A method and system for joint control of urban drainage system

Abstract

The invention discloses a method and system for joint control of an urban drainage system, and relates to the technical field of rainwater and sewage control. Detection equipment is set at each node of an urban drainage network, and water quality and water quantity data of the drainage network are stored in a forest storage manner, and then an LSTM model is used to predict the water quality and water quantity of the urban drainage network; based on the constraints of a sewage treatment plant model, an artificial wetland model, and an urban river and lake model, an urban drainage system control model is further constructed, and the model is solved by a particle swarm algorithm, so as to reduce pollution, protect the urban water environment, and realize comprehensive management and efficient utilization of urban water resources while meeting the water quality and water quantity requirements of sewage treatment plants, artificial wetlands, and urban rivers and lakes.

Description

Technical Field

[0001] The present invention relates to the technical field of rainwater and sewage regulation, and more particularly to a method and system for joint regulation of urban drainage systems. Background Art

[0002] Urban drainage system refers to the general term for drainage pipelines, sewage treatment plants, artificial wetlands, rivers and lakes within the city. The construction and management of the urban drainage system has an important impact on urban development, residents' lives, and urban ecological environment.

[0003] However, the existing urban rainwater and sewage control methods are usually applied independently to the drainage network, sewage treatment plants, artificial wetlands, natural rivers and lakes, and no complete joint control system has been formed. Although these independent control methods can play a certain role in certain specific situations, they cannot fully consider the relationship between urban drainage networks, sewage treatment plants, artificial wetlands and urban rivers and lakes, and conduct unified coordinated control, which is not conducive to reducing pollution emissions, protecting the water environment, and realizing the efficient use and management of urban water resources.

[0004] Therefore, how to jointly regulate the urban drainage system is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0005] In view of this, the present invention provides a method and system for joint regulation of urban drainage systems, which predicts the rainwater and sewage data of the urban drainage network, solves the data according to the urban drainage system regulation model, and then regulates the drainage network, sewage treatment plants, artificial wetlands, rivers and lakes, thereby protecting the water environment and realizing efficient utilization and management of urban water resources.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] The present invention discloses a method for joint regulation of urban drainage system, and the specific steps are as follows:

[0008] Step 1: Obtain urban drainage network data in different areas at different times;

[0009] Step 2: Obtain the temperature, humidity, precipitation data, industrial water consumption, domestic water consumption, and population data of each area at different times, and build a data set in combination with the urban drainage network data; train and verify the LSTM model through the data set, and use the trained LSTM model to predict the water quality and water quantity of the urban drainage network to obtain the water quantity prediction data and water quality prediction data entering the sewage treatment plant;

[0010] Step 3: Construct the sewage treatment plant model, artificial wetland model, urban river and lake model respectively, and further construct the urban drainage system regulation model;

[0011] Step 4: Input the water volume prediction data and the water quality prediction data into the urban drainage system control model, and use the particle swarm algorithm to solve it, so as to obtain the drainage volume from the sewage treatment plant to the artificial wetland and the effluent flow from the artificial wetland to the urban rivers and lakes, and control the urban rainwater and sewage according to the solution results;

[0012] Step 5: Monitor the amount and quality of water entering the sewage treatment plant, the water quality of artificial wetlands, and the water quality of urban rivers and lakes at all times, provide feedback based on the monitoring and testing results, conduct upward regulation, and carry out two-way joint regulation of the urban drainage system.

[0013] Furthermore, the step 1 comprises:

[0014] Step 1.1: Obtain a map of the urban drainage network and mark the main rainwater and sewage pipes, branch rainwater and sewage pipes, and the rainwater and sewage collection points and inlets in the branch rainwater and sewage pipes;

[0015] Step 1.2: Detection equipment is set at the rainwater and sewage collection point and the rainwater and sewage inlet, and rainwater and sewage flow rate, flow rate, rainwater and sewage pH value, COD, BOD, NH3-N, TP index data are obtained at set time intervals, and the data of the detection equipment at the rainwater and sewage collection point is used as the branch node data, and the data of the detection equipment at the rainwater and sewage inlet is used as the leaf node data;

[0016] Step 1.3: Obtain the diameter and length data of the pipe between the rainwater and sewage collection point and the rainwater and sewage inlet as branch data;

[0017] Step 1.4: The leaf node data, branch node data and trunk data are used to form a storage tree, each tree represents an area of ​​the city, and multiple storage trees form a storage forest to store the urban drainage network data.

[0018] Furthermore, the step 2 comprises:

[0019] Step 2.1: The rainwater and sewage flow rate, flow rate, rainwater and sewage pH value, COD, BOD, NH3-N, TP index data of the leaf node at a certain moment, as well as the temperature, humidity, precipitation data of the area where the leaf node is located at that moment, as well as industrial water consumption, domestic water consumption, and population data, constitute a data unit; the leaf node is at time t1~t n All data units in the sequence are organized into a sequence in chronological order as a sample data;

[0020] Step 2.2: traverse the storage forest, obtain multiple sample data based on the leaf node data in the storage forest to construct a data set, and divide it into a training data set and a verification data set;

[0021] Step 2.3: construct an LSTM model, train it using the training data set, and verify it using the verification data set;

[0022] Step 2.4: According to step 2.1, obtain the prediction data set at the current moment, and input the trained LSTM model operation to predict the rainwater and sewage flow and flow rate of all leaf nodes at the next moment as water volume prediction data, and the rainwater and sewage pH value, COD, BOD, NH3-N, and TP indicator data as water quality prediction data.

[0023] Furthermore, the step 3 comprises:

[0024] Step 3.1: Obtain the buffer tank capacity, daily NH3-N treatment capacity, daily TP treatment capacity, daily COD treatment capacity, and daily BOD treatment capacity of the sewage treatment plant, and establish a sewage treatment plant model;

[0025] Step 3.2: Obtain the water inflow and outflow, water consumption, NH3-N, TP, COD, BOD index data of the artificial wetland, as well as the daily absorption of NH3-N, TP, COD and BOD of the artificial wetland, and establish an artificial wetland model;

[0026] Step 3.3: Obtain the water inflow and water quality background data of urban rivers and lakes, urban water intake data, and the daily NH3-N absorption, TP absorption, COD absorption, and BOD absorption of urban rivers and lakes to establish an urban river and lake model;

[0027] Step 3.4: Construct an urban drainage system control model based on the constraints of the sewage treatment plant model, the constraints of the artificial wetland model, and the constraints of the urban river and lake model.

