A water quality change trend prediction system and method based on source-flow model

Abstract

The present invention discloses a water quality change trend prediction system and method based on a source-flow-reach model, the system comprising a source module, a flow module and a reach module. The present invention estimates the impact of sewage discharge on the water environment of the receiving water body by analyzing the concentration changes of pollutants after sewage is transmitted and transported through various links; combined with the water quality target requirements of the receiving water body, it is fed back to the sewage treatment link to improve the treatment efficiency, further reduce the concentration of pollutants, reduce the water quality concentration at the sewage outlet, reduce the pollution risk to the water quality of the receiving water body, and realize the intelligent management of the whole process of sewage treatment.

Description

Technical Field

[0001] The present invention relates to the technical field of urban sewage monitoring, and in particular to a system and method for predicting water quality change trends based on a source-flow model. Background Art

[0002] Urban water supply is discharged after consumption by various users, and then enters the sewage treatment plant through the drainage network. After being treated to meet the standards, it is discharged into the receiving water body through the network again. In this process, the discharge of various users after consuming water resources can be regarded as the "source" of sewage discharge. The drainage network is the channel for sewage transfer and can be used as the "flow" of sewage transmission. The rivers, lakes, and wetlands that receive the treated sewage can be regarded as the "reach" of sewage. In the usual prediction method of water quality change trend, the modules "source", "flow", and "reach" through which sewage flows are separated and predicted separately. There is a lack of good treatment of the interfaces of each module, which makes the prediction of the change trend of pollutant concentration in sewage have large deviations. Summary of the invention

[0003] In view of the above-mentioned deficiencies in the prior art, the present invention provides a system and method for predicting water quality change trends based on a source-flow model.

[0004] In order to achieve the above-mentioned object of the invention, the technical solution adopted by the present invention is:

[0005] In the first aspect, the present invention proposes a water quality change trend prediction system based on a source-flow model, comprising:

[0006] Source module, which is used to collect demographic, socioeconomic and lifestyle data related to different types of sewage discharge, and estimate the pollutant load in different types of sewage based on the collected data;

[0007] The flow module is used to estimate the pollutant attenuation load in sewage using the pollutant load estimated by the source module as the initial value, the drainage network for sewage discharge as the upper boundary, and the sewage outlets of rivers, lakes, and wetlands as the lower boundary. It collects the data of the drainage network and sewage treatment plant as boundary conditions, and estimates the pollutant attenuation load in sewage; and adjusts the sewage treatment conditions of the sewage treatment plant according to the prediction results fed back by the module;

[0008] The module is used to use the pollutant attenuation load estimated by the flow module as the initial value, collect the receiving river, lake, wetland topography, climate and hydrology, upstream flow, and water quality background values ​​as boundary conditions, predict the diffusion process of pollutants after entering the receiving water body and the water quality change trend of the receiving water body, and feed the prediction results back to the flow module.

[0009] Optionally, estimating the pollutant attenuation load in sewage comprises the following steps:

[0010] A1. Construct the objective function based on the square of the difference between the measured value and the estimated value of the pollutant attenuation load;

[0011] A2, select pollutant load as the iteration parameter, drainage network and sewage treatment plant data as boundary conditions, set the population size and randomize the speed and position of the initial particles to generate the initial population;

[0012] A3. Set the individual extreme value of the particle to the current position, and the global extreme value of the particle to the position of the best particle in the initial population;

[0013] A4, determine whether the iteration stop condition is met; if so, jump to A8; otherwise, execute A5;

[0014] A5. Perform two perturbations and updates on all particles in the particle swarm;

[0015] A6. Update the best position experienced by all particles in the particle swarm;

[0016] A7, determine whether the iteration stop condition is met; if so, jump to A8; otherwise, execute A5;

[0017] A8. Determine the pollutant attenuation load in sewage based on the estimated pollutant load.

