A method and system for processing water treatment efficiency data in recirculating aquaculture systems.

Abstract

This invention relates to the field of wastewater treatment technology, and discloses a method and system for processing water treatment efficiency data in recirculating aquaculture systems (RAS). The method includes: assessing the influence of trace element parameters in standard water quality data of the RAS area on the RAS area, and converting them into influence weights corresponding to the trace element parameters; adjusting the influence weights based on the synergistic and antagonistic reactions between trace elements in the standard water quality data to obtain optimized influence weights; merging the trace element parameters and optimized influence weights into a comprehensive water treatment efficiency index for the RAS area; determining that the RAS area is in an inefficient operating state when the comprehensive water treatment efficiency index is lower than the lower limit of the historical threshold range; and selecting water quality adjustment strategies corresponding to the inefficient operating state from a preset water quality adjustment strategy library. This invention can improve the efficiency of RAS water treatment efficiency data processing.

Description

Technical Field

[0001] This invention relates to the field of wastewater treatment technology, and in particular to a method and system for processing water treatment efficiency data in recirculating aquaculture systems. Background Technology

[0002] In the field of data processing for water treatment efficiency in recirculating aquaculture systems, existing technologies have significant shortcomings in the acquisition of water quality data and the assessment of impact weights. Their preprocessing of raw water quality data lacks a systematic approach, failing to effectively remove interfering components such as suspended particles and colloids, resulting in insufficient accuracy in trace element detection data. Furthermore, when assessing the impact of trace elements on aquaculture areas, they only consider the concentration of a single parameter in isolation, without establishing a scientific correlation between historical water quality and aquaculture organism growth indicators. This makes the allocation of impact weights lack an objective basis and fails to truly reflect the actual value of each parameter.

[0003] Existing technologies also neglect the synergistic and antagonistic effects between trace elements and fail to make targeted adjustments to the initial influence weights, resulting in a large deviation in the calculation of the comprehensive water treatment efficiency index, making it difficult to accurately represent the actual treatment effect. In addition, in terms of determining the operating status and matching adjustment strategies, there is a lack of dynamic comparison and multi-dimensional verification with historical threshold ranges. This makes it difficult to quickly and accurately identify inefficient operating states and to select water quality adjustment strategies with strong adaptability and guaranteed application effects, which seriously restricts the timeliness and reliability of water treatment efficiency data processing. Therefore, how to improve the data processing efficiency of recirculating aquaculture water treatment has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a method and system for processing water treatment efficiency data in recirculating aquaculture systems to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a method for processing water treatment efficiency data in recirculating aquaculture systems, comprising: S1. Obtain standard water quality data for the recirculating aquaculture zone; S2. Evaluate the degree of influence of the trace element parameters in the standard water quality data on the recirculating aquaculture area, and convert the degree of influence into the influence weight corresponding to the trace element parameters; S3. Based on the synergistic and antagonistic reactions between trace elements in the standard water quality data, adjust the influence weights to obtain the optimized influence weights of the trace element parameters; S4. The trace element parameters and the optimized influence weights are integrated into the comprehensive water treatment efficiency index of the recirculating aquaculture area. S5. Query the historical threshold range corresponding to the recirculating aquaculture area. When the comprehensive water treatment efficiency index is lower than the lower limit of the historical threshold range, it is determined that the recirculating aquaculture area is in an inefficient operating state. S6. Filter the water quality adjustment strategies in the preset water quality adjustment strategy library that correspond to the inefficient operating state.

[0006] In a preferred embodiment, obtaining standard water quality data for the recirculating aquaculture zone includes: The original water sample from the recirculating aquaculture area was subjected to static sedimentation treatment to obtain a preliminary treated water sample from the recirculating aquaculture area. By retaining the tiny suspended particles and colloidal substances in the pre-treated water sample, a purified water sample from the recirculating aquaculture area is obtained. Qualitative and quantitative analysis of trace elements in the purified water sample was performed to obtain the types and corresponding concentration data of trace elements in the purified water sample. By integrating the types and corresponding concentration data of the trace elements, standard water quality data for the recirculating aquaculture area are obtained.

[0007] In a preferred embodiment, the step of assessing the impact of trace element parameters in the standard water quality data on the recirculating aquaculture area, and converting the impact into the impact weights corresponding to the trace element parameters, includes: The properties and concentration data of trace elements in the standard water quality data are integrated into the trace element parameters of the standard water quality data; The trace element parameters are mapped to the historical water quality database of the recirculating aquaculture area to obtain historical concentration change data of the trace element parameters and corresponding growth index data of the cultured organisms; Based on the correlation between the historical concentration change data and the corresponding growth index data of aquaculture organisms, the correlation coefficient of the trace element parameters is determined; Match the influence degree corresponding to the correlation coefficient in the preset influence degree mapping library, and convert the influence degree into the influence weight corresponding to the trace element parameter.

[0008] In a preferred embodiment, the formula for calculating the influence weight is as follows: ; In the formula, This indicates the influence weight. Indicates the first The influence degree value of each of the aforementioned trace element parameters. Indicates the first The influence degree value of each of the aforementioned trace element parameters. This represents the arithmetic mean of the values ​​indicating the degree of influence of the trace element parameters. This represents a preset scaling factor used to control the relative scaling of the degree of influence. This represents the preset distribution shape adjustment factor used to adjust the sensitivity of the weights to bias. The standard deviation of the values ​​representing the influence of the trace element parameters is represented by n, where n represents the number of trace element parameters. The exponential function representing the nonlinear decay characteristics used to construct the weights. This represents the absolute value function used to measure the deviation of the influence value from the average value.

[0009] In a preferred embodiment, adjusting the influence weights based on the synergistic and antagonistic reactions between trace elements in the standard water quality data to obtain the optimized influence weights of the trace element parameters includes: The trace element parameters in the standard water quality data are analyzed to identify the trace element parameter pairs that interact with each other, and a set of potential interaction pairs of the trace element parameters is generated. Based on the influence of the trace element parameters on biological activity, the trace element parameter pairs in the potential interaction pair set are classified into synergistic pair subsets and antagonistic pair subsets. The trace element parameter pairs in the subset of synergistic pairs and the subset of antagonistic pairs are mapped to a preset interaction effect intensity comparison table to obtain the synergistic adjustment coefficient and antagonistic adjustment coefficient of the trace element parameter pairs. Based on the synergistic adjustment coefficient and the antagonistic adjustment coefficient, the influence weights are corrected to obtain the optimized influence weights of the trace element parameters.

[0010] In a preferred embodiment, classifying the trace element parameter pairs in the potential interaction pair set into subsets of synergistic and antagonistic pairs based on the influence of the trace element parameters on bioactivity includes: Historical water quality monitoring data and corresponding biological activity index data of the recirculating aquaculture area are obtained to establish a dataset for analyzing the interaction effects of the trace element parameters. Based on the trace element parameter pairs in the potential interaction pair set, extract the corresponding concentration combination sequence and bioactivity index sequence from the interaction influence analysis dataset; The correlation between the concentration combination sequence and the bioactivity index sequence is evaluated to obtain the correlation determination result of the trace element parameter pair; Analyzing the statistical significance determination results, the trace element parameter pairs whose bioactivity indicators increase with the simultaneous increase of parameter concentration are classified into the synergistic effect subset, and the trace element parameter pairs whose bioactivity indicators decrease with the simultaneous increase of parameter concentration are classified into the antagonistic effect subset.

[0011] In a preferred embodiment, the formula for calculating the comprehensive water treatment efficiency index is as follows: ; In the formula, This represents the comprehensive water treatment efficiency index. This represents the optimization influence weight of the i-th trace element parameter. This represents the current concentration of the i-th trace element parameter. This represents the historical average concentration of the i-th trace element parameter obtained from the historical water quality database. This represents the historical standard deviation of the i-th trace element parameter obtained from the historical water quality database, where n represents the number of trace element parameters. This represents an exponential function used to calculate the degree of concentration decline from the historical average.