[0028] Furthermore, the step 3.1 includes:

[0029] According to the water volume prediction data and the water quality prediction data, the total amount of rainwater and sewage entering the sewage treatment plant and the amount of COD, BOD, NH3-N, and TP are calculated; according to the total amount of rainwater and sewage and the water volume constraints of the buffer tank, the daily COD treatment volume and the COD index constraints of the sewage treatment plant drainage, the daily BOD treatment volume and the BOD index constraints of the sewage treatment plant drainage, the daily NH3-N treatment volume and the NH3-N index constraints of the sewage treatment plant drainage, the daily TP treatment volume and the TP index constraints of the sewage treatment plant drainage, a sewage treatment plant model is established with the goal of maximizing the rainwater and sewage treatment volume.

[0030] Further, the step 3.2 includes:

[0031] According to the inflow and outflow of artificial wetlands, water consumption, NH3-N, TP, COD, BOD content data in the water, as well as the treated water discharge and water quality data of the sewage treatment plant, the total amount of NH3-N, TP, COD and BOD in the artificial wetlands was calculated. According to the constraints of the total water volume of artificial wetlands, the COD absorption capacity and the COD index constraints of artificial wetland effluent, the BOD absorption capacity and the BOD index constraints of artificial wetland effluent, the NH3-N absorption capacity and the NH3-N index constraints of artificial wetland effluent, and the TP absorption capacity and the TP index constraints of artificial wetland effluent, an artificial wetland model was established with the goal of optimizing the water quality of artificial wetlands.

[0032] Further, the step 3.3 includes:

[0033] Based on the total inflow of urban rivers and lakes, urban water intake, background content data of NH3-N, TP, COD and BOD in water, combined with data on point source, non-point source and endogenous pollution of rivers and lakes, as well as data on water volume and quality of artificial wetlands replenishing urban rivers and lakes, the total amount of NH3-N, TP, COD and BOD in urban rivers and lakes is calculated. Based on the COD absorption capacity of rivers and lakes and the COD index constraints of downstream water transmission from rivers and lakes, the BOD absorption capacity of rivers and lakes and the BOD index constraints of downstream water transmission from rivers and lakes, the NH3-N absorption capacity of rivers and lakes and the NH3-N index constraints of downstream water transmission from rivers and lakes, and the TP absorption capacity of rivers and lakes and the TP index constraints of downstream water transmission from rivers and lakes, an urban river and lake model is established with the goal of optimizing the water quality output from urban rivers and lakes to downstream.

[0034] Further, the step 4 comprises:

[0035] Step 4.1: Initialize the particle swarm parameters, including: particle swarm size, particle swarm dimension, number of iterations, learning factor, and iteration step range;

[0036] Step 4.2: Randomly initialize the position, velocity and acceleration of each particle;

[0037] Step 4.3: Update the velocity, acceleration and position of each particle and calculate the fitness value of each particle;

[0038] Step 4.4: Determine the individual's historical optimal position and optimal fitness value, as well as the group's historical optimal position and optimal fitness value, and update the learning factor;

[0039] Step 4.5: Determine whether the maximum number of iterations is met, or whether the difference in the optimal fitness value of the group between two iterations meets the minimum requirement. If neither is met, return to step 4.3;

[0040] Step 4.6: Output the optimal solution and save it.

[0041] Further, the step 5 comprises:

[0042] According to the water volume monitoring data entering the sewage treatment plant at each moment and the water volume forecast data entering the sewage treatment plant, a measured data sequence of the water volume entering the sewage treatment plant and a water volume forecast data sequence are obtained, and the difference between the measured data sequence and the forecast data sequence at the corresponding moment is calculated to obtain an error sequence; based on the error sequence, an error prediction model is used to predict the error value at the next moment, so as to feedback and adjust the water volume data entering the sewage treatment plant predicted in step 2;

[0043] Based on the water quality monitoring data entering the sewage treatment plant at each moment, the measured water quality data sequence entering the sewage treatment plant is sorted out, and then the average water quality entering the sewage treatment plant over a period of time is calculated. When the average water quality is not within the preset threshold range, feedback is given to the rainwater and sewage drainage network, and recommended strategies for exploration, maintenance, reconstruction or expansion of the regional rainwater and sewage drainage network are proposed;

[0044] According to the water quality monitoring data of artificial wetlands at each moment, the measured water quality data sequence of artificial wetlands is obtained, and then the average water quality of artificial wetlands over a period of time is calculated. When the average water quality exceeds the preset threshold range, feedback is given to the sewage treatment plant, and a recommended strategy for adjusting the operation plan of the sewage treatment plant is proposed;

[0045] Based on the water quality monitoring data of urban rivers and lakes at various times, a sequence of measured data on the water quality of urban rivers and lakes is compiled to calculate the average water quality of urban rivers and lakes over a period of time. When the average water quality exceeds the preset threshold range, feedback is given to the artificial wetland, and recommended strategies for the operation plan of the artificial wetland and the investigation and remediation of pollution sources in urban rivers and lakes are proposed.

[0046] The present invention also discloses a combined control system for urban drainage systems, the system comprising:

[0047] Basic data module: obtain urban drainage network data in different areas at different times;

[0048] Data prediction module: obtain the temperature, humidity, precipitation data, industrial water consumption, domestic water consumption, and population data of each area at different times, and build a data set in combination with the urban drainage network data; train and verify the LSTM model through the data set, and use the trained LSTM model to predict the water quality and water quantity of the urban drainage network, and obtain the water quantity prediction data and water quality prediction data entering the sewage treatment plant;

[0049] Model building module: construct sewage treatment plant model, artificial wetland model, urban river and lake model, and further construct urban drainage system regulation model;

[0050] Model solving module: input the water volume prediction data and the water quality prediction data into the urban drainage system control model, and use the particle swarm algorithm to solve it, so as to obtain the drainage volume from the sewage treatment plant to the artificial wetland and the effluent flow from the artificial wetland to the urban rivers and lakes, and control the urban rainwater and sewage according to the solution results;

[0051] Feedback strategy module: monitor the amount and quality of water entering the sewage treatment plant, the water quality of artificial wetlands, and the water quality of urban rivers and lakes at all times, provide feedback based on the monitoring and detection results, conduct upward regulation, and carry out two-way joint regulation of the urban drainage system.

