obtain the real-time water quality load.

[0085] The water purification parameters include at least one of the water distribution ratio of each water purification module in the water purification module assembly and the return ratio between water purification modules.

[0086] Furthermore, in one embodiment, based on the real-time water quality load and the initial connection topology, water purification parameters are optimized according to simulation analysis, including: A physical model of the water purification module is constructed, and multiple physical models are connected to generate a simulation analysis environment based on the initial connection topology. By combining the purification performance parameters of the water purification module with the preset purification constraints of the target scenario, the boundary conditions of the simulation analysis environment are defined, and the simulation analysis environment is initialized according to the real-time water quality load. A parameter evaluation function is defined, including purification cost factor and water quality compliance factor, and iterative simulation analysis is performed in the simulation analysis environment with water purification parameters as the optimization objective. The water purification parameter corresponding to the parameter with the largest value in the iterative simulation analysis results is selected as the optimized water purification parameter.

[0087] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0088] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0089] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A multi-module combined aquaculture water purification method, characterized in that, include: Interact with the target scenario to obtain the rated aquaculture load and module distribution information of multiple aquaculture modules; Based on the rated aquaculture load and the module distribution information, the initial connection topology between multiple water purification modules is determined through a preset prior experience model, wherein the initial connection topology includes at least one combination of water purification modules. Collect real-time monitoring data from multiple aquaculture modules and calculate real-time water quality load based on the real-time monitoring data; Based on the real-time water quality load and the initial connection topology, water quality purification parameters are optimized based on simulation analysis, and the water quality purification of the target scenario is controlled based on the optimization results of the water quality purification parameters.

2. The multi-module combined aquaculture water purification method as described in claim 1, characterized in that, The interactive target scenario obtains the rated aquaculture load and module distribution information for multiple aquaculture modules, including: Obtain the aquaculture planning parameters and spatial location information of the aquaculture module in the target scenario; Based on the aquaculture planning parameters, the rated aquaculture load of the aquaculture module is determined, wherein the rated aquaculture load includes aquaculture capacity information, aquaculture target information, and associated aquaculture category information; Based on the spatial location information of multiple aquaculture modules, output module distribution information.

3. The multi-module combined aquaculture water purification method as described in claim 2, characterized in that, Based on the rated aquaculture load and the module distribution information, the initial connection topology between multiple water purification modules is determined through a preset prior experience model, including: Historical water quality records of the aquaculture module are obtained, and combined with preset water quality indicator intervals, the typical water quality probability distribution of the aquaculture module is analyzed and obtained. The number of merges in the aquaculture module is a variable. The joint probability set under multiple merge numbers is calculated by iterating through the set of joint probability and the probability distribution of merged water quality under multiple merge numbers is obtained based on the joint probability set. Calculate the expected value of water quality indicators and the standard deviation of water quality fluctuation for the typical water quality probability distribution and the multiple merged water quality probability distributions respectively; By combining the elbow method with the calculated standard deviations of multiple water quality fluctuations, the optimal number of samples to be merged was determined.

4. The multi-module combined aquaculture water purification method as described in claim 2, characterized in that, Based on the rated aquaculture load and the module distribution information, the initial connection topology between multiple water purification modules is determined through a preset prior experience model, including: Input the rated aquaculture load into the pre-constructed water quality mapping model to obtain the expected water quality load of the aquaculture module; Based on the preset optimal merging quantity, and combined with the module distribution information, multiple aquaculture modules are divided into zones. Taking any aquaculture module combination in the zoning results as the analysis target, the equivalent water quality load is calculated and obtained in combination with the expected water quality load. By combining the equivalent water quality load and the prior experience model, a water quality purification assessment is conducted to determine the initial connection topology between multiple water quality purification modules.

5. The multi-module combined aquaculture water purification method as described in claim 4, characterized in that, Also includes: Based on the rated aquaculture load, extract aquaculture category information, and initialize the water quality mapping model based on the aquaculture category information, wherein the water quality mapping model is a mathematical model; Analyze the rated aquaculture load, obtain the most unfavorable aquaculture load for the target scenario, and extract its features; Input the feature extraction results into the initialized water quality mapping model to obtain the desired water quality load.

6. The multi-module combined aquaculture water purification method as described in claim 4, characterized in that, Water quality purification assessment is conducted by combining the equivalent water quality load and the prior experience model to determine the initial connection topology between multiple water quality purification modules, including: Obtain the purification performance parameters of the water purification module, and calculate the initial number of modules to be used in combination based on the purification performance parameters and the equivalent water quality load; By combining the initial number of combined water purification modules, the purification performance parameters, and the prior experience model, the purification performance of the initial number of combined water purification modules is verified. The initial combined dosage was randomly fluctuated, and the purification performance was iteratively verified. Multiple initial combined quantities that meet the preset purification constraints are selected, and the one with the highest matching degree between purification performance and purification constraints is selected as the target combined quantity. Based on the target number of combined applications, multiple water purification modules are grouped and divided to obtain the initial connection topology.

7. The multi-module combined aquaculture water purification method as described in claim 1, characterized in that, Collecting real-time monitoring data from multiple aquaculture modules and calculating real-time water quality load based on the real-time monitoring data includes: Based on the preset collection interval and collection window, N aquaculture modules are randomly selected for sequence data collection to obtain real-time monitoring data, where N is greater than or equal to 2. The real-time monitoring data is traversed, and the average water quality value of the acquisition window is calculated for N sets of sequence data to obtain the real-time water quality load.

8. The multi-module combined aquaculture water purification method as described in claim 1, characterized in that, Based on the real-time water quality load and the initial connection topology, water purification parameters are optimized using simulation analysis, including: A physical model of the water purification module is constructed, and multiple physical models are connected to generate a simulation analysis environment based on the initial connection topology. By combining the purification performance parameters of the water purification module with the preset purification constraints of the target scenario, the boundary conditions of the simulation analysis environment are defined, and the simulation analysis environment is initialized according to the real-time water quality load. A parameter evaluation function is defined, including purification cost factor and water quality compliance factor, and iterative simulation analysis is performed in the simulation analysis environment with water purification parameters as the optimization objective. The water purification parameter corresponding to the parameter with the largest value in the iterative simulation analysis results is selected as the optimized water purification parameter.

9. The multi-module combined aquaculture water purification method as described in claim 1, characterized in that, The water purification parameters include at least one of the following: the water distribution ratio of each water purification module within the water purification module assembly and the return ratio between water purification modules.

10. A multi-module combined aquaculture water purification system, characterized in that, The method for implementing the multi-module combined aquaculture water purification method according to any one of claims 1-9 includes: The information acquisition module is used to interact with the target scenario and acquire the rated aquaculture load and module distribution information of multiple aquaculture modules; The data processing module is used to determine the initial connection topology between multiple water purification modules based on the rated aquaculture load and the module distribution information through a preset prior experience model, wherein the initial connection topology includes at least one combination of water purification modules. The load calculation module is used to collect real-time monitoring data from multiple aquaculture modules and calculate real-time water quality load based on the real-time monitoring data. The water purification module is used to optimize water purification parameters based on simulation analysis according to the real-time water quality load and the initial connection topology, and to control the water purification of aquaculture in the target scenario based on the optimized water purification parameters.

Images