Dynamic monitoring and early warning system for sewage treatment

Abstract

The invention discloses a dynamic monitoring and early warning system for sewage treatment, relates to the technical field of sewage treatment, and solves the technical problem of high cost of dynamic monitoring and early warning for sewage treatment in the prior art. According to the invention, the pollution evaluation coefficient of each monitoring area is calculated based on the sewage index data; acquiring the acquisition frequency of each monitoring area based on the pollution evaluation coefficient and the environmental data; inputting the sewage inflow of the regulating reservoir into a sewage inflow prediction model to obtain predicted sewage inflow; controlling the operation state of the lift pump based on the predicted water inflow and the water level information; and regulating and controlling the sewage treatment facility based on the early warning level. The method comprises the following steps: acquiring a maximum derivative value in a pollution degree fluctuation derivative function, and marking the maximum derivative value as a water quality stability characteristic value; the water quality stability characteristic value obtained through calculation can accurately reflect the water quality fluctuation condition of each monitoring area, and the cost of dynamic monitoring and early warning on sewage treatment can be reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of sewage treatment, and in particular is a dynamic monitoring and early warning system for sewage treatment. Background Art

[0002] With the acceleration of urbanization, the problem of urban sewage treatment has become increasingly prominent. Especially in the context of smart city construction, how to treat sewage efficiently and intelligently has become an important issue. Traditional sewage treatment methods mostly rely on physical, chemical and biological treatment technologies. Although these methods have certain efficiency in treating large-scale sewage, they usually lack sufficient flexibility and real-time response capabilities, and it is difficult to effectively treat specific pollutants. In recent years, with the introduction of Internet of Things technology, the Internet of Things technology can improve the intelligence level of sewage treatment by real-time monitoring of sewage quality and remote control of treatment facilities.

[0003] The existing technology realizes dynamic monitoring and early warning of sewage treatment by continuously collecting the water quality of sewage in the sewage pool and monitoring the changes in water quality. However, in the actual sewage treatment process, the pollution degree of sewage and the water inflow fluctuate greatly. It is difficult for the existing technology to collect stable sewage indicator data, resulting in low accuracy of dynamic monitoring and early warning of sewage treatment. In addition, most of the existing technologies use a fixed collection frequency to obtain the water quality of sewage. However, if the collection frequency is not reduced when the water quality of sewage is relatively stable, the cost of dynamic monitoring and early warning of sewage treatment will increase.

[0004] The present invention proposes a dynamic monitoring and early warning system for sewage treatment to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a dynamic monitoring and early warning system for sewage treatment, which is used to solve the problem that the pollution degree and water inflow of sewage in the actual sewage treatment process are relatively volatile, and the prior art is difficult to collect stable sewage index data, resulting in low accuracy of dynamic monitoring and early warning of sewage treatment; in addition, most of the prior art adopts a fixed collection frequency to obtain the water quality of sewage, but when the water quality of sewage is relatively stable, if the collection frequency is not reduced, it will lead to the technical problem of increased cost of dynamic monitoring and early warning of sewage treatment.

[0006] To achieve the above-mentioned object, the first aspect of the present invention provides a dynamic monitoring and early warning system for sewage treatment, comprising: a data processing module, and a data acquisition module and a monitoring and early warning module connected thereto;

[0007] The data acquisition module is used to divide the regulating pool into several monitoring areas; collect sewage index data and environmental data of each monitoring area in real time; and monitor the sewage inflow and water level information of the regulating pool in real time; wherein the sewage index data include nitrogen content, phosphorus content, pH value and dissolved oxygen concentration; and the environmental data include temperature and wind speed;

[0008] The data processing module is used to calculate the pollution assessment coefficient of each monitoring area based on the sewage index data; obtain the collection frequency of each monitoring area based on the pollution assessment coefficient and environmental data; and

[0009] The sewage inflow of the regulating tank is input into the sewage inflow prediction model to obtain the predicted sewage inflow; the operation state of the lift pump is controlled based on the predicted inflow and water level information; wherein the operation state includes on and off, and the sewage inflow prediction model is obtained by training the artificial intelligence model;

[0010] The monitoring and early warning module is used to determine the early warning level based on the pollution assessment coefficient; and to regulate the sewage treatment facilities based on the early warning level; wherein the early warning level includes level one early warning, level two early warning and level three early warning.