[0018] Optionally, the perturbing and updating all particles in the particle swarm twice comprises the following steps:

[0019] A5-1, generate a random number, and determine whether the random number is less than the set first disturbance probability; if so, execute A5-2; otherwise, set the global extreme value and individual extreme value to the new position after disturbance;

[0020] A5-2. Perform a perturbation on the global extreme value and the individual extreme value with a set first perturbation probability, and then perform a second perturbation on the points obtained after the first perturbation with a set second perturbation probability;

[0021] A5-3. Update the positions and velocities of the particles in the particle swarm after the two disturbances to obtain the next generation of particle swarms, so that the positions and velocities of all particles in the next generation of particle swarms are within the boundary conditions;

[0022] A5-4. The individual extreme value of each particle in the next generation particle swarm is updated using the particle comparison criterion.

[0023] Optionally, the predicting of the diffusion process of pollutants after entering the receiving water body and the water quality change trend of the receiving water body comprises the following steps:

[0024] B1. Construct the objective function based on the square of the difference between the measured value and the predicted value of the receiving water quality;

[0025] B2. Select the water quality of the receiving water body as the iteration parameter, the receiving river, lake, wetland topography, climate and hydrology, upstream flow, and water quality status background value as the boundary conditions, set the population size and randomize the speed and position of the initial particles to generate the initial population;

[0026] B3. Set the individual extreme value of the particle to the current position, and the global extreme value of the particle to the position of the best particle in the initial population;

[0027] B4, determine whether the iteration stop condition is met; if so, jump to B8; otherwise, execute B5;

[0028] B5. Perform two perturbations and updates on all particles in the particle swarm;

[0029] B6. Update the best position experienced by all particles in the particle swarm;

[0030] B7, determine whether the iteration stop condition is met; if so, jump to B8; otherwise, execute B5;

[0031] B8. Determine the diffusion process of pollutants after they enter the receiving waters and the changing trend of the receiving water quality based on the predicted receiving water quality.

[0032] Optionally, the perturbing and updating all particles in the particle swarm twice comprises the following steps:

[0033] B5-1, generate a random number, and determine whether the random number is less than the set first disturbance probability; if so, execute B5-2; otherwise, set the global extreme value and individual extreme value to the new position after disturbance;

[0034] B5-2, the global extreme value and the individual extreme value are disturbed once with the set first disturbance probability, and then the points obtained after the first disturbance are disturbed for the second time with the set second disturbance probability;

[0035] B5-3. Update the positions and velocities of the particles in the particle swarm after the two disturbances to obtain the next generation of particle swarms, so that the positions and velocities of all particles in the next generation of particle swarms are within the boundary conditions;

[0036] B5-4. The individual extreme value of each particle in the next generation particle swarm is updated using the particle comparison criterion.

[0037] Optionally, the source module includes a domestic sewage submodule, an industrial wastewater submodule, and a surface runoff submodule;

[0038] The domestic sewage submodule is used to collect population, water supply and drainage, and lifestyle data associated with domestic sewage discharge;

[0039] The industrial wastewater submodule is used to collect data such as output value, wastewater per unit output value, and pollutant emissions associated with industrial wastewater discharge;

[0040] The surface runoff submodule is used to collect data such as rainfall, underlying surface type, and impervious surface area associated with surface runoff discharge.

[0041] Optionally, the flow module includes a pipe network submodule and a sewage treatment plant submodule;

[0042] The pipe network submodule is used to collect pipe network data;

[0043] The sewage treatment plant submodule is used to collect sewage treatment plant data.

[0044] Optionally, the module includes a river submodule, a lake submodule and a wetland submodule;

[0045] The river channel submodule is used to collect the receiving river channel topography, climate and hydrology, upstream flow, and water quality status background value data;

[0046] The lake submodule is used to collect background data on the topography, climate and hydrology, inflow and water quality, outflow, lake water level and water quality of the receiving lake;

[0047] The wetland submodule is used to collect background value data on the receiving wetland topography, climate and hydrology, inflow and water quality, outflow and water quality.