[0012] In a preferred embodiment, querying the historical threshold range corresponding to the recirculating aquaculture zone, and determining that the recirculating aquaculture zone is in an inefficient operating state when the comprehensive water treatment efficiency index is lower than the lower limit of the historical threshold range, includes: Retrieve historical threshold range parameters for the recirculating aquaculture system area; The comprehensive water treatment efficiency index is compared with the lower limit threshold in the historical threshold range parameters, and the comprehensive water treatment efficiency index below the lower limit threshold is marked as an abnormal state index. Within a fixed sliding window, the frequency and duration of consecutive occurrences of the abnormal state index are counted. When the frequency of occurrence and the duration exceed a preset threshold, the recirculating aquaculture area is determined to be in an inefficient operating state.

[0013] In a preferred embodiment, the step of screening the water quality adjustment strategies in the preset water quality adjustment strategy library that correspond to the inefficient operating state includes: Based on the type characteristics and corresponding severity of the inefficient operating state, the key features of the inefficient operating state are extracted; Match candidate adjustment strategies corresponding to the key features in the preset water quality adjustment strategy library; By reviewing the application effect records of the candidate adjustment strategies in similar aquaculture scenarios, the strategies that achieve the required application effect are selected as the water quality adjustment strategies for the recirculating aquaculture area.

[0014] To address the above problems, the present invention also provides a data processing system for water treatment efficiency in recirculating aquaculture systems, the system comprising: The data acquisition and preprocessing module is used to acquire standard water quality data for recirculating aquaculture areas; The initial weighting module is used to evaluate the degree of influence of trace element parameters in the standard water quality data on the recirculating aquaculture area, and to convert the degree of influence into the influence weights corresponding to the trace element parameters. The weight optimization module is used to adjust the influence weights based on the synergistic and antagonistic reactions between trace elements in the standard water quality data, so as to obtain the optimized influence weights of the trace element parameters. An index synthesis module is used to integrate the trace element parameters and the optimized influence weights into a comprehensive water treatment efficiency index for the recirculating aquaculture zone. The status diagnosis module is used to query the historical threshold range corresponding to the recirculating aquaculture area. When the comprehensive water treatment efficiency index is lower than the lower limit of the historical threshold range, it is determined that the recirculating aquaculture area is in an inefficient operating state. The strategy matching module is used to filter the water quality adjustment strategies in the preset water quality adjustment strategy library that correspond to the inefficient operating state.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention purifies water samples through steps such as static sedimentation and impurity interception to ensure the accuracy of standard water quality data; it determines the influencing weights by combining historical water quality and aquatic organism growth indicators, and then optimizes the weights based on the synergistic and antagonistic reactions between trace elements. Combined with scientific calculation formulas, this allows the comprehensive water treatment efficiency index to truly reflect the actual treatment effect and reduce data deviation.

[0016] 2. This invention quickly and accurately identifies inefficient operating states by comparing with historical threshold ranges and combining the frequency and duration of abnormal indices through sliding window statistics. Based on the key feature matching strategy library of inefficient states and referring to the application effects of similar scenarios to select compliant strategies, this invention not only improves data processing efficiency but also provides reliable guidance for water treatment optimization, helping aquaculture areas to operate efficiently. Attached Figure Description

[0017] Figure 1 This is a schematic flowchart of a method for processing water treatment efficiency data in recirculating aquaculture systems, provided in an embodiment of the present invention. Figure 2A functional block diagram of a recirculating aquaculture water treatment efficiency data processing system provided in an embodiment of the present invention; The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] This application provides a method for processing water treatment efficiency data in recirculating aquaculture systems. The executing entity of this method includes, but is not limited to, at least one electronic device configured to execute the method provided in this application, such as a server or a terminal. In other words, the method can be executed by software or hardware installed on a terminal device or a server-side device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cluster of cloud servers. The server can be an independent server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0020] Reference Figure 1 The diagram shown is a flowchart illustrating a method for processing water treatment efficiency data in recirculating aquaculture systems according to an embodiment of the present invention. In this embodiment, the method includes: S1. Obtain standard water quality data for the recirculating aquaculture zone; In this embodiment of the invention, obtaining standard water quality data for the recirculating aquaculture area includes: The original water sample from the recirculating aquaculture area was subjected to static sedimentation treatment to obtain a preliminary treated water sample from the recirculating aquaculture area. By retaining the tiny suspended particles and colloidal substances in the pre-treated water sample, a purified water sample from the recirculating aquaculture area is obtained. Qualitative and quantitative analysis of trace elements in the purified water sample was performed to obtain the types and corresponding concentration data of trace elements in the purified water sample. By integrating the types and corresponding concentration data of the trace elements, standard water quality data for the recirculating aquaculture area are obtained.

[0021] Select a clean, impurity-free glass container with a smooth, scratch-free surface that will not chemically react with the water sample, ensuring the sample remains uncontaminated. Slowly scoop the original water sample from the middle layer of the recirculating aquaculture area, keeping the container tilted during scooping to allow the water to flow slowly along the container wall, avoiding stirring the sediment at the bottom. This ensures the collected original water sample accurately reflects the water quality of the aquaculture area. Place the glass container containing the original water sample in a cool, well-ventilated environment away from vibration sources and direct sunlight to prevent temperature changes or vibrations from affecting the settling of suspended particles. Do not move the container or stir the water sample during placement, allowing it to naturally stabilize and allowing gravity to gradually settle large suspended particles to the bottom of the container. Continue to let it stand until the liquid on the top of the container becomes clear and transparent with no obvious suspended particles floating. At this point, a layer of sediment has formed at the bottom. Slowly use a clean glass pipette to draw up the clear liquid on the top of the container. This liquid is the preliminary treated water sample for the recirculating aquaculture area. During the drawing process, avoid touching the sediment at the bottom of the container with the pipette to prevent the sediment from mixing back into the liquid and affecting the treatment effect.

[0022] An organic ceramic composite ultrafiltration membrane is used as the retention medium. This ultrafiltration membrane has a uniform pore structure, which can effectively block the passage of small suspended particles and colloidal substances. It is also chemically stable and will not react with the components in the water sample. Before use, the ultrafiltration membrane is rinsed with clean water. During rinsing, the water flows slowly over one side of the membrane to remove any residual impurities or dust on the membrane surface, ensuring that the membrane's retention performance is not affected. The pre-treated water sample is poured into the storage tank of a dedicated filtration device. This filtration device is tightly connected to the ultrafiltration membrane, and the bottom of the storage tank has a flow channel to guide the water sample to flow evenly across the surface of the ultrafiltration membrane. The flow valve of the filtration device is opened, allowing the pre-treated water sample to generate a stable flow rate under its own gravity, slowly flowing through the ultrafiltration membrane. Water molecules and small molecules in the water sample, because their particle size is smaller than the membrane pore size, can pass smoothly through the pores of the ultrafiltration membrane. However, small suspended particles and colloidal substances in the pre-treated water sample, because their particle size is larger than the membrane pore size, are blocked on the surface of the ultrafiltration membrane and cannot pass through the pores. During the filtration process, the filtration rate is monitored in real time. If a significant slowdown in flow rate is observed, it indicates that too many impurities are trapped on the membrane surface. In this case, the flow diversion valve is closed, filtration is stopped, and the membrane is backwashed with clean water from the other side to remove any remaining tiny suspended particles and colloidal substances. The flow diversion valve is then reopened to continue filtration until all pre-treated water samples have been filtered. The clear liquid flowing out of the device outlet after ultrafiltration is collected; this liquid is the purified water sample from the recirculating aquaculture area. The collection container is also cleaned to prevent secondary contamination.

[0023] Atomic absorption spectrophotometry was used to detect trace elements in purified water samples. The detection device included a sample introduction system, an atomizer, a monochromatic light generator, a detector, and a data recording unit. First, qualitative detection was performed. The purified water sample was injected into the sample container of the sample introduction system. The system slowly and evenly transported the water sample to the atomizer using a peristaltic conveying method. The atomizer heated the water sample electrically, causing the water to evaporate rapidly. The remaining solid components were further heated to an atomized state, transforming into ground-state atomic vapor. The monochromatic light generator emitted monochromatic light of continuous wavelengths. This monochromatic light passed through the ground-state atomic vapor region within the atomizer. Different types of trace elements selectively absorbed specific wavelengths of monochromatic light, causing changes in the intensity of the monochromatic light. The detector captured this wavelength-specific absorption signal and transmitted it to the data recording unit. By comparing the signal with the characteristic absorption wavelengths of known trace elements, the types of trace elements present in the purified water sample could be determined. After qualitative detection, quantitative detection is performed while maintaining constant operating conditions such as atomizer temperature and monochromatic light intensity. High-purity standard substances corresponding to the detected trace elements are selected, and a series of standard solutions with different concentrations are prepared. Following the same delivery method as for the purified water sample, each standard solution is sequentially injected into the injection system. The monochromatic light absorption intensity of each standard solution is measured, and the data recording unit records the concentration of the standard solution and its corresponding absorption intensity, establishing a clear correspondence. The purified water sample is then injected into the injection system again, and its corresponding absorption intensity is measured. The correspondence between this absorption intensity and the standard solution is compared, and the specific concentration of the trace element in the purified water sample is determined based on the matching of absorption intensities. Following the same operating procedure, the quantitative detection of all qualitatively identified trace elements is completed sequentially, ultimately obtaining the types and corresponding concentrations of trace elements in the purified water sample. Throughout the entire detection process, the injection volume is kept stable, and the operating steps are consistent to avoid inaccurate results due to operational differences.

