Multi-stage water purification and recycling method and system for spray tower dust treatment

Abstract

The invention provides a multi-stage water quality purification and recycling method and system for spray tower dust treatment, and relates to the technical field, the method comprises the following steps: detecting spray tower wastewater quality parameters in real time through an online monitoring unit, obtaining water quality comprehensive evaluation parameters by a central controller based on multivariable coupling calculation, and comparing the water quality comprehensive evaluation parameters with a preset threshold value; and wastewater discharge and fresh water supplement are controlled. And the central controller also establishes a water quality prediction model based on a deep neural network, predicts the next discharge time point, and starts optimized discharge and water supplement control in advance, so that intelligent closed-loop control of the water quality of the waste water of the spray tower is realized, the water quality stability is improved, water is saved, and the operation cost is reduced.

Description

Technical Field

[0001] The invention relates to recycling technology, in particular to a multi-stage water purification and recycling method and system for spray tower dust treatment. Background Art

[0002] Spray towers are widely used in industrial production. In the production and processing industry of smart home panels, they are mainly used to treat wood chips, dust and other particles collected from the exhaust gas treatment of automated panel cutting lines. The working principle of the spray tower is to use liquid (usually water) to contact the flue gas, capture and settle the dust particles, and thus purify the flue gas. During the spraying process, the circulating water will continuously accumulate dust and dissolve harmful substances in the flue gas, causing the water quality to deteriorate.

[0003] Water quality monitoring is not timely: Traditional spray tower water quality monitoring relies on manual sampling and laboratory analysis, which has a lag and cannot reflect water quality changes in real time, making it difficult to effectively control water quality.

[0004] Serious waste of water resources: Due to the lack of scientific discharge and water replenishment strategies, conservative discharge strategies are often adopted, that is, frequent discharge of wastewater, resulting in a large amount of water resource waste.

[0005] Low control accuracy: Manual experience control cannot accurately calculate the discharge and water replenishment amounts, resulting in large fluctuations in the water quality of the spray tower, affecting purification efficiency and even causing secondary pollution. Summary of the invention

[0006] The embodiment of the present invention provides a multi-stage water purification and recycling method and system for spray tower dust treatment, which can solve the problems in the prior art.

[0007] According to a first aspect of the embodiments of the present invention,

[0008] Provide multi-stage water purification and recycling methods for spray tower dust treatment, including:

[0009] The wastewater from the spray tower first enters the first online monitoring unit, which performs real-time detection of the pH value, conductivity value and turbidity value in the wastewater from the spray tower; the central controller receives the pH value, conductivity value and turbidity value output by the first online monitoring unit, and obtains the comprehensive water quality evaluation parameter through multivariable coupling calculation based on the spray tower system pressure value collected by the pressure sensor and the system temperature value collected by the temperature sensor; the central controller compares the comprehensive water quality evaluation parameter with the preset control threshold value, and when the comprehensive water quality evaluation parameter is greater than the control threshold value, the central controller calculates the optimal discharge volume and discharge rate, generates a discharge control instruction, and controls the wastewater discharge pump to perform the discharge operation; the electromagnetic flowmeter records the dynamic data of the actual discharge volume and the actual discharge rate in real time;

[0010] The central controller calculates the optimal replenishment volume and replenishment rate of the replenishment water through an adaptive replenishment algorithm based on the dynamic data of the actual discharge volume and the actual discharge rate, combined with the comprehensive water quality evaluation parameters; the variable frequency replenishment pump replenishes fresh water to the spray tower system according to the optimal replenishment volume and the replenishment rate; the second online monitoring unit monitors the mixed water after replenishment with fresh water in real time, and calculates the comprehensive water quality evaluation parameters of the mixed water; the central controller compares the comprehensive water quality evaluation parameters of the mixed water with the target water quality threshold value, and when the comprehensive water quality evaluation parameters of the mixed water are greater than the target water quality threshold value, the adaptive replenishment algorithm recalculates the optimal replenishment volume and replenishment rate until the comprehensive water quality evaluation parameters of the mixed water are less than the target water quality threshold value;

[0011] The central controller establishes a water quality prediction model based on a deep neural network. The model uses the comprehensive water quality evaluation parameters, the actual discharge volume, the actual discharge rate, the optimal water replenishment volume, the water replenishment rate and the comprehensive water quality evaluation parameters of the mixed water as input variables to predict the time point when the next discharge is required; when the predicted time is less than the early warning threshold, the central controller starts the optimized discharge control instructions and water replenishment control instructions in advance; the water quality prediction model continuously optimizes the model parameters through online learning, improves the prediction accuracy, and realizes intelligent closed-loop control of the water quality of the spray tower wastewater.

[0012] The wastewater from the spray tower first enters the first online monitoring unit, which performs real-time detection of the pH value, conductivity value and turbidity value in the wastewater from the spray tower; the central controller receives the pH value, conductivity value and turbidity value output by the first online monitoring unit, and obtains the comprehensive water quality evaluation parameters through multivariable coupling calculation based on the pressure value of the spray tower system collected by the pressure sensor and the system temperature value collected by the temperature sensor, including:

[0013] The wastewater from the spray tower first enters the first online monitoring unit, which includes a double-structure composite glass pH electrode, a four-electrode conductivity sensor and a scattering turbidity meter; the double-structure composite glass pH electrode monitors the pH value of the wastewater from the spray tower in real time, the four-electrode conductivity sensor monitors the conductivity value of the wastewater from the spray tower in real time, and the scattering turbidity meter monitors the turbidity value of the wastewater from the spray tower in real time; the first online monitoring unit uses a median filtering algorithm to perform interference elimination processing on the pH value, the conductivity value and the turbidity value, and uses a Kalman filtering algorithm to perform noise smoothing processing on the data after the interference elimination processing, and transmits the processed pH value, the conductivity value and the turbidity value to the central controller through the RS485 bus;

[0014] The central controller receives the spray tower system pressure value collected by the pressure sensor and the system temperature value collected by the temperature sensor; the central controller calculates the pressure correction coefficient based on the system pressure value, and the pressure correction coefficient is the square root of the ratio of the system pressure value to the standard pressure value; the central controller calculates the temperature correction coefficient based on the system temperature value, and the temperature correction coefficient is the product of the temperature difference between the system temperature value and the standard temperature value and the temperature compensation coefficient plus one;

[0015] The central controller obtains comprehensive water quality evaluation parameters through multivariable coupling calculation, calculates pH value deviation, conductivity standardization value and turbidity standardization value, wherein the pH value deviation is the absolute difference between the pH value and the target pH value, the conductivity standardization value is the ratio of the conductivity value to the initial conductivity value, and the turbidity standardization value is the ratio of the turbidity value to the initial turbidity value; the pH value deviation, the conductivity standardization value, the turbidity standardization value, the pressure correction coefficient and the temperature correction coefficient are respectively multiplied by the weight coefficients obtained by least squares optimization and then summed to obtain the comprehensive water quality evaluation parameters characterizing the overall water quality of the spray tower wastewater.

[0016] The central controller compares the water quality comprehensive evaluation parameter with a preset control threshold. When the water quality comprehensive evaluation parameter is greater than the control threshold, the central controller calculates the optimal discharge volume and discharge rate, generates a discharge control instruction, and controls the wastewater discharge pump to perform the discharge operation; the electromagnetic flowmeter records the dynamic data of the actual discharge volume and the actual discharge rate in real time, including:

[0017] The control threshold and the three-level warning threshold are set based on the central controller, and the three-level warning threshold includes a first warning threshold, a second warning threshold and a third warning threshold; the central controller compares the comprehensive water quality evaluation parameter with the three-level warning threshold and the control threshold in sequence; when the comprehensive water quality evaluation parameter is greater than the first warning threshold, the central controller enters a warning state; when the comprehensive water quality evaluation parameter is greater than the second warning threshold, the central controller starts a preprocessing program;

[0018] When the water quality comprehensive evaluation parameter is greater than the third warning threshold, the central controller enters a ready state; when the water quality comprehensive evaluation parameter is greater than the control threshold, the central controller starts a drainage control instruction;

[0019] The central controller calculates the optimal discharge volume according to the comprehensive water quality evaluation parameters, the system nominal volume, the proportionality coefficient, and the change rate coefficient, and calculates the optimal discharge rate according to the optimal discharge volume, the reference discharge time, and the rate adjustment coefficient;

[0020] The optimal discharge volume calculation formula is as follows:

[0021]

[0022] Among them, V opt is the optimal discharge volume, V 0 is the nominal volume of the system, k p is the proportionality coefficient, Q is the current comprehensive water quality evaluation parameter, Q 0 is the target water quality benchmark value, k d is the rate of change coefficient, is the change rate of comprehensive water quality evaluation parameters;

[0023] The optimal emission rate calculation formula is as follows:

[0024]

[0025] Among them, R opt is the optimal discharge rate, T 0 is the reference emission time, α is the rate adjustment coefficient;

[0026] The calculation formula for comprehensive water quality evaluation parameters is as follows:

[0027]

[0028] Among them, P is the comprehensive evaluation parameter of water quality, w i is the weight parameter of the i-th water quality index, C i is the measured concentration value of the i-th water quality index, C i,std is the standard limit of the i-th water quality index, and n is the number of water quality indexes involved in the evaluation;

[0029] The formula for calculating the rate of change is as follows:

[0030]

[0031] Among them, Q t -Q t-Δt is the comprehensive evaluation parameter of water quality at the previous moment, Δt is the sampling time interval;

[0032] The central controller generates a discharge control instruction according to the optimal discharge volume and the optimal discharge rate, and controls the variable frequency pump to perform the drainage operation; the electromagnetic flowmeter adopts the vortex flow detection principle, has a built-in temperature and pressure compensation module, and collects the actual discharge volume and actual discharge rate in real time.