[0011] Preferably, the regulating pool is divided into several monitoring areas, including:

[0012] The regulating pond is divided into a number of monitoring areas, and the monitoring area is marked as i; wherein i = 1, 2, ..., n, and n is the total number of monitoring areas.

[0013] Preferably, the calculation of the pollution assessment coefficient of each monitoring area based on the sewage index data includes:

[0014] A1: Extract sewage index data;

[0015] A2: The pollution assessment coefficient WXi of the monitoring area i is calculated by the formula WXi=a×DHi+b×LHi+c×|PHi-7|+d×YHi; where DHi is the nitrogen content, LHi is the phosphorus content, PHi is the pH, YHi is the dissolved oxygen concentration, and a, b, c, and d are all proportional coefficients greater than 0.

[0016] Preferably, the acquisition frequency of each monitoring area based on the pollution assessment coefficient and environmental data includes:

[0017] B1: Extract the pollution assessment coefficient WXi and environmental data of each monitoring area;

[0018] B2: Obtain the water quality stability state of each monitoring area based on the pollution assessment coefficient; the water quality stability state includes high stability and low stability;

[0019] B3: The acquisition frequency CPi of the monitoring area with low stability in water quality stability is calculated by the formula CPi=(e×WXi+f×WD) / (h×FS+g); where WD is temperature, FS is wind speed, e, f, and h are all proportional coefficients greater than 0, and g is a non-zero constant and 0 <g<0.1;

[0020] B4: The water quality in the monitoring area with high stability is collected once a day.

[0021] It should be noted that the collection frequency refers to the number of times the data collection module collects the water quality of sewage in the monitoring area every day. When the calculated collection frequency CPi is a decimal, it is rounded up for processing.

[0022] The present invention obtains the water quality stability state of the monitoring area through the pollution assessment coefficient, and adopts the corresponding collection frequency according to the different water quality stability states of the monitoring area; for the monitoring area with low water quality stability, the corresponding collection frequency is calculated through a formula based on the pollution assessment coefficient and environmental data, and the collection frequency can be adaptively adjusted with the changes in the pollution degree and the environment, which is beneficial to improving the accuracy of dynamic monitoring and early warning of sewage treatment; for the monitoring area with high water quality stability, the collection frequency is set to once a day, which can save the energy and consumables of the detection device required in the process of collecting pollution index data, and is beneficial to reducing the cost of dynamic monitoring and early warning of sewage treatment.

[0023] Preferably, the step of obtaining the water quality stability state of each monitoring area based on the pollution assessment coefficient includes:

[0024] C1: Generate pollution degree fluctuation function based on pollution assessment coefficient;

[0025] C2: Derivative the pollution degree fluctuation function to obtain the pollution degree fluctuation derivative function;

[0026] C3: Obtain the maximum derivative value in the pollution degree fluctuation derivative function, and mark the maximum derivative value as the water quality stable characteristic value;

[0027] C4: Determine whether the water quality stability characteristic value is greater than the preset fluctuation threshold; if yes, mark the water quality stability state of the corresponding monitoring area as low stability; if no, mark the water quality stability state of the corresponding monitoring area as high stability.

[0028] The present invention generates a pollution degree fluctuation function based on a pollution assessment coefficient, and derives the pollution degree fluctuation function to obtain a pollution degree fluctuation derivative function; obtains a maximum derivative value in the pollution degree fluctuation derivative function, and marks the maximum derivative value as a water quality stability characteristic value; the calculated water quality stability characteristic value is able to accurately reflect the water quality fluctuation situation of each monitoring area, facilitates the subsequent setting of the corresponding collection frequency according to the water quality stability state of the monitoring area, is conducive to improving the accuracy of dynamic monitoring and early warning of sewage treatment, and is conducive to reducing the cost of dynamic monitoring and early warning of sewage treatment.

[0029] Preferably, generating a pollution degree fluctuation function based on the pollution assessment coefficient includes:

[0030] The pollution assessment coefficient corresponding to each regulating pool in several consecutive periods is extracted; the pollution degree fluctuation function corresponding to each regulating pool is obtained by taking time as the independent variable and the pollution assessment coefficient as the dependent variable.