[0048] In a second aspect, the present invention proposes a method for predicting water quality change trends based on a source-flow model, comprising the following steps:

[0049] Use the source module to collect demographic, socioeconomic, and lifestyle data associated with different types of sewage discharge, and estimate the pollutant loads in different types of sewage based on the collected data;

[0050] The flow module uses the pollutant load estimated by the source module as the initial value, the drainage network of sewage discharge as the upper boundary, and the sewage outlets of rivers, lakes, and wetlands as the lower boundary. The drainage network and sewage treatment plant data are collected as boundary conditions to estimate the pollutant attenuation load in the sewage; and the sewage treatment conditions of the sewage treatment plant are adjusted according to the prediction results fed back by the module.

[0051] The D module uses the pollutant attenuation load estimated by the flow module as the initial value, collects the receiving river, lake, wetland topography, climate and hydrology, upstream flow, and water quality background values ​​as boundary conditions, predicts the diffusion process of pollutants after entering the receiving water body and the water quality change trend of the receiving water body, and feeds the prediction results back to the flow module.

[0052] The present invention has the following beneficial effects:

[0053] The present invention estimates the impact of sewage discharge on the water environment of the receiving water body by analyzing the changes in the concentration of pollutants after the sewage is transmitted and transported through various links; combined with the water quality target requirements of the receiving water body, the feedback is given to the sewage treatment link to improve the treatment efficiency, further reduce the pollutant concentration, reduce the water quality concentration at the sewage outlet, reduce the pollution risk to the water quality of the receiving water body, and realize intelligent management of the entire sewage treatment process. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a schematic diagram of the structure of a water quality change trend prediction system based on a source-flow model in Example 1 of the present invention;

[0055] Figure 2 Schematic diagram of the flow of a method for predicting water quality change trends based on a source-flow model in Example 2 of the present invention. DETAILED DESCRIPTION

[0056] The specific implementation modes of the present invention are described below so that those skilled in the art can understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.

[0057] Example 1

[0058] like Figure 1 As shown, the embodiment of the present invention proposes a water quality change trend prediction system based on a source-flow model, including:

[0059] Source module, which is used to collect demographic, socioeconomic and lifestyle data related to different types of sewage discharge, and estimate the pollutant load in different types of sewage based on the collected data;

[0060] The flow module is used to estimate the pollutant attenuation load in sewage using the pollutant load estimated by the source module as the initial value, the drainage network for sewage discharge as the upper boundary, and the sewage outlets of rivers, lakes, and wetlands as the lower boundary. It collects the data of the drainage network and sewage treatment plant as boundary conditions, and estimates the pollutant attenuation load in sewage; and adjusts the sewage treatment conditions of the sewage treatment plant according to the prediction results fed back by the module;

[0061] The module is used to use the pollutant attenuation load estimated by the flow module as the initial value, collect the receiving river, lake, wetland topography, climate and hydrology, upstream flow, and water quality background values ​​as boundary conditions, predict the diffusion process of pollutants after entering the receiving water body and the water quality change trend of the receiving water body, and feed the prediction results back to the flow module.

[0062] In an optional embodiment of the present invention, the source module of the present invention includes a domestic sewage submodule, an industrial wastewater submodule, and a surface runoff submodule;

[0063] The domestic sewage submodule is used to collect population, water supply and drainage, and lifestyle data associated with domestic sewage discharge;

[0064] The industrial wastewater submodule is used to collect data such as output value, wastewater per unit output value, and pollutant emissions associated with industrial wastewater discharge;

[0065] The surface runoff submodule is used to collect data such as rainfall, underlying surface type, and impervious surface area associated with surface runoff discharge.

[0066] The source module of the present invention simulates the generation process of pollutants in sewage. According to the nature of sewage, domestic sewage submodule, industrial wastewater submodule, surface runoff submodule, etc. are set respectively; by collecting data such as population, socio-economics, and lifestyle, the load of major pollutants in various types of sewage is estimated.

[0067] The source module of the present invention uses the SWAT model to estimate the pollutant load in different types of sewage.