[0033] The central controller calculates the optimal replenishment volume and replenishment rate of the replenishment water through an adaptive replenishment algorithm based on the dynamic data of the actual discharge volume and the actual discharge rate, combined with the water quality comprehensive evaluation parameters; the variable frequency replenishment pump replenishes fresh water to the spray tower system according to the optimal replenishment volume and the replenishment rate; the second online monitoring unit monitors the mixed water after the fresh water is replenished in real time, and calculates the comprehensive water quality evaluation parameters of the mixed water, including:

[0034] The central controller calculates the system water loss value based on the dynamic data of the actual discharge volume and the actual discharge rate, and inputs the system water loss value and the water quality comprehensive evaluation parameter into the adaptive water replenishment algorithm; the central controller calculates the optimal water replenishment volume based on the system water loss value, the system operating volume, the water quality comprehensive evaluation parameter and the target water quality parameter through the adaptive water replenishment algorithm, and the optimal water replenishment volume is obtained by the product of the water balance weight and the system water loss value, the water quality adjustment weight, the difference between the water quality comprehensive evaluation parameter and the target water quality parameter, and the product of the system operating volume;

[0035] The optimal water replenishment volume calculation formula is as follows:

[0036] V supply =w v ·V loss +w q ·(QQ target )·V sys ;

[0037] Among them, V supply is the optimal water replenishment volume, w v is the water balance weight, V loss is the system water loss value, w q is the water quality regulation weight, Q target is the target water quality parameter, V sys is the system operating volume;

[0038] The system water loss value calculation formula is as follows:

[0039] V loss =V evap +V drift +V blow ;

[0040] Among them, V evap is the evaporation loss, V drift is the drift loss, V blow is the amount of sewage loss;

[0041] The calculation formula for dynamic adjustment of water balance weight is as follows:

[0042]

[0043] Among them, w v0 is the base water weight, k 1 is the adjustment coefficient, V target is the target operating volume;

[0044] The calculation formula for dynamic adjustment of water quality regulation weight is as follows:

[0045]

[0046] Among them, w q0 is the benchmark water quality weight, k 2 is the adjustment coefficient;

[0047] The central controller calculates the water replenishment rate based on the change rate of the comprehensive water quality evaluation parameter, and the water replenishment rate is obtained by the ratio of the optimal water replenishment volume to the reference water replenishment time, the product of the proportionality coefficient and the difference between the comprehensive water quality evaluation parameter and the target water quality parameter, and the product of the differential coefficient and the change rate of the comprehensive water quality evaluation parameter;

[0048] The water replenishment rate calculation formula is as follows:

[0049]

[0050] Among them, R supply is the water replenishment rate, T 0 is the benchmark water replenishment time, k p is the proportionality coefficient, k s is the differential coefficient;

[0051] The dynamic adjustment calculation formula of the proportional coefficient is as follows:

[0052]

[0053] Among them, k p0 is the base proportional coefficient, β is the adjustment coefficient;

[0054] The calculation formula for dynamic adjustment of differential coefficient is as follows:

[0055]

[0056] Among them, k d0 is the reference differential coefficient, γ is the attenuation coefficient;

[0057] The central controller generates a water replenishment control instruction according to the optimal water replenishment volume and the water replenishment rate, and controls the variable frequency water replenishment pump to replenish fresh water to the spray tower system;

[0058] The central controller adjusts the water balance weight in real time, and the adjustment amount of the water balance weight is the product of the first learning rate, the first control error and the water loss value; the central controller adjusts the water quality regulation weight in real time, and the adjustment amount of the water quality regulation weight is the product of the second learning rate, the second control error and the difference between the comprehensive water quality evaluation parameter and the target water quality parameter; the second online monitoring unit performs multi-parameter real-time monitoring of the mixed water after the fresh water is supplemented, and the central controller calculates the comprehensive water quality evaluation parameters of the mixed water after the fresh water is supplemented according to the multi-parameter real-time monitoring.

[0059] The central controller compares the comprehensive water quality evaluation parameter of the mixed water with the target water quality threshold. When the comprehensive water quality evaluation parameter of the mixed water is greater than the target water quality threshold, the adaptive water replenishment algorithm recalculates the optimal water replenishment volume and water replenishment rate until the comprehensive water quality evaluation parameter of the mixed water is less than the target water quality threshold. The method includes:

[0060] After the water replenishment of the spray tower system is completed based on the water replenishment control instruction, the water quality comprehensive evaluation parameter of the mixed water after the water replenishment is compared with the target water quality threshold value based on the central control instruction; when the water quality comprehensive evaluation parameter of the mixed water after the water replenishment is still greater than the target water quality threshold value, the adaptive water replenishment algorithm recalculates the optimal water replenishment volume and water replenishment rate;

[0061] The adaptive water replenishment algorithm calculates the optimal water replenishment volume and the water replenishment rate by an iterative optimization method; in each iteration, the central controller calculates the gradient value of the water replenishment volume and the gradient value of the water replenishment rate based on the objective function; the central controller uses the product of the adaptive learning rate and the gradient value of the water replenishment volume as the adjustment amount of the water replenishment volume, and uses the product of the adaptive learning rate and the gradient value of the water replenishment rate as the adjustment amount of the water replenishment rate;

[0062] The objective function calculation formula is as follows:

[0063] J(V supply , R supply )=w 1 (PQ tsrget ) 2 +w 2 (V sys -V target ) 2 +w 3 (ΔR supply );

[0064] Among them, J is the objective function value, w 1 , w 2 , w 3 is the weight coefficient, ΔR supplyis the change in water replenishment rate;

[0065] The calculation formula of water replenishment gradient value is as follows:

[0066]

[0067] in, is the water replenishment volume gradient, The sensitivity of water quality to replenishment volume;

[0068] The water replenishment rate gradient calculation formula is as follows:

[0069]

[0070] in, is the water replenishment rate gradient, is the sensitivity of water quality to the rate of water replenishment;

[0071] The adaptive learning rate calculation formula is as follows:

[0072]

[0073] Among them, η t is the learning rate of the current iteration, η 0 is the initial learning rate, η is the adaptive coefficient, t is the iteration coefficient, J t -J t-1 is the objective function value of the current and previous step;

[0074] The calculation formula for iterative update of water replenishment volume is as follows:

[0075]

[0076] in, is the updated water replenishment volume, is the current water replenishment volume, k is the number of water replenishment steps;

[0077] The iterative update calculation formula of the water replenishment rate is as follows:

[0078]

[0079] in, is the updated water replenishment rate, is the current water replenishment rate;

[0080] The central controller dynamically adjusts the adaptive learning rate based on the relative change of the objective function; the adjustment amount of the adaptive learning rate is the product of the adaptive learning rate and an exponential function, and the exponential term of the product of the exponential function is the inverse of the absolute value of the attenuation coefficient and the relative change of the objective function; the central controller repeatedly executes the above-mentioned iterative optimization process until the comprehensive water quality evaluation parameter of the mixed water is less than the target water quality threshold.

[0081] When the prediction time is less than the warning threshold, the central controller starts the optimized emission control command and water replenishment control command in advance; the water quality prediction model continuously optimizes the model parameters through online learning to improve the prediction accuracy and realize the intelligent closed-loop control of the wastewater quality of the spray tower, including:

[0082] When the prediction time is less than the warning threshold, the central controller starts the model prediction controller; the model prediction controller establishes an optimization objective function in the prediction time domain, and the optimization objective function includes a water quality prediction deviation term, a water replenishment change term, and a drainage change term; the model prediction controller optimizes the optimization objective function to obtain an optimized emission control instruction and an optimized water replenishment control instruction;

[0083] The central controller starts the optimized emission control instruction and the optimized water replenishment control instruction in advance; the central controller obtains actual water quality data after executing the optimized emission control instruction and the optimized water replenishment control instruction; the central controller inputs the actual water quality data into the water quality prediction model for online learning, and continuously optimizes the model parameters of the water quality prediction model;

[0084] The central controller updates the model parameters of the water quality prediction model by exponential sliding average, and the updated model parameters are the weighted average of the model parameters at the previous moment and the current model parameters; the central controller repeats the above prediction, optimization and control processes based on the updated water quality prediction model to realize intelligent closed-loop control of the water quality of the spray tower wastewater.

[0085] According to a second aspect of the embodiments of the present invention,

[0086] Provide multi-stage water purification and recycling system for spray tower dust treatment, including:

[0087] The first unit is used for the wastewater from the spray tower to first enter the first online monitoring unit, and the first online monitoring unit performs real-time detection on the pH value, conductivity value and turbidity value in the wastewater from the spray tower; the central controller receives the pH value, conductivity value and turbidity value output by the first online monitoring unit, and obtains the comprehensive water quality evaluation parameter through multivariable coupling calculation based on the pressure value of the spray tower system collected by the pressure sensor and the system temperature value collected by the temperature sensor; the central controller compares the comprehensive water quality evaluation parameter with a preset control threshold value, and when the comprehensive water quality evaluation parameter is greater than the control threshold value, the central controller calculates the optimal discharge volume and discharge rate, generates a discharge control instruction, and controls the wastewater discharge pump to perform the discharge operation; the electromagnetic flowmeter records the dynamic data of the actual discharge volume and the actual discharge rate in real time;

[0088] The second unit is used for the central controller to calculate the optimal replenishment volume and replenishment rate of the replenishment water through an adaptive replenishment algorithm based on the dynamic data of the actual discharge volume and the actual discharge rate, combined with the water quality comprehensive evaluation parameters; the variable frequency replenishment pump replenishes fresh water to the spray tower system according to the optimal replenishment volume and the replenishment rate; the second online monitoring unit monitors the mixed water after replenishment with fresh water in real time, and calculates the comprehensive water quality evaluation parameters of the mixed water; the central controller compares the comprehensive water quality evaluation parameters of the mixed water with the target water quality threshold value, and when the comprehensive water quality evaluation parameters of the mixed water are greater than the target water quality threshold value, the adaptive replenishment algorithm recalculates the optimal replenishment volume and replenishment rate until the comprehensive water quality evaluation parameters of the mixed water are less than the target water quality threshold value;

[0089] The third unit is used for the central controller to establish a water quality prediction model based on a deep neural network. The model uses the comprehensive water quality evaluation parameters, the actual discharge volume, the actual discharge rate, the optimal water replenishment volume, the water replenishment rate and the comprehensive water quality evaluation parameters of the mixed water as input variables to predict the time point when the next discharge is required; when the predicted time is less than the early warning threshold, the central controller starts the optimized discharge control instructions and water replenishment control instructions in advance; the water quality prediction model continuously optimizes the model parameters through online learning, improves the prediction accuracy, and realizes intelligent closed-loop control of the water quality of the spray tower wastewater.

