Seawater pond culture tail water dynamic monitoring method and system

Abstract

The invention discloses a seawater pond culture tail water dynamic monitoring method and system, and the method comprises the steps: collecting multi-region pollutant monitoring data in a culture period, and extracting a pollutant sequence according to a preset time interval; calculating a concentration growth rate based on the pollutant sequence to generate a change sequence; fusing the two types of sequence data, mining an association relationship of the two types of sequence data in different regions by using an Apriori algorithm, and marking high and low influence regions for the current region; the tail water treatment scheme of the current area and the affected area is further dynamically adjusted, the tail water treatment effect of the current area is cooperatively controlled in the area, dynamic optimization of tail water treatment is achieved, and the overall pollution treatment efficiency of the aquaculture system is improved.

Description

Technical Field

[0001] The present invention relates to the field of seawater aquaculture monitoring and regulation, and more specifically, to a method and system for dynamically monitoring the tail water of seawater pond aquaculture. Background Art

[0002] With the development of the seawater pond aquaculture industry, it faces environmental pollution and ecological risk problems caused by tail water discharge.

[0003] Traditional tail water monitoring methods often have the following defects. Pollution early warning has a lag, lacking real-time data analysis and prediction capabilities, resulting in a delayed response to pollution events, low data utilization rate, and difficulty in mining pollution correlation laws. In addition, between pond aquaculture areas, affected by tides, water currents, meteorology, and aquaculture plans, there are certain correlation and influence relationships among pollutants in aquaculture ponds. However, in the prior art, the influence process is difficult to be mined and analyzed, lacking an effective correlation analysis process. For the monitoring data and the regulation of the tail water treatment plan, it often relies on manual experience for analysis and plan setting, with low levels of intelligence and automation. Summary of the Invention

[0004] The present invention overcomes the defects of the prior art and provides a method and system for dynamically monitoring the tail water of seawater pond aquaculture.

[0005] The first aspect of the present invention provides a method for dynamically monitoring the tail water of seawater pond aquaculture, including: S101: During a breeding cycle, collect pollutant monitoring data in different breeding areas of a seawater pond; S102: Based on a preset interval, divide the breeding cycle into N time points. Based on the N time points, extract the concentration values of multiple pollutants from the pollutant monitoring data, and serialize the extracted values to obtain multiple pollutant sequence data; S103: Based on each pollutant sequence data, dynamically analyze the growth rate of the values at adjacent time points to generate change sequence data; S104: Use all pollutant sequence data and change sequence data as data items, preprocess the data items, and based on the Apriori algorithm, screen out frequent item sets from all data items, and based on a preset confidence level, construct strong association and weak association rules from the frequent item sets; S105: Select a breeding area as the current area, analyze the association relationship between data items through strong association and weak association rules, and based on the breeding area to which the data items belong, screen out the areas associated with the current area, and mark them as high-impact areas and low-impact areas respectively; S106: Set the primary tail water treatment plan for the current area, and combine the high-impact areas and low-impact areas to adjust the primary tail water treatment plan and set the tail water treatment plan for the impact areas.

[0006] In this solution, the S101 is specifically as follows: In a seawater pond, set up monitoring units based on each aquaculture area, monitor and analyze the content of various pollutants through the monitoring units, and obtain pollutant monitoring data.

[0007] In this solution, the S102 is specifically as follows: Set a preset interval, and divide the aquaculture cycle into N consecutive time points, with the interval between adjacent time points being the preset interval; Extract the concentration values of each pollutant from the pollutant monitoring data to obtain multiple data points, and perform time serialization on the multiple data points to obtain pollutant sequence data; Based on various pollutants, obtain multiple pollutant sequence data.

[0008] In this solution, the S103 is specifically as follows: Select a pollutant sequence data, calculate the growth rate for two adjacent data points, and sort the growth rate based on the time dimension to obtain change sequence data; Generate multiple change sequence data based on multiple pollutant sequence data.

[0009] In this solution, the S104 is specifically as follows: Take all pollutant sequence data and change sequence data as data items; Perform preprocessing on the data items, including data cleaning, duplicate removal, and invalid data elimination; Based on the Apriori algorithm, set the minimum support, the first confidence level, and the second confidence level; Calculate the support of each data item, and filter out the frequent item sets based on the minimum support. For each frequent item set, calculate its confidence level; Filter out the frequent item sets with a confidence level greater than the first confidence level and construct strong association rules; Filter out the frequent item sets with a confidence level greater than the second confidence level and construct weak association rules.

[0010] In this solution, the S105 is specifically as follows: Based on the tail water treatment requirements, select a aquaculture area to be treated as the current area; Through the strong association rules, retrieve the data items with strong associations in the current area, determine the aquaculture areas to which the associated data items belong, and mark the aquaculture areas as high-impact areas; Retrieve the data items with weak associations in the current area through weak association rules, determine the aquaculture areas to which the associated data items belong, and mark the aquaculture areas as low-impact areas.