[0052] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a method and system for joint control of an urban drainage system. By constructing a storage forest, it can accurately record the amount and quality information of rainwater and sewage at each rainwater and sewage access point and node in the urban drainage network; based on the historical data of the drainage network, the LSTM model is used to predict the water quality and amount data of the urban drainage network for a certain period of time in the future; and based on the constraints of the sewage treatment plant model, the artificial wetland model and the urban river and lake model, an urban drainage system control model is further constructed, and the model is solved by the particle swarm algorithm to realize downward control of urban rainwater and sewage; combined with the actual monitoring of sewage treatment plants, artificial wetlands and urban rivers and lakes and the model prediction results, they are fed back to the upper level step by step to realize upward feedback control. The present invention can realize real-time monitoring, rapid analysis and intelligent regulation, greatly improving the management efficiency and regulation level of the urban drainage system, and organically combining the various parts of the urban drainage system to form a complete two-way regulation system, which can more comprehensively solve various problems in the urban drainage system, reduce pollution emissions, protect the urban water environment, and realize the comprehensive management and efficient utilization of urban water resources while meeting the water quality and quantity requirements of sewage treatment plants, artificial wetlands, and urban rivers and lakes. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0054] Figure 1 It is a schematic diagram of the overall process of the present invention.

[0055] Figure 2 This is a schematic diagram of a combined regulation scheme for rainwater and sewage pipe network - sewage treatment plant - artificial wetland - urban rivers and lakes in a city along the Yangtze River according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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.

[0057] The embodiment of the present invention discloses a method for joint control of urban drainage system. Figure 1 As shown, the specific steps are as follows:

[0058] Step 1: Obtain urban drainage network data in different areas at different times;

[0059] Step 2: Obtain temperature, humidity, precipitation data, industrial water consumption, domestic water consumption, and population data for each region at different times, and build a data set in combination with the urban drainage network data; train and verify the LSTM model using the data set, and use the trained LSTM model to predict the water quality and water quantity of the urban drainage network, and obtain the water quantity and water quality prediction data entering the sewage treatment plant;

[0060] Step 3: Construct the sewage treatment plant model, artificial wetland model, urban river and lake model respectively, and further construct the urban drainage system regulation model;

[0061] Step 4: Input the water volume prediction data and water quality prediction data into the urban drainage system control model, and use the particle swarm algorithm to solve it, so as to obtain the drainage volume from the sewage treatment plant to the artificial wetland and the outflow volume from the artificial wetland to the urban rivers and lakes, and perform the downstream control of urban rainwater and sewage according to the solution results;

[0062] Step 5: Monitor the amount and quality of water entering the sewage treatment plant, the water quality of artificial wetlands, and the water quality of urban rivers and lakes at all times, provide feedback based on the monitoring and testing results, conduct upward regulation, and carry out two-way joint regulation of the urban drainage system.

[0063] In a specific embodiment, step 1 includes:

[0064] Step 1.1: Obtain a map of the urban drainage network and mark the main drainage pipes, branch drainage pipes, and the rainwater and sewage collection points and rainwater and sewage inlet points in the branch drainage pipes;

[0065] Step 1.2: Set up detection equipment at the rainwater and sewage collection point and the rainwater and sewage inlet, and obtain rainwater and sewage flow, flow rate, rainwater and sewage pH value, COD, BOD, NH3-N, TP index data at set time intervals, and use the data of the detection equipment at the rainwater and sewage collection point as the branch node data, and the data of the detection equipment at the rainwater and sewage inlet as the leaf node data;

[0066] Step 1.3: Obtain the pipe diameter and length data between the rainwater and sewage collection point and the rainwater and sewage inlet as branch data;

[0067] Step 1.4: A storage tree is constructed with leaf node data, branch node data, and trunk data. Each tree represents an area of ​​the city, and multiple storage trees form a storage forest to store urban drainage network data. By setting up detection equipment at the key nodes of the drainage network and using storage trees for storage, the rainwater and sewage water volume and water quality data of the key nodes of the urban drainage network can be accurately grasped by traversing the storage tree; by comparing and calculating the leaf node data, branch node data, and trunk data of the storage tree, it can also be determined whether the urban drainage network is blocked or leaking, and an alarm can be issued.

[0068] In a specific embodiment, step 2 includes:

[0069] Step 2.1: The sewage flow rate, flow rate, sewage pH value, COD, BOD, NH3-N, TP index data in the sewage at a certain moment of the leaf node, as well as the temperature, humidity, precipitation data, industrial water consumption, domestic water consumption, and population data of the area where the leaf node is located at that moment, constitute a data unit; based on the temperature, humidity, precipitation data, industrial water consumption, domestic water consumption, and population data in each data unit, the theoretical drainage volume of the area can be calculated. The ratio of the theoretical drainage volume to the actual drainage volume of the area monitored calculated by the storage tree can be used to measure whether the rainwater and sewage collection rate meets the requirements. If not, feedback is given to the drainage network engineering planning, design, and operation management department; and, by monitoring the COD and BOD concentrations in each drainage network, it can be used as a constraint condition to feedback the drainage network engineering planning, design, and operation management department. The leaf node is at time t1~t n All data units in the data set are organized into a sequence in chronological order as a sample data; for missing or abnormal data in the sample data, replacements can be calculated based on adjacent leaf node data and score node data, or for leaked or blocked node data, the sample data can be directly deleted.

[0070] Step 2.2: Traverse the storage forest, obtain multiple sample data based on the data of each leaf node in the storage forest to build a data set, and divide it into a training data set and a validation data set;

[0071] Step 2.3: Build an LSTM model, train it using the training dataset, and verify it using the validation dataset;

[0072] Step 2.4: According to step 2.1, obtain the prediction data set at the current moment, and input the trained LSTM model operation to predict the rainwater and sewage flow and flow rate of all leaf nodes at the next moment as water volume prediction data, and the rainwater and sewage pH value, COD, BOD, NH3-N, and TP index data as water quality prediction data. By predicting the future rainwater and sewage water volume and water quality of each leaf node of the drainage network, and then predicting the water quality and water volume of rainwater and sewage entering the sewage treatment plant in the future based on the water quality and water volume of each leaf node, the accuracy of the prediction of the sewage water volume and water quality entering the sewage treatment plant can be improved.