[0090] According to a third aspect of the embodiments of the present invention,

[0091] An electronic device is provided, comprising:

[0092] processor;

[0093] a memory for storing processor-executable instructions;

[0094] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0095] A fourth aspect of the embodiments of the present invention is:

[0096] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0097] The beneficial effects of this application are as follows:

[0098] 1. The precise control and intelligent management of the wastewater quality of the spray tower has been achieved. By calculating the comprehensive evaluation parameters of water quality through multivariable coupling, and controlling discharge and replenishment according to real-time monitoring data and prediction models, the water quality can be effectively maintained within the target range, avoiding environmental pollution and reduced production efficiency caused by water quality deterioration.

[0099] 2. Improved water resource utilization efficiency. Through adaptive water replenishment algorithm and precise emission control, wastewater discharge can be minimized, and water resources can be recycled and reused, saving water resources and reducing production costs.

[0100] 3. Enhanced the system's predictive and adaptive capabilities. The water quality prediction model based on deep neural networks can predict the trend of water quality changes in advance and start the optimized control strategy in advance, improve the system's predictability and response capabilities, realize intelligent closed-loop control of the spray tower wastewater quality, reduce manual intervention, and improve the level of automation. BRIEF DESCRIPTION OF THE DRAWINGS

[0101] Figure 1 A schematic flow chart of a multi-stage water purification and recycling method for spray tower dust treatment according to an embodiment of the present invention;

[0102] Figure 2 It is a structural schematic diagram of a multi-stage water purification and recycling system for spray tower dust treatment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0103] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0104] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0105] Figure 1 FIG. 1 is a flow chart of a multi-stage water purification and recycling method for treating dust in a spray tower according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0106] Provide multi-stage water purification and recycling methods for spray tower dust treatment, including:

[0107] S11. The wastewater from the spray tower first enters the first online monitoring unit, which performs real-time detection of the pH value, conductivity value and turbidity value in the wastewater from the spray tower; the central controller receives the pH value, conductivity value and turbidity value output by the first online monitoring unit, and obtains the comprehensive water quality evaluation parameter through multivariable coupling calculation based on the spray tower system pressure value collected by the pressure sensor and the system temperature value collected by the temperature sensor; the central controller compares the comprehensive water quality evaluation parameter with the preset control threshold value, and when the comprehensive water quality evaluation parameter is greater than the control threshold value, the central controller calculates the optimal discharge volume and discharge rate, generates a discharge control instruction, and controls the wastewater discharge pump to perform the discharge operation; the electromagnetic flowmeter records the dynamic data of the actual discharge volume and the actual discharge rate in real time;

[0108] S12. The central controller calculates the optimal replenishment volume and replenishment rate of the replenishment water through an adaptive replenishment algorithm based on the dynamic data of the actual discharge volume and the actual discharge rate, combined with the comprehensive water quality evaluation parameters; the variable frequency replenishment pump replenishes fresh water to the spray tower system according to the optimal replenishment volume and the replenishment rate; the second online monitoring unit monitors the mixed water after replenishment with fresh water in real time, and calculates the comprehensive water quality evaluation parameters of the mixed water; the central controller compares the comprehensive water quality evaluation parameters of the mixed water with the target water quality threshold value, and when the comprehensive water quality evaluation parameters of the mixed water are greater than the target water quality threshold value, the adaptive replenishment algorithm recalculates the optimal replenishment volume and replenishment rate until the comprehensive water quality evaluation parameters of the mixed water are less than the target water quality threshold value;

[0109] S13. The central controller establishes a water quality prediction model based on a deep neural network. The model uses the comprehensive water quality evaluation parameters, the actual discharge volume, the actual discharge rate, the optimal water replenishment volume, the water replenishment rate and the comprehensive water quality evaluation parameters of the mixed water as input variables to predict the time point when the next discharge is required; when the predicted time is less than the early warning threshold, the central controller starts the optimized discharge control instructions and water replenishment control instructions in advance; the water quality prediction model continuously optimizes the model parameters through online learning, improves the prediction accuracy, and realizes intelligent closed-loop control of the water quality of the spray tower wastewater.

[0110] In an optional embodiment, the spray tower wastewater first enters the first online monitoring unit, which performs real-time detection of the pH value, conductivity value and turbidity value in the spray tower wastewater; the central controller receives the pH value, conductivity value and turbidity value output by the first online monitoring unit, and obtains the comprehensive water quality evaluation parameters through multivariable coupling calculation based on the spray tower system pressure value collected by the pressure sensor and the system temperature value collected by the temperature sensor, including:

[0111] The wastewater from the spray tower first enters the first online monitoring unit, which includes a double-structure composite glass pH electrode, a four-electrode conductivity sensor and a scattering turbidity meter; the double-structure composite glass pH electrode monitors the pH value of the wastewater from the spray tower in real time, the four-electrode conductivity sensor monitors the conductivity value of the wastewater from the spray tower in real time, and the scattering turbidity meter monitors the turbidity value of the wastewater from the spray tower in real time; the first online monitoring unit uses a median filtering algorithm to perform interference elimination processing on the pH value, the conductivity value and the turbidity value, and uses a Kalman filtering algorithm to perform noise smoothing processing on the data after the interference elimination processing, and transmits the processed pH value, the conductivity value and the turbidity value to the central controller through the RS485 bus;

[0112] The central controller receives the spray tower system pressure value collected by the pressure sensor and the system temperature value collected by the temperature sensor; the central controller calculates the pressure correction coefficient based on the system pressure value, and the pressure correction coefficient is the square root of the ratio of the system pressure value to the standard pressure value; the central controller calculates the temperature correction coefficient based on the system temperature value, and the temperature correction coefficient is the product of the temperature difference between the system temperature value and the standard temperature value and the temperature compensation coefficient plus one;

[0113] The central controller obtains comprehensive water quality evaluation parameters through multivariable coupling calculation, calculates pH value deviation, conductivity standardization value and turbidity standardization value, wherein the pH value deviation is the absolute difference between the pH value and the target pH value, the conductivity standardization value is the ratio of the conductivity value to the initial conductivity value, and the turbidity standardization value is the ratio of the turbidity value to the initial turbidity value; the pH value deviation, the conductivity standardization value, the turbidity standardization value, the pressure correction coefficient and the temperature correction coefficient are respectively multiplied by the weight coefficients obtained by least squares optimization and then summed to obtain the comprehensive water quality evaluation parameters characterizing the overall water quality of the spray tower wastewater.

[0114] The online monitoring and comprehensive evaluation method of spray tower wastewater quality is implemented as follows:

[0115] First, the wastewater discharged from the spray tower is monitored online in real time. The wastewater is introduced into the first online monitoring unit, which is equipped with a variety of sensors for measuring different water quality parameters. Among them, the double-structure composite glass pH electrode is responsible for monitoring the pH value of the wastewater, the four-electrode conductivity sensor is responsible for monitoring the conductivity value of the wastewater, and the scattering turbidity meter is responsible for monitoring the turbidity value of the wastewater.

[0116] In order to ensure the accuracy of the measurement data, the collected pH value, conductivity value and turbidity value are processed. First, the median filter algorithm is used to remove possible abnormal interference data. For example, a window containing 5 consecutive measurement values ​​is set, the values ​​in the window are sorted, and the middle value is taken as the final value. This can effectively remove sudden spikes or outliers. Then, the Kalman filter algorithm is used to smooth the data after median filtering to further reduce the impact of noise and make the data more stable and reliable. For example, the Kalman filter algorithm is used to predict the range of the next measurement value, and the actual measurement value and the predicted value are weighted averaged to obtain a more accurate value. Finally, the processed pH value, conductivity value and turbidity value are transmitted to the central controller through the RS485 bus to provide a data basis for subsequent comprehensive evaluation.

[0117] At the same time, the central controller receives signals from the pressure sensor and temperature sensor to obtain the pressure and temperature values ​​of the spray tower system respectively. These parameters will affect the measurement results of water quality parameters, so they need to be corrected.

[0118] In order to eliminate the influence of pressure on the measurement results, the central controller calculates the pressure correction coefficient based on the collected system pressure value. The specific calculation method is: compare the system pressure value with the preset standard pressure value, calculate the square root of the ratio of the two, and obtain the pressure correction coefficient. For example, if the system pressure value is 1.2 standard atmospheres and the standard pressure value is 1 standard atmosphere, the pressure correction coefficient is the square root of 1.2, which is about 1.095.

[0119] Similarly, in order to eliminate the influence of temperature on the measurement results, the central controller calculates the temperature correction coefficient based on the collected system temperature value. The specific calculation method is: compare the system temperature value with the preset standard temperature value, calculate the difference between the two, then multiply the difference with the preset temperature compensation coefficient, and finally add 1 to the result to obtain the temperature correction coefficient. For example, if the system temperature value is 25 degrees Celsius, the standard temperature value is 20 degrees Celsius, and the temperature compensation coefficient is 0.02, then the temperature correction coefficient is (25-20)*0.02+1=1.1.