[0031] Preferably, the sewage inflow prediction model is obtained by training an artificial intelligence model, including:

[0032] Extract the sewage inflow of several consecutive periods and integrate them into several groups of training data and test data; use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model according to the test results; finally obtain a sewage inflow prediction model whose input is the sewage inflow of several recent consecutive periods and whose output is the sewage inflow of the prediction period; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0033] The present invention extracts pollution assessment coefficients for training artificial intelligence models. After the training is completed, a sewage inflow prediction model is obtained. By inputting the sewage inflow of several consecutive cycles into the sewage inflow prediction model, the sewage inflow of the prediction cycle is obtained. The water level changes in the regulating tank can be predicted, which is convenient for timely adjustment of the operating status of the lifting pump, so that the workload of the sewage treatment equipment remains relatively stable, which is beneficial to improving the efficiency of dynamic monitoring and early warning of sewage treatment.

[0034] Preferably, the controlling the operating state of the lift pump based on the predicted water inflow and water level information includes:

[0035] D1: Extract predicted water inflow and water level information;

[0036] D2: Obtain the predicted water level based on the predicted water inflow and water level information;

[0037] D3: Determine whether the predicted water level is greater than the preset maximum water level; if yes, control the operation state of the lift pump to be on; if no, jump to D4;

[0038] D4: Determine whether the predicted water level is less than the preset minimum water level; if yes, control the operation state of the lift pump to be off; if no, jump to D1.

[0039] Preferably, obtaining the predicted water level based on the predicted water inflow and water level information includes:

[0040] Extract the predicted water inflow and water level information; calculate the predicted water level YSW by the formula YSW=α×SW+β×YJS+γ; where SW is the water level information, YJS is the predicted water inflow, α is the influence coefficient of the water level information, β is the influence coefficient of the predicted water inflow, γ is a constant, and α, β, and γ are all greater than 0.

[0041] Preferably, determining the warning level based on the pollution assessment coefficient includes:

[0042] E1: Extract pollution assessment coefficient WXi;

[0043] E2: Set the pollution range threshold [WY1, WY2], and WY1 <WY2;

[0044] E3: Determine whether the pollution assessment coefficient WXi is within the pollution range threshold [WY1, WY2]; if yes, mark the warning level as level 2 warning; if no, jump to E4;

[0045] E4: Determine whether the pollution assessment coefficient WXi is greater than WY2; if yes, mark the warning level as level one warning; if no, mark the warning level as level three warning.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] 1. The present invention obtains the water quality stability state of the monitoring area through the pollution assessment coefficient, and adopts the corresponding collection frequency according to the different water quality stability states of the monitoring area; for the monitoring area with low water quality stability, the corresponding collection frequency is calculated by the pollution assessment coefficient and environmental data through a formula, and the collection frequency can be adaptively adjusted with the changes in the pollution degree and the environment, which is beneficial to improve the accuracy of dynamic monitoring and early warning of sewage treatment; for the monitoring area with high water quality stability, the collection frequency is set to once a day, which can save the energy and consumables of the detection device required in the process of collecting pollution index data, and is beneficial to reduce the cost of dynamic monitoring and early warning of sewage treatment.

[0048] 2. The present invention generates a pollution degree fluctuation function based on the pollution assessment coefficient, and derives the pollution degree fluctuation function to obtain the pollution degree fluctuation derivative function; obtains the maximum derivative value in the pollution degree fluctuation derivative function, and marks the maximum derivative value as the water quality stability characteristic value; the calculated water quality stability characteristic value can accurately reflect the water quality fluctuation situation of each monitoring area, which is convenient for setting the corresponding collection frequency according to the water quality stability state of the monitoring area, which is beneficial to improving the accuracy of dynamic monitoring and early warning of sewage treatment and reducing the cost of dynamic monitoring and early warning of sewage treatment.

[0049] 3. The present invention extracts pollution assessment coefficients for training artificial intelligence models. After the training is completed, a sewage inflow prediction model is obtained. By inputting the sewage inflow of several consecutive cycles into the sewage inflow prediction model, the sewage inflow of the prediction cycle is obtained. The water level changes in the regulating tank can be predicted, which is convenient for timely adjustment of the operating status of the lifting pump, so that the workload of the sewage treatment equipment remains relatively stable, which is conducive to improving the efficiency of dynamic monitoring and early warning of sewage treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 It is a schematic diagram of the principle of the dynamic monitoring and early warning system for sewage treatment in the present invention;

[0052] Figure 2 It is an overall flow chart of the dynamic monitoring and early warning system for sewage treatment in the present invention;

[0053] Figure 3 This is a flow chart for obtaining the stable state of water quality in each monitoring area in the present invention. DETAILED DESCRIPTION