[0011] In this solution, S106 is specifically as follows: Based on the pollutant sequence data and change sequence data of the current area, analyze the pollutant status and set a primary tail water treatment plan; The tail water treatment plan includes the amount of tail water purification, the amount of tail water discharge, and the tail water treatment process; According to the high-impact area and the low-impact area, optimize and adjust the tail water treatment plan to generate a secondary tail water treatment plan and a tertiary tail water treatment plan, and apply them to the high-impact area and the low-impact area respectively.

[0012] The second aspect of the present invention also provides a dynamic monitoring system for the tail water of seawater pond aquaculture. The system includes: a memory and a processor. The memory includes a dynamic monitoring program for the tail water of seawater pond aquaculture. When the dynamic monitoring program for the tail water of seawater pond aquaculture is executed by the processor, the following steps are implemented: S101: During an aquaculture cycle, collect pollutant monitoring data from different aquaculture areas in the seawater pond; S102: Based on a preset interval, divide the aquaculture cycle into N time points. Based on the N time points, extract the concentration values of multiple pollutants from the pollutant monitoring data, serialize the extracted values, and obtain multiple pollutant sequence data; S103: Based on each pollutant sequence data, dynamically analyze the growth rate of the values at adjacent time points to generate change sequence data; S104: Use all the pollutant sequence data and change sequence data as data items, preprocess the data items, screen out the frequent item sets from all the data items based on the Apriori algorithm, and construct strong association and weak association rules from the frequent item sets based on a preset confidence level; S105: Select an aquaculture area as the current area, analyze the association relationship between the data items through the strong association and weak association rules, and based on the aquaculture areas to which the data items belong, screen out the areas associated with the current area and mark them as high-impact areas and low-impact areas respectively; S106: Set a primary tail water treatment plan for the current area, and combine the high-impact area and the low-impact area to adjust the primary tail water treatment plan and set the tail water treatment plan for the impact area.

[0013] The third aspect of the present invention further provides a computer-readable storage medium, which includes a program for dynamically monitoring the tail water of seawater pond aquaculture. When the program for dynamically monitoring the tail water of seawater pond aquaculture is executed by a processor, the steps of the method for dynamically monitoring the tail water of seawater pond aquaculture as described in any one of the above are implemented.

[0014] The present invention discloses a method and system for dynamically monitoring the tail water of seawater pond aquaculture. During the aquaculture cycle, pollutant monitoring data in multiple regions are collected, and pollutant sequences are extracted at preset time intervals; based on the pollutant sequences, the concentration growth rate is calculated to generate a change sequence; the two types of sequence data are fused, and the Apriori algorithm is used to mine the correlation relationship between the two types of sequence data in different regions, and the high and low impact regions for the current region are marked; further, the tail water treatment plan for the current region and the impact region is dynamically adjusted, and the regional cooperation is used to control the tail water treatment effect of the current region, realizing the dynamic optimization of tail water treatment and improving the overall pollution treatment efficiency of the aquaculture system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The flowchart of a method for dynamically monitoring the tail water of seawater pond aquaculture according to the present invention is shown; Figure 2 The block diagram of a system for dynamically monitoring the tail water of seawater pond aquaculture according to the present invention is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0017] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0018] Figure 1 The flowchart of a method for dynamically monitoring the tail water of seawater pond aquaculture according to the present invention is shown.

[0019] As Figure 1 shown, the first aspect of the present invention provides a method for dynamically monitoring the tail water of seawater pond aquaculture, including: S101: During an aquaculture cycle, collect pollutant monitoring data in different aquaculture regions of the seawater pond; S102: Divide the breeding cycle into N time points based on a preset interval. Based on the N time points, extract the concentration values of various pollutants from the pollutant monitoring data, serialize the extracted values, and obtain multiple pollutant sequence data; S103: Based on each pollutant sequence data, dynamically analyze the growth rate of the values at adjacent time points to generate change sequence data; S104: Use all pollutant sequence data and change sequence data as data items, preprocess the data items, screen out frequent item sets from all data items based on the Apriori algorithm, and construct strong association and weak association rules from the frequent item sets based on a preset confidence level; S105: Select a breeding area as the current area, analyze the association relationships between data items through strong association and weak association rules, and based on the breeding areas to which the data items belong, screen out the areas associated with the current area, and mark them as high-impact areas and low-impact areas respectively; S106: Set a primary tail water treatment plan for the current area, and combine the high-impact areas and low-impact areas to adjust the primary tail water treatment plan and set the tail water treatment plans for the impact areas.

[0020] It should be noted that in a seawater pond, there are usually multiple breeding areas or breeding ponds. There are certain association and influence relationships between pollutants in different breeding areas. And due to differences in breeding plans, in different breeding areas, the contents, concentrations and pollution impacts of different types of pollutants are different.

[0021] According to the embodiments of the present invention, the S101 is specifically: In a seawater pond, set up monitoring units based on each breeding area, monitor and analyze the contents of various pollutants through the monitoring units, and obtain pollutant monitoring data.