[0024] The trace elements obtained from qualitative and quantitative detection were listed one by one and organized systematically according to the natural classification rules of elements. First, metallic trace elements were sorted, followed by non-metallic trace elements, ensuring that each detected trace element was included in the sorting scope without omissions or duplicates. For each listed trace element, its corresponding concentration data was linked to its name, clearly labeling the specific name and corresponding concentration of each element during the recording process to avoid data misalignment or name confusion. A comprehensive review of the linked element types and concentration data was conducted, verifying each original record from the detection process to confirm the accurate labeling of each trace element's name and the absence of spelling errors. The concentration data records were also checked to ensure consistency with the original signals transmitted by the detector, guaranteeing accurate data recording without alterations or miswriting. Any problems discovered during the review process were promptly corrected to ensure the accuracy and completeness of all data. After verification, the types and corresponding concentrations of trace elements are compiled and summarized in a unified manner. The summary follows the organized classification order, clearly presenting the name and specific content of each element, forming a complete and systematic dataset. This dataset serves as the standard water quality data for the recirculating aquaculture area. This data comprehensively covers all trace element information detected in the purified water samples, accurately reflecting the composition and content of trace elements in the aquaculture area's water quality, and providing reliable basic data support for subsequent water quality assessment, aquaculture environment control, and other work.

[0025] The beneficial effects are as follows: Through standardized raw water sample collection and sedimentation, large suspended particles in the water are effectively removed, resulting in a pre-treated water sample with stable composition and no obvious impurities, laying a pure foundation for subsequent purification steps. Utilizing the precise retention effect of the organic ceramic composite ultrafiltration membrane, tiny suspended particles and colloidal substances in the pre-treated water sample are efficiently separated, significantly improving water cleanliness and obtaining a purer purified water sample, avoiding interference from impurities in subsequent test results. Atomic absorption spectrophotometry is used for qualitative and quantitative detection of trace elements. By strictly controlling the testing conditions and standardizing the operating procedures, accurate identification and precise determination of the types and concentrations of trace elements in the purified water sample are achieved, ensuring the authenticity and reliability of the test data. Through orderly organization, correlation verification, and systematic summarization of the test data, complete and comprehensive standard water quality data for recirculating aquaculture areas are formed. This data clearly presents the composition and content of trace elements in the water, providing a scientific basis for water quality evaluation, environmental control, and aquaculture management in aquaculture areas, ensuring the stability and safety of the recirculating aquaculture environment, and contributing to the healthy development of the aquaculture industry.

[0026] S2. Evaluate the degree of influence of the trace element parameters in the standard water quality data on the recirculating aquaculture area, and convert the degree of influence into the influence weight corresponding to the trace element parameters; In this embodiment of the invention, the step of assessing the influence of trace element parameters in the standard water quality data on the recirculating aquaculture area, and converting the influence degree into the influence weight corresponding to the trace element parameters, includes: The properties and concentration data of trace elements in the standard water quality data are integrated into the trace element parameters of the standard water quality data; The trace element parameters are mapped to the historical water quality database of the recirculating aquaculture area to obtain historical concentration change data of the trace element parameters and corresponding growth index data of the cultured organisms; Based on the correlation between the historical concentration change data and the corresponding growth index data of aquaculture organisms, the correlation coefficient of the trace element parameters is determined; Match the influence degree corresponding to the correlation coefficient in the preset influence degree mapping library, and convert the influence degree into the influence weight corresponding to the trace element parameter.

[0027] The formula for calculating the influence weight is as follows: ; In the formula, This indicates the influence weight. Indicates the first The influence degree value of each of the aforementioned trace element parameters. Indicates the first The influence degree value of each of the aforementioned trace element parameters. This represents the arithmetic mean of the values ​​indicating the degree of influence of the trace element parameters. This represents a preset scaling factor used to control the relative scaling of the degree of influence. This represents the preset distribution shape adjustment factor used to adjust the sensitivity of the weights to bias. The standard deviation of the values ​​representing the influence of the trace element parameters is represented by n, where n represents the number of trace element parameters. The exponential function representing the nonlinear decay characteristics used to construct the weights. This represents the absolute value function used to measure the deviation of the influence value from the average value.

[0028] All trace element information recorded in the standard water quality data was reviewed, and the attribute content of each trace element was extracted one by one. These attributes include fixed characteristics such as the element's chemical category, biological functional characteristics, and its form in aquaculture water, ensuring that the attribute information of each element is complete and without omission of key features. The extracted attribute information of each trace element was then correlated with the corresponding concentration data of that element in the standard water quality data, using the element name as the sole basis for correlation to avoid confusion between the attributes and concentration data of different elements. The correlated information was then structured, establishing independent information units for each trace element. Each information unit clearly presents the complete attribute content and corresponding concentration data of the element, ensuring a one-to-one correspondence between attributes and concentration data, without misalignment or duplication. All the organized trace element information units were then summarized and integrated to form trace element parameters in a unified format. These parameters fully cover the attributes and corresponding concentration data of each trace element, and the format of each information unit is consistent, facilitating subsequent data processing and analysis.

[0029] The storage structure of the historical water quality database is clearly defined. This database contains water quality testing data from recirculating aquaculture areas at different times and corresponding growth records of cultured organisms. The water quality testing data includes concentration information of various trace elements, and the growth records contain growth indicators such as weight gain, survival rate, and health status scores of the cultured organisms. All data is stored in chronological order. Using the name of each trace element as a search keyword, a precise search is initiated in the historical water quality database to find all historical water quality records that perfectly match each element name. For each retrieved historical water quality record, the concentration data corresponding to that element is extracted, and the corresponding testing time point is recorded. Simultaneously, the growth indicator data of the cultured organisms that perfectly match the time point is extracted from the growth records of the cultured organisms in the historical database, ensuring that the concentration data and growth indicator data correspond precisely in the time dimension without any time deviation. All historical concentration data for each element are arranged in chronological order of detection time to form historical concentration change data for that element. At the same time, the corresponding growth index data are arranged in the same chronological order to form a one-to-one correlation set with the historical concentration change data. Finally, the historical concentration change data and the corresponding growth index data of aquaculture organisms for each trace element parameter are obtained.

[0030] Historical concentration change data for each trace element and corresponding growth index data for aquaculture organisms were synchronously arranged in chronological order to ensure that each time point's concentration data had a unique corresponding growth index data. The concentration data and growth index data for each time point were compared and analyzed one by one. It was observed whether the corresponding growth index of aquaculture organisms showed an increasing or decreasing trend when the trace element concentration increased, and whether the growth index changed accordingly when the trace element concentration decreased. The number of times the concentration change and growth index change were synchronized was counted, and the proportion of synchronized changes to the total number of data records was calculated. A high proportion indicates a strong correlation between the concentration change of the trace element and the change in the growth index of aquaculture organisms; a medium proportion indicates a moderate correlation; and a low proportion indicates a weak correlation. Based on the correlation strength corresponding to the above proportions, the correlation coefficient for each trace element parameter was determined. A strong correlation corresponds to a high correlation coefficient, a moderate correlation corresponds to a medium correlation coefficient, and a weak correlation corresponds to a low correlation coefficient. The entire process, through one-by-one comparison, statistics, and analysis of the data, ensured that the correlation coefficient accurately reflected the correlation between trace element concentration and the growth index of aquaculture organisms.