[0054] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] See also Figure 1-Figure 3, the first aspect of the present invention provides a dynamic monitoring and early warning system for sewage treatment, comprising: a data processing module, and a data acquisition module and a monitoring and early warning module connected thereto;

[0056] Data acquisition module: used to divide the regulating pool into several monitoring areas; collect sewage index data and environmental data of each monitoring area in real time; monitor the sewage inflow and water level information of the regulating pool in real time; sewage index data include nitrogen content, phosphorus content, pH and dissolved oxygen concentration; environmental data include temperature and wind speed;

[0057] Data processing module: used to calculate the pollution assessment coefficient of each monitoring area based on sewage index data; obtain the collection frequency of each monitoring area based on the pollution assessment coefficient and environmental data; and,

[0058] The sewage inflow of the regulating tank is input into the sewage inflow prediction model to obtain the predicted sewage inflow; the operation state of the lift pump is controlled based on the predicted inflow and water level information; wherein the operation state includes on and off, and the sewage inflow prediction model is obtained by training the artificial intelligence model;

[0059] Monitoring and early warning module: used to determine the early warning level based on the pollution assessment coefficient; to regulate the sewage treatment facilities based on the early warning level; among which, the early warning levels include level one, level two and level three.

[0060] In this embodiment, the regulating pool is divided into several monitoring areas, including:

[0061] The regulating pond is divided into a number of monitoring areas, and the monitoring area is marked as i; wherein i = 1, 2, ..., n, and n is the total number of monitoring areas.

[0062] Exemplarily, the area of ​​the regulating pond is divided into four monitoring areas, namely monitoring area 1, monitoring area 2, monitoring area 3 and monitoring area 4.

[0063] In this embodiment, the pollution assessment coefficient of each monitoring area is calculated based on the sewage index data, including:

[0064] A1: Extract sewage index data;

[0065] A2: The pollution assessment coefficient WXi of the monitoring area i is calculated by the formula WXi=a×DHi+b×LHi+c×|PHi-7|+d×YHi; where DHi is the nitrogen content, LHi is the phosphorus content, PHi is the pH, YHi is the dissolved oxygen concentration, and a, b, c, and d are all proportional coefficients greater than 0.

[0066] Exemplarily, set a=1, b=1.8, c=20, d=15; nitrogen content DH2=30 mg / L, phosphorus content LH2=12 mg / L, pH PH2=6.4, dissolved oxygen concentration YH2=2.8 mg / L; the pollution assessment coefficient WX2=105.6 of monitoring area 2 is calculated by the formula.

[0067] In this embodiment, the acquisition frequency of each monitoring area is obtained based on the pollution assessment coefficient and environmental data, including:

[0068] B1: Extract the pollution assessment coefficient WXi and environmental data of each monitoring area;

[0069] B2: Obtain the water quality stability state of each monitoring area based on the pollution assessment coefficient; the water quality stability state includes high stability and low stability;

[0070] B3: The acquisition frequency CPi of the monitoring area with low stability in water quality stability is calculated by the formula CPi=(e×WXi+f×WD) / (h×FS+g); where WD is temperature, FS is wind speed, e, f, and h are all proportional coefficients greater than 0, and g is a non-zero constant and 0 <g<0.1;

[0071] B4: The water quality in the monitoring area with high stability is collected once a day.

[0072] It should be noted that the collection frequency refers to the number of times the data collection module collects the water quality of sewage in the monitoring area every day. When the calculated collection frequency CPi is a decimal, it is rounded up for processing.

[0073] Exemplarily, set e=1, f=2, h=5, g=0.01, temperature WD=27°C, wind speed FS=3.5m / s, the water quality stable state of monitoring area 1 is high stability, the water quality stable state of monitoring area 2 is low stability, and the pollution assessment coefficient WX2=105.6 corresponding to monitoring area 2; the acquisition frequency CP2≈9.11 of monitoring area 2 is calculated by the formula, and the acquisition frequency CP2=10 is rounded up; since the water quality stable state of monitoring area 1 is high stability, the acquisition frequency of monitoring area 1 is set to once a day.