[0022] It should be noted that the pollutant monitoring data includes the numerical values of various pollution-related monitoring indicators, such as ammonia nitrogen content, dissolved oxygen content, heavy metal content, chemical oxygen demand, nitrate content, phosphorus content and other indicators. The pollutant content is generally the same as the concentration representation. Each breeding area includes independent pollutant monitoring data. The monitoring unit is a movable water body detection unit for detecting pollutant content.

[0023] According to the embodiments of the present invention, the S102 is specifically: Set a preset interval, and divide the breeding cycle into N consecutive time points, with the interval between adjacent time points being the preset interval; Extract the concentration value of each pollutant from the pollutant monitoring data to obtain multiple data points, and perform time serialization on the multiple data points to obtain pollutant sequence data; Based on multiple pollutants, multiple pollutant sequence data are obtained.

[0024] It should be noted that the breeding cycle is generally a relatively long time period, measured in days, and the preset interval is the interval set by the user, which is used to divide the monitoring data of pollutants into multiple data points. For example, if the breeding cycle is set to 7×24 hours and the preset interval is set to 1 hour, then 7×24 data points are obtained. For each pollutant, corresponding data points are set to obtain different sequence segments.

[0025] According to an embodiment of the present invention, the S103 is specifically as follows: Select a pollutant sequence data, calculate the growth rate for two adjacent data points, and sort the growth rate based on the time dimension to obtain the change sequence data; Generate multiple change sequence data based on multiple pollutant sequence data.

[0026] It should be noted that the pollutant sequence data includes multiple data points. If there are K data points, then the growth rate of adjacent data points is calculated K - 1 times. A growth rate less than 0 represents negative growth, that is, the value decreases. When serializing the monitoring data, dynamic calculation and analysis can be performed to generate a change sequence. For example, in the pollutant sequence data of ammonia nitrogen content, there are three data points, {0.1, 0.15, 0.2}, with the corresponding unit of milligram per liter, then the change sequence is {50%, 33.3%}.

[0027] According to an embodiment of the present invention, the S104 is specifically as follows: Take all pollutant sequence data and change sequence data as data items; Perform preprocessing of data cleaning, duplicate removal, and invalid data elimination on the data items; Based on the Apriori algorithm, set the minimum support, the first confidence level, and the second confidence level; Calculate the support of each data item, and screen out the frequent item sets based on the minimum support. For each frequent item set, calculate its confidence level; Screen out the frequent item sets with a confidence level greater than the first confidence level and construct strong association rules; Screen out the frequent item sets with a confidence level greater than the second confidence level and construct weak association rules.

[0028] It should be noted that the first confidence level is greater than the second confidence level. After screening out the strong association rules, the data items with strong associations are eliminated, and weak association rules are further constructed (screening weak association data items). In a preferred embodiment, the minimum support can be set to 40%, and the first confidence level and the second confidence level are set to 80% and 50% respectively.

[0029] It is worth noting here that the present invention adopts the Apriori association algorithm, which can quickly and effectively mine the correlation of different pollutant monitoring data in different regions, and can mine multiple association relationships, and mark the impact area for the current region based on the association characteristics, so as to set an effective tail water regulation and treatment plan, improve the intelligent monitoring and automation level of tail water treatment, and reduce the impact of potential pollution factors through the regulation of the impact area, improve the tail water treatment efficiency and optimize the marine ecological environment.

[0030] In addition, when analyzing data items, the present invention introduces two sequences, one is the original numerical sequence of pollutants, and the other is the change sequence, and conducts association analysis as data items, so as to be able to distinguish the correlation between different pollutant changes, and introduce different confidence levels to judge the strength relationship of data items, effectively mine the regulation relationship and change association situation between pollutants, and provide strong data support for tail water treatment.

[0031] There are often a large number of pollutant measurement data in the monitoring data. If the comparison and association analysis are carried out for each data item one by one, it will greatly consume manpower, material resources and computing power. Therefore, there are few effective association analysis processes for multiple pollutant monitoring data in the prior art. The present invention introduces the growth rate for sequence analysis to distinguish the correlation of the growth of different pollutants. Through the Apriori association algorithm, it can quickly analyze the influence of pollutants with association patterns and pollutants between different regions within a short period, effectively reducing the complex data analysis process.

[0032] According to an embodiment of the present invention, the S105 is specifically as follows: Based on the tail water treatment requirements, select a breeding area to be treated as the current area; Through strong association rules, retrieve the data items with strong associations in the current area, and judge the breeding area to which the associated data items belong, and mark the breeding area to which they belong as a high-impact area; Through weak association rules, retrieve the data items with weak associations in the current area, and judge the breeding area to which the associated data items belong, and mark the breeding area to which they belong as a low-impact area.

[0033] It should be noted that the data items corresponding to the breeding area include the pollutant sequence data and change sequence data of various pollutants. The high-impact area and the low-impact area are for the current area. The corresponding impact areas of different breeding areas are different.