[0068] The SWAT model is a distributed hydrological and water quality model developed by the United States Department of Agriculture (USDA) based on the SWRRB model. Its main function is to simulate the surface water environment by inputting data such as meteorology, topography, land use type, soil, water diversion, and pollution sources, and through a series of regulatory measures, such as changing land use types and adjusting fertilizer application amounts, the model can predict changes in water quantity and quality.

[0069] The present invention estimates the pollutant loads in different types of sewage by inputting the collected population, socioeconomic and lifestyle data associated with different types of sewage discharge into the SWAT model.

[0070] In an optional embodiment of the present invention, the flow module of the present invention includes a pipe network submodule and a sewage treatment plant submodule;

[0071] The pipe network submodule is used to collect pipe network data;

[0072] The sewage treatment plant submodule is used to collect sewage treatment plant data.

[0073] The flow module of the present invention realizes the simulation of the transport process of pollutants in sewage, from the lower boundary of the "source" to the upper boundary of the "reach", that is, the sewage outlets along the rivers, lakes, and wetlands; according to the sewage transport channel and the transport process, the pipe network sub-module and the sewage treatment plant sub-module are respectively set; the pollutant load estimated by the source module is used as the initial value, and the pipe network and sewage treatment plant data are collected as boundary conditions, so as to estimate the attenuation / reduction load of the main pollutants in the sewage.

[0074] The present invention estimates the pollutant attenuation load in sewage, comprising the following steps:

[0075] A1. Construct the objective function based on the square of the difference between the measured value and the estimated value of the pollutant attenuation load;

[0076] A2, select pollutant load as the iteration parameter, drainage network and sewage treatment plant data as boundary conditions, set the population size and randomize the speed and position of the initial particles to generate the initial population;

[0077] A3. Set the individual extreme value of the particle to the current position, and the global extreme value of the particle to the position of the best particle in the initial population;

[0078] A4, determine whether the iteration stop condition is met; if so, jump to A8; otherwise, execute A5; the iteration stop condition here can be a set maximum number of iterations, or can be determined based on the fact that there is no new improvement on the optimal solution for a certain number of consecutive generations.

[0079] A5. Perform two perturbations and updates on all particles in the particle swarm, specifically including the following steps:

[0080] A5-1, generate a random number, and determine whether the random number is less than the set first disturbance probability; if so, execute A5-2; otherwise, set the global extreme value and individual extreme value to the new position after disturbance;

[0081] A5-2. The global extreme value and the individual extreme value are disturbed once with the set first disturbance probability. The point obtained after the disturbance is

[0082]

[0083] Where λ is the direction along which the particle is located at Y The length of the steps taken. F(Y)=∑F i (X i ,Y),F i (X i ,Y) is determined by the following formula

[0084]

[0085] Where Φ(X i ) is particle Xi The moving direction of point Y is determined by all particles in the current group, and the direction is biased towards the position of particles with smaller constraint violations or smaller template function values.

[0086] In order to avoid point Y being disturbed in one direction all the time, the point obtained after the first disturbance is disturbed for the second time with the set second disturbance probability; assuming that FY1 will be disturbed for the second time, the disturbance is recorded as

[0087]

[0088] Where ΔZ obeys the n-dimensional normal distribution.

[0089] A5-3. Update the position and velocity of the particles in the particle swarm after two disturbances. The update equation is:

[0090] v ij (t+1)=ωv ij (t)+c1r 1j (t)(fpbest ij (t)+c2r 2j (t)()fgbest j (t)-x ij (t))

[0091] x ij (t+1)=x ij (t)+v ij (t+1)

[0092] Obtain the next generation of particle swarms, so that the positions and velocities of all particles in the next generation of particle swarms are within the boundary conditions;

[0093] A5-4. The individual extreme value of each particle in the next generation particle swarm is updated using the particle comparison criterion.

[0094] The particle comparison criteria are as follows:

[0095] (1) When two particles are both feasible particles, their objective function values ​​are compared, and the particle with the smaller objective function value is the best;

[0096] (2) When two particles are both infeasible particles, if their constraint violation degrees are both less than the set threshold, the particle with the smaller objective function value is preferred; otherwise, the particle with the smaller constraint violation degree is preferred;

[0097] (3) When particle X is not feasible but particle Y is feasible, if some of the constraints of particle X are violated Then compare their objective function values, and the particle with a smaller fitness value is better; otherwise, particle Y is better.

