Shallow lake water pollution control system and method

Abstract

The present invention discloses a system and method for treating water pollution in shallow lakes, which relates to the technical field of water pollution. The system and method construct a disturbance intensity index DIX and an ammonia nitrogen concentration change curve through step S1 to achieve quantitative identification of sediment disturbance and pollution release behavior, and use this to train a rebound risk prediction model, output a rebound risk prediction coefficient Ft, and effectively improve the ability to predict the rebound trend of ammonia nitrogen pollution. In step S2, the adjusted aeration response frequency BAF is dynamically generated based on the rebound risk prediction coefficient Ft value, so that the aeration behavior is converted from the traditional timing system to the risk-driven system, further reducing energy consumption and disturbance intensity, and improving treatment efficiency. Step S3 further introduces the treatment residual coefficient GRC to construct a complete feedback closed loop, realize accurate evaluation of each round of treatment effect and secondary strategy optimization, thereby avoiding the problem of effect regression or excessive disturbance after treatment.

Description

Technical Field

[0001] The present invention relates to the technical field of water pollution, and in particular to a system and method for treating water pollution in shallow lakes. Background Art

[0002] Shallow lakes, as crucial components of urban wetlands, water storage, and regional ecological stability, are characterized by shallow depths, slow hydrodynamics, and a strong capacity for pollutant deposition and retention. These lakes are prone to the interactive effects of ammonia nitrogen accumulation and sediment release, leading to significant problems such as water quality deterioration, eutrophication, and resurgence. To improve the sustainability and stability of ammonia nitrogen pollution control in shallow lakes, it is imperative to develop intelligent control mechanisms that can dynamically respond to disturbances and pollution rebound trends.

[0003] Existing treatment methods for water pollution in shallow lakes mainly rely on manual intervention, timed aeration or fixed-point drug administration. However, these methods generally rely on fixed control cycles and lack the ability to predict pollution rebound trends. In particular, under the influence of factors such as sediment disturbance and dissolved oxygen fluctuations after treatment, a "treatment rebound" phenomenon of ammonia nitrogen concentration rising again is often triggered, which is not conducive to the effective treatment of water pollution in shallow lakes. Summary of the Invention

[0004] In view of the deficiencies in the prior art, the present invention provides a system and method for treating water pollution in shallow lakes, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for treating water pollution in shallow lakes, comprising the following steps:

[0006] S1: Use underwater monitoring equipment to obtain the operational characteristics of shallow lake sediments in real time. Based on the operational characteristics, evaluate the disturbance intensity and its potential risk to pollutant release to obtain the disturbance intensity index DIX. Construct ammonia nitrogen concentration change curves before and after ammonia nitrogen treatment, and extract the dynamic behavior of the rebound trend from them. Use the operational characteristics and ammonia nitrogen concentration change curves to train a risk prediction model to output the rebound risk prediction coefficient Ft.

[0007] S2: Based on the rebound risk prediction coefficient Ft value, dynamic regulation is performed to obtain the adjusted aeration response frequency BAF, and aeration intervention is performed in shallow lakes based on the adjusted aeration response frequency BAF;

[0008] S3: Real-time monitoring of the ammonia nitrogen concentration change curve after the intervention of aeration in shallow lakes to provide feedback on the effect analysis of dynamic regulation in S2, and to re-execute the regulation mechanism to achieve water pollution control in shallow lakes.

[0009] Preferably, the specific steps of S1 include:

[0010] S11: Install several sets of monitoring equipment in shallow lakes in advance to monitor and obtain the operational characteristics of shallow lake sediments in real time. The operational characteristics include the number of disturbance events in the shallow lake sediments during the monitoring period. , sediment ammonia nitrogen release intensity and the minimum dissolved oxygen in bottom water ;

[0011] S12: Based on the operating characteristics and after dimensionless processing of the information in the operating characteristics, the disturbance intensity and its risk to the potential release of pollutants are evaluated to calculate the disturbance intensity index DIX. The disturbance intensity index DIX is obtained by the following calculation method:

[0012] ;

[0013] Where, represents the number of disturbance events during the monitoring period, Indicates the release intensity of ammonia nitrogen in sediment, Indicates the minimum dissolved oxygen in bottom water. Represents a small constant.

[0014] Preferably, the specific step S1 further includes:

[0015] S13: The potential data in the water body is obtained in real time through the ammonia nitrogen ion selective electrode sensor, and the ammonia nitrogen concentration value is converted based on the Nernst equation. The ammonia nitrogen concentration sequence is continuously sampled and converted to form an ammonia nitrogen concentration change curve in the time dimension. Among them, the potential data refers to the electrode potential value E of the corresponding acquisition period. The Nernst equation is as follows:

[0016] ;

[0017] Where, is the standard electrode potential, is the gas constant, T is the temperature, is the ion charge number, F is the Faraday constant, is the ammonium ion concentration in water;

[0018] S14: Extract the time point of each ammonia nitrogen treatment from the operation characteristics and mark it in the ammonia nitrogen concentration change curve to form the ammonia nitrogen concentration change curve before and after the ammonia nitrogen treatment. Extract the dynamic behavior of the rebound trend from the ammonia nitrogen concentration change curve before and after the ammonia nitrogen treatment, where the dynamic behavior includes the start date of each treatment. (reference benchmark) and on the corresponding governance start date The ammonium ion concentration in the water body every day thereafter ;

[0019] S15: Based on the dynamic behavior, analyze and calculate the daily growth rate Rn of the ammonium ion concentration in the water body after the corresponding treatment, specifically:

[0020] ;

[0021] Where, is the daily growth rate of ammonium ion concentration in the water body at time t after treatment, On the corresponding governance start date The ammonium ion concentration in the water at time t is: On the corresponding governance start date The concentration of ammonium ions in water at is the moment number, The corresponding governance start date.

