Modular constructed wetland optimization method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of purification, in particular to a modular constructed wetland optimization method and device, electronic equipment and a storage medium, and is applied to a water purification system.The method comprises the steps that the inflow water amount, the inflow water quality and the outflow water quality are obtained; and calculating the water quality removal rate according to the inlet water quality and the outlet water quality. According to the method, the water quality removal rate of the water purification system is monitored, multi-level data processing is carried out through the pre-trained adjustment model, the preset comprehensive index prediction result of each index is calculated firstly, and under the condition that the comprehensive index prediction result does not meet the process requirement, the water quality removal rate of the water purification system is monitored. According to the method, the target adjustment index is determined based on the multi-target optimization model, the preliminary adjustment strategy is determined, then the preliminary adjustment strategy is further refined based on the strategy evaluation model, and therefore the target adjustment strategy is determined, intelligent and accurate adjustment of the water purification system is achieved, and the target adjustment strategy meeting the preset purification requirement is obtained.

Description

Technical Field

[0001] The present invention relates to the field of purification technology, and in particular to a modular artificial wetland optimization method, device, electronic equipment and storage medium. Background Art

[0002] Artificial wetlands play an important role in sewage treatment and ecological restoration. However, traditional artificial wetlands have clogging problems, which affect long-term operating efficiency. The present invention optimizes water distribution and reflux through modular design and artificial intelligence technology, improves the anti-clogging ability of the system, and achieves the optimization of water quality, economy and greenhouse gas emissions. Summary of the invention

[0003] In view of this, the object of the present invention is to provide a modular artificial wetland optimization method, device, electronic equipment, and storage medium.

[0004] In a first aspect, an embodiment of the present invention provides a modular artificial wetland optimization method, which is applied to a water purification system. The method includes: Obtain inlet water volume, inlet water quality and outlet water quality; Calculate the water removal rate based on the inlet and outlet water quality; Input the influent water volume and water quality removal rate into the pre-trained adjustment model and output the target adjustment strategy; Optimize water purification systems based on goal-adjusted strategies; Among them, the adjustment model includes a prediction model, a multi-objective optimization model and a strategy evaluation model which are connected in sequence.

[0005] In combination with the first aspect, the steps of inputting the influent water volume and water quality removal rate into the pre-trained adjustment model and outputting the target adjustment strategy include: Input the influent water volume and water quality removal rate into the prediction model, and output the comprehensive index prediction results of multiple indicators; Determine whether the comprehensive index prediction results meet the preset requirements; If not, the comprehensive index prediction results are input into the multi-objective optimization model, and the target adjustment index and initial adjustment strategy are output; The strategy evaluation model is called, and the target adjustment strategy is determined according to the strategy evaluation model, the initial adjustment strategy, each reflux pipeline and each reflux pump. The target adjustment strategy includes the opening and closing angles of the reflux pipeline and the target reflux pump.

[0006] In combination with the first aspect, the steps of inputting the influent water volume and water quality removal rate into the prediction model and outputting the comprehensive index prediction results include: Input the influent water volume and water quality removal rate into the prediction model to obtain multiple prediction results corresponding to multiple indicators; Combine multiple prediction results and the weight coefficient corresponding to each indicator to calculate the comprehensive indicator prediction result.

[0007] In combination with the first aspect, the steps of inputting the comprehensive index prediction results into the multi-objective optimization model and outputting the target adjustment index and the initial adjustment strategy include: The multi-objective optimization model is trained through comprehensive index prediction results, and the target adjustment index is determined based on the multi-objective optimization algorithm; Based on the target adjustment indicator, an initial adjustment strategy corresponding to the target adjustment indicator is determined.

[0008] In combination with the first aspect, calling the strategy evaluation model, and determining the target adjustment strategy according to the strategy evaluation model, the initial adjustment strategy, each reflux pipeline and each reflux pump, includes: The strategy evaluation model is used to evaluate the comprehensive indicators corresponding to the opening and closing angles of each reflux pipeline and each reflux pump in the initial adjustment strategy to determine the target adjustment strategy.

[0009] In combination with the first aspect, the step of calculating the water removal rate according to the influent water quality and the effluent water quality includes: Calculate the difference between the outlet water quality and the inlet water quality to obtain the water removal rate.

[0010] In combination with the first aspect, after the step of judging whether the comprehensive index prediction result meets the preset requirements, it also includes: If yes, the water purification system is controlled to continue to operate with the current control strategy.

[0011] In a second aspect, the present application provides a modular artificial wetland optimization device, which is applied to a water purification system, and the device comprises: An acquisition module is used to obtain the inlet water volume, inlet water quality and outlet water quality; A calculation module, used to calculate the water removal rate according to the inlet water quality and the outlet water quality; An output module is used to input the influent water volume and water quality removal rate into a pre-trained adjustment model and output a target adjustment strategy; An optimization module, which is used to optimize the water purification system according to the target adjustment strategy; Among them, the adjustment model includes a prediction model, a multi-objective optimization model and a strategy evaluation model which are connected in sequence.