[0031] The preset influence level mapping library is a pre-constructed structured dataset that stores the correspondence between different correlation coefficients and influence levels, as well as the specific influence weight standard for each influence level. A higher correlation coefficient corresponds to a stronger influence level, and a stronger influence level corresponds to a larger influence weight. All correspondences and weight standards are clearly defined and fixed rules, without ambiguity. Using the correlation coefficient determined in step three as the retrieval basis, a precise match is performed in the preset influence level mapping library to find the influence level description that perfectly corresponds to the correlation coefficient, ensuring that the matching result is unique and accurate. Following the conversion rules set in the preset influence level mapping library, the matched influence levels are directly converted into corresponding influence weights. The conversion process strictly follows the fixed standards in the mapping library without any additional adjustments. For example, a strong influence level corresponds to a high weight value, a medium influence level corresponds to a medium weight value, and a weak influence level corresponds to a low weight value. Through the above matching and conversion operations, the influence weight corresponding to each trace element parameter is finally obtained. This influence weight can quantitatively reflect the magnitude of the influence of trace elements on the growth indicators of cultured organisms.

[0032] The influence weight to be determined; and It is the influence degree value of each trace element parameter, which is the result obtained from the previous process of converting the influence degree into influence weight; It is the arithmetic mean of the influence values ​​of all trace element parameters, calculated by adding the influence values ​​of all trace element parameters and then dividing by the number of trace element parameters. get; It is a pre-set scaling factor used to control the relative scaling of the degree of influence; It is a pre-defined distribution shape adjustment factor used to adjust the sensitivity of the weights to deviations; This is the standard deviation of the influence values ​​of trace element parameters. First, calculate the standard deviation of each influence value relative to the standard deviation of the trace element parameter. Sum of squared differences, divided by The square root is obtained later; The quantity of trace element parameters is determined by the types of trace elements actually detected.

[0033] This formula is used to calculate the first... The influence weight of trace element parameters When calculating, first calculate the numerator, that is, the first... The degree of influence of trace element parameters and The ratio is raised to the power of k, and then multiplied by an exponential function, the exponent of which is... Multiply and The absolute value of the deviation divided by Next, calculate the denominator for all... Calculate the trace element parameters from 1 to n for each... and The ratio is raised to the kth power, multiplied by the corresponding exponential function, and then summed; finally, the numerator is divided by the denominator to obtain the k-th... The influence weight of each trace element parameter is used to quantify the proportion of each trace element parameter's influence on relevant aquaculture indicators.

[0034] When the The degree of influence of trace element parameters and The larger the absolute value of the deviation, and When the value is large, the exponential function in the molecule decays more significantly. The smaller; when The closer , The larger the relative size. When it increases, if Greater than The value of this part in the molecule increases. Increase, and vice versa. The larger the value, the smaller the absolute value of the exponential portion for the same deviation, and the slower the decay. The differences are relatively reduced.

[0035] The beneficial effects include: systematically sorting through trace element information in standard water quality data, accurately extracting the attribute characteristics of each element and correlating them with corresponding concentration data, and structurally organizing them into standardized trace element parameters. This ensures the completeness and accuracy of the parameter information, providing a standardized data foundation for subsequent data comparison and analysis. By using trace element names as search keywords, precise searches are conducted in historical water quality databases, simultaneously extracting historical concentration data and aquaculture organism growth index data for the corresponding periods. This achieves precise matching of the two types of data in the time dimension, providing comprehensive and realistic historical data support for exploring the correlation between trace elements and aquaculture organism growth. By arranging historical concentration change data and aquaculture organism growth index data synchronously in chronological order, and comparing and analyzing the data at each time point, the synchronous changes of the two are statistically analyzed, and the correlation coefficient is determined. This ensures that the coefficient can truly and objectively reflect the closeness of the correlation between trace element concentration and aquaculture organism growth, providing a reliable basis for quantifying the magnitude of the impact. By using a pre-defined structured impact degree mapping library, precise matching is performed based on the correlation coefficient. The impact degree is converted into corresponding impact weights according to fixed rules, thereby quantifying the magnitude of the impact of trace elements. The resulting impact weights are accurate and consistent, providing a scientific reference for management decisions such as water quality control and aquaculture program optimization in recirculating aquaculture areas. This helps improve the pertinence and effectiveness of aquaculture management and ensures the healthy growth of aquaculture organisms.

[0036] S3. Based on the synergistic and antagonistic reactions between trace elements in the standard water quality data, adjust the influence weights to obtain the optimized influence weights of the trace element parameters; In this embodiment of the invention, adjusting the influence weights based on the synergistic and antagonistic reactions between trace elements in the standard water quality data to obtain the optimized influence weights of the trace element parameters includes: The trace element parameters in the standard water quality data are analyzed to identify the trace element parameter pairs that interact with each other, and a set of potential interaction pairs of the trace element parameters is generated. Based on the influence of the trace element parameters on biological activity, the trace element parameter pairs in the potential interaction pair set are classified into synergistic pair subsets and antagonistic pair subsets. The trace element parameter pairs in the subset of synergistic pairs and the subset of antagonistic pairs are mapped to a preset interaction effect intensity comparison table to obtain the synergistic adjustment coefficient and antagonistic adjustment coefficient of the trace element parameter pairs. Based on the synergistic adjustment coefficient and the antagonistic adjustment coefficient, the influence weights are corrected to obtain the optimized influence weights of the trace element parameters.

[0037] The method of classifying trace element parameter pairs in the potential interaction pair set into synergistic and antagonistic subsets based on the influence of the trace element parameters on biological activity includes: Historical water quality monitoring data and corresponding biological activity index data of the recirculating aquaculture area are obtained to establish a dataset for analyzing the interaction effects of the trace element parameters. Based on the trace element parameter pairs in the potential interaction pair set, extract the corresponding concentration combination sequence and bioactivity index sequence from the interaction influence analysis dataset; The correlation between the concentration combination sequence and the bioactivity index sequence is evaluated to obtain the correlation determination result of the trace element parameter pair; Analyzing the statistical significance determination results, the trace element parameter pairs whose bioactivity indicators increase with the simultaneous increase of parameter concentration are classified into the synergistic effect subset, and the trace element parameter pairs whose bioactivity indicators decrease with the simultaneous increase of parameter concentration are classified into the antagonistic effect subset.

[0038] All trace element parameters in the standard water quality data were analyzed, clarifying the attribute characteristics and corresponding concentration data of each parameter to ensure complete extraction of all parameter information without omissions or information biases. All trace element parameters were paired to form all possible parameter combinations, adhering to the principles of no repetition and no omission during the combination process to ensure that each pair of different trace element parameters forms a unique parameter pair. Based on known fundamental theories of trace element interactions and relevant research findings in recirculating aquaculture systems, the chemical properties, biological functions, and forms of the two trace elements in each parameter pair were analyzed to determine the possibility of interactions such as chemical reactions, absorption competition, and metabolic linkages. Simultaneously, the concentration change trends of the two trace elements in the standard water quality data were referenced. If the concentrations of the two elements showed a synchronous increase, synchronous decrease, or inverse change at different detection periods, it further corroborated the possibility of their interaction. All parameter pairs confirmed to have interactions after theoretical analysis and data trend verification were selected and compiled into a set of potential interaction pairs of trace element parameters, with the name of each interacting trace element parameter clearly labeled in the set.

[0039] The core evaluation indicators of bioactivity were clearly defined, including key indicators related to the survival and growth of cultured organisms such as growth rate, weight gain, survival rate, immunity level, and physiological metabolic efficiency. For each pair of trace element parameters in the potential interaction pair set, data on the physiological metabolic mechanisms of recirculating aquaculture organisms were consulted to analyze the comprehensive impact of the co-existence of the two trace elements on the above bioactivity indicators. If the effect of the two trace elements acting together on bioactivity is greater than the sum of the effects of each trace element acting alone, or the effect on inhibiting bioactivity is less than the sum of the effects of each trace element acting alone, then the parameter pair is determined to be a synergistic pair. If the effect of the two trace elements acting together on bioactivity is less than the sum of the effects of each trace element acting alone, or the effect on inhibiting bioactivity is greater than the sum of the effects of each trace element acting alone, or even if one trace element weakens the original effect of the other trace element on bioactivity, then the parameter pair is determined to be an antagonistic pair. All parameter pairs identified as synergistic are grouped into a synergistic pair subset, and all parameter pairs identified as antagonistic are grouped into an antagonistic pair subset, ensuring that each parameter pair can accurately correspond to the corresponding subset without any classification errors.