[0022] Preferably, the specific step S1 further includes:

[0023] S16: The convolutional neural network model is trained and verified by taking the operating characteristics and the ammonia nitrogen concentration change curve as the input information of the convolutional neural network model, and dividing the input information into a training set and a validation set after dimensionless processing. The trained convolutional neural network model is used as a risk prediction model, and the rebound risk prediction coefficient Ft is output from the output end of the risk prediction model.

[0024] Preferably, the specific steps of S2 include:

[0025] S21: Pre-set the risk threshold and compare the risk threshold with the rebound risk prediction coefficient Ft to determine whether dynamic regulation of the current shallow lake is required. The specific contents are as follows:

[0026] If the rebound risk prediction coefficient Ft exceeds the risk threshold, it indicates that the current shallow lake has rebounded abnormally after ammonia nitrogen treatment, and the No. 1 regulation mechanism will be triggered;

[0027] If the rebound risk prediction coefficient Ft does not exceed the risk threshold, it indicates that there is no abnormal rebound in the current shallow water lake after ammonia nitrogen treatment, and the No. 1 regulation mechanism will not be triggered at this time.

[0028] Preferably, the specific step S2 further includes:

[0029] S22: Start the No. 1 adjustment mechanism and dynamically adjust the aeration frequency based on the rebound risk prediction coefficient Ft to obtain the adjusted aeration response frequency BAF. The adjusted aeration response frequency BAF is specifically obtained by the following formula:

[0030] ;

[0031] Where, is the basic aeration frequency, is the response amplification factor, is the rebound risk prediction coefficient at the tth moment after governance, For the hyperbolic tangent function, use This is to ensure smooth control response;

[0032] S23: Ammonia nitrogen treatment is being carried out in the current shallow water lake according to the adjusted aeration response frequency BAF.

[0033] Preferably, the specific steps of S3 include:

[0034] S31: Based on S23, real-time monitoring and acquisition of ammonia nitrogen concentration change curve after aeration intervention in shallow lakes are performed, so as to extract preliminary ammonium ion concentration in water bodies after aeration intervention in shallow lakes from the ammonia nitrogen concentration change curve after aeration intervention in shallow lakes. , and based on the ammonia nitrogen concentration change curve after the aeration intervention in the shallow lake, re-execute the contents of S13 to S23 to re-determine the adjusted aeration response frequency BAF in S22, and re-update the ammonia nitrogen concentration change curve on the basis of re-determining the adjusted aeration response frequency BAF in S22, and extract the ammonium ion concentration in the water body after the aeration intervention in the shallow lake again. , the concentration of ammonium ions in the water after the aeration intervention in the shallow lake will be Marked as the concentration after intervention No. 2 , the concentration of ammonium ions in the water after the initial intervention of aeration in shallow lakes Marked as post-intervention concentration No. .

[0035] Preferably, the specific step S3 further includes:

[0036] S32: According to the concentration after intervention No. 1 obtained in S31 and the concentration after intervention , feedback is given on the effect analysis of the dynamic regulation of shallow lakes to obtain the two-time governance residual coefficient GRC, which is obtained by the following calculation method:

[0037] ;

[0038] ;

[0039] Where, and are the residual coefficients of the treatment after the initial intervention on aeration in shallow lakes and the residual coefficients of the treatment after the second intervention on aeration in shallow lakes, target concentration thresholds set for remediation;

[0040] S33: Repeat the contents of S31 and S32 to obtain several times of governance residual coefficients GRC, and arrange the several times of governance residual coefficients GRC in ascending order to obtain a numerical sequence, and extract the ammonia nitrogen concentration change curve after intervention corresponding to the first two groups of governance residual coefficients GRC from the numerical sequence.

[0041] Preferably, the specific step S3 further includes:

[0042] S34: According to the ammonia nitrogen concentration change curves after intervention corresponding to the first two groups of treatment residual coefficients GRC, determine the intervention numbers of the first two groups of treatment residual coefficients GRC, and according to the two groups of intervention numbers, determine the treatment residual coefficients GRC and the difference of treatment residual coefficients after intervention on aeration in shallow lakes under the two groups of intervention numbers ;

[0043] S35: The ammonia nitrogen concentration change curves after intervention corresponding to the first two groups of treatment residual coefficients GRC are triggered by the second regulation mechanism to achieve water pollution control in shallow lakes, specifically:

[0044] ;

[0045] Where, is the aeration response intensity after the xth intervention, is the base value of aeration intensity, is the governance residual coefficient after the xth intervention, is the difference in governance residual coefficients after the xth intervention, where x is the intervention number, and are the governance residual coefficients after the xth intervention and the difference in governance residual coefficients after the xth intervention The weight of

[0046] S36: Based on the content of S35, determine the aeration response intensity of the first two groups after intervention , and according to the aeration response intensity of the first two groups after intervention , respectively, carry out intensity intervention on the current shallow lakes, and obtain the ammonia nitrogen concentration change curve after the aeration intervention in the shallow lakes by monitoring again, and determine the treatment residual coefficient GRC of the first two groups after the intensity intervention. By comparing the treatment residual coefficient GRC of the first two groups after the intensity intervention, the aeration response intensity corresponding to the treatment residual coefficient GRC with the smallest value is selected. As a targeted intervention to control water pollution in shallow lakes.

[0047] A shallow lake water pollution control system includes a risk analysis module, a first intervention module and a second intervention module;

[0048] The risk analysis module is used to use underwater monitoring equipment to obtain the operational characteristics of shallow lake sediments in real time. Based on the operational characteristics, it evaluates the disturbance intensity and its risk of potential pollutant release to obtain the disturbance intensity index DIX. It also constructs ammonia nitrogen concentration change curves before and after ammonia nitrogen treatment, from which it extracts the dynamic behavior of the rebound trend. Based on the operational characteristics and ammonia nitrogen concentration change curves, it trains a risk prediction model to output the rebound risk prediction coefficient Ft.