[0120] After the central controller obtains all the necessary data, it starts multivariable coupling calculation to obtain the final comprehensive water quality evaluation parameters. First, the pH deviation is calculated, that is, the currently measured pH value is compared with the preset target pH value, and the absolute value of the difference between the two is taken. For example, if the current pH value is 7.5 and the target pH value is 7, the pH deviation is |7.5-7|=0.5. Then, the conductivity standardization value is calculated, that is, the currently measured conductivity value is compared with the initial conductivity value, and the ratio between the two is calculated. For example, if the current conductivity value is 1000 microSiemens / cm and the initial conductivity value is 800 microSiemens / cm, the conductivity standardization value is 1000 / 800=1.25. Similarly, the turbidity standardization value is calculated, that is, the currently measured turbidity value is compared with the initial turbidity value, and the ratio between the two is calculated.

[0121] Finally, the pH deviation, conductivity standardization value, turbidity standardization value, pressure correction coefficient and temperature correction coefficient are respectively multiplied by the weight coefficients obtained by the least squares method optimization in advance, and then all the products are added to obtain the final comprehensive water quality evaluation parameter. This parameter comprehensively reflects the overall water quality of the spray tower wastewater. For example, assuming that the weight coefficient of pH deviation is 0.3, the weight coefficient of conductivity standardization value is 0.2, the weight coefficient of turbidity standardization value is 0.2, the weight coefficient of pressure correction coefficient is 0.15, and the weight coefficient of temperature correction coefficient is 0.15, then the comprehensive water quality evaluation parameter is 0.3*0.5+0.2*1.25+0.2*1.1+0.15*1.095+0.15*1.1=1.03.

[0122] The solution of this application can:

[0123] Improve monitoring accuracy: By using median filtering and Kalman filtering algorithms to process online monitoring data, interference and noise are effectively eliminated, and the accuracy and reliability of monitoring data are improved. Realize comprehensive water quality evaluation: Through multivariable coupling calculation, multiple water quality parameters and system parameters are comprehensively considered to obtain a more comprehensive and objective evaluation result of spray tower wastewater quality. Facilitate real-time monitoring and early warning: This method realizes online monitoring and real-time evaluation of spray tower wastewater quality, which can detect water quality abnormalities in a timely manner, provide a basis for taking corresponding control measures, and avoid environmental pollution.

[0124] In an optional embodiment, the central controller compares the water quality comprehensive evaluation parameter with a preset control threshold. When the water quality comprehensive evaluation parameter is greater than the control threshold, the central controller calculates the optimal discharge volume and discharge rate, generates a discharge control instruction, and controls the wastewater discharge pump to perform the discharge operation; the electromagnetic flowmeter records the dynamic data of the actual discharge volume and the actual discharge rate in real time, including:

[0125] The control threshold and the three-level warning threshold are set based on the central controller, and the three-level warning threshold includes a first warning threshold, a second warning threshold and a third warning threshold; the central controller compares the comprehensive water quality evaluation parameter with the three-level warning threshold and the control threshold in sequence; when the comprehensive water quality evaluation parameter is greater than the first warning threshold, the central controller enters a warning state; when the comprehensive water quality evaluation parameter is greater than the second warning threshold, the central controller starts a preprocessing program;

[0126] When the water quality comprehensive evaluation parameter is greater than the third warning threshold, the central controller enters a ready state; when the water quality comprehensive evaluation parameter is greater than the control threshold, the central controller starts a drainage control instruction;

[0127] The central controller calculates the optimal discharge volume according to the comprehensive water quality evaluation parameters, the system nominal volume, the proportionality coefficient, and the change rate coefficient, and calculates the optimal discharge rate according to the optimal discharge volume, the reference discharge time, and the rate adjustment coefficient;

[0128] The optimal discharge volume calculation formula is as follows:

[0129]

[0130] Among them, V opt is the optimal discharge volume, V 0 is the nominal volume of the system, k p is the proportionality coefficient, Q is the current comprehensive water quality evaluation parameter, Q 0 is the target water quality benchmark value, k d is the rate of change coefficient, is the change rate of comprehensive water quality evaluation parameters;

[0131] The optimal emission rate calculation formula is as follows:

[0132]

[0133] Among them, R opt is the optimal discharge rate, T 0 is the reference emission time, α is the rate adjustment coefficient;

[0134] The calculation formula for comprehensive water quality evaluation parameters is as follows:

[0135]

[0136] Among them, P is the comprehensive evaluation parameter of water quality, w i is the weight parameter of the i-th water quality index, C i is the measured concentration value of the i-th water quality index, C i,std is the standard limit of the i-th water quality index, and n is the number of water quality indexes involved in the evaluation;

[0137] The formula for calculating the rate of change is as follows:

[0138]

[0139] Among them, Q t -Q t-Δt is the comprehensive evaluation parameter of water quality at the previous moment, Δt is the sampling time interval;

[0140] The central controller generates a discharge control instruction according to the optimal discharge volume and the optimal discharge rate, and controls the variable frequency pump to perform the drainage operation; the electromagnetic flowmeter adopts the vortex flow detection principle, has a built-in temperature and pressure compensation module, and collects the actual discharge volume and actual discharge rate in real time.

[0141] The invention discloses a wastewater intelligent discharge control system and method, which aims to intelligently control wastewater discharge according to real-time water quality conditions, avoid excessive discharge, and protect the water environment.

[0142] First, the system monitors water quality in real time. Multiple sensors simultaneously monitor multiple water quality indicators, such as chemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, etc., and transmit the monitoring data to the central controller. For example, at a certain moment, the chemical oxygen demand is monitored to be 80mg / L, ammonia nitrogen is 15mg / L, total phosphorus is 2mg / L, and total nitrogen is 25mg / L.

[0143] Next, the system conducts a comprehensive water quality evaluation. The central controller compares the measured concentration values ​​of each water quality indicator with its corresponding standard limit, and calculates the comprehensive water quality evaluation parameters based on the preset weight parameters.

[0144] Subsequently, the system performs early warning and pretreatment. The central controller compares the calculated water quality comprehensive evaluation parameters with the preset three-level early warning threshold and control threshold. Assume that the first early warning threshold is 0.6, the second early warning threshold is 0.7, the third early warning threshold is 0.8, and the control threshold is 0.9. Since the current water quality comprehensive evaluation parameter 0.76 is greater than the second early warning threshold 0.7, the central controller starts the pretreatment program, such as increasing the aeration volume, adding chemicals, etc., to improve the water quality.

[0145] If the comprehensive water quality evaluation parameters continue to rise and exceed the control threshold, the system will start intelligent discharge control. The central controller calculates the optimal discharge volume based on the current comprehensive water quality evaluation parameters, system nominal volume, proportional coefficient, and change rate coefficient.

[0146] Then, the central controller calculates the optimal discharge rate according to the optimal discharge volume, the reference discharge time, and the rate adjustment coefficient. Assuming that the reference discharge time is 2 hours and the rate adjustment coefficient is 0.8, the optimal discharge rate is 136 / (2*0.8)=85 cubic meters / hour.

[0147] Finally, the central controller generates a discharge control instruction based on the calculated optimal discharge volume and optimal discharge rate, and controls the variable frequency pump to perform the drainage operation. The electromagnetic flowmeter records the actual discharge volume and actual discharge rate in real time, and feeds the data back to the central controller to form a closed-loop control.

[0148] The solution of this application can:

[0149] Improve the effect of water environment protection: through real-time monitoring of water quality and intelligent control of emissions, avoid excessive emissions, effectively reduce the total amount of pollutant emissions, and significantly improve the quality of the water environment. Realize refined management: Based on the multi-level early warning and control mechanism of comprehensive water quality evaluation parameters and preset thresholds, the refined management of wastewater discharge is realized, and the efficiency of water pollution control is improved. Reduce operating costs: The system intelligently adjusts the discharge volume and rate according to the water quality conditions, avoiding unnecessary excessive treatment and energy consumption, and saving operating costs.

[0150] In an optional embodiment, the central controller calculates the optimal replenishment volume and replenishment rate of the replenishment water through an adaptive replenishment algorithm based on the dynamic data of the actual discharge volume and the actual discharge rate, combined with the water quality comprehensive evaluation parameters; the variable frequency replenishment pump replenishes fresh water to the spray tower system according to the optimal replenishment volume and the replenishment rate; the second online monitoring unit monitors the mixed water after the fresh water is replenished in real time, and calculates the comprehensive water quality evaluation parameters of the mixed water, including:

[0151] The central controller calculates the system water loss value based on the dynamic data of the actual discharge volume and the actual discharge rate, and inputs the system water loss value and the water quality comprehensive evaluation parameter into the adaptive water replenishment algorithm; the central controller calculates the optimal water replenishment volume based on the system water loss value, the system operating volume, the water quality comprehensive evaluation parameter and the target water quality parameter through the adaptive water replenishment algorithm, and the optimal water replenishment volume is obtained by the product of the water balance weight and the system water loss value, the water quality adjustment weight, the difference between the water quality comprehensive evaluation parameter and the target water quality parameter, and the product of the system operating volume;

[0152] The optimal water replenishment volume calculation formula is as follows:

[0153] V supply =w v ·V loss +w q ·(QQ target )·V sys ;

[0154] Among them, V supply is the optimal water replenishment volume, w v is the water balance weight, V loss is the system water loss value, w q is the water quality regulation weight, Q target is the target water quality parameter, V sys is the system operating volume;

[0155] The system water loss value calculation formula is as follows:

[0156] V loss =V evap +V drift +V blow ;