[0098] The constraints are processed one by one, that is, the number of constraints processed is different in different algebras.

[0099] A6. Update the best position experienced by all particles in the particle swarm;

[0100] A7, determine whether the iteration stop condition is met; if so, jump to A8; otherwise, execute A5;

[0101] A8. Determine the pollutant attenuation load in sewage based on the estimated pollutant load.

[0102] In an optional embodiment of the present invention, the module of the present invention includes a river submodule, a lake submodule and a wetland submodule;

[0103] The river channel submodule is used to collect the receiving river channel topography, climate and hydrology, upstream flow, and water quality status background value data;

[0104] The lake submodule is used to collect background data on the topography, climate and hydrology, inflow and water quality, outflow, lake water level and water quality of the receiving lake;

[0105] The wetland submodule is used to collect background value data on the receiving wetland topography, climate and hydrology, inflow and water quality, outflow and water quality.

[0106] The module of the present invention realizes the process of simulating the reduction of pollutants through self-purification after sewage enters the receiving river, lake or wetland, including a river channel sub-module, a lake sub-module and a wetland sub-module. If the receiving water body is a pond or reservoir, it is included in the lake sub-module. The pollutant load estimated by the flow module is used as the initial value, and the topography, climate and hydrology, upstream flow, and current background value of water quality of the receiving river, lake and wetland are collected as boundary conditions. The module estimates the diffusion and attenuation of pollutants after entering the receiving water body, and predicts the trend of water quality changes in the receiving water body.

[0107] The present invention predicts the diffusion process of pollutants after entering the receiving water body and the water quality change trend of the receiving water body, including the following steps:

[0108] B1. Construct the objective function based on the square of the difference between the measured value and the predicted value of the receiving water quality;

[0109] B2. Select the water quality of the receiving water body as the iteration parameter, the receiving river, lake, wetland topography, climate and hydrology, upstream flow, and water quality status background value as the boundary conditions, set the population size and randomize the speed and position of the initial particles to generate the initial population;

[0110] B3. Set the individual extreme value of the particle to the current position, and the global extreme value of the particle to the position of the best particle in the initial population;

[0111] B4, determine whether the iteration stop condition is met; if so, jump to B8; otherwise, execute B5;

[0112] B5. Perform two perturbations and updates on all particles in the particle swarm, specifically including the following steps:

[0113] B5-1, generate a random number, and determine whether the random number is less than the set first disturbance probability; if so, execute B5-2; otherwise, set the global extreme value and individual extreme value to the new position after disturbance;

[0114] B5-2, the global extreme value and the individual extreme value are disturbed once with the set first disturbance probability, and then the points obtained after the first disturbance are disturbed for the second time with the set second disturbance probability;

[0115] B5-3. Update the positions and velocities of the particles in the particle swarm after the two disturbances to obtain the next generation of particle swarms, so that the positions and velocities of all particles in the next generation of particle swarms are within the boundary conditions;

[0116] B5-4. The individual extreme value of each particle in the next generation particle swarm is updated using the particle comparison criterion.

[0117] B6. Update the best position experienced by all particles in the particle swarm;

[0118] B7, determine whether the iteration stop condition is met; if so, jump to B8; otherwise, execute B5;

[0119] B8. Determine the diffusion process of pollutants after they enter the receiving waters and the changing trend of the receiving water quality based on the predicted receiving water quality.

[0120] The interfaces among the three modules in the present invention are smooth, which respectively estimate the pollutant load discharged by users, the reduction of pollutants by urban drainage systems and sewage treatment plant systems, simulate the attenuation process of pollutants after entering the receiving water body, and the water quality change trend of the receiving water body; each sub-module is called according to the simulation scenario, and those not involved can be ignored. For example, if the receiving water body is a river, the lake sub-module and the wetland sub-module can be silent.