[0049] The first intervention module will dynamically adjust and control the rebound risk prediction coefficient Ft to obtain the adjusted aeration response frequency BAF, and intervene in the aeration in the shallow lake according to the adjusted aeration response frequency BAF;

[0050] The second intervention module is used to monitor in real time the ammonia nitrogen concentration change curve after the aeration intervention in the shallow lake, to provide feedback on the effect analysis of dynamic regulation, and to re-execute the regulation mechanism to achieve water pollution control in the shallow lake.

[0051] The present invention provides a system and method for treating water pollution in shallow lakes, which has the following beneficial effects:

[0052] (1) Through step S1, the disturbance intensity index DIX and the ammonia nitrogen concentration change curve are constructed to achieve quantitative identification of sediment disturbance and pollution release behavior, and the rebound risk prediction model is trained based on this, and the rebound risk prediction coefficient Ft is output, which effectively improves the ability to predict the rebound trend of ammonia nitrogen pollution. In step S2, the adjusted aeration response frequency BAF is dynamically generated based on the rebound risk prediction coefficient Ft value, so that the aeration behavior is transformed from the traditional timing system to the risk-driven system, further reducing energy consumption and disturbance intensity, and improving treatment efficiency. Step S3 further introduces the treatment residual coefficient GRC to construct a complete feedback closed loop, realize accurate evaluation of each round of treatment effect and secondary strategy optimization, thereby avoiding the problem of effect regression or excessive disturbance after treatment. The overall method realizes the closed-loop control of the whole process from disturbance identification, risk prediction, response intervention to effect evaluation, and has the comprehensive treatment capabilities of feedforward prediction, adaptive regulation and multi-round optimization, which is suitable for ammonia nitrogen pollution control in various types of shallow lakes.

[0053] (2) By using sediment disturbance characteristics and ammonia nitrogen concentration change curves as model inputs in S16, combined with multi-dimensional parameters such as the historical ammonia nitrogen fluctuation coefficient, the disturbance intensity index DIX, and the ammonium ion concentration growth rate Rn, the trained neural network model can output a core indicator reflecting the intensity of pollution rebound. This prediction coefficient can detect potential risks after ammonia nitrogen treatment in advance. In S21, by comparing the rebound risk prediction coefficient Ft with the set risk threshold in real time, it can automatically determine whether there is a rebound anomaly and accurately trigger the No. 1 regulation mechanism, realizing the transformation of pollution control from post-intervention to active prediction response.

[0054] (3) By marking the concentrations of No. 1 and No. 2 after intervention and continuously revising the aeration response frequency (BAF) value based on the updated risk assessment results, the system can continuously iterate and optimize the treatment plan, gradually approaching the optimal control path. This method effectively avoids the problems of overexposure disturbance or response lag, improves the energy efficiency and timeliness of the treatment behavior, and realizes the precision, dynamic and closed-loop feedback optimization control of pollution control.

[0055] (4) In S34 to S35, the system constructs an aeration response intensity function based on the two sets of residual coefficients and their change differences. The aeration power is adaptively adjusted based on the degree of treatment deviation and the change trend, achieving a deep expansion from frequency regulation to intensity regulation. Finally, in S36, by comparing multiple groups of intervention intensities and response effects, the aeration intensity corresponding to the minimum treatment residual is selected as the final control strategy to achieve the target intervention in shallow lakes. This method establishes a closed-loop self-learning control mechanism of "intensity-effect-feedback-optimization" in multiple rounds of intervention, which can effectively avoid the response deviation problem caused by a single control strategy and achieve stable control and precise treatment delivery in high-frequency disturbance scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a schematic flow chart of a shallow lake water pollution control method according to the present invention;

[0057] Figure 2 This is an overall logic diagram of a shallow lake water pollution control method of the present invention;

[0058] Figure 3 This is a partial logic diagram of a shallow lake water pollution control method of the present invention;

[0059] Figure 4 This is a block diagram of a shallow lake water pollution control system according to the present invention. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0061] Example 1

[0062] See also Figures 1 to 3 The present invention provides a method for treating water pollution in shallow lakes, comprising the following steps:

[0063] S1: Use underwater monitoring equipment to obtain the operational characteristics of shallow lake sediments in real time. Based on the operational characteristics, evaluate the disturbance intensity and its potential risk of pollutant release (such as ammonia nitrogen) to obtain the disturbance intensity index DIX. Construct ammonia nitrogen concentration change curves before and after ammonia nitrogen treatment, and extract the dynamic behavior of the rebound trend from them. Use the operational characteristics and ammonia nitrogen concentration change curves to train a risk prediction model to output the rebound risk prediction coefficient Ft.

[0064] S2: Based on the rebound risk prediction coefficient Ft value, dynamic regulation is performed to obtain the adjusted aeration response frequency BAF, and aeration intervention is performed in shallow lakes based on the adjusted aeration response frequency BAF;

[0065] S3: Real-time monitoring of the ammonia nitrogen concentration change curve after the intervention of aeration in shallow lakes to provide feedback on the effect analysis of dynamic regulation in S2, and to re-execute the regulation mechanism to achieve water pollution control in shallow lakes.

[0066] In this embodiment, by constructing a governance process centered on disturbance behavior identification, ammonia nitrogen concentration trend extraction, risk prediction, and dynamic aeration regulation, the system realizes a fully closed-loop control mechanism of feedforward prediction, active response, and feedback optimization for ammonia nitrogen pollution in shallow lakes.