[0157] Among them, V evap is the evaporation loss, V drift is the drift loss, V blow is the amount of sewage loss;

[0158] The calculation formula for dynamic adjustment of water balance weight is as follows:

[0159]

[0160] Among them, w v0 is the base water weight, k 1 is the adjustment coefficient, V target is the target operating volume;

[0161] The calculation formula for dynamic adjustment of water quality regulation weight is as follows:

[0162]

[0163] Among them, w q0 is the benchmark water quality weight, k 2 is the adjustment coefficient;

[0164] The central controller calculates the water replenishment rate based on the change rate of the comprehensive water quality evaluation parameter, and the water replenishment rate is obtained by the ratio of the optimal water replenishment volume to the reference water replenishment time, the product of the proportionality coefficient and the difference between the comprehensive water quality evaluation parameter and the target water quality parameter, and the product of the differential coefficient and the change rate of the comprehensive water quality evaluation parameter;

[0165] The water replenishment rate calculation formula is as follows:

[0166]

[0167] Among them, R supply is the water replenishment rate, T 0 is the benchmark water replenishment time, k p is the proportionality coefficient, k s is the differential coefficient;

[0168] The dynamic adjustment calculation formula of the proportional coefficient is as follows:

[0169]

[0170] Among them, k p0 is the base proportional coefficient, β is the adjustment coefficient;

[0171] The calculation formula for dynamic adjustment of differential coefficient is as follows:

[0172]

[0173] Among them, k d0 is the reference differential coefficient, γ is the attenuation coefficient;

[0174] The central controller generates a water replenishment control instruction according to the optimal water replenishment volume and the water replenishment rate, and controls the variable frequency water replenishment pump to replenish fresh water to the spray tower system;

[0175] The central controller adjusts the water balance weight in real time, and the adjustment amount of the water balance weight is the product of the first learning rate, the first control error and the water loss value; the central controller adjusts the water quality regulation weight in real time, and the adjustment amount of the water quality regulation weight is the product of the second learning rate, the second control error and the difference between the comprehensive water quality evaluation parameter and the target water quality parameter; the second online monitoring unit performs multi-parameter real-time monitoring of the mixed water after the fresh water is supplemented, and the central controller calculates the comprehensive water quality evaluation parameters of the mixed water after the fresh water is supplemented according to the multi-parameter real-time monitoring.

[0176] An intelligent water replenishment control method for a spray tower system, which uses real-time monitoring and an adaptive algorithm to accurately control the amount and rate of water replenishment, thereby maintaining system water balance and stable water quality.

[0177] First, multiple sensors are deployed to form the first online monitoring unit and the second online monitoring unit. The first online monitoring unit monitors the actual discharge volume and actual discharge rate of the spray tower system in real time. For example, the discharge volume is measured by a flow meter, and the change of the discharge rate is monitored by a liquid level sensor. At the same time, the first online monitoring unit is also responsible for monitoring factors that cause water loss such as evaporation, drift and sewage discharge. For example, the evaporation loss, drift loss and sewage discharge loss are measured by using an evaporation sensor, a drift sensor and a sewage discharge sensor, respectively. These losses can be accumulated to obtain the system water loss value.

[0178] The second online monitoring unit monitors the circulating water in the spray tower system in real time, obtains multiple water quality parameters, such as pH value, conductivity, turbidity, temperature, etc., and integrates these parameters into a comprehensive water quality evaluation parameter based on a preset weight coefficient. For example, the comprehensive water quality evaluation parameter can be calculated by a weighted average method.

[0179] The central controller receives real-time data from two online monitoring units. It first calculates the system water loss value based on the actual discharge volume, discharge rate, and evaporation, drift, and blowdown losses. For example, assuming that the evaporation loss is 10L, the drift loss is 5L, and the blowdown loss is 2L, the system water loss value is 10+5+2=17L. Then, the central controller inputs the system water loss value, the current water quality comprehensive evaluation parameters, the preset target water quality parameters, and the system operating volume into the adaptive water replenishment algorithm.

[0180] The core of the adaptive water replenishment algorithm is to dynamically adjust the water balance weight and water quality regulation weight according to the two goals of water balance and water quality regulation, and calculate the optimal water replenishment volume and water replenishment rate. The calculation of the optimal water replenishment volume comprehensively considers the system water loss value and the deviation of water quality from the target water quality.

[0181] The calculation of the water replenishment rate takes into account the optimal water replenishment volume, the deviation between the water quality and the target water quality, and the rate of change of the comprehensive water quality evaluation parameters.

[0182] The central controller generates control instructions based on the calculated optimal water replenishment volume and water replenishment rate, and controls the variable frequency water replenishment pump to replenish fresh water to the spray tower system. At the same time, the central controller adjusts the water balance weight and water quality adjustment weight in real time according to the actual operation of the system and the change of water quality to achieve more precise control. For example, assuming that the first learning rate is 0.01 and the first control error is 1, the adjustment amount of the water balance weight is 0.01*1*17=0.17; assuming that the second learning rate is 0.005 and the second control error is 0.5, the adjustment amount of the water quality adjustment weight is 0.005*0.5*(204.45-200)=0.011.

[0183] The solution of this application can:

[0184] Water-saving effect: By accurately calculating the amount of water replenishment, the waste caused by excessive water replenishment is avoided, and water conservation is achieved. Stable water quality: By real-time monitoring of water quality parameters and dynamically adjusting the water replenishment strategy, the water quality can be maintained within the target range, ensuring the stable operation of the system. Intelligent control: This method uses an adaptive algorithm, which can automatically adjust the control parameters according to the actual operation of the system without manual intervention, realizing intelligent control.

[0185] In an optional embodiment, the central controller compares the comprehensive water quality evaluation parameter of the mixed water with the target water quality threshold. When the comprehensive water quality evaluation parameter of the mixed water is greater than the target water quality threshold, the adaptive water replenishment algorithm recalculates the optimal water replenishment volume and water replenishment rate until the comprehensive water quality evaluation parameter of the mixed water is less than the target water quality threshold, including:

[0186] After the water replenishment of the spray tower system is completed based on the water replenishment control instruction, the water quality comprehensive evaluation parameter of the mixed water after the water replenishment is compared with the target water quality threshold value based on the central control instruction; when the water quality comprehensive evaluation parameter of the mixed water after the water replenishment is still greater than the target water quality threshold value, the adaptive water replenishment algorithm recalculates the optimal water replenishment volume and water replenishment rate;

[0187] The adaptive water replenishment algorithm calculates the optimal water replenishment volume and the water replenishment rate by an iterative optimization method; in each iteration, the central controller calculates the gradient value of the water replenishment volume and the gradient value of the water replenishment rate based on the objective function; the central controller uses the product of the adaptive learning rate and the gradient value of the water replenishment volume as the adjustment amount of the water replenishment volume, and uses the product of the adaptive learning rate and the gradient value of the water replenishment rate as the adjustment amount of the water replenishment rate;

[0188] The objective function calculation formula is as follows:

[0189] J(V supply , R supply )=w1 (PQ tsrget ) 2 +w 2 (V sys -V target ) 2 +W 3 (ΔR supply );

[0190] Among them, J is the objective function value, w 1 , w 2 , w 3 is the weight coefficient, ΔR supply is the change in water replenishment rate;

[0191] The calculation formula of water replenishment gradient value is as follows:

[0192]

[0193] in, is the water replenishment volume gradient, The sensitivity of water quality to replenishment volume;

[0194] The water replenishment rate gradient calculation formula is as follows:

[0195]

[0196] in, is the water replenishment rate gradient, is the sensitivity of water quality to the rate of water replenishment;

[0197] The adaptive learning rate calculation formula is as follows:

[0198]

[0199] Among them, η t is the learning rate of the current iteration, η 0 is the initial learning rate, η is the adaptive coefficient, t is the iteration coefficient, J t -J t-1 The objective function values ​​of the current and previous steps;

[0200] The calculation formula for iterative update of water replenishment volume is as follows:

[0201]

[0202] in, is the updated water replenishment volume, is the current water replenishment volume, k is the number of water replenishment steps;

[0203] The iterative update calculation formula of the water replenishment rate is as follows:

[0204]

[0205] in, is the updated water replenishment rate, is the current water replenishment rate;

[0206] The central controller dynamically adjusts the adaptive learning rate based on the relative change of the objective function; the adjustment amount of the adaptive learning rate is the product of the adaptive learning rate and an exponential function, and the exponential term of the product of the exponential function is the inverse of the absolute value of the attenuation coefficient and the relative change of the objective function; the central controller repeatedly executes the above-mentioned iterative optimization process until the comprehensive water quality evaluation parameter of the mixed water is less than the target water quality threshold.

[0207] An adaptive spray tower water replenishment control method aims to accurately control the water replenishment amount to ensure that the mixed water quality meets the standard. The core of this method is to dynamically adjust the water replenishment volume and water replenishment rate according to the gap between the current water quality and the target water quality until the water quality meets the standard.

[0208] First, the central controller issues a command to start the initial water replenishment process of the spray tower system. For example, the initial water replenishment volume is set to 10 cubic meters and the water replenishment rate is 2 cubic meters per minute.

[0209] After the water replenishment is completed, the system will conduct a comprehensive water quality evaluation on the mixed water. Assume that the comprehensive water quality evaluation parameters are composed of three sub-parameters: turbidity, pH value and conductivity. Each sub-parameter is set with a weight, for example, the turbidity weight is 0.4, the pH weight is 0.3, and the conductivity weight is 0.3. The absolute value of the difference between the measured value of each sub-parameter and its target threshold is multiplied by the corresponding weight, and then the three weighted differences are added to obtain the final comprehensive water quality evaluation parameters. For example, if the target turbidity is 5NTU and the measured turbidity is 7NTU, the weighted difference of turbidity is (7-5)*0.4=0.8. Similarly, the weighted differences of pH value and conductivity are calculated, and finally the three weighted differences are added to obtain the comprehensive water quality evaluation parameters.