[0073] In a specific embodiment, step 3 includes:

[0074] Step 3.1: Obtain the buffer tank capacity, daily NH3-N treatment capacity, daily TP treatment capacity, daily COD treatment capacity, and daily BOD treatment capacity of the sewage treatment plant, and establish a sewage treatment plant model;

[0075] Step 3.2: Obtain the water inflow and outflow, water consumption, NH3-N, TP, COD, BOD index data of the artificial wetland, as well as the daily absorption of NH3-N, TP, COD and BOD of the artificial wetland, and establish an artificial wetland model;

[0076] Step 3.3: Obtain the water volume and water quality data of urban rivers and lakes, urban water intake data, and the daily NH3-N absorption, TP absorption, COD absorption, and BOD absorption of urban rivers and lakes to establish an urban river and lake model;

[0077] Step 3.4: Construct an urban drainage system regulation model based on the constraints of the sewage treatment plant model, the artificial wetland model, and the urban river and lake model.

[0078] In a specific embodiment, step 3.1 includes:

[0079] According to the water volume forecast data and water quality forecast data, the total amount of rainwater and sewage entering the sewage treatment plant every day and the total amount of COD, BOD, NH3-N, and TP are calculated; according to the total amount of rainwater and sewage and the water volume constraints of the buffer pool, the daily COD treatment volume and the COD index constraints of the sewage treatment plant, the daily BOD treatment volume and the BOD index constraints of the sewage treatment plant, the daily NH3-N treatment volume and the NH3-N index constraints of the sewage treatment plant, the daily TP treatment volume and the TP index constraints of the sewage treatment plant, with the goal of maximizing the rainwater and sewage treatment volume, a sewage treatment plant model is established. The total amount of rainwater and sewage is obtained by adding the predicted water volume data of each leaf node in the urban drainage network sewage water volume forecast data, and the COD, BOD, NH3-N, and TP of the drainage network are calculated according to the sewage flow of each leaf node and the COD, BOD, NH3-N, and TP index data in the sewage. The sum of the total amount of rainwater and sewage entering the sewage treatment plant every day and the existing total amount of rainwater and sewage in the buffer pool minus the daily sewage treatment volume Q of the sewage treatment plant ST The final capacity should be less than the maximum capacity of the buffer tank. The maximum capacity of the buffer tank refers to the sum of the capacities of the sedimentation tank and the primary sedimentation tank in the sewage treatment plant. According to the COD, BOD, NH3-N and TP in the existing sewage in the buffer tank, the COD, BOD, NH3-N and TP entering the sewage treatment plant, the daily treatment capacity of COD, BOD, NH3-N and TP of the sewage, and the daily sewage treatment volume Q of the sewage treatment plant ST , and calculate the COD, BOD, NH3-N, and TP indicators of the sewage treatment plant respectively, and all indicators of the sewage meet the discharge constraints of the sewage treatment plant.

[0080] In a specific embodiment, the daily sewage treatment capacity of the sewage treatment plant is Q ST It is also necessary to meet the constraints of sewage treatment plant sewage treatment rate, facility and equipment utilization rate, hydraulic load, as well as energy consumption, material consumption, and carbon emissions, so that the sewage treatment rate, facility and equipment utilization rate, and hydraulic load are within the design value range of the sewage treatment plant, and the energy consumption, material consumption, and carbon emissions reach or exceed the industry average.

[0081] In a specific embodiment, step 3.2 includes:

[0082] According to the water inflow and outflow, water consumption, NH3-N, TP, COD, BOD content data of the artificial wetland, as well as the treated water discharge and water quality data of the sewage treatment plant, the total amount of NH3-N, TP, COD, and BOD of the artificial wetland is calculated. According to the total water volume constraint of the artificial wetland, the COD absorption capacity and the COD index constraint conditions of the artificial wetland effluent, the BOD absorption capacity and the BOD index constraint conditions of the artificial wetland effluent, the NH3-N absorption capacity and the NH3-N index constraint conditions of the artificial wetland effluent, the TP absorption capacity and the TP index constraint conditions of the artificial wetland effluent, the artificial wetland model is established with the goal of optimizing the water quality of the artificial wetland. Among them, the water quality M of the artificial wetland AW Expressed as: M AW =aM AW NH3-N +bM AW TP +cM AW COD +dM AW BOD , M AW NH3-N NH3-N index of artificial wetland, M AW TP is the artificial wetland TP index, M AW COD COD index of artificial wetland, M AW BOD is the BOD index of the artificial wetland, a, b, c, d are the weight coefficients of each index respectively; the total water volume of the artificial wetland is calculated by the inflow and outflow, water consumption and the discharge of the sewage treatment plant, and the total water volume should meet the total water volume constraint of the artificial wetland determined by the design index of the surface flow wetland water body sensory system; the water consumption is calculated according to the artificial wetland itself (such as the blockage rate of the artificial wetland subsurface flow wetland bed, the permeability, the wetland surface evaporation rate, etc.).

[0083] In a specific embodiment, step 3.3 includes:

[0084] Based on the total inflow of urban rivers and lakes, urban water intake, downstream water delivery, NH3-N, TP, COD, BOD content in water, combined with the data of point source, non-point source and endogenous pollution in rivers and lakes (predicted by prediction model based on historical data), and the water volume and water quality data of artificial wetlands replenishing urban rivers and lakes, the total amount of NH3-N, TP, COD and BOD in urban rivers and lakes is calculated; based on the COD absorption capacity of urban rivers and lakes and the COD index constraints of urban rivers and lakes downstream water delivery, the BOD absorption capacity of urban rivers and lakes and the BOD index constraints of urban rivers and lakes downstream water delivery, the NH3-N absorption capacity of urban rivers and lakes and the NH3-N index constraints of urban rivers and lakes downstream water delivery, the TP absorption capacity of urban rivers and lakes and the TP index constraints of urban rivers and lakes downstream water delivery, with the goal of optimizing the water quality of urban rivers and lakes to the downstream, an urban river and lake model is established. Among them, the urban river and lake water quality M RL Expressed as: M RL =a'M RL NH3-N +b'M RL TP +c'M RL COD +d'M RL BOD , M RL NH3-N NH3-N index for urban rivers and lakes, M RL TP is the TP index of urban rivers and lakes, M RL COD COD index for urban rivers and lakes, M AW BOD The BOD index of urban rivers and lakes, a', b', c', d' are the weight coefficients of each index.