[0121] Example 2

[0122] Based on the prediction system described in Example 1, the present invention proposes a method for predicting water quality change trends based on a source-flow model. Figure 2 As shown, the following steps are included:

[0123] Use the source module to collect demographic, socioeconomic, and lifestyle data associated with different types of sewage discharge, and estimate the pollutant loads in different types of sewage based on the collected data;

[0124] The flow module uses the pollutant load estimated by the source module as the initial value, the drainage network of sewage discharge as the upper boundary, and the sewage outlets of rivers, lakes, and wetlands as the lower boundary. The drainage network and sewage treatment plant data are collected as boundary conditions to estimate the pollutant attenuation load in the sewage; and the sewage treatment conditions of the sewage treatment plant are adjusted according to the prediction results fed back by the module.

[0125] The D module uses the pollutant attenuation load estimated by the flow module as the initial value, collects the receiving river, lake, wetland topography, climate and hydrology, upstream flow, and water quality background values ​​as boundary conditions, predicts the diffusion process of pollutants after entering the receiving water body and the water quality change trend of the receiving water body, and feeds the prediction results back to the flow module.

[0126] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0127] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0128] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0129] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0130] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A water quality change trend prediction system based on source-flow model, characterized in that: include: Source module, which is used to collect demographic, socioeconomic and lifestyle data related to different types of sewage discharge, and estimate the pollutant load in different types of sewage based on the collected data; The flow module is used to estimate the pollutant attenuation load in sewage using the pollutant load estimated by the source module as the initial value, the drainage network of sewage discharge as the upper boundary, the sewage outlet of rivers, lakes and wetlands as the lower boundary, and the drainage network and sewage treatment plant data as boundary conditions; And adjust the sewage treatment conditions of the sewage treatment plant according to the prediction results fed back by the module; The method of estimating the pollutant attenuation load in sewage comprises the following steps: A1. Construct the objective function based on the square of the difference between the measured value and the estimated value of the pollutant attenuation load; A2, select pollutant load as the iteration parameter, drainage network and sewage treatment plant data as boundary conditions, set the population size and randomize the speed and position of the initial particles to generate the initial population; A3. Set the individual extreme value of the particle to the current position, and the global extreme value of the particle to the position of the best particle in the initial population; A4, determine whether the iteration stop condition is met; if so, jump to A8; otherwise, execute A5; A5. Perform two perturbations and updates on all particles in the particle swarm; A6. Update the best position experienced by all particles in the particle swarm; A7, determine whether the iteration stop condition is met; if so, jump to A8; otherwise, execute A5; A8. Determine the pollutant attenuation load in the sewage based on the estimated pollutant load; The method of performing two perturbations and updates on all particles in the particle swarm comprises the following steps: A5-1, generate a random number, and determine whether the random number is less than the set first disturbance probability; if so, execute A5-2; otherwise, set the global extreme value and individual extreme value to the new position after disturbance; A5-2. Perform a perturbation on the global extreme value and the individual extreme value with a set first perturbation probability, and then perform a second perturbation on the points obtained after the first perturbation with a set second perturbation probability; A5-3. Update the positions and velocities of the particles in the particle swarm after the two disturbances to obtain the next generation of particle swarms, so that the positions and velocities of all particles in the next generation of particle swarms are within the boundary conditions; A5-4. Update the individual extreme value of each particle in the next generation particle swarm using the particle comparison criterion; The module is used to use the pollutant attenuation load estimated by the flow module as the initial value, collect the topography and geomorphology of the receiving river, lake, wetland, climate and hydrology, upstream flow, and the background value of the current water quality as boundary conditions, predict the diffusion process of pollutants after entering the receiving water body and the trend of water quality change of the receiving water body, and feed the prediction results back to the flow module; The prediction of the diffusion process of pollutants after entering the receiving water body and the water quality change trend of the receiving water body includes the following steps: B1. Construct the objective function based on the square of the difference between the measured value and the predicted value of the receiving water quality; B2. Select the water quality of the receiving water body as the iteration parameter, the receiving river, lake, wetland topography, climate and hydrology, upstream flow, and water quality status background value as the boundary conditions, set the population size and randomize the speed and position of the initial particles to generate the initial population; B3. Set the individual extreme value of the particle to the current position, and the global extreme value of the particle to the position of the best particle in the initial population; B4, determine whether the iteration stop condition is met; if so, jump to B8; otherwise, execute B5; B5. Perform two perturbations and updates on all particles in the particle swarm; B6. Update the best position experienced by all particles in the particle swarm; B7, determine whether the iteration stop condition is met; if so, jump to B8; otherwise, execute B5; B8. Determine the diffusion process of pollutants after they enter the receiving waters and the changing trend of the receiving water quality based on the predicted receiving water quality.