[0210] The calculated comprehensive water quality evaluation parameter is compared with the preset target water quality threshold. Assuming the target water quality threshold is 1.5, if the current comprehensive water quality evaluation parameter is greater than 1.5, for example, 2.0, it means that the water quality does not meet the standard and further water replenishment is required.

[0211] At this point, the adaptive water replenishment algorithm starts. The core of this algorithm is to gradually approach the optimal water replenishment volume and water replenishment rate through iterative optimization.

[0212] In each iteration, the central controller calculates the objective function. The objective function is designed to measure the gap between the current water replenishment plan and the ideal water replenishment plan. It consists of three parts: the difference between the comprehensive water quality evaluation parameter and the target water quality threshold, the change in the water replenishment volume, and the change in the water replenishment rate. Each part is multiplied by a weight coefficient to reflect its importance. For example, the weight of the water quality parameter is 0.5, the weight of the change in the water replenishment volume is 0.3, and the weight of the change in the water replenishment rate is 0.2.

[0213] Then, the gradient values ​​of the water replenishment volume and water replenishment rate are calculated. The gradient value indicates how fast the objective function value changes with the change of water replenishment volume or water replenishment rate. The sensitivity of water quality to water replenishment volume and the sensitivity of water quality to water replenishment rate are used to calculate the gradient values ​​of water replenishment volume and water replenishment rate respectively. For example, if the water quality comprehensive evaluation parameter decreases by 0.2 when the water replenishment volume increases by 1 cubic meter, the sensitivity of water quality to water replenishment volume is 0.2.

[0214] Next, calculate the adaptive learning rate. The learning rate determines the adjustment of the water replenishment volume and water replenishment rate in each iteration. It is determined by the initial learning rate, the adaptive coefficient, the number of iterations, and the objective function values ​​of the current and previous steps. For example, if the initial learning rate is set to 0.1, the adaptive coefficient is set to 0.9, and the current iteration is the first iteration, then the learning rate is 0.1.

[0215] Multiply the learning rate by the gradient values ​​of the water filling volume and water filling rate to get the adjustment amount of the water filling volume and water filling rate. For example, if the gradient value of the water filling volume is -0.5 and the learning rate is 0.1, the adjustment amount of the water filling volume is -0.05 cubic meters.

[0216] Add the current water replenishment volume and water replenishment rate to the corresponding adjustment amount to obtain the updated water replenishment volume and water replenishment rate. For example, if the current water replenishment volume is 10 cubic meters and the adjustment amount is -0.05 cubic meters, the updated water replenishment volume is 9.95 cubic meters.

[0217] The central controller will dynamically adjust the adaptive learning rate according to the relative change of the objective function. If the objective function value drops quickly, it means that the current learning rate is appropriate and can be increased appropriately; otherwise, the learning rate needs to be reduced. The adjustment amount is obtained by multiplying the learning rate by an exponential function. The exponential term of the exponential function is determined by the attenuation coefficient and the absolute value of the relative change of the objective function.

[0218] Repeat the above iterative optimization process until the comprehensive water quality evaluation parameter is less than the target threshold. For example, after multiple iterations, if the comprehensive water quality evaluation parameter is reduced to 1.2, which is less than the target threshold of 1.5, the iteration is stopped, and the final calculated water replenishment volume and water replenishment rate are sent to the spray tower system as control instructions for execution.

[0219] The solution of this application can:

[0220] Precise control: This method can dynamically adjust the water replenishment according to the real-time changes in water quality, avoid excessive or insufficient water replenishment, achieve precise control, and ensure that the water quality meets the standard. High efficiency and energy saving: Through the iterative optimization algorithm, the optimal water replenishment volume and water replenishment rate can be found, thereby minimizing the waste of water resources and reducing energy consumption. Intelligence: This method uses an adaptive learning rate and can automatically adjust parameters according to the operation of the system without manual intervention, which improves the intelligence level of the system.

[0221] In an optional implementation, when the prediction time is less than the warning threshold, the central controller starts the optimized emission control instruction and water replenishment control instruction in advance; the water quality prediction model continuously optimizes the model parameters through online learning to improve the prediction accuracy, and realizes the intelligent closed-loop control of the water quality of the spray tower wastewater, including:

[0222] When the prediction time is less than the warning threshold, the central controller starts the model prediction controller; the model prediction controller establishes an optimization objective function in the prediction time domain, and the optimization objective function includes a water quality prediction deviation term, a water replenishment change term, and a drainage change term; the model prediction controller optimizes the optimization objective function to obtain an optimized emission control instruction and an optimized water replenishment control instruction;

[0223] The central controller starts the optimized emission control instruction and the optimized water replenishment control instruction in advance; the central controller obtains actual water quality data after executing the optimized emission control instruction and the optimized water replenishment control instruction; the central controller inputs the actual water quality data into the water quality prediction model for online learning, and continuously optimizes the model parameters of the water quality prediction model;

[0224] The central controller updates the model parameters of the water quality prediction model by exponential sliding average, and the updated model parameters are the weighted average of the model parameters at the previous moment and the current model parameters; the central controller repeats the above prediction, optimization and control processes based on the updated water quality prediction model to realize intelligent closed-loop control of the water quality of the spray tower wastewater.

[0225] The invention discloses an intelligent closed-loop control method for the water quality of wastewater from a spray tower, relates to the field of wastewater treatment, and aims to achieve accurate control of the water quality of wastewater from the spray tower and prevent the water quality from exceeding the standard.

[0226] First, establish a water quality prediction model. This model can predict wastewater quality indicators in the future, such as pH value, COD (chemical oxygen demand), ammonia nitrogen, etc., based on historical water quality data, waste gas composition data, spray water volume and other factors. The prediction model can use a variety of machine learning algorithms, such as support vector machines, neural networks, etc. For example, collect the operation data of the spray tower in the past year, including daily inlet COD, pH value, ammonia nitrogen value, waste gas composition, spray water volume, discharge volume, etc., and use these data to train a water quality prediction model based on a neural network.

[0227] Set the warning threshold and prediction time. The warning threshold is a warning line for water quality indicators. When the predicted water quality indicators exceed the warning threshold, the system will start the optimization control instruction. The prediction time is the future time length predicted by the model, such as predicting the wastewater quality in the next 1 hour, 2 hours or more. For example, set the warning threshold of pH value to 6.5 and the prediction time to 1 hour.

[0228] The central controller monitors the prediction time and water quality prediction value in real time. When the prediction time is less than the warning threshold, for example, the pH value is predicted to be lower than 6.5 in 1 hour, the central controller will start the model prediction controller.

[0229] The model predictive controller establishes an optimization objective function in the prediction time domain. The goal of the optimization objective function is to minimize the water quality prediction deviation, the change in water replenishment, and the change in water discharge. For example, the goal is to make the predicted pH value as close as possible to the target value of 7.0, while keeping the water replenishment and water discharge stable and avoiding large fluctuations.

[0230] The model predictive controller uses an optimization algorithm to optimize the objective function and obtain optimized emission control instructions and water replenishment control instructions. The optimization algorithm can be, for example, a genetic algorithm, a particle swarm algorithm, etc. For example, the genetic algorithm calculates that the optimal emission in the next hour is 10 liters per minute, and the optimal water replenishment is 12 liters per minute.

[0231] The central controller starts the optimized discharge control command and water replenishment control command in advance. For example, when it is predicted that the pH value will be lower than 6.5 in one hour, the optimized discharge and water replenishment control command is immediately executed to adjust the discharge volume to 10 liters per minute and the water replenishment volume to 12 liters per minute.

[0232] The central controller obtains the actual water quality data after executing the control instruction. For example, after executing the control instruction for a period of time, such as 30 minutes, the actual pH value, COD, ammonia nitrogen and other indicators of the spray tower are measured. Assume that the measured pH value is 6.8.

[0233] The central controller inputs the actual water quality data into the water quality prediction model for online learning and continuously optimizes the model parameters. For example, the measured pH value of 6.8 and the exhaust gas composition and spray water volume at that time are input into the water quality prediction model, and the model parameters are updated using the exponential moving average method. Assume that the prediction accuracy of the updated model is improved by 0.5%.

[0234] The central controller repeats the above prediction, optimization and control process based on the updated water quality prediction model to achieve intelligent closed-loop control of the spray tower wastewater quality.

[0235] The solution of this application can:

[0236] Improve water quality control accuracy: Through the prediction model and optimization control algorithm, the trend of water quality changes can be predicted in advance, and control measures can be taken in time to avoid water quality exceeding the standard and achieve precise control. Reduce operating costs: By optimizing the amount of water replenishment and drainage, the waste of water resources and treatment costs can be reduced. Enhance system stability: Through online learning and continuous optimization of model parameters, the accuracy and robustness of the prediction model can be improved, and the stability and reliability of the system can be enhanced.