[0074] The present invention obtains the water quality stability state of the monitoring area through the pollution assessment coefficient, and adopts the corresponding collection frequency according to the different water quality stability states of the monitoring area; for the monitoring area with low water quality stability, the corresponding collection frequency is calculated through a formula based on the pollution assessment coefficient and environmental data, and the collection frequency can be adaptively adjusted with the changes in the pollution degree and the environment, which is beneficial to improving the accuracy of dynamic monitoring and early warning of sewage treatment; for the monitoring area with high water quality stability, the collection frequency is set to once a day, which can save the energy and consumables of the detection device required in the process of collecting pollution index data, and is beneficial to reducing the cost of dynamic monitoring and early warning of sewage treatment.

[0075] In this embodiment, the water quality stability state of each monitoring area is obtained based on the pollution assessment coefficient, including:

[0076] C1: Generate pollution degree fluctuation function based on pollution assessment coefficient;

[0077] C2: Derivative the pollution degree fluctuation function to obtain the pollution degree fluctuation derivative function;

[0078] C3: Obtain the maximum derivative value in the pollution degree fluctuation derivative function, and mark the maximum derivative value as the water quality stable characteristic value;

[0079] C4: Determine whether the water quality stability characteristic value is greater than the preset fluctuation threshold; if yes, mark the water quality stability state of the corresponding monitoring area as low stability; if no, mark the water quality stability state of the corresponding monitoring area as high stability.

[0080] Exemplarily, the maximum derivative value in the pollution degree fluctuation derivative function corresponding to monitoring area 1 is set to 0.3, and the maximum derivative value is marked as the water quality stability characteristic value; the fluctuation threshold is set to 0.5. Since the water quality stability characteristic value is less than the preset fluctuation threshold, the water quality stability state of monitoring area 1 is marked as high stability.

[0081] The present invention generates a pollution degree fluctuation function based on a pollution assessment coefficient, and derives the pollution degree fluctuation function to obtain a pollution degree fluctuation derivative function; obtains a maximum derivative value in the pollution degree fluctuation derivative function, and marks the maximum derivative value as a water quality stability characteristic value; the calculated water quality stability characteristic value is able to accurately reflect the water quality fluctuation situation of each monitoring area, facilitates the subsequent setting of the corresponding collection frequency according to the water quality stability state of the monitoring area, is conducive to improving the accuracy of dynamic monitoring and early warning of sewage treatment, and is conducive to reducing the cost of dynamic monitoring and early warning of sewage treatment.

[0082] In this embodiment, the pollution degree fluctuation function is generated based on the pollution assessment coefficient, including:

[0083] The pollution assessment coefficient corresponding to each regulating pool in several consecutive periods is extracted; the pollution degree fluctuation function corresponding to each regulating pool is obtained by taking time as the independent variable and the pollution assessment coefficient as the dependent variable.

[0084] In this embodiment, the sewage inflow prediction model is obtained by training an artificial intelligence model, including:

[0085] Extract the sewage inflow of several consecutive cycles and integrate them into several groups of original data, use 80% of the original data as training data and 20% as test data; use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model according to the test results; finally obtain a sewage inflow prediction model whose input is the sewage inflow of several recent consecutive cycles and whose output is the sewage inflow of the prediction cycle; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0086] The present invention extracts pollution assessment coefficients for training artificial intelligence models. After the training is completed, a sewage inflow prediction model is obtained. By inputting the sewage inflow of several consecutive cycles into the sewage inflow prediction model, the sewage inflow of the prediction cycle is obtained. The water level changes in the regulating tank can be predicted, which is convenient for timely adjustment of the operating status of the lifting pump, so that the workload of the sewage treatment equipment remains relatively stable, which is beneficial to improving the efficiency of dynamic monitoring and early warning of sewage treatment.

[0087] In this embodiment, the operation state of the lift pump is controlled based on the predicted water inflow and water level information, including:

[0088] D1: Extract predicted water inflow and water level information;

[0089] D2: Obtain the predicted water level based on the predicted water inflow and water level information;

[0090] D3: Determine whether the predicted water level is greater than the preset maximum water level; if yes, control the operation state of the lifting pump to be turned on, and the lifting pump pumps the sewage in the regulating tank to the sedimentation tank; if no, jump to D4;

[0091] D4: Determine whether the predicted water level is less than the preset minimum water level; if yes, control the operation state of the lift pump to be off; if no, jump to D1.

[0092] Exemplarily, the predicted water level YSW is set to 3.6m, the preset maximum water level is 3.2m, and the preset minimum water level is 2m; since the predicted water level is greater than the preset maximum water level, the operating state of the lift pump is controlled to be on, and the lift pump pumps the sewage in the regulating tank to the sedimentation tank.