[0040] The pre-defined interaction effect intensity comparison table is a standardized data table constructed based on extensive experimental data from recirculating aquaculture systems and research findings on trace element interactions. The table clearly lists common trace element parameter pairs, their corresponding action types, interaction effect intensity levels, and specific adjustment coefficients for each intensity level. The interaction effect intensity levels in the comparison table are categorized according to the significance of the interaction between the two trace elements on biological activity, with different levels set sequentially from weak to strong. Each level corresponds to a fixed, non-negative adjustment coefficient, and the adjustment coefficients for synergistic and antagonistic effects are listed separately in the table with clear boundaries. For each parameter pair in the synergistic effect subset, a precise search is performed in the pre-defined interaction effect intensity comparison table using both parameter pair name and synergistic effect type as dual search criteria. Once a completely matching entry is found, the corresponding adjustment coefficient is extracted, which is the synergistic adjustment coefficient for that trace element parameter pair. For each parameter pair in the antagonistic effect subset, a precise search is performed in the pre-defined interaction effect intensity comparison table using both parameter pair name and antagonistic effect type as dual search criteria. Once a completely matching entry is found, the corresponding adjustment coefficient is extracted, which is the antagonistic adjustment coefficient for that trace element parameter pair. If a parameter pair does not have a completely matching entry in the lookup table, the corresponding adjustment coefficient is determined based on the properties and mechanisms of action of the two elements in the parameter pair, referring to the adjustment coefficients of parameter pairs with similar properties and similar modes of action in the lookup table, to ensure that each parameter pair can obtain a clear synergistic adjustment coefficient or antagonistic adjustment coefficient.

[0041] Extract the influence weights of each trace element parameter obtained in the previous steps and use them as the initial influence weights before correction, ensuring the accuracy of the initial data and their one-to-one correspondence with the corresponding trace element parameters. For each trace element parameter, systematically examine the subset of synergistic pairs to find all synergistic pairs containing that parameter, collect the corresponding synergistic adjustment coefficients, and sum all the collected synergistic adjustment coefficients to obtain the total synergistic adjustment value for that trace element parameter. During the summation process, ensure that all relevant synergistic adjustment coefficients are included without omissions or duplicate calculations. Similarly, systematically examine the subset of antagonistic pairs to find all antagonistic pairs containing that parameter, collect the corresponding antagonistic adjustment coefficients, and sum all the collected antagonistic adjustment coefficients to obtain the total antagonistic adjustment value for that trace element parameter. The summation process strictly follows the same calculation specifications as for the synergistic adjustment value. Based on the initial influence weights, add the total synergistic adjustment value to the initial influence weights, and then subtract the total antagonistic adjustment value from the result. Through this series of numerical calculations, obtain the corrected influence weights. If a trace element parameter does not participate in any synergistic or antagonistic pairs, its total synergistic adjustment value and total antagonistic adjustment value are both zero, and the initial influence weight is directly used as the corrected influence weight. All corrected influence weights are compiled and summarized to obtain the optimized influence weight for each trace element parameter. This weight fully considers the interactions between trace elements and can more accurately reflect the actual influence of each trace element on the growth indicators of cultured organisms.

[0042] All complete water quality monitoring records and corresponding aquaculture management files from the recirculating aquaculture system (RAS) area were collected. The water quality monitoring records must cover the actual measured concentrations of each trace element at different monitoring time points; these data will serve as the core source of trace element parameters. The aquaculture management files must include bioactivity index records that completely correspond to the water quality monitoring time points, specifically including key indicators such as growth rate, weight gain, survival rate, disease resistance, and physiological function status of the aquaculture organisms. The collected historical water quality monitoring records were screened, removing invalid data that was missing, unclear, or contained significant detection errors, ensuring that the retained trace element concentration data was authentic, reliable, complete, and standardized. Simultaneously, the bioactivity index data in the aquaculture management files were verified to ensure that each water quality monitoring time point had a unique corresponding bioactivity index data, without any time misalignment or data discrepancies. The verified trace element concentration data and corresponding bioactivity index data were then systematically integrated according to the monitoring time sequence to form a three-dimensional dataset containing time, trace element parameter, and bioactivity index dimensions. This dataset constitutes the dataset for the interaction analysis of trace element parameters.

[0043] Each trace element parameter pair is extracted one by one from the potential interaction pair set, and the names of the two specific trace elements contained in each parameter pair are identified. Based on the extracted trace element parameter pairs, a targeted search is performed in the interaction influence analysis dataset to find the concentration data of the two trace elements in the parameter pair at all monitoring time points. The concentration data of the two trace elements at the same time point are paired and combined in chronological order to form a series of continuous concentration combination units. All concentration combination units are arranged in chronological order to form the concentration combination sequence of the trace element parameter pair. At the same time, bioactivity index data that completely corresponds to the above monitoring time points are extracted from the interaction influence analysis dataset. The bioactivity index data are arranged in the same chronological order to form the bioactivity index sequence corresponding to the trace element parameter pair, ensuring that the concentration combination sequence and the bioactivity index sequence are completely synchronized in the time dimension, and that each concentration combination unit has a unique corresponding bioactivity index data.

[0044] A time-point synchronous comparative analysis was performed on the concentration combination sequence and the bioactivity index sequence. First, the direction of change in the concentrations of the two trace elements in each concentration combination unit at each time point was observed to determine whether they increased simultaneously, decreased simultaneously, or one increased while the other decreased. Then, the direction of change in the bioactivity index data at the corresponding time point was recorded to determine whether it increased, decreased, or remained stable. The matching between the direction of change in the concentrations of the two trace elements and the direction of change in the bioactivity index was statistically analyzed across all time points, and the proportion of time points where the concentration changes and bioactivity index changes showed a synchronous trend was calculated out of the total number of monitoring time points. Combining this proportion with the correlation between the magnitude of change in the concentrations of the two trace elements and the magnitude of change in the bioactivity index, the strength of the correlation between the trace element parameter pair and the bioactivity index was comprehensively judged. If the proportion of synchronous changes was high and the magnitude of change was significantly correlated, it was determined to be a strong correlation; if the proportion of synchronous changes was moderate and the magnitude of change was somewhat correlated, it was determined to be a moderate correlation; if the proportion of synchronous changes was low and the magnitude of change was not significantly correlated, it was determined to be a weak correlation. Finally, the correlation determination result for each trace element parameter pair was formed.

[0045] The correlation determination results for each trace element parameter pair were analyzed one by one, with a focus on strongly and moderately correlated parameter pairs. Weakly correlated parameter pairs were not included in the subset division due to insufficient correlation. For strongly or moderately correlated trace element parameter pairs, the changing trends of the concentrations of the two trace elements in their concentration combination sequence and the changing trends of the corresponding bioactivity index sequence were further analyzed. If the concentrations of the two trace elements simultaneously increased at most monitoring time points, and the corresponding bioactivity index data also showed a significant increasing trend, that is, the bioactivity index increased with the simultaneous increase of parameter concentration, it indicates that the two trace elements in this parameter pair have a mutually promoting effect on bioactivity, and this trace element parameter pair was classified into the synergistic effect pair subset. If the concentrations of two trace elements increase simultaneously at most monitoring time points, but the corresponding bioactivity index data show a significant decreasing trend, that is, the bioactivity index decreases as the parameter concentration increases, it indicates that the two trace elements in this parameter pair have a mutually inhibitory effect on bioactivity. This trace element parameter pair should be classified into the antagonistic pair subset. During the classification process, it should be ensured that each parameter pair that meets the conditions can be accurately classified into the corresponding subset without omission or classification error.