[0034] Through the strong association rule, retrieve the data items with strong associations in the current area, and determine the aquaculture areas to which the associated data items belong. That is, first screen out a group of data items with strong associations from the association rules. Among this group of data items, if a certain data item belongs to the aquaculture area of the current area, mark the aquaculture areas to which other associated data items in this group of data items belong as the strong influence areas for the current area. The weak influence areas are screened and analyzed in the same way.

[0035] In the strong and weak association rules, the data items with associations are saved, and the data items come from the monitoring data of different aquaculture areas. For example, if there is a strong association relationship between the ammonia nitrogen content sequence in the current area and the phosphorus content sequence in a certain aquaculture area (which can be retrieved through the association rule), then mark the corresponding aquaculture area as the high influence area. In addition, the pollutants with an association relationship can also be the same pollutant. For the current area, the pollution status of the high influence area will affect the current area in real time, and the low influence area has an interactive relationship with the current area to a certain extent. Therefore, when treating the tail water of the current area, performing linkage treatment on the associated areas can improve the treatment efficiency of pollutants, enhance the continuous purification ability of pollutants in the aquaculture area, and reduce the negative impact of pollutants among multiple areas in the overall aquaculture pond.

[0036] It is worth mentioning here that among the aquaculture areas, affected by tides, water currents, meteorology, and aquaculture plans, there are certain association relationships and influence relationships among the pollutants in the aquaculture pond. The increase in pollutants in a certain aquaculture area will affect the pollutant changes and water quality conditions in other aquaculture areas, such as the mutual influence of the same or similar pollutants. However, in the prior art, it is difficult to mine and analyze the influence process, lacking an effective association analysis process, and often relying on manual experience for pollution data analysis and the setting of emission plans, with low levels of intelligence and automation. The embodiments of the present invention can effectively solve the above problems.

[0037] According to the embodiments of the present invention, the S106 is specifically as follows: Based on the pollutant sequence data and change sequence data of the current area, analyze the pollutant status and set a primary tail water treatment plan; The tail water treatment plan includes the tail water purification amount, the tail water discharge amount, and the tail water treatment process; According to the high influence area and the low influence area, optimize and adjust the tail water treatment plan to generate a secondary tail water treatment plan and a tertiary tail water treatment plan, and apply them to the high influence area and the low influence area respectively.

[0038] It should be noted that during the tail water treatment process, since the highly affected area and the lowly affected area have different degrees of pollution impact on the current area, when adjusting the tail water treatment plan for the current area, it is necessary to optimize the plan according to the situation and set it in the affected area. For example, in the primary tail water treatment plan, it includes the tail water purification volume, the tail water discharge volume, and the tail water treatment process. In the secondary tail water treatment plan, specifically in the case of the primary tail water treatment plan, the tail water purification volume and the tail water discharge volume are reduced by a certain proportion (such as 50%), and a certain amount of the tail water treatment process is reduced to generate the secondary plan and apply it to the highly affected area, so as to optimize the plan through a certain adjustment proportion and apply it to the affected area. Similarly, for the tertiary tail water treatment plan, the plan is optimized by a certain proportion and the treatment process is streamlined (such as 70%), thereby ensuring the effectiveness and accuracy of the tail water treatment. The tail water treatment process generally includes multiple functional area treatment stages, and different stages correspond to different pollutant removals.

[0039] The treatment plan with a lower grade value has more treatment processes and a more complex treatment process.

[0040] According to the embodiments of the present invention, it further includes: Based on the breeding situation and water body situation of the current area, set preset pollutants; Construct an ARIMA prediction model; During the breeding cycle, use the pollutant sequence data of the current area corresponding to the preset pollutants as the time series of the prediction model, and analyze the autocorrelation graph and partial autocorrelation graph of the time series; Determine the p, d, and q parameters of the prediction model according to the autocorrelation graph and partial autocorrelation graph; p represents the autoregressive order of the time series, d represents the differencing order of the time series, and q represents the moving average order of the time series; Import the time series as training data into the prediction model for prediction training until the model reaches the expected fitting degree; Based on the pollutant sequence data of the highly affected area and the lowly affected area corresponding to the preset pollutants, construct and train the corresponding ARIMA prediction models; During the tail water treatment process of the current area, set a treatment cycle, collect the pollutant sequence data of the current area, the highly affected area, and the lowly affected area corresponding to the preset pollutants within the treatment cycle, and label them as the first sequence, the second sequence, and the third sequence; Through the prediction model, perform sequence prediction on the first sequence, the second sequence, and the third sequence respectively, set the number of predicted data points, and generate the first prediction sequence, the second prediction sequence, and the third prediction sequence respectively; Compare the first prediction sequence with the expected value of the preset pollutants in real time to achieve the first-level pollution warning; Perform weighted averaging on the data points of the second prediction sequence and the third prediction sequence based on preset weights to generate a weighted prediction sequence; Achieve secondary pollution warning by comparing the weighted prediction sequence with the preset expected pollutant values in real time.