[0067] On the one hand, the disturbance intensity index (DIX) is used to quantify the potential risk of ammonia nitrogen release from sediment disturbance, improving the ability to identify endogenous pollution releases. On the other hand, based on the real-time monitoring of ammonia nitrogen concentration changes, rebound trends before and after treatment are extracted. The risk prediction coefficient (Ft) generated by training guides the dynamic adjustment of the aeration frequency (BAF), thus avoiding the "delayed response" caused by treatment rebound, energy waste, and ecological disturbance risks in traditional treatment methods. For example, during a lake treatment practice, the system monitored frequent sediment disturbance, low dissolved oxygen, and volatile ammonia nitrogen concentrations, with a rapidly increasing DIX value. At this time, the prediction model output Ft exceeded the threshold, and the system automatically increased the aeration frequency from 1 to 2.4 times per day as an emergency response. Subsequently, ammonia nitrogen concentrations were observed to stabilize and decrease, and the treatment residual coefficient (GRC) was significantly reduced, effectively suppressing the secondary rebound of ammonia nitrogen. This method achieves "on-demand aeration, quantitative control, and real-time correction", improving treatment efficiency, reducing operating costs, and enhancing the system's adaptability to complex pollution dynamics.

[0068] Among them, aeration is an intervention method that suppresses the anaerobic environment of the sediment by oxygenating it and reduces the release of ammonia nitrogen and phosphorus.

[0069] Example 2

[0070] Please refer to Figure 1 , specifically: S1 specific steps include:

[0071] S11: Install several sets of monitoring equipment in shallow lakes in advance to monitor and obtain the operational characteristics of shallow lake sediments in real time. The operational characteristics include the number of disturbance events in the shallow lake sediments during the monitoring period. , sediment ammonia nitrogen release intensity and the minimum dissolved oxygen in bottom water ;

[0072] S12: Based on the operating characteristics and after dimensionless processing of the information in the operating characteristics, the disturbance intensity and its potential risk to the release of pollutants (such as ammonia nitrogen) are evaluated to calculate the disturbance intensity index DIX. The disturbance intensity index DIX is obtained by the following calculation method:

[0073] ;

[0074] Where, Indicates the number of disturbance events during the monitoring period, including wind and waves, aquatic animals and mechanical agitation, Indicates the release intensity of ammonia nitrogen in sediment, Indicates the minimum dissolved oxygen in bottom water. Represents a small constant used to prevent division by zero errors; It is a logarithmic function; the log function can compress extreme values, making the indicator have a continuous, controllable, and smoothly changing response structure. When the pollution release intensity increases rapidly, if the log function is not used, the output value may be too large;

[0075] Number of disturbance events during the monitoring period It is used to reflect the frequency of sediment disturbance. The higher the value, the more frequent the disturbance, and the more likely it is to cause pollutant release. It is monitored and obtained through acoustic sediment disturbance probes.

[0076] Sediment ammonia nitrogen release intensity It is used to measure the release intensity of sediment pollutants. The larger the value, the higher the pollutant load in the sediment and the more likely it is to cause rebound. It uses ammonia nitrogen ion selective electrode sensors deployed at two depths of the sediment surface and the overlying water to obtain the difference in ammonia nitrogen concentration between the two layers in real time. Combined with the effective diffusion coefficient and the spacing between sampling points, an estimation model based on Fick's diffusion law is used to derive and calculate the ammonia nitrogen release rate from the sediment to the overlying water per unit time.

[0077] Minimum dissolved oxygen in bottom water Used to influence sediment release behavior. The lower the value, the easier it is to release (hence it appears in the denominator). It is monitored and obtained by an optical dissolved oxygen sensor.

[0078] pass , if the release is strong and the oxygen content is low, it is more likely to release ammonia nitrogen (with a high rebound risk); Represents the activity level of disturbance behavior, which is a combination logic similar to "trigger probability × danger level" (similar to the idea of ​​constructing risk factors in environmental risk calculation);

[0079] The disturbance intensity index DIX is used to indicate the intensity of disturbance and its potential risk of pollutant release. The higher the value of the disturbance intensity index DIX, the greater the risk of sediment disturbance and pollution release, and the higher the risk of endogenous pollution re-release.

[0080] The specific steps of S1 also include:

[0081] S13: The potential data in the water body is obtained in real time through the ammonia nitrogen ion selective electrode sensor, and the ammonia nitrogen concentration value is converted based on the Nernst equation. The ammonia nitrogen concentration sequence is continuously sampled and converted to form an ammonia nitrogen concentration change curve in the time dimension. Among them, the potential data refers to the electrode potential value E of the corresponding acquisition period. The Nernst equation is as follows:

[0082] ;

[0083] Where, is the standard electrode potential, is the gas constant, T is the temperature, is the ion charge number, F is the Faraday constant, is the ammonium ion concentration in water; since the response of the ion-selective electrode to ions is "logarithmic linear" (the potential increases by about 59 mV for every 10-fold change in concentration), it must be converted logarithmically.

[0084] S14: Extract the time point of each ammonia nitrogen treatment from the operation characteristics and mark it in the ammonia nitrogen concentration change curve to form the ammonia nitrogen concentration change curve before and after the ammonia nitrogen treatment. Extract the dynamic behavior of the rebound trend from the ammonia nitrogen concentration change curve before and after the ammonia nitrogen treatment, where the dynamic behavior includes the start date of each treatment. (reference benchmark) and on the corresponding governance start date The ammonium ion concentration in the water body every day thereafter ;

[0085] S15: Based on the dynamic behavior, analyze and calculate the daily growth rate Rn of the ammonium ion concentration in the water body after the corresponding treatment, specifically:

[0086] ;

[0087] Where, is the daily growth rate of ammonium ion concentration in the water body at time t after treatment, On the corresponding governance start date The ammonium ion concentration in the water at time t is: On the corresponding governance start date The concentration of ammonium ions in water at is the moment number, The corresponding governance start date.

[0088] In this embodiment, the present invention constructs a pollution control pre-modeling mechanism based on disturbance behavior identification and concentration trend tracking through the refined decomposition of step S1. First, through step S12, the system deploys underwater monitoring equipment to obtain the disturbance characteristics of the bottom sediment, and introduces the three factors of the number of disturbance events, ammonia nitrogen release rate and minimum dissolved oxygen to calculate the disturbance intensity index DIX, and quantify the risk of endogenous pollution release caused by disturbance. Secondly, S13 uses an ammonia nitrogen ion selective electrode sensor to collect potential data, and converts it into a continuous concentration sequence through the Nernst equation to form a concentration change curve before and after treatment, and then extracts the dynamic behavior of the rebound trend through the treatment mark, so as to realize the accurate identification of the pollution rebound period and response window. Finally, in S15, the daily growth rate Rn is calculated to form a dynamic rebound trend indicator chain, which provides a direct quantitative basis for risk prediction and regulatory decision-making.