[0085] In a specific embodiment, the urban drainage system control model aims to maximize the comprehensive water transfer coefficient M, M = st·Q ST +aw·1 / M AW +rl·1 / M RL , where st, aw, and rl are the weight coefficients corresponding to the daily sewage treatment capacity of the sewage treatment plant, the water quality of the artificial wetland, and the water quality of urban rivers and lakes, respectively.

[0086] In a specific embodiment, step 4 includes:

[0087] Step 4.1: Initialize the particle swarm parameters, including: particle swarm size, particle swarm dimension, number of iterations, learning factor, and iteration step range; each particle represents a possible solution of the urban drainage system regulation model, and the particle dimensions are respectively the daily sewage treatment volume Q of the sewage treatment plant ST and outflow from artificial wetlands to urban rivers and lakes.

[0088] Step 4.2: Randomly initialize the position, velocity and acceleration of each particle;

[0089] Step 4.3: Update the position, velocity and acceleration of each particle and calculate the fitness value of each particle; the particle position is updated by the original position and velocity value, the velocity is updated according to the original velocity and acceleration, the acceleration is updated according to the original acceleration and the learning factor, and the fitness value is the water regulation comprehensive coefficient M;

[0090] Step 4.4: Determine the individual's historical optimal position and optimal fitness value, as well as the group's historical optimal position and optimal fitness value, and update the learning factor, which is the distance and direction between each particle and the current group's optimal position;

[0091] Step 4.5: Determine whether the maximum number of iterations is met, or whether the difference in the optimal fitness value of the group between two iterations meets the minimum requirement. If neither is met, return to step 4.3;

[0092] Step 4.6: Output the optimal solution and save it; determine the daily sewage treatment capacity of the sewage treatment plant and the discharge capacity of the artificial wetland to the city's rivers and lakes based on the optimal solution.

[0093] In a specific embodiment, step 5 includes:

[0094] Step 5.1: Based on the water volume monitoring data entering the sewage treatment plant at each moment and the water volume forecast data entering the sewage treatment plant, the measured data sequence of the water volume entering the sewage treatment plant and the water volume forecast data sequence are sorted out, and the difference between the measured data sequence and the forecast data sequence at the corresponding moment is calculated to obtain the error sequence; based on the error sequence, the error prediction model is used to predict the error value at the next moment, so as to feedback and adjust the water volume data entering the sewage treatment plant predicted in step 2;

[0095] According to the water quality monitoring data entering the sewage treatment plant at each time, the measured water quality data sequence entering the sewage treatment plant is sorted out, and then the average water quality entering the sewage treatment plant over a period of time is calculated. When the average water quality is not within the preset threshold range, feedback is given to the rainwater and sewage drainage network, and a recommended strategy for exploration, maintenance, reconstruction or expansion of the regional rainwater and sewage drainage network is proposed. Specifically, according to the total amount of rainwater and sewage actually monitored by the sewage treatment plant, as well as the COD, BOD, NH3-N, and TP concentrations of the drainage network, the sewage treatment plant inlet water volume index and water quality index are obtained. When the inlet water volume index and water quality index are lower than the sewage treatment plant design index within the set time period, indicating that the drainage network has risks such as blockage and leakage, feedback is given, and corresponding exploration and maintenance of the regional rainwater and sewage drainage network is proposed; if it is higher than the sewage treatment plant design index, it means that the drainage network has been in high-load operation for a long time, and there is a risk of being unable to meet the collection and discharge of rainwater and sewage, feedback is given, and a recommended strategy for corresponding reconstruction or expansion of the regional rainwater and sewage drainage network is proposed.

[0096] Step 5.2: According to the water quality monitoring data of the artificial wetland at each moment, the measured water quality data sequence of the artificial wetland is sorted out, and then the average water quality of the artificial wetland over a period of time is calculated. When the average water quality exceeds the preset threshold range, feedback is given to the sewage treatment plant, and a recommended strategy for adjusting the operation plan of the sewage treatment plant is proposed. Specifically, the NH3-N, TP, COD, and BOD index data in the artificial wetland influent are monitored. When the index is lower than the artificial wetland design index within the set time, feedback is given, and a recommended strategy for adjusting the operation plan of the sewage treatment plant to reduce energy consumption and material consumption is proposed; when the index is higher than the artificial wetland design index within the set time, feedback is given, and a recommended strategy for reconstructing and expanding the operation plan of the sewage treatment plant and adjusting the treatment capacity is proposed.

[0097] Step 5.3: According to the water quality monitoring data of urban rivers and lakes at each time, the measured data sequence of urban river and lake water quality is sorted out, and then the average water quality of urban rivers and lakes over a period of time is calculated. When the average water quality exceeds the preset threshold range, the artificial wetland is fed back, and the operation plan of the artificial wetland and the investigation and remediation of urban river and lake pollution sources are proposed. Specifically, the NH3-N, TP, COD, and BOD index data in the middle and lower reaches of urban rivers and lakes are monitored. When the index is higher than the specified index within the set time, feedback is given, indicating that the treatment efficiency of the artificial wetland is insufficient or the point source, non-point source, and endogenous pollutants in urban rivers and lakes have a greater impact. It is proposed to adjust and optimize the operation plan of the artificial wetland, and propose a recommended strategy for the investigation and remediation of point source, non-point source, and endogenous pollution points in the city that have not been uniformly treated with sewage.

[0098] In a specific embodiment, the error prediction model performs error prediction as follows:

[0099] According to the measured water volume data sequence and the predicted water volume data sequence, the error sequence is calculated and expressed as:

[0100] x (0) ={x (0) (1),x (0) (2),x (0) (3),……,x (0) (n)};

[0101] Among them, x (0) (k) represents the kth error in the error sequence, k = 1, 2, 3, ..., n, n is the total number of errors in the error sequence, and n ≥ 5.

[0102] The initial error sequence is accumulated once to obtain the first-order accumulation generation operator, which is expressed as:

[0103] x (1) ={x (1) (1),x (1) (2),x (1) (3),……,x (1) (n)};

[0104] Among them, x (1) is a first-order cumulative sequence. The kth data x in the first-order cumulative sequence (1) (k), is the sum of the first k errors in the error sequence, expressed as: where x (0) (i) represents the i-th error in the error sequence.