[0012] In a third aspect, the present application provides an electronic device, which includes a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the above method.

[0013] In a fourth aspect, the present application provides a readable storage medium, in which computer program instructions are stored. When the computer program instructions are read and executed by a processor, the above method is executed.

[0014] The embodiments of the present invention bring the following beneficial effects: A modular artificial wetland optimization method provided by the present application is applied to a water purification system, the method comprising: obtaining inlet water volume, inlet water quality and outlet water quality; calculating a water quality removal rate according to the inlet water quality and the outlet water quality; inputting the inlet water volume and the water quality removal rate into a pre-trained adjustment model, and outputting a target adjustment strategy; optimizing the water purification system according to the target adjustment strategy; wherein the adjustment model comprises a prediction model, a multi-objective optimization model and a strategy evaluation model connected in sequence.

[0015] The present application monitors the water quality removal rate of the water purification system, performs multi-level data processing through a pre-trained adjustment model, first calculates the comprehensive indicator prediction results of the preset indicators, and when the comprehensive indicator prediction results do not meet the process requirements, first determines the target adjustment indicator based on the multi-objective optimization model to determine the preliminary adjustment strategy, and then further refines the preliminary adjustment strategy based on the strategy evaluation model, so as to determine the target adjustment strategy, and then realize intelligent and accurate adjustment of the water purification system to obtain the target adjustment strategy that meets the preset purification requirements.

[0016] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A flow chart of a modular artificial wetland optimization method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a modular artificial wetland optimization device provided by an embodiment of the present invention; Figure 3A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0020] Reference numerals: 10-acquisition module, 20-calculation module, 30-output module, 40-optimization module; 130 - processor, 131 - memory, 132 - bus, 133 - communication interface. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0022] In order to facilitate the understanding of this embodiment, the application scenarios and design concepts of the embodiments of the present application are briefly introduced below.

[0023] Artificial wetlands play an important role in sewage treatment and ecological restoration. However, traditional artificial wetlands have clogging problems, which affect long-term operation efficiency, are difficult to regulate manually, and have a low level of intelligence.

[0024] Based on this, the embodiment of the present application provides a modular artificial wetland optimization method, device, electronic device, and storage medium. The method is applied to a water purification system, which includes a plurality of purification modules connected in series and in parallel. Along the direction of water flow, a return pipeline is connected between the plurality of purification modules connected in series. A return pump is provided on the return pipeline to guide the water flow in the rear purification module to the front purification module. A water quality sensor is provided at the outlet and inlet of each purification module to detect the water quality. It is understandable that the number and assembly method of the purification modules can be increased or decreased according to factors such as the terrain of the application scenario and the floor area.

[0025] Example 1 This application provides a modular artificial wetland optimization method for use in water purification systems, combined with Figure 1 As shown, the method includes: S110, obtaining the inlet water volume, inlet water quality and outlet water quality.

[0026] S120, calculating the water removal rate according to the inlet water quality and the outlet water quality.

[0027] S130, inputting the influent water volume and water quality removal rate into a pre-trained adjustment model, and outputting a target adjustment strategy.

[0028] S140, optimizing the water purification system according to the target adjustment strategy.

[0029] Among them, the adjustment model includes a prediction model, a multi-objective optimization model and a strategy evaluation model which are connected in sequence.

[0030] In this embodiment, by calculating the water quality removal rate of the water purification system, under the action of the prediction model, multi-objective optimization model and strategy evaluation model in the adjustment model, an adjustment strategy that meets the current water purification demand is output, and then the operation of the water purification system is controlled according to the adjustment strategy to meet the expected water purification demand, realize automation and precise regulation, and improve purification efficiency.

[0031] In combination with the first aspect, step S120 includes: S121, calculating the difference between the outgoing water quality and the inlet water quality to obtain the water quality removal rate.

[0032] It can be understood that water quality sensors are respectively provided at the water inlet and outlet of the water purification system to monitor the water quality of the water flowing through; the water purification system includes at least one water purification module, and the water quality removal rate of the water purification system can be obtained by measuring the difference between the water quality of the outlet water of the water purification system and the water quality of the inlet water. Similarly, the water quality removal rate of the water purification module can be obtained by measuring the difference between the water quality of the outlet water of each water purification module and the water quality of the inlet water of the water purification module.

[0033] It can be understood that the water removal rate can characterize the water purification capacity of the water purification system or the water purification module. It can be understood that the higher the water removal rate, the stronger the water purification capacity and the higher the water purification efficiency.

[0034] In this embodiment, a plurality of water purification modules are connected in series and in parallel in the water purification system. Usually, the number of water purification modules connected in series is generally less than or equal to 3, and the number of water purification modules connected in parallel is not limited.