[0089] For example, when a lake area initiated its first treatment on a certain day, monitoring from S13 to S15 revealed that ammonia nitrogen concentrations had been increasing at a rate of 0.22 mg / L per day since the start of treatment, while the DIX value reached a high of 2.91. The system immediately issued a high-risk warning, prompting the initiation of enhanced aeration intervention, further preventing the possibility of ammonia nitrogen concentration exceeding the standard later. This demonstrates that this method has the ability to identify and respond to rebound trends early, significantly improving the foresight and proactive nature of treatment.

[0090] Example 3

[0091] Please refer to Figure 1 Specifically: S1 includes the following steps:

[0092] S16: The operation characteristics and the ammonia nitrogen concentration change curve are used as the input information of the convolutional neural network model, and the input information is divided into a training set and a validation set after dimensionless processing to train and validate the convolutional neural network model. The trained convolutional neural network model is used as a risk prediction model, and the rebound risk prediction coefficient Ft is output from the output end of the risk prediction model. The rebound risk prediction coefficient Ft is obtained by the following calculation method:

[0093] ;

[0094] Where, is the rebound risk prediction coefficient at the tth moment after governance, is the historical ammonia nitrogen fluctuation coefficient (standard deviation, indicating system stability), 、 and They represent the disturbance intensity index DIX, the daily growth rate of ammonium ion concentration in the water body at the tth moment after treatment, and and historical ammonia nitrogen fluctuation coefficient The weighted coefficient can be obtained by calculating the risk prediction model;

[0095] The rebound risk prediction coefficient Ft is obtained by multi-dimensional fusion to determine whether there will be a rebound phenomenon of ammonia nitrogen in the future. The output rebound risk prediction coefficient Ft is the core control indicator of the entire system.

[0096] The aforementioned S1 step is used to construct a basic model for predicting the pollution "rebound trend".

[0097] The specific steps of S2 include:

[0098] S21: Pre-set the risk threshold and compare the risk threshold with the rebound risk prediction coefficient Ft to determine whether dynamic regulation of the current shallow lake is required. The specific contents are as follows:

[0099] If the rebound risk prediction coefficient Ft exceeds the risk threshold, it indicates that the current shallow lake has rebounded abnormally after ammonia nitrogen treatment, and the No. 1 regulation mechanism will be triggered;

[0100] If the rebound risk prediction coefficient Ft does not exceed the risk threshold, it indicates that there is no abnormal rebound in the current shallow water lake after ammonia nitrogen treatment, and the No. 1 regulation mechanism will not be triggered at this time.

[0101] In this embodiment, in step S16, the system takes the sediment disturbance operation characteristics and the ammonia nitrogen concentration change curve as input to construct multidimensional training data, and realizes effective training and verification of the CNN model through dimensionless processing and sample division. The rebound risk prediction coefficient Ft output by the model comprehensively integrates key indicators such as disturbance intensity DIX, ammonia nitrogen concentration growth rate Rn and historical fluctuation coefficient, and can dynamically evaluate the risk of pollution rebound.

[0102] Subsequently, by comparing Ft with the risk threshold set by the system, the No. 1 regulation mechanism is automatically triggered when the rebound risk prediction coefficient Ft exceeds the threshold, and precise aeration control intervention is carried out to prevent the spread of pollution. For example, if the ammonia nitrogen concentration in a certain lake area does not increase significantly on the third day after treatment, the CNN model identifies a high disturbance frequency, low oxygen level and large volatility. The calculated rebound risk prediction coefficient Ft = 0.82 is higher than the threshold of 0.75, which triggers an early aeration response, thereby avoiding the rebound peak that may occur on the fifth day. This mechanism has the advantages of "prediction first, active regulation", which significantly improves the stability and foresight of the treatment effect.

[0103] By constructing a dynamic prediction and response control process for ammonia nitrogen rebound in shallow lakes, the trend risk of "ammonia nitrogen rising again" can be identified in advance in the later stage of treatment, and the control mechanism can be linked to make intensity corrections to prevent the rebound of treatment from failing.

[0104] Example 4

[0105] Please refer to Figure 1 Specifically: S2 specific steps also include:

[0106] S22: Start the No. 1 adjustment mechanism and dynamically adjust the aeration frequency based on the rebound risk prediction coefficient Ft to obtain the adjusted aeration response frequency BAF. The adjusted aeration response frequency BAF is specifically obtained by the following formula:

[0107] ;

[0108] Where, is the basic aeration frequency (system default initial value), is the response amplification factor, used to control the adjustment amplitude, is the rebound risk prediction coefficient at the tth moment after governance, For the hyperbolic tangent function, use This is to ensure smooth control response and suppress extreme amplification;

[0109] S23: Ammonia nitrogen treatment is being carried out in the current shallow water lake according to the adjusted aeration response frequency BAF.

[0110] The specific steps of S3 include:

[0111] S31: Based on S23, real-time monitoring and acquisition of ammonia nitrogen concentration change curve after aeration intervention in shallow lakes are performed, so as to extract preliminary ammonium ion concentration in water bodies after aeration intervention in shallow lakes from the ammonia nitrogen concentration change curve after aeration intervention in shallow lakes. , and based on the ammonia nitrogen concentration change curve after the aeration intervention in the shallow lake, re-execute the contents of S13 to S23 to re-determine the adjusted aeration response frequency BAF in S22, and re-update the ammonia nitrogen concentration change curve on the basis of re-determining the adjusted aeration response frequency BAF in S22, and extract the ammonium ion concentration in the water body after the aeration intervention in the shallow lake again. , the concentration of ammonium ions in the water after the aeration intervention in the shallow lake will be Marked as the concentration after intervention No. 2 , the concentration of ammonium ions in the water after the initial intervention of aeration in shallow lakes Marked as post-intervention concentration No. .