[0105] The error prediction model is expressed as a single variable first-order differential equation:

[0106]

[0107] Among them, a is the development coefficient, b is the gray action; t is the current sequence node; solve the values ​​of a and b, and use the adjacent mean of the accumulation result to construct the matrix vector B and the constant vector Y n , the specific formula is as follows:

[0108]

[0109] Y n =(x (0) (2),x (0) (3),……,x (0) (n)) T ;

[0110]

[0111] in, For x(1) The nearest neighbor mean of (1), For x (1) (2) is the nearest neighbor mean, For x (1) After obtaining the values ​​of a and b, we put them into the single variable first-order differential equation and solve it using the least squares method to obtain the general representation of the error prediction model, which is:

[0112]

[0113] in, is the predicted value of the next error sequence node, that is, the error value of the next moment predicted according to the error sequence. Through iterative calculation, the error prediction values ​​of multiple time nodes after the error sequence can be obtained. According to the error prediction values, the predicted water volume data entering the sewage treatment plant is feedback-adjusted, thereby improving the accuracy of the water volume prediction data.

[0114] An embodiment of the present invention further discloses a city drainage system joint control system, the system comprising:

[0115] Basic data module: obtain urban drainage network data in different areas at different times;

[0116] Data prediction module: obtains temperature, humidity, precipitation data, industrial water consumption, domestic water consumption, and population data of each region at different times, and builds a data set in combination with urban drainage network data; trains and verifies the LSTM model through the data set, and uses the trained LSTM model to predict the water quality and water quantity of the urban drainage network, and obtains the water quantity and water quality prediction data entering the sewage treatment plant;

[0117] Model building module: construct sewage treatment plant model, artificial wetland model, urban river and lake model, and further construct urban drainage system regulation model;

[0118] Model solving module: input the water volume prediction data and water quality prediction data into the urban drainage system control model, and use the particle swarm algorithm to solve it, so as to obtain the drainage volume from the sewage treatment plant to the artificial wetland and the outflow volume from the artificial wetland to the urban rivers and lakes, and carry out the downstream control of urban rainwater and sewage according to the solution results;

[0119] Feedback strategy module: monitor the amount and quality of water entering the sewage treatment plant, the water quality of artificial wetlands, and the water quality of urban rivers and lakes at all times, provide feedback based on the monitoring and detection results, conduct upward regulation, and carry out two-way joint regulation of the urban drainage system.

[0120] In a specific embodiment, take the rainwater and sewage pipe network-sewage treatment plant-artificial wetland-urban river and lake joint control plan of a city on the Yangtze River as an example. Figure 2 As shown. Controlled by the urban drainage system joint control system:

[0121] (1) The centralized collection rate of rainwater and sewage in the area reached 70.4%, and the average COD concentration of sewage entering the plant was 157.8 mg / L, meeting industry requirements.

[0122] (2) The sewage treatment rate of the sewage treatment plant reached 95.7%, the utilization rate of facilities and equipment was 100%, the average hydraulic load rate was 91.8%, and the average COD load was 45.1%, meeting the industry requirements; the effluent quality met the GB18918-2002 Class A emission standard and met the design requirements; the unit sewage power consumption of the sewage treatment plant was 0.31 kWh / m 3 , which is lower than the median power consumption of urban sewage treatment plants along the Yangtze River, which is 0.33 kWh / m 3 However, the amount of sludge produced per unit COD removed is 3.32 kg / kgCOD, which is higher than the average sludge produced per unit COD removed by urban sewage treatment plants along the Yangtze River, which is 2.71 kg / kgCOD. The carbon emission per unit sewage treatment is 527.9 gCO 2e / m 3 , which is higher than the leading enterprises in the sewage treatment plant industry of the same scale. Therefore, the sewage treatment plant is fed back through the urban water system optimization and control platform to carry out energy conservation, consumption reduction and emission reduction.

[0123] (3) The water volume and quality of the artificial wetland inflow were stable, and the effluent quality met the design requirements (the main indicators COD, NH3-N, and TP met the Class IV standard of GB3838-2002). However, when the temperature was high, eutrophication occurred in the surface flow wetland. Therefore, the artificial wetland was fed back through the urban water system optimization and control platform to adopt intermittent non-continuous operation and adjustment of operating parameters.

[0124] (4) After the effluent from the artificial wetland meets the standards, it is discharged into the urban river as ecological water replenishment. The average daily water replenishment is 20,000 t / d. The average COD, NH3-N and TP values ​​of the replenishment water source are 20.74, 0.38 and 0.14 mg / L respectively; the river ecological flow rate is 2m 3 / s, since the river turns black and smells seasonally, the black and smelly level is mild. Analysis shows that it is greatly affected by upstream flows and endogenous pollution loads, and is severely polluted by overflow in the rainy season. Therefore, the urban water system optimization and control platform is used to feed back to the artificial wetland for appropriate water replenishment; at the same time, it is fed back to the district sewage pipe network system to carry out leak inspections and repairs in the district sewage pipe network, especially for the sediment deposition in the sewage pipe network on sunny days and the scouring of pollutants in the sewage pipe network on rainy days, and each section is inspected and dredged; in addition, pollution source control and endogenous remediation are carried out along the river, supplemented by measures such as in-situ ecological purification of water quality in the river, to ensure that the river water quality assessment section meets the standards.