[0046] The beneficial effects are as follows: By comprehensively reviewing trace element parameters and conducting pairwise analysis, and combining theory with data trends, we can accurately identify parameter pairs with interactions, generate a set of potential interaction pairs, and systematically mine the relationships between trace elements, providing a complete data foundation for subsequent analysis. By clarifying bioactivity evaluation indicators and based on physiological metabolic mechanisms and element effects, potential interaction pairs are precisely classified into synergistic and antagonistic subsets, making the interaction types between elements clear and providing a targeted basis for subsequent adjustment of influence weights. By pre-setting a reference table containing the correspondence between interaction effect strength and adjustment coefficients, precise matching is performed based on parameter pair names and action types to obtain clear synergistic and antagonistic adjustment coefficients, realizing the quantification of interaction effects and providing accurate and unified numerical support for correcting influence weights. By integrating synergistic and antagonistic adjustment coefficients, the initial influence weights are precisely corrected to obtain optimized influence weights. These weights fully consider the interactions between trace elements and can more realistically and accurately reflect the actual impact of each trace element on the growth indicators of cultured organisms. This provides a more scientific and targeted basis for management decisions such as water quality control and optimization of aquaculture programs in recirculating aquaculture areas, helping to improve the effectiveness of aquaculture management and the healthy growth level of cultured organisms.

[0047] S4. The trace element parameters and the optimized influence weights are integrated into the comprehensive water treatment efficiency index of the recirculating aquaculture area. In this embodiment of the invention, the formula for calculating the comprehensive water treatment efficiency index is as follows: ; In the formula, This represents the comprehensive water treatment efficiency index. This represents the optimization influence weight of the i-th trace element parameter. This represents the current concentration of the i-th trace element parameter. This represents the historical average concentration of the i-th trace element parameter obtained from the historical water quality database. This represents the historical standard deviation of the i-th trace element parameter obtained from the historical water quality database, where n represents the number of trace element parameters. This represents an exponential function used to calculate the degree of concentration decline from the historical average.

[0048] The desired comprehensive water treatment efficiency index; It is the first The optimization influence weight of each trace element parameter comes from the step of correcting the influence weight; It is the first The current concentration of each trace element parameter is obtained by detecting the current water sample in the recirculating aquaculture area; It is the first The historical average concentration of a trace element parameter is obtained by extracting all historical concentration data of that element from the historical water quality database, adding them together, and then dividing by the number of data points. It is the first The historical standard deviation of each trace element parameter is first calculated, along with the historical concentration of that element. The sum of squared differences is obtained by dividing by the number of data points and then taking the square root. The quantity of trace element parameters is determined by the types of trace elements actually detected.

[0049] This formula is used to calculate the comprehensive water treatment efficiency index of recirculating aquaculture systems. During the calculation, for each trace element parameter... First calculate its current concentration. Compared with historical average concentration The square of the difference, divided by twice the historical standard deviation. The square of the result, then the negative value, is used as the exponent of the exponential function; the result of this exponential function is then combined with the optimization influence weight of the element. Multiply the results; finally, add up the calculated results of all trace element parameters to obtain the comprehensive water treatment efficiency index. This study aims to comprehensively measure the overall impact of various trace element parameters on the water treatment efficiency of recirculating aquaculture areas, reflecting the degree of comprehensive effect on water treatment efficiency when the current concentration of trace elements in the water deviates from the historical average level.

[0050] When the current concentration of a certain trace element parameter The closer to its historical average concentration The closer the result of the exponential function is to 1, the better the element is to the desired value. The closer the contribution is to its optimization influence weight ;like Deviation The more elements there are, the more pronounced the decay of the exponential function's result becomes; the more the element affects the... The smaller the contribution, the better. Optimize the influence weights. The larger the element, the greater its concentration deviation from the equilibrium value. The greater the impact, the better. When the current concentrations of multiple elements are close to their historical average concentrations, A higher value indicates better overall water treatment efficiency; if the concentrations of multiple elements deviate significantly from the historical average concentration, A lower value indicates poor overall water treatment efficiency.

[0051] S5. Query the historical threshold range corresponding to the recirculating aquaculture area. When the comprehensive water treatment efficiency index is lower than the lower limit of the historical threshold range, it is determined that the recirculating aquaculture area is in an inefficient operating state. In this embodiment of the invention, querying the historical threshold range corresponding to the recirculating aquaculture zone, and determining that the recirculating aquaculture zone is in an inefficient operating state when the comprehensive water treatment efficiency index is lower than the lower limit of the historical threshold range, includes: Retrieve historical threshold range parameters for the recirculating aquaculture system area; The comprehensive water treatment efficiency index is compared with the lower limit threshold in the historical threshold range parameters, and the comprehensive water treatment efficiency index below the lower limit threshold is marked as an abnormal state index. Within a fixed sliding window, the frequency and duration of consecutive occurrences of the abnormal state index are counted. When the frequency of occurrence and the duration exceed a preset threshold, the recirculating aquaculture area is determined to be in an inefficient operating state.

[0052] We reviewed past water quality management records, monitoring data reports, and aquaculture operation records for the recirculating aquaculture system (RAS) area to determine the storage location of historical threshold range parameters. These parameters are based on statistical analysis of the comprehensive water treatment efficiency index (CHI) data under long-term stable aquaculture conditions. We collected historical CHI data from different seasons and aquaculture stages over several years, eliminating extreme anomalies caused by equipment failures, sudden pollution, or other special circumstances to ensure that all historical data used for statistics came from normal aquaculture operation scenarios. Statistical analysis methods were used to organize the filtered historical data, calculating the central tendency and dispersion to determine the normal fluctuation range of the CHI. The lower threshold is the minimum critical value to ensure normal growth of aquaculture organisms and effective operation of the water treatment system, while the upper threshold is the optimal critical value for efficient operation of the water treatment system. These two thresholds were integrated to form a complete historical threshold range parameter, ensuring that the parameters accurately reflect the efficiency standards under normal aquaculture conditions.

[0053] All comprehensive water treatment efficiency indices calculated using the formula are arranged sequentially according to monitoring time, forming a continuous index time series. Each index corresponds to a specific monitoring time point, ensuring completeness in the time dimension. A clear lower limit threshold is extracted from historical threshold range parameters and used as the standard line for judging whether an index is abnormal. A point-by-point comparison method is used to compare the value of each comprehensive water treatment efficiency index in the index time series with the lower limit threshold. When the value of a comprehensive water treatment efficiency index is lower than the lower limit threshold, an abnormal state is immediately marked in the corresponding record, and the monitoring time and specific value of the abnormal index are recorded in detail to avoid missing any abnormal data points. All indices marked as abnormal are collected and organized into an abnormal state index set, clearly presenting the core information of each abnormal state index, providing a standardized data foundation for subsequent statistical analysis.

[0054] Based on the water quality monitoring frequency and water quality change patterns in the recirculating aquaculture system (RAS) area, a fixed-duration sliding window is established. The window duration must cover a sufficient monitoring period to ensure the capture of continuous abnormal trends while avoiding statistical lag due to excessively long windows. The sliding window moves continuously, with each step consistent with the water quality monitoring period. That is, after completing the statistical analysis of the current window, the window moves forward by one monitoring period to cover the next segment of continuous monitoring data. Within each sliding window, the comprehensive water treatment efficiency index records for that time period are checked one by one. By comparing these records with the abnormal state index set, all abnormal state indices within the window's time range are identified. To determine if an abnormal state index occurs consecutively, the monitoring period following the previous abnormal state index is checked to see if it is still an abnormal state index. If there is no normal index interval in between, it is considered consecutive. The total number of consecutive occurrences of abnormal state indices within the window is counted, which is the consecutive occurrence frequency. Simultaneously, record the occurrence time of the first abnormal state index and the occurrence time of the last abnormal state index within the window, calculate the time difference between the two, and obtain the continuous duration of the abnormal state index. Accurately record the continuous occurrence frequency and duration of each window to form a statistical ledger.

[0055] Based on the actual aquaculture conditions in the recirculating aquaculture zone, and referring to the tolerance limits of cultured organisms to water quality efficiency, the minimum design operating efficiency standards of water treatment equipment, and historical abnormal statistics on inefficient operation, scientifically set preset thresholds, including preset thresholds for the frequency of consecutive occurrences and preset thresholds for the duration of occurrences. This ensures that the preset thresholds can promptly identify genuine inefficient operating states without misjudging due to overly strict standards. The frequency of consecutive occurrences and the duration of abnormal state indices for each sliding window are extracted from the statistical ledger and compared with the corresponding preset thresholds. When the frequency of consecutive occurrences within a sliding window exceeds the preset frequency threshold, and the duration within that window also exceeds the preset time threshold, the recirculating aquaculture zone is directly determined to be in an inefficient operating state. This criterion ensures that only continuous and frequent abnormalities are identified as inefficient, avoiding misjudgments caused by short-term, occasional abnormalities. If only one threshold condition is met, it is judged as a temporary abnormal fluctuation and is not included in the inefficient operating state. After the determination, the start time, end time, and corresponding abnormal statistical data of the inefficient operating state are recorded in detail to form a complete determination report, providing a clear basis for subsequent system adjustments and water quality optimization.