[0112] The aforementioned S2 step is used to quantify the "potential rebound risk" currently faced by shallow lakes and serve as an input basis for subsequent regulation.

[0113] In this embodiment, the present invention realizes adaptive adjustment and response optimization of aeration frequency by introducing a dynamic control mechanism based on the rebound risk prediction coefficient Ft, thereby enhancing the control flexibility and closed-loop nature of ammonia nitrogen pollution rebound.

[0114] In S22, the system calls the hyperbolic tangent function to perform smooth amplification processing based on the Ft value to avoid sudden changes in aeration frequency due to abnormal disturbances, thereby obtaining the adjusted aeration response frequency BAF, and applying it to the actual aeration control process through S23 to effectively improve the control accuracy.

[0115] S31 further constructs a circular feedback mechanism to continuously obtain the ammonia nitrogen concentration change curve after aeration intervention, recalculate the aeration response frequency BAF and update the control strategy in real time, forming a closed-loop structure of "monitoring-adjustment-feedback-readjustment". This mechanism significantly improves the timeliness and intelligence of pollution control, avoids over-exposure disturbance and waste of resources, and is suitable for multiple rounds of ammonia nitrogen control in complex dynamic lake environments.

[0116] Example 5

[0117] Please refer to Figure 1 and Figure 3 , specifically: S3 specific steps also include:

[0118] S32: According to the concentration after intervention No. 1 obtained in S31 and the concentration after intervention , feedback is given on the effect analysis of the dynamic regulation of shallow lakes to obtain the two-time governance residual coefficient GRC, which is obtained by the following calculation method:

[0119] ;

[0120] ;

[0121] Where, and are the residual coefficients of the treatment after the initial intervention on aeration in shallow lakes and the residual coefficients of the treatment after the second intervention on aeration in shallow lakes, Target concentration thresholds set for remediation (e.g., national surface water standard Class I ≤ 1.0 mg / L);

[0122] The larger the governance residual coefficient GRC is, the more serious the deviation of the current governance effect from the target is;

[0123] S33: Repeat the contents of S31 and S32 to obtain several times of governance residual coefficients GRC, and arrange the several times of governance residual coefficients GRC in ascending order to obtain a numerical sequence, and extract the ammonia nitrogen concentration change curve after intervention corresponding to the first two groups of governance residual coefficients GRC from the numerical sequence.

[0124] The specific steps of S3 also include:

[0125] S34: According to the ammonia nitrogen concentration change curves after the intervention corresponding to the first two groups of treatment residual coefficients GRC, determine the intervention numbers (i.e., the number of interventions) of the first two groups of treatment residual coefficients GRC, and according to the two groups of intervention numbers, determine the treatment residual coefficients GRC and the difference of treatment residual coefficients after the intervention of aeration in shallow water lakes under the two groups of intervention numbers ;

[0126] S35: The ammonia nitrogen concentration change curves after intervention corresponding to the first two groups of treatment residual coefficients GRC are triggered by the second regulation mechanism to achieve water pollution control in shallow lakes, specifically:

[0127] ;

[0128] Where, is the aeration response intensity after the xth intervention, is the base value of aeration intensity, is the governance residual coefficient after the xth intervention, is the difference in governance residual coefficients after the xth intervention, where x is the intervention number, and are the governance residual coefficients after the xth intervention and the difference in governance residual coefficients after the xth intervention The weight of is used to adjust the response sensitivity (experience setting or learning optimization);

[0129] Among them, the difference of governance residual coefficient Refers to the difference between the governance residual coefficient after the xth intervention and the governance residual coefficient after the previous intervention. Indicates the deviation change trend, that is, whether the deviation is getting worse or slower, and is used to adjust the response acceleration trend; when only the difference in the residual coefficient of the treatment is considered When the current deviation is large but the change is small ( ≈0) may lead to misjudgment of system stability and stop governance. If the governance residual coefficient difference The inherent volatility is strong and easily affected by measurement interference, resulting in unstable control or oscillation;

[0130] The governance residual coefficient GRC is used to adjust the basic amplitude of the response. When only the governance residual coefficient GRC is considered, the system can only see the size of the deviation but cannot perceive whether the deviation is improving, which will cause excessive control (energy waste). The system cannot distinguish the potential loss of control caused by the worsening deviation, which will cause delayed response and miss the optimal governance window.

[0131] S36: Based on the content of S35, determine the aeration response intensity of the first two groups after intervention , and according to the aeration response intensity of the first two groups after intervention , respectively, carry out intensity intervention on the current shallow lakes, and obtain the ammonia nitrogen concentration change curve after the aeration intervention in the shallow lakes by monitoring again, and determine the treatment residual coefficient GRC of the first two groups after the intensity intervention. By comparing the treatment residual coefficient GRC of the first two groups after the intensity intervention, the aeration response intensity corresponding to the treatment residual coefficient GRC with the smallest value is selected. As a targeted intervention to control water pollution in shallow lakes.

[0132] The aforementioned S3 step is used to determine whether each round of control behavior is effective or lagging, providing a basis for closed-loop feedback, and building a "result identifier" for system governance performance, promoting continuous optimization of governance paths and intelligent evolution of strategies.

[0133] In this embodiment, the present invention constructs an iterative intensity intervention system for the control of ammonia nitrogen pollution in shallow lakes by introducing multi-round feedback analysis and response intensity optimization mechanism based on the control residual coefficient GRC, which greatly improves the control accuracy and decision-making optimization efficiency.

[0134] In steps S32 to S36, the system extracts the ammonia nitrogen concentration change curves under different intervention rounds, calculates the corresponding governance residual coefficient GRC, and constructs an ascending sequence based on the degree of deviation to determine the intervention number with relatively better response effect in history.