[0041] It should be noted that the preset pollutants are the core pollutants for the current area, and one or more can be set by the user for analysis. When the expected fitting degree is reached, that is, the prediction deviation is controlled within a low value. The processing cycle is generally less than the breeding cycle, and the data points of the first, second, and third sequences are generally less than N. Based on the pollutant sequence data of the preset pollutants corresponding to the high-impact area and the low-impact area, corresponding ARIMA prediction models are constructed and trained. Different areas generate corresponding ARIMA prediction models, that is, three ARIMA prediction model instances, and the prediction models are trained based on different sequence segments, and the corresponding model parameters are also different. When performing sequence prediction on the first sequence, the second sequence, and the third sequence through the prediction models, three prediction models are applied for analysis and prediction.

[0042] It should be mentioned here that in the actual tail water treatment process, affected by factors such as the complex seawater environment, tides, and meteorological environment, there are often inaccurate monitoring feedback and insufficient analysis of the dynamic monitoring changes in the tail water treatment of the selected area, resulting in a certain monitoring and analysis delay. It is often necessary to wait for a period of time after the tail water is completely treated to accurately monitor the tail water situation.

[0043] Based on this, the present invention analyzes the associated impact areas. During the tail water treatment stage, by setting an ARIMA prediction model, it performs prediction analysis on the real-time collected pollutant data, makes a primary pollution warning judgment for the current area, dynamically monitors the tail water treatment effect, and predicts the monitoring data corresponding to the high-impact area and the low-impact area. By weighting the prediction sequence segment and comparing it with the expected value, it realizes secondary warning for the tail water treatment of the current area from the impact areas, achieves dual warning of the tail water treatment, effectively judges the trend and treatment situation of the pollutants, and then effectively regulates the treatment plan or the breeding area.

[0044] The preset weights include the first and second weights. The first weight is greater than the second weight, and they respectively correspond to the data points of the second prediction sequence and the third prediction sequence (that is, the first weight corresponds to the sequence segment of the high-impact area, and the second weight corresponds to the sequence segment of the low-impact area). The preset expected pollutant values corresponding to the two comparisons can be set to different values, specifically based on the regional impact relationship or user settings.

[0045] Figure 2 Shows a block diagram of a dynamic monitoring system for seawater pond aquaculture tail water according to the present invention.

[0046] In the second aspect of the present invention, a dynamic monitoring system 2 for the tail water of seawater pond aquaculture is further provided. The system includes: a memory 21 and a processor 22. The memory includes a dynamic monitoring program for the tail water of seawater pond aquaculture. When the dynamic monitoring program for the tail water of seawater pond aquaculture is executed by the processor, the following steps are implemented: S101: During a breeding cycle, collect pollutant monitoring data from different breeding areas in the seawater pond; S102: Based on a preset interval, divide the breeding cycle into N time points. Based on the N time points, extract the concentration values of multiple pollutants from the pollutant monitoring data, serialize the extracted values, and obtain multiple pollutant sequence data; S103: Based on each pollutant sequence data, dynamically analyze the growth rate of the values at adjacent time points, and generate change sequence data; S104: Use all pollutant sequence data and change sequence data as data items, preprocess the data items, based on the Apriori algorithm, screen out frequent item sets from all data items, and based on a preset confidence level, construct strong association and weak association rules from the frequent item sets; S105: Select a breeding area as the current area, analyze the association relationship between data items through strong association and weak association rules, and based on the breeding area to which the data items belong, screen out the areas associated with the current area, and mark them as high-impact areas and low-impact areas respectively; S106: Set a primary tail water treatment plan for the current area, and combine the high-impact area and the low-impact area to adjust the primary tail water treatment plan and set the tail water treatment plans for the impact areas.

[0047] It should be noted that in a seawater pond, there are usually multiple breeding areas or breeding ponds. There is a certain association and influence relationship between pollutants in different breeding areas. And due to the differences in breeding plans, in different breeding areas, the contents, concentrations and pollution impacts of different types of pollutants are different.

[0048] According to the embodiments of the present invention, the S101 is specifically: In the seawater pond, based on each breeding area, set a monitoring unit, and through the monitoring unit, monitor and analyze the contents of multiple pollutants to obtain pollutant monitoring data.

[0049] It should be noted that the pollutant monitoring data includes the numerical values of multiple monitoring indicators related to pollution, such as ammonia nitrogen content, dissolved oxygen content, heavy metal content, chemical oxygen demand, nitrate content, phosphorus content and other indicators. The pollutant content is generally expressed in the same way as the concentration. Each breeding area includes independent pollutant monitoring data. The monitoring unit is a movable water body detection unit for detecting the pollutant content.

[0050] According to an embodiment of the present invention, the S102 is specifically as follows: Set a preset interval, and divide the breeding cycle into N consecutive time points, with the interval between adjacent time points being the preset interval; Extract the concentration values of each pollutant from the pollutant monitoring data to obtain a plurality of data points, and perform time serialization on the plurality of data points to obtain pollutant sequence data; Based on multiple pollutants, obtain multiple pollutant sequence data.