[0056] The beneficial effects include: by sorting through historical data, screening normal data, and conducting statistical analysis, accurate and reliable historical threshold range parameters are obtained, providing a scientific standard for judging anomalies in the comprehensive water treatment efficiency index. By comparing the comprehensive water treatment efficiency index with the lower limit threshold point by point, abnormal state indices are accurately marked and aggregated, achieving comprehensive identification and data collection of potential risks of inefficiency. By setting a sliding window that fits the pattern of water quality changes and moving the statistics, the frequency and duration of continuous occurrence of abnormal state indices are accurately captured, providing a quantitative basis for judging the trend of inefficient operation. By scientifically setting preset thresholds in combination with actual aquaculture conditions, the statistical results of the sliding window can be accurately compared, enabling timely and accurate determination of whether the recirculating aquaculture area is in an inefficient operating state, avoiding misjudgments or omissions, providing clear guidance for subsequent water quality control and system optimization, and ensuring the stable and efficient operation of the aquaculture area and the healthy growth of aquaculture organisms.

[0057] S6. Filter the water quality adjustment strategies in the preset water quality adjustment strategy library that correspond to the inefficient operating state.

[0058] In this embodiment of the invention, the step of selecting water quality adjustment strategies from the preset water quality adjustment strategy library that correspond to the inefficient operating state includes: Based on the type characteristics and corresponding severity of the inefficient operating state, the key features of the inefficient operating state are extracted; Match candidate adjustment strategies corresponding to the key features in the preset water quality adjustment strategy library; By reviewing the application effect records of the candidate adjustment strategies in similar aquaculture scenarios, the strategies that achieve the required application effect are selected as the water quality adjustment strategies for the recirculating aquaculture area.

[0059] Identify the type of inefficient operation, such as nutrient imbalance caused by a significant deviation of trace element concentrations from historical averages, equipment inefficiency due to decreased filtration efficiency of water treatment equipment, or bio-disruption caused by abnormal metabolism of aquatic organisms. Determine the severity based on the previously determined frequency and duration of occurrence; a long duration and high frequency indicate severity, while low frequency and low duration indicate mild or moderate severity. Extract key information for each type and severity. For example, in severe nutrient imbalance, identify the specific trace element with excessively low or high concentrations, the extent of deviation from historical averages, and the duration of this deviation. In severe equipment inefficiency, identify the affected water treatment equipment (e.g., filtration or aeration systems) and the specific manifestations of performance degradation, such as reduced filtration accuracy or insufficient dissolved oxygen. In severe bio-disruption, identify the species of aquatic organisms and the impact of their metabolic products on water quality, such as abnormally high levels of ammonia nitrogen and nitrite. By integrating these clearly defined type characteristics and the specific information corresponding to their severity, key characteristics of inefficient operation are formed, ensuring that each key characteristic accurately reflects the root cause and severity of inefficiency.

[0060] The pre-built water quality adjustment strategy library is a structured collection of strategies pre-constructed based on professional knowledge, successful cases, and research findings in the field of recirculating aquaculture. Each strategy entry in the library is labeled with corresponding key features, covering information such as the type of inefficiency, its severity, and specific manifestations. Using the key features extracted in the first step as search criteria, a comprehensive search is performed in the pre-built water quality adjustment strategy library. The key feature descriptions of each strategy entry in the library are compared one by one, and entries that completely match the extracted key features are found. Each matching entry is the corresponding candidate adjustment strategy. For example, if the key feature is that the concentration of a certain trace element is severely low and has lasted for a long time, the strategy library will find an entry labeled "supplement the trace element, using a slow-release method, and determine the amount to be added based on the concentration gap," and this will be used as a candidate adjustment strategy. If the key feature is that the filtration system efficiency is low and severe, the entry labeled "replace the high-precision filter membrane, increase the filtration frequency, and clean the filter media" will be found as a candidate adjustment strategy. This ensures that all candidate strategies matching the key features are extracted without omission.

[0061] We collected industry case studies, internal aquaculture records, and application effect reports from academic research in the field of recirculating aquaculture systems (RAS). These materials detailed the implementation process and effects of various water quality adjustment strategies in similar aquaculture scenarios. For each candidate adjustment strategy, we conducted targeted searches within the aforementioned materials to find aquaculture scenarios completely similar to the current RAS area in terms of aquaculture species, water volume, and inefficiency types. We examined the application effects of the candidate strategy in these scenarios, including the improvement of water quality indicators, such as whether trace element concentrations returned to normal ranges and whether the comprehensive water treatment efficiency index rebounded; the growth of cultured organisms, such as whether survival rates and growth rates improved; and the sustained effects after strategy implementation, such as the duration of water quality stabilization. We evaluated the application effects and set clear standards for achieving these standards, such as water quality indicators returning to historical normal ranges and remaining stable for more than one aquaculture cycle, and cultured organism growth indicators reaching normal levels. We screened candidate adjustment strategies one by one, and only strategies whose application effects fully met the standards were adopted as water quality adjustment strategies for the RAS area, ensuring that the selected strategies were truly effective and could solve the current inefficient operation.

[0062] The beneficial effects include: by clearly defining the specific types and severity of inefficient operation, accurately extracting key features reflecting the root causes, manifestations, and scope of impact of inefficiency, making the core information of the inefficiency problem clear and providing a precise targeting basis for subsequent matching and adjustment strategies. By pre-setting a structured adjustment strategy library covering various inefficient aquaculture scenarios and corresponding strategies, precise matching is performed using key features as the core of the search, quickly identifying candidate adjustment strategies highly suitable for the current inefficiency problem, avoiding the time wasted on blind screening, and improving the targeting and efficiency of strategy matching. By reviewing the actual application effect records of candidate adjustment strategies in similar aquaculture scenarios, and conducting rigorous screening based on clear compliance standards, it is ensured that the final selected water quality adjustment strategy has been practically verified and can effectively solve the inefficient operation problem in the current recirculating aquaculture area, effectively improve water quality, increase water treatment efficiency, ensure the healthy growth of aquaculture organisms and the stable and efficient operation of the aquaculture area, while reducing the risk of strategy implementation and improving the scientific nature and reliability of aquaculture management.

[0063] like Figure 2 The diagram shown is a functional block diagram of a recirculating aquaculture water treatment efficiency data processing system provided in an embodiment of the present invention.

[0064] The recirculating aquaculture system (RAS) water treatment efficiency data processing system 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the RAS water treatment efficiency data processing system 100 may include a data acquisition and preprocessing module 101, a weight initial assignment module 102, a weight optimization module 103, an index synthesis module 104, a state diagnosis module 105, and a strategy matching module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0065] In this embodiment, the functions of each module / unit are as follows: The data acquisition and preprocessing module 101 is used to acquire standard water quality data for the recirculating aquaculture area. The initial weighting module 102 is used to evaluate the degree of influence of trace element parameters in the standard water quality data on the recirculating aquaculture area, and convert the degree of influence into the influence weight corresponding to the trace element parameters. The weight optimization module 103 is used to adjust the influence weights based on the synergistic and antagonistic reactions between trace elements in the standard water quality data, so as to obtain the optimized influence weights of the trace element parameters. The index synthesis module 104 is used to integrate the trace element parameters and the optimized influence weights into the comprehensive water treatment efficiency index of the recirculating aquaculture area. The status diagnosis module 105 is used to query the historical threshold range corresponding to the recirculating aquaculture area. When the comprehensive water treatment efficiency index is lower than the lower limit of the historical threshold range, it is determined that the recirculating aquaculture area is in an inefficient operating state. The strategy matching module 106 is used to filter water quality adjustment strategies in the preset water quality adjustment strategy library that correspond to the inefficient operating state.