[0125] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0126] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for joint regulation of urban drainage system, characterized in that: The specific steps are as follows: Step 1: Obtain urban drainage network data in different areas at different times; Step 2: Obtain the temperature, humidity, precipitation data, industrial water consumption, domestic water consumption, and population data of each area at different times, and build a data set in combination with the urban drainage network data; train and verify the LSTM model through the data set, and use the trained LSTM model to predict the water quality and water quantity of the urban drainage network to obtain the water quantity prediction data and water quality prediction data entering the sewage treatment plant; Step 3: Construct the sewage treatment plant model, artificial wetland model, urban river and lake model respectively, and further construct the urban drainage system regulation model; Step 4: Input the water volume prediction data and the water quality prediction data into the urban drainage system control model, and use the particle swarm algorithm to solve it, so as to obtain the drainage volume from the sewage treatment plant to the artificial wetland and the effluent flow from the artificial wetland to the urban rivers and lakes, and perform the downstream control of urban rainwater and sewage according to the solution results; Step 5: Monitor the amount and quality of water entering the sewage treatment plant, the water quality of artificial wetlands, and the water quality of urban rivers and lakes at all times, provide feedback based on the monitoring and testing results, conduct upward regulation, and conduct two-way joint regulation of the urban drainage system; The step 3 comprises: Step 3.1: Obtain the buffer tank capacity, daily NH3-N treatment capacity, daily TP treatment capacity, daily COD treatment capacity, and daily BOD treatment capacity of the sewage treatment plant, and establish a sewage treatment plant model; Step 3.2: Obtain the water inflow and outflow, water consumption, NH3-N, TP, COD, BOD index data of the artificial wetland, as well as the daily absorption of NH3-N, TP, COD and BOD of the artificial wetland, and establish an artificial wetland model; Step 3.3: Obtain the water inflow and water quality background data of urban rivers and lakes, urban water intake data, and the daily NH3-N absorption, TP absorption, COD absorption, and BOD absorption of urban rivers and lakes, and establish an urban river and lake model; Step 3.4: constructing an urban drainage system control model according to the constraints of the sewage treatment plant model, the constraints of the artificial wetland model, and the constraints of the urban river and lake model; The step 3.1 comprises: According to the water volume prediction data and the water quality prediction data, the total amount of rainwater and sewage entering the sewage treatment plant and the amount of COD, BOD, NH3-N, and TP are calculated; according to the total amount of rainwater and sewage and the water volume constraints of the buffer tank, the daily COD treatment volume and the COD index constraints of the sewage treatment plant drainage, the daily BOD treatment volume and the BOD index constraints of the sewage treatment plant drainage, the daily NH3-N treatment volume and the NH3-N index constraints of the sewage treatment plant drainage, the daily TP treatment volume and the TP index constraints of the sewage treatment plant drainage, with the goal of maximizing the rainwater and sewage treatment volume, a sewage treatment plant model is established; The step 3.2 comprises: According to the inflow and outflow of artificial wetlands, water consumption, NH3-N, TP, COD, BOD content data in the water, and the treated water discharge and water quality data of the sewage treatment plant, the total amount of NH3-N, TP, COD, and BOD in the artificial wetlands is calculated. According to the total water volume constraints of the artificial wetlands, the COD absorption capacity and the COD index constraints of the artificial wetland effluent, the BOD absorption capacity and the BOD index constraints of the artificial wetland effluent, the NH3-N absorption capacity and the NH3-N index constraints of the artificial wetland effluent, the TP absorption capacity and the TP index constraints of the artificial wetland effluent, with the goal of optimizing the water quality of the artificial wetlands, an artificial wetland model is established; The step 3.3 comprises: Based on the total inflow of urban rivers and lakes, urban water intake, background content data of NH3-N, TP, COD and BOD in water, combined with data on point source, non-point source and endogenous pollution of rivers and lakes, as well as data on water volume and quality of artificial wetlands replenishing urban rivers and lakes, the total amount of NH3-N, TP, COD and BOD in urban rivers and lakes is calculated. Based on the COD absorption capacity of rivers and lakes and the COD index constraints of downstream water transmission from rivers and lakes, the BOD absorption capacity of rivers and lakes and the BOD index constraints of downstream water transmission from rivers and lakes, the NH3-N absorption capacity of rivers and lakes and the NH3-N index constraints of downstream water transmission from rivers and lakes, and the TP absorption capacity of rivers and lakes and the TP index constraints of downstream water transmission from rivers and lakes, an urban river and lake model is established with the goal of optimizing the water quality output from urban rivers and lakes to downstream.

2. A method for joint control of urban drainage system according to claim 1, characterized in that: The step 1 comprises: Step 1.1: Obtain a map of the urban drainage network and mark the main drainage pipes, branch drainage pipes, and the rainwater and sewage collection points and rainwater and sewage inlet points in the branch drainage pipes; Step 1.2: Detection equipment is set at the rainwater and sewage collection point and the rainwater and sewage inlet, and rainwater and sewage flow rate, flow rate, rainwater and sewage pH value, COD, BOD, NH3-N, TP index data are obtained at set time intervals, and the data of the detection equipment at the rainwater and sewage collection point is used as the branch node data, and the data of the detection equipment at the rainwater and sewage inlet is used as the leaf node data; Step 1.3: Obtain the diameter and length data of the pipe between the rainwater and sewage collection point and the rainwater and sewage inlet as branch data; Step 1.4: The leaf node data, branch node data and trunk data are used to form a storage tree, each tree represents an area of ​​the city, and multiple storage trees form a storage forest to store the urban drainage network data.

3. A method for joint control of urban drainage system according to claim 2, characterized in that: The step 2 comprises: Step 2.1: The rainwater and sewage flow rate, flow rate, rainwater and sewage pH value, COD, BOD, NH3-N, TP index data of the leaf node at a certain moment, as well as the temperature, humidity, precipitation data of the area where the leaf node is located at that moment, as well as industrial water consumption, domestic water consumption, and population data, constitute a data unit; the leaf node is at time t1~t n All data units in the sequence are organized into a sequence in chronological order as a sample data; Step 2.2: traverse the storage forest, obtain multiple sample data based on the leaf node data in the storage forest to construct a data set, and divide it into a training data set and a verification data set; Step 2.3: construct an LSTM model, train it using the training data set, and verify it using the verification data set; Step 2.4: According to step 2.1, obtain the prediction data set at the current moment, and input the trained LSTM model operation to predict the rainwater and sewage flow and flow rate of all leaf nodes at the next moment as water volume prediction data, and the rainwater and sewage pH value, COD, BOD, NH3-N, and TP indicator data as water quality prediction data.

4. The urban drainage system joint control method according to claim 1, characterized in that: The step 4 comprises: Step 4.1: Initialize the particle swarm parameters, including: particle swarm size, particle swarm dimension, number of iterations, learning factor, and iteration step range; Step 4.2: Randomly initialize the position, velocity and acceleration of each particle; Step 4.3: Update the velocity, acceleration and position of each particle and calculate the fitness value of each particle; Step 4.4: Determine the individual's historical optimal position and optimal fitness value, as well as the group's historical optimal position and optimal fitness value, and update the learning factor; Step 4.5: Determine whether the maximum number of iterations is met, or whether the difference in the optimal fitness value of the group between two iterations meets the minimum requirement. If neither is met, return to step 4.3; Step 4.6: Output the optimal solution and save it.