[0051] It should be noted that the breeding cycle is generally a relatively long time period, in days, and the preset interval is the interval set by the user for dividing the monitoring data of pollutants into multiple data points. For example, if the breeding cycle is set to 7×24 hours and the preset interval is set to 1 hour, then 7×24 data points are obtained, and corresponding data points are set for each pollutant to obtain different sequence segments.

[0052] According to an embodiment of the present invention, the S103 is specifically as follows: Select a pollutant sequence data, calculate the growth rate for two adjacent data points, and sort the growth rate based on the time dimension to obtain change sequence data; Generate multiple change sequence data based on multiple pollutant sequence data.

[0053] It should be noted that the pollutant sequence data includes multiple data points. If there are K data points, then the growth rate of adjacent data points is calculated K - 1 times. A growth rate less than 0 represents negative growth, that is, the value decreases. When serializing the monitoring data, dynamic calculation and analysis can be performed to generate a change sequence. For example, in the pollutant sequence data of ammonia nitrogen content, there are three data points, {0.1, 0.15, 0.2}, with the corresponding unit being milligrams per liter, then the change sequence is {50%, 33.3%}.

[0054] According to an embodiment of the present invention, the S104 is specifically as follows: Take all pollutant sequence data and change sequence data as data items; Perform preprocessing on the data items, including data cleaning, duplicate removal, and invalid data elimination; Based on the Apriori algorithm, set the minimum support, the first confidence level, and the second confidence level; Calculate the support of each data item, and filter out the frequent item sets based on the minimum support. For each frequent item set, calculate its confidence level; Filter out the frequent item sets with a confidence level greater than the first confidence level and construct strong association rules; Filter out the frequent item sets with a confidence level greater than the second confidence level and construct weak association rules.

[0055] It should be noted that the first confidence level is greater than the second confidence level. After screening the strong association rules, the data items with strong associations are eliminated, and the weak association rules are further constructed (screening weak association data items). In a preferred embodiment, the minimum support can be set to 40%, and the first confidence level and the second confidence level are set to 80% and 50% respectively.

[0056] It is worth mentioning here that the present invention adopts the Apriori association algorithm, which can quickly and effectively mine the associations of different pollutant monitoring data in different regions, and can mine multiple association relationships, and mark the impact area for the current region based on the association characteristics, so as to set effective tail water regulation and treatment plans, improve the intelligent monitoring and automation level of tail water treatment, and reduce the impact of potential pollution factors through the regulation of the impact area, improve the tail water treatment efficiency and optimize the marine ecological environment.

[0057] In addition, when analyzing data items, the present invention introduces two sequences, one is the original numerical sequence of pollutants, and the other is the change sequence, and they are used as data items for association analysis, so as to be able to distinguish the associations between the changes of different pollutants, and introduce different confidence levels to distinguish the strength relationship of data items, effectively mine the regulation relationship and change association situation between pollutants, and provide strong data support for tail water treatment.

[0058] There are often a large number of pollutant measurement data in the monitoring data. If each data is compared and associated for analysis, it will greatly consume manpower, material resources and computing power. Therefore, there are few effective association analysis processes for multiple pollutant monitoring data in the prior art. The present invention introduces the growth rate for sequence analysis to distinguish the associations of the growth situations of different pollutants. Through the Apriori association algorithm, it can quickly analyze the influence situations between pollutants with association patterns and pollutants in different regions within a short period, effectively reducing the complex data analysis process.

[0059] According to the embodiment of the present invention, the S105 is specifically: Based on the tail water treatment requirements, select a breeding area to be treated as the current area; Through the strong association rules, retrieve the data items with strong associations in the current area, and judge the breeding area to which the associated data items belong, and mark the breeding area to which they belong as a high-impact area; Through the weak association rules, retrieve the data items with weak associations in the current area, and judge the breeding area to which the associated data items belong, and mark the breeding area to which they belong as a low-impact area.

[0060] It should be noted that the data items corresponding to the aquaculture areas include pollutant sequence data and change sequence data of various pollutants. The high-impact area and the low-impact area are in relation to the current area. The corresponding impact areas of different aquaculture areas are different.

[0061] Through the strong association rules, retrieve the data items with strong associations in the current area, and determine the aquaculture areas to which the associated data items belong. That is, first screen out a group of data items with strong associations from the association rules. Among this group of data items, if a certain data item belongs to the current area, mark the aquaculture areas to which the other associated data items in this group belong as the strong-impact areas for the current area. The weak-impact areas are screened and analyzed in the same way.