[0237] Figure 2 FIG. 1 is a schematic diagram of the structure of a multi-stage water purification and recycling system for spray tower dust treatment according to an embodiment of the present invention. Figure 2 As shown, the system comprises:

[0238] The first unit is used for the wastewater from the spray tower to first enter the first online monitoring unit, and the first online monitoring unit performs real-time detection on the pH value, conductivity value and turbidity value in the wastewater from the spray tower; the central controller receives the pH value, conductivity value and turbidity value output by the first online monitoring unit, and obtains the comprehensive water quality evaluation parameter through multivariable coupling calculation based on the pressure value of the spray tower system collected by the pressure sensor and the system temperature value collected by the temperature sensor; the central controller compares the comprehensive water quality evaluation parameter with a preset control threshold value, and when the comprehensive water quality evaluation parameter is greater than the control threshold value, the central controller calculates the optimal discharge volume and discharge rate, generates a discharge control instruction, and controls the wastewater discharge pump to perform the discharge operation; the electromagnetic flowmeter records the dynamic data of the actual discharge volume and the actual discharge rate in real time;

[0239] The second unit is used for the central controller to calculate the optimal replenishment volume and replenishment rate of the replenishment water through an adaptive replenishment algorithm based on the dynamic data of the actual discharge volume and the actual discharge rate, combined with the water quality comprehensive evaluation parameters; the variable frequency replenishment pump replenishes fresh water to the spray tower system according to the optimal replenishment volume and the replenishment rate; the second online monitoring unit monitors the mixed water after replenishment with fresh water in real time, and calculates the comprehensive water quality evaluation parameters of the mixed water; the central controller compares the comprehensive water quality evaluation parameters of the mixed water with the target water quality threshold value, and when the comprehensive water quality evaluation parameters of the mixed water are greater than the target water quality threshold value, the adaptive replenishment algorithm recalculates the optimal replenishment volume and replenishment rate until the comprehensive water quality evaluation parameters of the mixed water are less than the target water quality threshold value;

[0240] The third unit is used for the central controller to establish a water quality prediction model based on a deep neural network. The model uses the comprehensive water quality evaluation parameters, the actual discharge volume, the actual discharge rate, the optimal water replenishment volume, the water replenishment rate and the comprehensive water quality evaluation parameters of the mixed water as input variables to predict the time point when the next discharge is required; when the predicted time is less than the early warning threshold, the central controller starts the optimized discharge control instructions and water replenishment control instructions in advance; the water quality prediction model continuously optimizes the model parameters through online learning, improves the prediction accuracy, and realizes intelligent closed-loop control of the water quality of the spray tower wastewater.

[0241] According to a third aspect of the embodiments of the present invention,

[0242] An electronic device is provided, comprising:

[0243] processor;

[0244] a memory for storing processor-executable instructions;

[0245] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0246] A fourth aspect of the embodiments of the present invention is:

[0247] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0248] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0249] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-stage water purification and recycling method for spray tower dust treatment, characterized in that: include: The wastewater from the spray tower first enters the first online monitoring unit, which performs real-time detection of the pH value, conductivity value and turbidity value in the wastewater from the spray tower; the central controller receives the pH value, conductivity value and turbidity value output by the first online monitoring unit, and obtains the comprehensive water quality evaluation parameter through multivariable coupling calculation based on the spray tower system pressure value collected by the pressure sensor and the system temperature value collected by the temperature sensor; the central controller compares the comprehensive water quality evaluation parameter with the preset control threshold value, and when the comprehensive water quality evaluation parameter is greater than the control threshold value, the central controller calculates the optimal discharge volume and discharge rate, generates a discharge control instruction, and controls the wastewater discharge pump to perform the discharge operation; the electromagnetic flowmeter records the dynamic data of the actual discharge volume and the actual discharge rate in real time; The central controller calculates the optimal replenishment volume and replenishment rate of the replenishment water through an adaptive replenishment algorithm based on the dynamic data of the actual discharge volume and the actual discharge rate, combined with the comprehensive water quality evaluation parameters; the variable frequency replenishment pump replenishes fresh water to the spray tower system according to the optimal replenishment volume and the replenishment rate; the second online monitoring unit monitors the mixed water after replenishment with fresh water in real time, and calculates the comprehensive water quality evaluation parameters of the mixed water; the central controller compares the comprehensive water quality evaluation parameters of the mixed water with the target water quality threshold value, and when the comprehensive water quality evaluation parameters of the mixed water are greater than the target water quality threshold value, the adaptive replenishment algorithm recalculates the optimal replenishment volume and replenishment rate until the comprehensive water quality evaluation parameters of the mixed water are less than the target water quality threshold value; The central controller establishes a water quality prediction model based on a deep neural network. The model uses the comprehensive water quality evaluation parameters, the actual discharge volume, the actual discharge rate, the optimal water replenishment volume, the water replenishment rate and the comprehensive water quality evaluation parameters of the mixed water as input variables to predict the time point when the next discharge is required; when the predicted time is less than the early warning threshold, the central controller starts the optimized discharge control instructions and water replenishment control instructions in advance; the water quality prediction model continuously optimizes the model parameters through online learning, improves the prediction accuracy, and realizes intelligent closed-loop control of the water quality of the spray tower wastewater.

2. The method according to claim 1, characterized in that The wastewater from the spray tower first enters the first online monitoring unit, which performs real-time detection of the pH value, conductivity value and turbidity value in the wastewater from the spray tower; the central controller receives the pH value, conductivity value and turbidity value output by the first online monitoring unit, and obtains the comprehensive water quality evaluation parameters through multivariable coupling calculation based on the pressure value of the spray tower system collected by the pressure sensor and the system temperature value collected by the temperature sensor, including: The wastewater from the spray tower first enters the first online monitoring unit, which includes a double-structure composite glass pH electrode, a four-electrode conductivity sensor and a scattering turbidity meter; the double-structure composite glass pH electrode monitors the pH value of the wastewater from the spray tower in real time, the four-electrode conductivity sensor monitors the conductivity value of the wastewater from the spray tower in real time, and the scattering turbidity meter monitors the turbidity value of the wastewater from the spray tower in real time; the first online monitoring unit uses a median filtering algorithm to perform interference elimination processing on the pH value, the conductivity value and the turbidity value, and uses a Kalman filtering algorithm to perform noise smoothing processing on the data after the interference elimination processing, and transmits the processed pH value, the conductivity value and the turbidity value to the central controller through the RS485 bus; The central controller receives the spray tower system pressure value collected by the pressure sensor and the system temperature value collected by the temperature sensor; the central controller calculates the pressure correction coefficient based on the system pressure value, and the pressure correction coefficient is the square root of the ratio of the system pressure value to the standard pressure value; the central controller calculates the temperature correction coefficient based on the system temperature value, and the temperature correction coefficient is the product of the temperature difference between the system temperature value and the standard temperature value and the temperature compensation coefficient plus one; The central controller obtains comprehensive water quality evaluation parameters through multivariable coupling calculation, calculates pH value deviation, conductivity standardization value and turbidity standardization value, wherein the pH value deviation is the absolute difference between the pH value and the target pH value, the conductivity standardization value is the ratio of the conductivity value to the initial conductivity value, and the turbidity standardization value is the ratio of the turbidity value to the initial turbidity value; the pH value deviation, the conductivity standardization value, the turbidity standardization value, the pressure correction coefficient and the temperature correction coefficient are respectively multiplied by the weight coefficients obtained by least squares optimization and then summed to obtain the comprehensive water quality evaluation parameters characterizing the overall water quality of the spray tower wastewater.

3. The method according to claim 1, characterized in that The central controller compares the water quality comprehensive evaluation parameter with a preset control threshold value. When the water quality comprehensive evaluation parameter is greater than the control threshold value, the central controller calculates the optimal discharge volume and discharge rate, generates a discharge control instruction, and controls the wastewater discharge pump to perform a discharge operation; The electromagnetic flowmeter records the actual discharge volume and actual discharge rate in real time, including: The control threshold and the three-level warning threshold are set based on the central controller, and the three-level warning threshold includes a first warning threshold, a second warning threshold and a third warning threshold; the central controller compares the comprehensive water quality evaluation parameter with the three-level warning threshold and the benchmark control threshold in sequence; when the comprehensive water quality evaluation parameter is greater than the first warning threshold, the central controller enters a warning state; when the comprehensive water quality evaluation parameter is greater than the second warning threshold, the central controller starts a preprocessing program; When the water quality comprehensive evaluation parameter is greater than the third warning threshold, the central controller enters a ready state; when the water quality comprehensive evaluation parameter is greater than the reference control threshold, the central controller starts a drainage control instruction; The central controller calculates the optimal discharge volume according to the comprehensive water quality evaluation parameters, the system nominal volume, the proportionality coefficient, and the change rate coefficient, and calculates the optimal discharge rate according to the optimal discharge volume, the reference discharge time, and the rate adjustment coefficient; The optimal discharge volume calculation formula is as follows: Among them, V opt is the optimal discharge volume, V0 is the nominal volume of the system, k p is the proportionality coefficient, Q is the current comprehensive water quality evaluation parameter, Q0 is the target water quality benchmark value, k d is the rate of change coefficient, is the change rate of comprehensive water quality evaluation parameters; The optimal emission rate calculation formula is as follows: Among them, R opt is the optimal emission rate, T0 is the reference emission time, and α is the rate adjustment coefficient; The calculation formula for comprehensive water quality evaluation parameters is as follows: Among them, P is the comprehensive evaluation parameter of water quality, w i is the weight parameter of the i-th water quality index, C i is the measured concentration value of the i-th water quality index, C i,std is the standard limit of the i-th water quality index, and n is the number of water quality indexes involved in the evaluation; The formula for calculating the rate of change is as follows: Among them, Q t -Q t-Δt is the comprehensive evaluation parameter of water quality at the previous moment, Δt is the sampling time interval; The central controller generates a discharge control instruction according to the optimal discharge volume and the optimal discharge rate, and controls the variable frequency pump to perform the drainage operation; the electromagnetic flowmeter adopts the vortex flow detection principle, has a built-in temperature and pressure compensation module, and collects the actual discharge volume and actual discharge rate in real time.