[0135] Furthermore, by comparing residual values ​​with residual differences, a second adjustment mechanism is introduced to calculate and apply differentiated aeration response intensities, enabling targeted intensity adjustments. After multiple rounds of intervention, the response intensity corresponding to the minimum deviation is ultimately selected as the target value by comparing the residual coefficients (GRC) of the new round of treatment, ensuring the system's self-optimization and convergence. In summary, this method further improves the consistency of treatment effects and target convergence capabilities, effectively avoiding issues such as response amplitude imbalance and strategy rigidity in traditional control, and embodies the evolution and self-regulation capabilities of intelligent pollution control.

[0136] Example 6

[0137] Please refer to Figure 4 ,Specifically: A shallow lake water pollution control system includes a risk analysis module, a first intervention module and a second intervention module;

[0138] The risk analysis module is used to use underwater monitoring equipment to obtain the operational characteristics of shallow lake sediments in real time. Based on the operational characteristics, it evaluates the disturbance intensity and its risk of potential pollutant release to obtain the disturbance intensity index DIX. It also constructs ammonia nitrogen concentration change curves before and after ammonia nitrogen treatment, from which it extracts the dynamic behavior of the rebound trend. Based on the operational characteristics and ammonia nitrogen concentration change curves, it trains a risk prediction model to output the rebound risk prediction coefficient Ft.

[0139] The first intervention module will dynamically adjust and control the rebound risk prediction coefficient Ft to obtain the adjusted aeration response frequency BAF, and intervene in the aeration in the shallow lake according to the adjusted aeration response frequency BAF;

[0140] The second intervention module is used to monitor in real time the ammonia nitrogen concentration change curve after the aeration intervention in the shallow lake, to provide feedback on the effect analysis of dynamic regulation, and to re-execute the regulation mechanism to achieve water pollution control in the shallow lake.

[0141] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for treating water pollution in shallow lakes, characterized by: The following steps are included: S1: Use underwater monitoring equipment to obtain the operational characteristics of shallow lake sediments in real time. Based on the operational characteristics, evaluate the disturbance intensity and its potential risk to pollutant release to obtain the disturbance intensity index DIX. Construct ammonia nitrogen concentration change curves before and after ammonia nitrogen treatment, and extract the dynamic behavior of the rebound trend from them. Use the operational characteristics and ammonia nitrogen concentration change curves to train a risk prediction model to output the rebound risk prediction coefficient Ft. S2: Based on the rebound risk prediction coefficient Ft value, dynamic regulation is performed to obtain the adjusted aeration response frequency BAF, and aeration intervention is performed in shallow lakes based on the adjusted aeration response frequency BAF; S3: Real-time monitoring of the ammonia nitrogen concentration change curve after the intervention of aeration in shallow lakes to provide feedback on the effect analysis of dynamic regulation in S2, and to re-execute the regulation mechanism to achieve water pollution control in shallow lakes.

2. A shallow lake water pollution control method according to claim 1, characterized in that: The specific steps of S1 include: S11: Install several sets of monitoring equipment in shallow lakes in advance to monitor and obtain the operational characteristics of shallow lake sediments in real time. The operational characteristics include the number of disturbance events in the shallow lake sediments during the monitoring period. , sediment ammonia nitrogen release intensity and the minimum dissolved oxygen in bottom water ; S12: Based on the operating characteristics and after dimensionless processing of the information in the operating characteristics, the disturbance intensity and its risk to the potential release of pollutants are evaluated to calculate the disturbance intensity index DIX. The disturbance intensity index DIX is obtained by the following calculation method: ； Where, represents the number of disturbance events during the monitoring period, Indicates the release intensity of ammonia nitrogen in sediment, Indicates the minimum dissolved oxygen in bottom water. Represents a small constant.

3. A shallow lake water pollution control method according to claim 2, characterized in that: The specific steps of S1 also include: S13: The potential data in the water body is obtained in real time through the ammonia nitrogen ion selective electrode sensor, and the ammonia nitrogen concentration value is converted based on the Nernst equation. The ammonia nitrogen concentration sequence is continuously sampled and converted to form an ammonia nitrogen concentration change curve in the time dimension. Among them, the potential data refers to the electrode potential value E of the corresponding acquisition period. The Nernst equation is as follows: ； Where, is the standard electrode potential, is the gas constant, T is the temperature, is the ion charge number, F is the Faraday constant, is the ammonium ion concentration in water; S14: Extract the time point of each ammonia nitrogen treatment from the operation characteristics and mark it in the ammonia nitrogen concentration change curve to form the ammonia nitrogen concentration change curve before and after the ammonia nitrogen treatment. Extract the dynamic behavior of the rebound trend from the ammonia nitrogen concentration change curve before and after the ammonia nitrogen treatment, where the dynamic behavior includes the start date of each treatment. and on the corresponding governance start date The ammonium ion concentration in the water body every day thereafter ; S15: Based on the dynamic behavior, analyze and calculate the daily growth rate Rn of the ammonium ion concentration in the water body after the corresponding treatment, specifically: ； Where, is the daily growth rate of ammonium ion concentration in the water body at time t after treatment, On the corresponding governance start date The ammonium ion concentration in the water at time t is: On the corresponding governance start date The concentration of ammonium ions in water at is the moment number, The corresponding governance start date.

4. A shallow lake water pollution control method according to claim 3, characterized in that: The specific steps of S1 also include: S16: The convolutional neural network model is trained and verified by taking the operating characteristics and the ammonia nitrogen concentration change curve as the input information of the convolutional neural network model, and dividing the input information into a training set and a validation set after dimensionless processing. The trained convolutional neural network model is used as a risk prediction model, and the rebound risk prediction coefficient Ft is output from the output end of the risk prediction model.