[0062] In the strong and weak association rules, the associated data items are saved, and the data items come from the monitoring data of different aquaculture areas. For example, if there is a strong association relationship between the ammonia nitrogen content sequence in the current area and the phosphorus content sequence in a certain aquaculture area (which can be retrieved through the association rules), then mark the corresponding aquaculture area as the high-impact area; in addition, the pollutants with an association relationship can also be the same pollutant. For the current area, the pollution status of the high-impact area will affect the current area in real time, and the low-impact area has an interactive relationship with the current area to a certain extent. Therefore, when treating the tail water of the current area, performing linkage treatment on the associated areas can improve the treatment efficiency of pollutants, enhance the continuous purification ability of pollutants for the aquaculture areas, and reduce the negative impacts of pollutants among multiple areas in the overall aquaculture ponds.

[0063] It is worth mentioning here that among the aquaculture areas, affected by tides, water currents, meteorology, and aquaculture plans, there are certain association relationships and influence relationships among the pollutants in the aquaculture ponds. The increase in pollutants in a certain aquaculture area will affect the pollutant changes and water quality conditions in other aquaculture areas, such as the mutual influence of the same or similar pollutants. However, in the prior art, the influence process is difficult to excavate and analyze, lacking an effective association analysis process, and often relying on manual experience for pollution data analysis and the setting of discharge plans, with low levels of intelligence and automation. The embodiments of the present invention can effectively solve the above problems.

[0064] According to the embodiments of the present invention, the S106 is specifically as follows: Based on the pollutant sequence data and change sequence data of the current area, analyze the pollutant status and set the primary tail water treatment plan; The tail water treatment plan includes the tail water purification amount, the tail water discharge amount, and the tail water treatment process; According to the high-impact area and the low-impact area, optimize and adjust the tail water treatment plan to generate the secondary tail water treatment plan and the tertiary tail water treatment plan, and apply them to the high-impact area and the low-impact area respectively.

[0065] It should be noted that during the process of treating tail water, since the high-impact area and the low-impact area have different degrees of pollution impact on the current area, when adjusting the tail water treatment plan for the current area, it is necessary to optimize the plan according to the situation and set it in the impact area. For example, in the primary tail water treatment plan, it includes the amount of tail water purification, the amount of tail water discharge, and the tail water treatment process. In the secondary tail water treatment plan, specifically in the case of the primary tail water treatment plan, the amount of tail water purification and the amount of tail water discharge are reduced by a certain proportion (such as 50%), and a certain amount of tail water treatment process is reduced to generate a secondary plan and apply it to the high-impact area, so as to optimize the plan through a certain adjustment proportion and apply it to the impact area. The tertiary tail water treatment plan is similarly optimized by a certain proportion and the treatment process is streamlined (such as 70%), so as to ensure the effectiveness and accuracy of tail water treatment. The tail water treatment process generally includes multiple functional area treatment stages, and different stages correspond to different pollutant removals.

[0066] The treatment plan with a lower grade value has more treatment processes and a more complex treatment process.

[0067] The third aspect of the present invention also provides a computer-readable storage medium, which includes a dynamic monitoring program for the tail water of seawater pond aquaculture. When the dynamic monitoring program for the tail water of seawater pond aquaculture is executed by a processor, the steps of the dynamic monitoring method for the tail water of seawater pond aquaculture as described in any one of the above are realized.

[0068] The present invention discloses a dynamic monitoring method and system for the tail water of seawater pond aquaculture. During the aquaculture cycle, multi-region pollutant monitoring data is collected, and pollutant sequences are extracted at preset time intervals; based on the pollutant sequences, the concentration growth rate is calculated to generate a change sequence; the two types of sequence data are fused, and the Apriori algorithm is used to mine the correlation relationship between the two types of sequence data in different regions, and the high- and low-impact regions for the current area are marked; further, the tail water treatment plans for the current area and the impact area are dynamically adjusted, and the regional cooperation is used to control the tail water treatment effect of the current area, realizing the dynamic optimization of tail water treatment and improving the overall pollution treatment efficiency of the aquaculture system.

[0069] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the couplings, direct couplings, or communication connections between the various components shown or discussed may be through some interfaces. The indirect couplings or communication connections of devices or units can be electrical, mechanical, or other forms.

[0070] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0071] In addition, each functional unit in each embodiment of the present invention can be all integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0072] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0073] Alternatively, if the above-mentioned integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

[0074] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. A dynamic monitoring method for the tail water of seawater pond aquaculture, characterized in that, Including: S101: During a breeding cycle, collect pollutant monitoring data from different breeding areas in a seawater pond; S102: Based on a preset interval, divide the breeding cycle into N time points. Based on the N time points, extract the concentration values of multiple pollutants from the pollutant monitoring data, serialize the extracted values, and obtain multiple pollutant sequence data; S103: Based on each pollutant sequence data, dynamically analyze the growth rate of the values at adjacent time points to generate change sequence data; S104: Use all pollutant sequence data and change sequence data as data items, preprocess the data items, and based on the Apriori algorithm, screen out frequent item sets from all data items, and based on a preset confidence level, construct strong association and weak association rules from the frequent item sets; S105: Select a breeding area as the current area, analyze the association relationship between data items through strong association and weak association rules, and based on the breeding area to which the data items belong, screen out the areas associated with the current area, and mark them as high-impact areas and low-impact areas respectively; S106: Set a primary tail water treatment plan for the current area, and combine the high-impact area and the low-impact area to adjust the primary tail water treatment plan and set the tail water treatment plans for the impact areas.