2. The water quality change trend prediction system based on the source-flow model according to claim 1 is characterized in that: The method of performing two perturbations and updates on all particles in the particle swarm comprises the following steps: B5-1, generate a random number, and determine whether the random number is less than the set first disturbance probability; if so, execute B5-2; otherwise, set the global extreme value and individual extreme value to the new position after disturbance; B5-2, the global extreme value and the individual extreme value are disturbed once with the set first disturbance probability, and then the points obtained after the first disturbance are disturbed for the second time with the set second disturbance probability; B5-3. Update the positions and velocities of the particles in the particle swarm after the two disturbances to obtain the next generation of particle swarms, so that the positions and velocities of all particles in the next generation of particle swarms are within the boundary conditions; B5-4. The individual extreme value of each particle in the next generation particle swarm is updated using the particle comparison criterion.

3. The water quality change trend prediction system based on the source-flow model according to claim 1 is characterized in that: The source module includes a domestic sewage submodule, an industrial wastewater submodule, and a surface runoff submodule; The domestic sewage submodule is used to collect population, water supply and drainage, and lifestyle data associated with domestic sewage discharge; The industrial wastewater submodule is used to collect data such as output value, wastewater per unit output value, and pollutant emissions associated with industrial wastewater discharge; The surface runoff submodule is used to collect data such as rainfall, underlying surface type, and impervious surface area associated with surface runoff discharge.

4. The water quality change trend prediction system based on the source-flow model according to claim 1 is characterized in that: The flow module includes a pipe network submodule and a sewage treatment plant submodule; The pipe network submodule is used to collect pipe network data; The sewage treatment plant submodule is used to collect sewage treatment plant data.

5. The water quality change trend prediction system based on the source-flow model according to claim 1 is characterized in that: The module includes a river submodule, a lake submodule and a wetland submodule; The river channel submodule is used to collect data on the topography, climate and hydrology, upstream inflow and water quality, downstream water level, and current background value of water quality of the receiving river channel; The lake submodule is used to collect background data on the topography, climate and hydrology, inflow and water quality, outflow, lake level and water quality of the receiving lake; The wetland submodule is used to collect background value data on the receiving wetland topography, climate and hydrology, inflow and water quality, outflow and water quality.

6. A method for predicting water quality change trends based on a source-flow model applied to the system of claim 1, characterized in that: The following steps are involved: Use the source module to collect demographic, socioeconomic, and lifestyle data associated with different types of sewage discharge, and estimate the pollutant loads in different types of sewage based on the collected data; Using the flow module, the pollutant load estimated by the source module is used as the initial value, the drainage network of sewage discharge is used as the upper boundary, the sewage outlet of the river, lake, and wetland is used as the lower boundary, and the drainage network and sewage treatment plant data are collected as boundary conditions to estimate the pollutant attenuation load in the sewage; And adjust the sewage treatment conditions of the sewage treatment plant according to the prediction results fed back by the module; The D module uses the pollutant attenuation load estimated by the flow module as the initial value, collects the receiving river, lake, wetland topography, climate and hydrology, upstream flow, and water quality background values ​​as boundary conditions, predicts the diffusion process of pollutants after entering the receiving water body and the water quality change trend of the receiving water body, and feeds the prediction results back to the flow module.

Images