[0066] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0067] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0068] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0069] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0070] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for processing water treatment efficiency data in recirculating aquaculture systems, characterized in that, The method includes: S1. Obtain standard water quality data for the recirculating aquaculture zone; S2. Evaluate the degree of influence of the trace element parameters in the standard water quality data on the recirculating aquaculture area, and convert the degree of influence into the influence weight corresponding to the trace element parameters; S3. Based on the synergistic and antagonistic reactions between trace elements in the standard water quality data, adjust the influence weights to obtain the optimized influence weights of the trace element parameters; S4. The trace element parameters and the optimized influence weights are integrated into the comprehensive water treatment efficiency index of the recirculating aquaculture area. S5. Query the historical threshold range corresponding to the recirculating aquaculture area. When the comprehensive water treatment efficiency index is lower than the lower limit of the historical threshold range, it is determined that the recirculating aquaculture area is in an inefficient operating state. S6. Filter the water quality adjustment strategies in the preset water quality adjustment strategy library that correspond to the inefficient operating state.

2. The method for processing water treatment efficiency data in recirculating aquaculture systems as described in claim 1, characterized in that, The acquisition of standard water quality data for the recirculating aquaculture zone includes: The original water sample from the recirculating aquaculture area was subjected to static sedimentation treatment to obtain a preliminary treated water sample from the recirculating aquaculture area. By retaining the tiny suspended particles and colloidal substances in the pre-treated water sample, a purified water sample from the recirculating aquaculture area is obtained. Qualitative and quantitative analysis of trace elements in the purified water sample was performed to obtain the types and corresponding concentration data of trace elements in the purified water sample. By integrating the types and corresponding concentration data of the trace elements, standard water quality data for the recirculating aquaculture area are obtained.

3. The method for processing water treatment efficiency data in recirculating aquaculture systems as described in claim 1, characterized in that, The assessment of the impact of trace element parameters in the standard water quality data on the recirculating aquaculture system, and the conversion of the impact into the corresponding impact weights for the trace element parameters, includes: The properties and concentration data of trace elements in the standard water quality data are integrated into the trace element parameters of the standard water quality data; The trace element parameters are mapped to the historical water quality database of the recirculating aquaculture area to obtain historical concentration change data of the trace element parameters and corresponding growth index data of the cultured organisms; Based on the correlation between the historical concentration change data and the corresponding growth index data of aquaculture organisms, the correlation coefficient of the trace element parameters is determined; Match the influence degree corresponding to the correlation coefficient in the preset influence degree mapping library, and convert the influence degree into the influence weight corresponding to the trace element parameter.

4. The method for processing water treatment efficiency data in recirculating aquaculture systems as described in claim 3, characterized in that, The formula for calculating the influence weight is as follows: ； In the formula, This indicates the influence weight. Indicates the first The influence degree value of each of the aforementioned trace element parameters. Indicates the first The influence degree value of each of the aforementioned trace element parameters. This represents the arithmetic mean of the values ​​indicating the degree of influence of the trace element parameters. This represents a preset scaling factor used to control the relative scaling of the degree of influence. This represents the preset distribution shape adjustment factor used to adjust the sensitivity of the weights to bias. The standard deviation of the values ​​representing the influence of the trace element parameters is represented by n, where n represents the number of trace element parameters. The exponential function representing the nonlinear decay characteristics used to construct the weights. This represents the absolute value function used to measure the deviation of the influence value from the average value.

5. The method of claim 1, wherein the method is characterized by: The step of adjusting the influence weights based on the synergistic and antagonistic reactions between trace elements in the standard water quality data to obtain the optimized influence weights of the trace element parameters includes: The trace element parameters in the standard water quality data are analyzed to identify the trace element parameter pairs that interact with each other, and a set of potential interaction pairs of the trace element parameters is generated. Based on the influence of the trace element parameters on biological activity, the trace element parameter pairs in the potential interaction pair set are classified into synergistic pair subsets and antagonistic pair subsets. The trace element parameter pairs in the subset of synergistic pairs and the subset of antagonistic pairs are mapped to a preset interaction effect intensity comparison table to obtain the synergistic adjustment coefficient and antagonistic adjustment coefficient of the trace element parameter pairs. Based on the synergistic adjustment coefficient and the antagonistic adjustment coefficient, the influence weights are corrected to obtain the optimized influence weights of the trace element parameters.

6. The method for processing water treatment efficiency data in recirculating aquaculture systems as described in claim 5, characterized in that, The method of classifying trace element parameter pairs in the potential interaction pair set into synergistic and antagonistic subsets based on the influence of the trace element parameters on biological activity includes: Historical water quality monitoring data and corresponding biological activity index data of the recirculating aquaculture area are obtained to establish a dataset for analyzing the interaction effects of the trace element parameters. Based on the trace element parameter pairs in the potential interaction pair set, extract the corresponding concentration combination sequence and bioactivity index sequence from the interaction influence analysis dataset; The correlation between the concentration combination sequence and the bioactivity index sequence is evaluated to obtain the correlation determination result of the trace element parameter pair; Analyzing the statistical significance determination results, the trace element parameter pairs whose bioactivity indicators increase with the simultaneous increase of parameter concentration are classified into the synergistic effect subset, and the trace element parameter pairs whose bioactivity indicators decrease with the simultaneous increase of parameter concentration are classified into the antagonistic effect subset.

7. The method for processing water treatment efficiency data in recirculating aquaculture systems as described in claim 1, characterized in that, The formula for calculating the comprehensive water treatment efficiency index is as follows: ； In the formula, This represents the comprehensive water treatment efficiency index. This represents the optimization influence weight of the i-th trace element parameter. This represents the current concentration of the i-th trace element parameter. This represents the historical average concentration of the i-th trace element parameter obtained from the historical water quality database. This represents the historical standard deviation of the i-th trace element parameter obtained from the historical water quality database, where n represents the number of trace element parameters. This represents an exponential function used to calculate the degree of concentration decline from the historical average.

8. The method of claim 1, wherein the method is a method of processing data for water treatment efficiency in a recirculating aquaculture system. The step of querying the historical threshold range corresponding to the recirculating aquaculture system (RAS) area, and determining that the RAS area is in an inefficient operating state when the comprehensive water treatment efficiency index is lower than the lower limit of the historical threshold range, includes: Retrieve historical threshold range parameters for the recirculating aquaculture system area; The comprehensive water treatment efficiency index is compared with the lower limit threshold in the historical threshold range parameters, and the comprehensive water treatment efficiency index below the lower limit threshold is marked as an abnormal state index. Within a fixed sliding window, the frequency and duration of consecutive occurrences of the abnormal state index are counted. When the frequency of occurrence and the duration exceed a preset threshold, the recirculating aquaculture area is determined to be in an inefficient operating state.

9. The method for processing water treatment efficiency data in recirculating aquaculture systems as described in claim 1, characterized in that, The step of filtering the water quality adjustment strategies in the preset water quality adjustment strategy library that correspond to the inefficient operating state includes: Based on the type characteristics and corresponding severity of the inefficient operating state, the key features of the inefficient operating state are extracted; Match candidate adjustment strategies corresponding to the key features in the preset water quality adjustment strategy library; By reviewing the application effect records of the candidate adjustment strategies in similar aquaculture scenarios, the strategies that achieve the required application effect are selected as the water quality adjustment strategies for the recirculating aquaculture area.

10. A recirculating aquaculture system for processing water treatment efficiency data, used to implement the recirculating aquaculture system for processing water treatment efficiency data as described in claim 1, the system comprising: The data acquisition and preprocessing module is used to acquire standard water quality data for recirculating aquaculture areas; The initial weighting module is used to evaluate the degree of influence of trace element parameters in the standard water quality data on the recirculating aquaculture area, and to convert the degree of influence into the influence weight corresponding to the trace element parameters. The weight optimization module is used to adjust the influence weights based on the synergistic and antagonistic reactions between trace elements in the standard water quality data, so as to obtain the optimized influence weights of the trace element parameters. An index synthesis module is used to integrate the trace element parameters and the optimized influence weights into a comprehensive water treatment efficiency index for the recirculating aquaculture zone. The status diagnosis module is used to query the historical threshold range corresponding to the recirculating aquaculture area. When the comprehensive water treatment efficiency index is lower than the lower limit of the historical threshold range, it is determined that the recirculating aquaculture area is in an inefficient operating state. The strategy matching module is used to filter the water quality adjustment strategies in the preset water quality adjustment strategy library that correspond to the inefficient operating state.

Images