2. The dynamic monitoring method for the tail water of seawater pond aquaculture according to claim 1, characterized in that, The S101 is specifically: In a seawater pond, set monitoring units based on each breeding area, and through the monitoring units, monitor and analyze the content of multiple pollutants to obtain pollutant monitoring data.

3. The dynamic monitoring method for the tail water of seawater pond aquaculture according to claim 1, wherein The S102 is specifically: Set a preset interval and divide the breeding cycle into N consecutive time points, and the interval between adjacent time points is the preset interval; Extract the concentration values of each pollutant from the pollutant monitoring data to obtain multiple data points, and perform time serialization on the multiple data points to obtain pollutant sequence data; Based on multiple pollutants, obtain multiple pollutant sequence data.

4. A method for dynamic monitoring of the tail water in a seawater pond aquaculture according to claim 1, characterized in that, The S103 is specifically: Select a pollutant sequence data, calculate the growth rate for two adjacent data points, and sort the growth rate based on the time dimension to obtain change sequence data; Generate multiple change sequence data based on multiple pollutant sequence data.

5. A dynamic monitoring method for the tail water of seawater pond aquaculture according to claim 1, characterized in that, The S104 is specifically: Use all pollutant sequence data and change sequence data as data items; Preprocess the data items by data cleaning, duplicate removal, and invalid data elimination; Based on the Apriori algorithm, set the minimum support, the first confidence level, and the second confidence level; Calculate the support of each data item, and screen out the frequent item sets based on the minimum support. For each frequent item set, calculate its confidence level; Screen out the frequent item sets with a confidence level greater than the first confidence level and construct strong association rules; Screen out the frequent item sets with a confidence level greater than the second confidence level and construct weak association rules.

6. The dynamic monitoring method for the tail water of seawater pond aquaculture according to claim 1, wherein The S105 is specifically: Based on the tail water treatment requirements, select a breeding area to be treated as the current area; Through strong association rules, retrieve the data items with strong associations in the current area, judge the breeding areas to which the associated data items belong, and mark the breeding areas to which they belong as high-impact areas; Retrieve data items with weak associations in the current area through weak association rules, determine the aquaculture areas to which the associated data items belong, and mark the aquaculture areas as low-impact areas.

7. The dynamic monitoring method for the tail water of seawater pond aquaculture according to claim 1, characterized in that Specifically, S106 is as follows: Analyze the pollutant status based on the pollutant sequence data and change sequence data in the current area, and set a primary tail water treatment plan; The tail water treatment plan includes the tail water purification volume, tail water discharge volume, and tail water treatment process; Based on the high-impact area and low-impact area, optimize and adjust the tail water treatment plan to generate a secondary tail water treatment plan and a tertiary tail water treatment plan, and apply them to the high-impact area and low-impact area respectively.

8. A dynamic monitoring system for the tail water of seawater pond aquaculture, characterized in that, The system includes: a memory and a processor. The memory includes a seawater pond aquaculture tail water dynamic monitoring program. When the seawater pond aquaculture tail water dynamic monitoring program is executed by the processor, the following steps are implemented: S101: During an aquaculture cycle, collect pollutant monitoring data from different aquaculture areas in the seawater pond; S102: Based on a preset interval, divide the aquaculture cycle into N time points. Based on the N time points, extract the concentration values of multiple pollutants from the pollutant monitoring data, and serialize the extracted values to obtain multiple pollutant sequence data; S103: Based on each pollutant sequence data, dynamically analyze the growth rate of the values at adjacent time points to generate change sequence data; S104: Use all the pollutant sequence data and change sequence data as data items, preprocess the data items, and based on the Apriori algorithm, screen out the frequent item sets from all the data items, and based on a preset confidence level, construct strong association and weak association rules from the frequent item sets; S105: Select an aquaculture area as the current area, analyze the association relationship between the data items through the strong association and weak association rules, and based on the aquaculture areas to which the data items belong, screen out the areas associated with the current area, and mark them as high-impact areas and low-impact areas respectively; S106: Set a primary tail water treatment plan for the current area, and combine the high-impact area and low-impact area to adjust the primary tail water treatment plan and set the tail water treatment plan for the impact area.

9. The dynamic monitoring system for the tail water of seawater pond aquaculture according to claim 8, wherein Specifically, S101 is as follows: In the seawater pond, set monitoring units based on each aquaculture area, and monitor and analyze the contents of multiple pollutants through the monitoring units to obtain pollutant monitoring data.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a seawater pond aquaculture tail water dynamic monitoring program. When the seawater pond aquaculture tail water dynamic monitoring program is executed by the processor, the steps of the seawater pond aquaculture tail water dynamic monitoring method according to any one of claims 1 to 7 are implemented.

Images