4. The method according to claim 1, characterized in that: The central controller calculates the optimal replenishment volume and replenishment rate of replenishment water through an adaptive replenishment algorithm based on the dynamic data of the actual discharge volume and the actual discharge rate, combined with the comprehensive water quality evaluation parameters; the variable frequency replenishment pump replenishes fresh water to the spray tower system according to the optimal replenishment volume and the replenishment rate; The second online monitoring unit monitors the mixed water after adding fresh water in real time, and calculates the comprehensive evaluation parameters of the mixed water quality including: The central controller calculates the system water loss value based on the dynamic data of the actual discharge volume and the actual discharge rate, and inputs the system water loss value and the water quality comprehensive evaluation parameter into the adaptive water replenishment algorithm; the central controller calculates the optimal water replenishment volume based on the system water loss value, the system operating volume, the water quality comprehensive evaluation parameter and the target water quality parameter through the adaptive water replenishment algorithm, and the optimal water replenishment volume is obtained by the product of the water balance weight and the water loss value, the water quality adjustment weight, the difference between the water quality comprehensive evaluation parameter and the target water quality parameter, and the product of the system operating volume; The optimal water replenishment volume calculation formula is as follows: V supply =w v ·V loss +w q ·(Q-Q target )·V sys ; Among them, V supply is the optimal water replenishment volume, w v is the water balance weight, V loss is the system water loss value, w q is the water quality regulation weight, Q target is the target water quality parameter, V sys is the system operating volume; The system water loss value calculation formula is as follows: V loss =V evap +V drift +V bow ; Among them, V evap is the evaporation loss, V drift is the drift loss, V blow is the amount of sewage loss; The calculation formula for dynamic adjustment of water balance weight is as follows: Among them, w v0 is the reference water weight, k1 is the adjustment coefficient, V target is the target operating volume; The calculation formula for dynamic adjustment of water quality regulation weight is as follows: Among them, w q0 is the benchmark water quality weight, k2 is the adjustment coefficient; The central controller calculates the water replenishment rate based on the change rate of the comprehensive water quality evaluation parameter, and the water replenishment rate is obtained by the ratio of the optimal water replenishment volume to the reference water replenishment time, the product of the proportionality coefficient and the difference between the comprehensive water quality evaluation parameter and the target water quality parameter, and the product of the differential coefficient and the change rate of the comprehensive water quality evaluation parameter; The water replenishment rate calculation formula is as follows: Among them, R supply is the water replenishment rate, T0 is the reference water replenishment time, k p is the proportionality coefficient, k s is the differential coefficient; The dynamic adjustment calculation formula of the proportional coefficient is as follows: Among them, k p0 is the base proportional coefficient, β is the adjustment coefficient; The calculation formula for dynamic adjustment of differential coefficient is as follows: Among them, k d0 is the reference differential coefficient, γ is the attenuation coefficient; The central controller generates a water replenishment control instruction according to the optimal water replenishment volume and the water replenishment rate, and controls the variable frequency water replenishment pump to replenish fresh water to the spray tower system; The central controller adjusts the water balance weight in real time, and the adjustment amount of the water balance weight is the product of the first learning rate, the first control error and the water loss value; the central controller adjusts the water quality regulation weight in real time, and the adjustment amount of the water quality regulation weight is the product of the second learning rate, the second control error and the difference between the comprehensive water quality evaluation parameter and the target water quality parameter; the second online monitoring unit performs multi-parameter real-time monitoring of the mixed water after the fresh water is supplemented, and the central controller calculates the comprehensive water quality evaluation parameters of the mixed water after the fresh water is supplemented according to the multi-parameter real-time monitoring.

5. The method according to claim 1, characterized in that The central controller compares the comprehensive water quality evaluation parameter of the mixed water with the target water quality threshold. When the comprehensive water quality evaluation parameter of the mixed water is greater than the target water quality threshold, the adaptive water replenishment algorithm recalculates the optimal water replenishment volume and water replenishment rate until the comprehensive water quality evaluation parameter of the mixed water is less than the target water quality threshold. The method includes: After the water replenishment of the spray tower system is completed based on the water replenishment control instruction, the water quality comprehensive evaluation parameter of the mixed water after the water replenishment is compared with the target water quality threshold value based on the central control instruction; when the water quality comprehensive evaluation parameter of the mixed water after the water replenishment is still greater than the target water quality threshold value, the adaptive water replenishment algorithm recalculates the optimal water replenishment volume and water replenishment rate; The adaptive water replenishment algorithm calculates the optimal water replenishment volume and the water replenishment rate by an iterative optimization method; in each iteration, the central controller calculates the gradient value of the water replenishment volume and the gradient value of the water replenishment rate based on the objective function; the central controller uses the product of the adaptive learning rate and the gradient value of the water replenishment volume as the adjustment amount of the water replenishment volume, and uses the product of the adaptive learning rate and the gradient value of the water replenishment rate as the adjustment amount of the water replenishment rate; The objective function calculation formula is as follows: J(V supply ,R supply )=w1(P-Q tsrget ) 2 +w2(V sys -V target ) 2 +w3(ΔR supply ) 2 ; Among them, J is the objective function value, w1, w2, w3 are weight coefficients, ΔR supply is the change in water replenishment rate; The calculation formula of water replenishment gradient value is as follows: in, is the water replenishment volume gradient, The sensitivity of water quality to replenishment volume; The water replenishment rate gradient calculation formula is as follows: in, is the water replenishment rate gradient, is the sensitivity of water quality to the rate of water replenishment; The adaptive learning rate calculation formula is as follows: Among them, η t is the learning rate of the current iteration step, η0 is the initial learning rate, η is the adaptive coefficient, t is the iteration coefficient, J t -J t-1 is the objective function value of the current and previous step; The calculation formula for iterative update of water replenishment volume is as follows: in, is the updated water replenishment volume, is the current water replenishment volume, k is the number of water replenishment steps; The iterative update calculation formula of the water replenishment rate is as follows: in, is the updated water replenishment rate, is the current water replenishment rate; The central controller dynamically adjusts the adaptive learning rate based on the relative change of the objective function; the adjustment amount of the adaptive learning rate is the product of the adaptive learning rate and an exponential function, and the exponential term of the product of the exponential function is the inverse of the absolute value of the attenuation coefficient and the relative change of the objective function; the central controller repeatedly executes the above-mentioned iterative optimization process until the comprehensive water quality evaluation parameter of the mixed water is less than the target water quality threshold.

6. The method according to claim 1, characterized in that When the prediction time is less than the warning threshold, the central controller starts the optimized emission control command and water replenishment control command in advance; the water quality prediction model continuously optimizes the model parameters through online learning to improve the prediction accuracy and realize the intelligent closed-loop control of the wastewater quality of the spray tower, including: When the prediction time is less than the warning threshold, the central controller starts the model prediction controller; the model prediction controller establishes an optimization objective function in the prediction time domain, and the optimization objective function includes a water quality prediction deviation term, a water replenishment change term, and a drainage change term; the model prediction controller optimizes the optimization objective function to obtain an optimized emission control instruction and an optimized water replenishment control instruction; The central controller starts the optimized emission control instruction and the optimized water replenishment control instruction in advance; the central controller obtains actual water quality data after executing the optimized emission control instruction and the optimized water replenishment control instruction; the central controller inputs the actual water quality data into the water quality prediction model for online learning, and continuously optimizes the model parameters of the water quality prediction model; The central controller updates the model parameters of the water quality prediction model by exponential sliding average, and the updated model parameters are the weighted average of the model parameters at the previous moment and the current model parameters; the central controller repeats the above prediction, optimization and control processes based on the updated water quality prediction model to realize intelligent closed-loop control of the water quality of the spray tower wastewater.

7. A multi-stage water purification and recycling system for spray tower dust treatment, used to implement the method described in any one of claims 1 to 6, characterized in that: include: The first unit is used for the wastewater from the spray tower to first enter the first online monitoring unit, and the first online monitoring unit performs real-time detection on the pH value, conductivity value and turbidity value in the wastewater from the spray tower; the central controller receives the pH value, conductivity value and turbidity value output by the first online monitoring unit, and obtains the comprehensive water quality evaluation parameter through multivariable coupling calculation based on the pressure value of the spray tower system collected by the pressure sensor and the system temperature value collected by the temperature sensor; the central controller compares the comprehensive water quality evaluation parameter with a preset control threshold value, and when the comprehensive water quality evaluation parameter is greater than the control threshold value, the central controller calculates the optimal discharge volume and discharge rate, generates a discharge control instruction, and controls the wastewater discharge pump to perform the discharge operation; the electromagnetic flowmeter records the dynamic data of the actual discharge volume and the actual discharge rate in real time; The second unit is used for the central controller to calculate the optimal replenishment volume and replenishment rate of the replenishment water through an adaptive replenishment algorithm based on the dynamic data of the actual discharge volume and the actual discharge rate, combined with the water quality comprehensive evaluation parameters; the variable frequency replenishment pump replenishes fresh water to the spray tower system according to the optimal replenishment volume and the replenishment rate; the second online monitoring unit monitors the mixed water after replenishment with fresh water in real time, and calculates the comprehensive water quality evaluation parameters of the mixed water; the central controller compares the comprehensive water quality evaluation parameters of the mixed water with the target water quality threshold value, and when the comprehensive water quality evaluation parameters of the mixed water are greater than the target water quality threshold value, the adaptive replenishment algorithm recalculates the optimal replenishment volume and replenishment rate until the comprehensive water quality evaluation parameters of the mixed water are less than the target water quality threshold value; The third unit is used for the central controller to establish a water quality prediction model based on a deep neural network. The model uses the comprehensive water quality evaluation parameters, the actual discharge volume, the actual discharge rate, the optimal water replenishment volume, the water replenishment rate and the comprehensive water quality evaluation parameters of the mixed water as input variables to predict the time point when the next discharge is required; when the predicted time is less than the early warning threshold, the central controller starts the optimized discharge control instructions and water replenishment control instructions in advance; the water quality prediction model continuously optimizes the model parameters through online learning, improves the prediction accuracy, and realizes intelligent closed-loop control of the water quality of the spray tower wastewater.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images