5. A shallow lake water pollution control method according to claim 4, characterized in that: The specific steps of S2 include: S21: Pre-set the risk threshold and compare the risk threshold with the rebound risk prediction coefficient Ft to determine whether dynamic regulation of the current shallow lake is required. The specific contents are as follows: If the rebound risk prediction coefficient Ft exceeds the risk threshold, it indicates that the current shallow lake has rebounded abnormally after ammonia nitrogen treatment, and the No. 1 regulation mechanism will be triggered; If the rebound risk prediction coefficient Ft does not exceed the risk threshold, it indicates that there is no abnormal rebound in the current shallow water lake after ammonia nitrogen treatment, and the No. 1 regulation mechanism will not be triggered at this time.

6. A shallow lake water pollution control method according to claim 5, characterized in that: The specific steps of S2 also include: S22: Start the No. 1 adjustment mechanism and dynamically adjust the aeration frequency based on the rebound risk prediction coefficient Ft to obtain the adjusted aeration response frequency BAF. The adjusted aeration response frequency BAF is specifically obtained by the following formula: ； Where, is the basic aeration frequency, is the response amplification factor, is the rebound risk prediction coefficient at the tth moment after governance, For the hyperbolic tangent function, use This is to ensure smooth control response; S23: Ammonia nitrogen treatment is being carried out in the current shallow water lake according to the adjusted aeration response frequency BAF.

7. A shallow lake water pollution control method according to claim 6, characterized in that: The specific steps of S3 include: S31: Based on S23, real-time monitoring and acquisition of ammonia nitrogen concentration change curve after aeration intervention in shallow lakes are performed, so as to extract preliminary ammonium ion concentration in water bodies after aeration intervention in shallow lakes from the ammonia nitrogen concentration change curve after aeration intervention in shallow lakes. , and based on the ammonia nitrogen concentration change curve after the aeration intervention in the shallow lake, re-execute the contents of S13 to S23 to re-determine the adjusted aeration response frequency BAF in S22, and re-update the ammonia nitrogen concentration change curve on the basis of re-determining the adjusted aeration response frequency BAF in S22, and extract the ammonium ion concentration in the water body after the aeration intervention in the shallow lake again. , the concentration of ammonium ions in the water after the aeration intervention in the shallow lake will be Marked as the concentration after intervention No. 2 , the concentration of ammonium ions in the water after the initial intervention of aeration in shallow lakes Marked as post-intervention concentration No. .

8. A shallow lake water pollution control method according to claim 7, characterized in that: The specific steps of S3 also include: S32: According to the concentration after intervention No. 1 obtained in S31 and the concentration after intervention , feedback is given on the effect analysis of the dynamic regulation of shallow lakes to obtain the two-time governance residual coefficient GRC, which is obtained by the following calculation method: ； ； Where, and are the residual coefficients of the treatment after the initial intervention on aeration in shallow lakes and the residual coefficients of the treatment after the second intervention on aeration in shallow lakes, target concentration thresholds set for remediation; S33: Repeat the contents of S31 and S32 to obtain several times of governance residual coefficients GRC, and arrange the several times of governance residual coefficients GRC in ascending order to obtain a numerical sequence, and extract the ammonia nitrogen concentration change curve after intervention corresponding to the first two groups of governance residual coefficients GRC from the numerical sequence.

9. The method for treating water pollution in shallow lakes according to claim 8, wherein: The specific steps of S3 also include: S34: According to the ammonia nitrogen concentration change curves after intervention corresponding to the first two groups of treatment residual coefficients GRC, determine the intervention numbers of the first two groups of treatment residual coefficients GRC, and according to the two groups of intervention numbers, determine the treatment residual coefficients GRC and the difference of treatment residual coefficients after intervention on aeration in shallow lakes under the two groups of intervention numbers ; S35: The ammonia nitrogen concentration change curves after intervention corresponding to the first two groups of treatment residual coefficients GRC are triggered by the second regulation mechanism to achieve water pollution control in shallow lakes, specifically: ； Where, is the aeration response intensity after the xth intervention, is the base value of aeration intensity, is the governance residual coefficient after the xth intervention, is the difference in governance residual coefficients after the xth intervention, where x is the intervention number, and are the governance residual coefficients after the xth intervention and the difference in governance residual coefficients after the xth intervention The weight of S36: Based on the content of S35, determine the aeration response intensity of the first two groups after intervention , and according to the aeration response intensity of the first two groups after intervention , respectively, carry out intensity intervention on the current shallow lakes, and obtain the ammonia nitrogen concentration change curve after the aeration intervention in the shallow lakes by monitoring again, and determine the treatment residual coefficient GRC of the first two groups after the intensity intervention. By comparing the treatment residual coefficient GRC of the first two groups after the intensity intervention, the aeration response intensity corresponding to the treatment residual coefficient GRC with the smallest value is selected. As a targeted intervention to control water pollution in shallow lakes.

10. A shallow lake water pollution control system, used to implement the shallow lake water pollution control method according to any one of claims 1 to 9, characterized in that: It includes a risk analysis module, a first intervention module and a second intervention module; The risk analysis module is used to use underwater monitoring equipment to obtain the operational characteristics of shallow lake sediments in real time. Based on the operational characteristics, it evaluates the disturbance intensity and its risk of potential pollutant release to obtain the disturbance intensity index DIX. It also constructs ammonia nitrogen concentration change curves before and after ammonia nitrogen treatment, from which it extracts the dynamic behavior of the rebound trend. Based on the operational characteristics and ammonia nitrogen concentration change curves, it trains a risk prediction model to output the rebound risk prediction coefficient Ft. The first intervention module will dynamically adjust and control the rebound risk prediction coefficient Ft to obtain the adjusted aeration response frequency BAF, and intervene in the aeration in the shallow lake according to the adjusted aeration response frequency BAF; The second intervention module is used to monitor in real time the ammonia nitrogen concentration change curve after the aeration intervention in the shallow lake, to provide feedback on the effect analysis of dynamic regulation, and to re-execute the regulation mechanism to achieve water pollution control in the shallow lake.

Images