[0093] The present invention obtains the predicted water level by predicting the water inflow and the current water level information of the regulating tank, and determines whether the predicted water level is between the preset minimum water level and the maximum water level, and controls the operating state of the lift pump according to the judgment result, so that the water level of the regulating tank is stabilized within the preset interval, thereby reducing the impact of the water level fluctuation of the regulating tank on the collection of pollution index data, which is beneficial to improving the accuracy of dynamic monitoring and early warning of sewage treatment.

[0094] In this embodiment, obtaining the predicted water level based on the predicted water inflow and water level information includes:

[0095] Extract the predicted water inflow and water level information; calculate the predicted water level YSW by the formula YSW=α×SW+β×YJS+γ; where SW is the water level information, YJS is the predicted water inflow, α is the influence coefficient of the water level information, β is the influence coefficient of the predicted water inflow, γ is a constant, and α, β, and γ are all greater than 0.

[0096] For example, α=1, β=0.05 / m 2 , γ=0.2m; water level information SW=2.4m, predicted water inflow YJS=20m 3 ; The predicted water level YSW=3.6m is calculated by the formula.

[0097] In this embodiment, the warning level is determined based on the pollution assessment coefficient, including:

[0098] E1: Extract pollution assessment coefficient WXi;

[0099] E2: Set the pollution range threshold [WY1, WY2], and WY1 <WY2;

[0100] E3: Determine whether the pollution assessment coefficient WXi is within the pollution range threshold [WY1, WY2]; if yes, mark the warning level as level 2 warning; if no, jump to E4;

[0101] E4: Determine whether the pollution assessment coefficient WXi is greater than WY2; if yes, mark the warning level as level one warning; if no, mark the warning level as level three warning.

[0102] Exemplarily, the pollution assessment coefficient WX1 is set to 113.6, and the pollution range threshold [WY1, WY2] is set to [100, 120]. Since the pollution assessment coefficient WX1 is within the pollution range threshold [WY1, WY2], the warning level is marked as a level 2 warning.

[0103] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0104] Working principle of the present invention:

[0105] The present invention divides a regulating tank into a number of monitoring areas; collects sewage index data and environmental data of each monitoring area in real time; monitors the sewage inflow and water level information of the regulating tank in real time; calculates the pollution assessment coefficient of each monitoring area based on the sewage index data; obtains the collection frequency of each monitoring area based on the pollution assessment coefficient and environmental data; inputs the sewage inflow of the regulating tank into a sewage inflow prediction model to obtain a predicted sewage inflow; controls the operating state of the lift pump based on the predicted inflow and water level information; determines the warning level based on the pollution assessment coefficient; and regulates the sewage treatment facilities based on the warning level.

[0106] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A dynamic monitoring and early warning system for sewage treatment, comprising: The data processing module, and the data acquisition module and monitoring and early warning module connected thereto are characterized in that: The data acquisition module is used to divide the regulating pool into several monitoring areas; collect sewage index data and environmental data of each monitoring area in real time; and monitor the sewage inflow and water level information of the regulating pool in real time; wherein the sewage index data include nitrogen content, phosphorus content, pH value and dissolved oxygen concentration; and the environmental data include temperature and wind speed; The data processing module is used to calculate the pollution assessment coefficient of each monitoring area based on the sewage index data; obtain the collection frequency of each monitoring area based on the pollution assessment coefficient and environmental data; and The sewage inflow of the regulating tank is input into the sewage inflow prediction model to obtain the predicted sewage inflow; the operation state of the lift pump is controlled based on the predicted inflow and water level information; wherein the operation state includes on and off, and the sewage inflow prediction model is obtained by training the artificial intelligence model; The monitoring and early warning module is used to determine the early warning level based on the pollution assessment coefficient; and to regulate the sewage treatment facilities based on the early warning level; wherein the early warning level includes level one early warning, level two early warning and level three early warning.

2. A dynamic monitoring and early warning system for sewage treatment according to claim 1, characterized in that: The regulating pool is divided into several monitoring areas, including: The regulating pond is divided into a number of monitoring areas, and the monitoring area is marked as i; wherein i = 1, 2, ..., n, and n is the total number of monitoring areas.