5. The urban drainage system joint control method according to claim 1, characterized in that: The step 5 comprises: According to the water volume monitoring data entering the sewage treatment plant at each moment and the water volume forecast data entering the sewage treatment plant, a measured data sequence of the water volume entering the sewage treatment plant and a water volume forecast data sequence are obtained, and the difference between the measured data sequence and the forecast data sequence at the corresponding moment is calculated to obtain an error sequence; based on the error sequence, an error prediction model is used to predict the error value at the next moment, so as to feedback and adjust the water volume data entering the sewage treatment plant predicted in step 2; Based on the water quality monitoring data entering the sewage treatment plant at each moment, the measured water quality data sequence entering the sewage treatment plant is sorted out, and then the average water quality entering the sewage treatment plant over a period of time is calculated. When the average water quality is not within the preset threshold range, feedback is given to the rainwater and sewage drainage network, and recommended strategies for exploration, maintenance, reconstruction or expansion of the regional rainwater and sewage drainage network are proposed; According to the water quality monitoring data of artificial wetlands at each moment, the measured water quality data sequence of artificial wetlands is obtained, and then the average water quality of artificial wetlands over a period of time is calculated. When the average water quality exceeds the preset threshold range, feedback is given to the sewage treatment plant, and a recommended strategy for adjusting the operation plan of the sewage treatment plant is proposed; Based on the water quality monitoring data of urban rivers and lakes at various times, a sequence of measured data on the water quality of urban rivers and lakes is compiled to calculate the average water quality of urban rivers and lakes over a period of time. When the average water quality exceeds the preset threshold range, feedback is given to the artificial wetland, and recommended strategies for the operation plan of the artificial wetland and the investigation and remediation of pollution sources in urban rivers and lakes are proposed.

6. A joint control system for urban drainage system, characterized in that: The system comprises: Basic data module: obtain urban drainage network data in different areas at different times; Data prediction module: obtain the temperature, humidity, precipitation data, industrial water consumption, domestic water consumption, and population data of each area at different times, and build a data set in combination with the urban drainage network data; train and verify the LSTM model through the data set, and use the trained LSTM model to predict the water quality and water quantity of the urban drainage network, and obtain the water quantity prediction data and water quality prediction data entering the sewage treatment plant; Model building module: construct sewage treatment plant model, artificial wetland model, urban river and lake model, and further construct urban drainage system regulation model; Model solving module: input the water volume prediction data and the water quality prediction data into the urban drainage system control model, and use the particle swarm algorithm to solve it, so as to obtain the drainage volume from the sewage treatment plant to the artificial wetland and the effluent flow from the artificial wetland to the urban rivers and lakes, and perform the downstream control of urban rainwater and sewage according to the solution results; Feedback strategy module: monitor the amount and quality of water entering the sewage treatment plant, the water quality of artificial wetlands, and the water quality of urban rivers and lakes at all times, provide feedback based on the monitoring and testing results, conduct upward regulation, and conduct two-way joint regulation of the urban drainage system; The model building module specifically performs the following steps: Step 3.1: Obtain the buffer tank capacity, daily NH3-N treatment capacity, daily TP treatment capacity, daily COD treatment capacity, and daily BOD treatment capacity of the sewage treatment plant, and establish a sewage treatment plant model; Step 3.2: Obtain the water inflow and outflow, water consumption, NH3-N, TP, COD, BOD index data of the artificial wetland, as well as the daily absorption of NH3-N, TP, COD and BOD of the artificial wetland, and establish an artificial wetland model; Step 3.3: Obtain the water inflow and water quality background data of urban rivers and lakes, urban water intake data, and the daily NH3-N absorption, TP absorption, COD absorption, and BOD absorption of urban rivers and lakes, and establish an urban river and lake model; Step 3.4: constructing an urban drainage system control model according to the constraints of the sewage treatment plant model, the constraints of the artificial wetland model, and the constraints of the urban river and lake model; The step 3.1 comprises: According to the water volume prediction data and the water quality prediction data, the total amount of rainwater and sewage entering the sewage treatment plant and the amount of COD, BOD, NH3-N, and TP are calculated; according to the total amount of rainwater and sewage and the water volume constraints of the buffer tank, the daily COD treatment volume and the COD index constraints of the sewage treatment plant drainage, the daily BOD treatment volume and the BOD index constraints of the sewage treatment plant drainage, the daily NH3-N treatment volume and the NH3-N index constraints of the sewage treatment plant drainage, the daily TP treatment volume and the TP index constraints of the sewage treatment plant drainage, with the goal of maximizing the rainwater and sewage treatment volume, a sewage treatment plant model is established; The step 3.2 comprises: According to the inflow and outflow of artificial wetlands, water consumption, NH3-N, TP, COD, BOD content data in the water, and the treated water discharge and water quality data of the sewage treatment plant, the total amount of NH3-N, TP, COD, and BOD in the artificial wetlands is calculated. According to the total water volume constraints of the artificial wetlands, the COD absorption capacity and the COD index constraints of the artificial wetland effluent, the BOD absorption capacity and the BOD index constraints of the artificial wetland effluent, the NH3-N absorption capacity and the NH3-N index constraints of the artificial wetland effluent, the TP absorption capacity and the TP index constraints of the artificial wetland effluent, with the goal of optimizing the water quality of the artificial wetlands, an artificial wetland model is established; The step 3.3 comprises: Based on the total inflow of urban rivers and lakes, urban water intake, background content data of NH3-N, TP, COD and BOD in water, combined with data on point source, non-point source and endogenous pollution of rivers and lakes, as well as data on water volume and quality of artificial wetlands replenishing urban rivers and lakes, the total amount of NH3-N, TP, COD and BOD in urban rivers and lakes is calculated. Based on the COD absorption capacity of rivers and lakes and the COD index constraints of downstream water transmission from rivers and lakes, the BOD absorption capacity of rivers and lakes and the BOD index constraints of downstream water transmission from rivers and lakes, the NH3-N absorption capacity of rivers and lakes and the NH3-N index constraints of downstream water transmission from rivers and lakes, and the TP absorption capacity of rivers and lakes and the TP index constraints of downstream water transmission from rivers and lakes, an urban river and lake model is established with the goal of optimizing the water quality output from urban rivers and lakes to downstream.

Images