3. A dynamic monitoring and early warning system for sewage treatment according to claim 1, characterized in that: The calculation of the pollution assessment coefficient of each monitoring area based on the sewage index data includes: A1: Extract sewage index data; A2: The pollution assessment coefficient WXi of the monitoring area i is calculated by the formula WXi=a×DHi+b×LHi+c×|PHi-7|+d×YHi; where DHi is the nitrogen content, LHi is the phosphorus content, PHi is the pH, YHi is the dissolved oxygen concentration, and a, b, c, and d are all proportional coefficients greater than 0.

4. A dynamic monitoring and early warning system for sewage treatment according to claim 1, characterized in that: The acquisition frequency of each monitoring area based on the pollution assessment coefficient and environmental data includes: B1: Extract the pollution assessment coefficient WXi and environmental data of each monitoring area; B2: Obtain the water quality stability state of each monitoring area based on the pollution assessment coefficient; the water quality stability state includes high stability and low stability; B3: Calculate the acquisition frequency CPi of the monitoring area where the water quality is stable and the stability is low by the formula CPi=(e×WXi+f×WD) / (h×FS+g); where WD is the temperature, FS is the wind speed, e, f, and h are all proportional coefficients greater than 0, and g is a non-zero constant; B4: The water quality in the monitoring area with high stability is collected once a day.

5. A dynamic monitoring and early warning system for sewage treatment according to claim 4, characterized in that: The method of obtaining the stable state of water quality in each monitoring area based on the pollution assessment coefficient includes: C1: Generate pollution degree fluctuation function based on pollution assessment coefficient; C2: Derivative the pollution degree fluctuation function to obtain the pollution degree fluctuation derivative function; C3: Obtain the maximum derivative value in the pollution degree fluctuation derivative function, and mark the maximum derivative value as the water quality stable characteristic value; C4: Determine whether the water quality stability characteristic value is greater than the preset fluctuation threshold; if yes, mark the water quality stability state of the corresponding monitoring area as low stability; if no, mark the water quality stability state of the corresponding monitoring area as high stability.

6. A dynamic monitoring and early warning system for sewage treatment according to claim 5, characterized in that: The generating of the pollution degree fluctuation function based on the pollution assessment coefficient comprises: The pollution assessment coefficient corresponding to each regulating pool in several consecutive periods is extracted; the pollution degree fluctuation function corresponding to each regulating pool is obtained by taking time as the independent variable and the pollution assessment coefficient as the dependent variable.

7. A dynamic monitoring and early warning system for sewage treatment according to claim 1, characterized in that: The sewage inflow prediction model is obtained through artificial intelligence model training, including: Extract the sewage inflow of several consecutive periods and integrate them into several groups of training data and test data; use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model according to the test results; finally obtain a sewage inflow prediction model whose input is the sewage inflow of several recent consecutive periods and whose output is the sewage inflow of the prediction period; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

8. A dynamic monitoring and early warning system for sewage treatment according to claim 1, characterized in that: The controlling the operating state of the lift pump based on the predicted water inflow and water level information includes: D1: Extract predicted water inflow and water level information; D2: Obtain the predicted water level based on the predicted water inflow and water level information; D3: Determine whether the predicted water level is greater than the preset maximum water level; if yes, control the operation state of the lift pump to be on; if no, jump to D4; D4: Determine whether the predicted water level is less than the preset minimum water level; if yes, control the operation state of the lift pump to be off; if no, jump to D1.

9. A dynamic monitoring and early warning system for sewage treatment according to claim 8, characterized in that: The method of obtaining the predicted water level based on the predicted water inflow and water level information includes: Extract the predicted water inflow and water level information; calculate the predicted water level YSW by the formula YSW=α×SW+β×YJS+γ; where SW is the water level information, YJS is the predicted water inflow, α is the influence coefficient of the water level information, β is the influence coefficient of the predicted water inflow, γ is a constant, and α, β, and γ are all greater than 0.

10. A dynamic monitoring and early warning system for sewage treatment according to claim 1, characterized in that: Determining the warning level based on the pollution assessment coefficient includes: E1: Extraction of pollution assessment coefficient; E2: Set the pollution range threshold [WY1, WY2], and WY1 <WY2; E3: Determine whether the pollution assessment coefficient WXi is within the pollution range threshold [WY1, WY2]; if yes, mark the warning level as level 2 warning; if no, jump to E4; E4: Determine whether the pollution assessment coefficient is greater than WY2; if so, mark the warning level as level one; If not, the warning level will be marked as level three warning.

Images