[0035] In combination with the first aspect, step S130 includes: S131, inputting the influent water volume and water quality removal rate into the prediction model, and outputting the comprehensive index prediction results of multiple indicators.

[0036] S132, judging whether the comprehensive index prediction result meets the preset requirements.

[0037] If yes, execute step S133; if no, execute steps S134-S135.

[0038] S133, controlling the water purification system to continue to operate with the current control strategy.

[0039] If the comprehensive indicator prediction results under the current control strategy operation meet the preset requirements, then it can be determined that the current control strategy is feasible and meets the work needs. At this time, no adjustment is required and it can continue to run.

[0040] S134, input the comprehensive index prediction results into the multi-objective optimization model, and output the target adjustment index and the initial adjustment strategy.

[0041] S135, calling the strategy evaluation model, and determining the target adjustment strategy according to the strategy evaluation model, the initial adjustment strategy, each reflux pipeline and each reflux pump; the target adjustment strategy includes the opening and closing angles of the reflux pipeline and the target reflux pump.

[0042] If the comprehensive index prediction results under the current control strategy operation do not meet the preset requirements, then it can be considered that the current control strategy needs to be adjusted to meet the work requirements. At this time, the final adjustment index and the target control strategy based on the adjustment index are further determined through the multi-objective optimization model and strategy evaluation model.

[0043] In combination with the first aspect, step S131 specifically includes: S1311, inputting the influent water volume and water quality removal rate into the prediction model to obtain multiple prediction results corresponding to multiple indicators.

[0044] S1312, combining multiple prediction results and the weight coefficient corresponding to each indicator to calculate the comprehensive indicator prediction result.

[0045] In this implementation, the indicators include at least: water quality indicators, economic indicators and gas emission flux indicators.

[0046] In this embodiment, water quality indicators include COD removal rate, ammonia nitrogen removal rate and total nitrogen removal rate; economic indicators include: reflux ratio, aeration, etc.; gas emission flux indicators include: methane, nitrous oxide, carbon dioxide emissions. It can be understood that the smaller the above gas emission flux indicators, the better, the less harm to the environment.

[0047] It is understandable that as the water removal rate increases, the aeration volume and reflow ratio of the economic indicators increase, and the amount of greenhouse gases generated is relatively large. Therefore, the operation strategy of the water purification system is not optimal when the water removal rate is the highest. Therefore, it is necessary to comprehensively determine the purification effect based on multiple indicators. Then, based on the weight coefficients corresponding to each indicator, the purification effect of the water purification system is comprehensively determined.

[0048] Among them, the prediction model is a model for prediction obtained by statistical analysis and machine learning algorithm training based on a large amount of historical data. Common prediction models can be linear regression models, logistic regression models, integrated models including decision trees and random forests, support vector machines, and neural networks that integrate deep learning technology. In this embodiment, the sample data used for model training includes water inflow and water quality removal rate, and the comprehensive index prediction results are output. In this embodiment, there is a mutual influence relationship between the water inflow and the water quality removal rate. The linear regression model can be used to continuously predict the prediction results corresponding to multiple indicators by fitting the data and predicting according to the linear equation. Subsequently, the weight coefficient is determined based on the influence ratio to calculate the comprehensive index prediction result. Among them, the comprehensive index prediction result P= ,in, is the prediction result of the nth indicator, is the weight coefficient of the nth indicator.

[0049] In combination with the first aspect, step S134 specifically includes: S1341, training the multi-objective optimization model through the comprehensive index prediction results, and determining the target adjustment index based on the multi-objective optimization algorithm.

[0050] The multi-objective optimization model is a mathematical model constructed based on multi-objective optimization technology to determine the target adjustment index from multiple adjustment indexes. It can be understood that the adjustment index can refer to any one of the above-mentioned indexes, such as adjusting the inlet water volume to adjust the output water quality removal rate, gas emission flux, etc., or adjusting the reflow ratio to adjust the water quality removal rate, gas emission flux, etc. of the entire artificial wetland.

[0051] S1342: Based on the target adjustment indicator, determine an initial adjustment strategy corresponding to the target adjustment indicator.

[0052] In this embodiment, the most preferred target adjustment index is determined through the data processing capability of the multi-objective optimization model. Since the adjustment of any one index will cause changes in other indexes, in order to improve the comprehensive purification efficiency and control accuracy, any one index is adjusted and predicted in this application, and then based on the multi-objective optimization algorithm, the optimal solution is found that can meet the work requirements and have a fast response and ideal purification effect.

[0053] In this embodiment, the training process of the multi-objective optimization model is as follows: First, a training sample set is obtained. The training sample set includes multiple training samples, and each training sample consists of multiple adjustment indicators.

[0054] Specifically, the training sample includes at least water quality indicators, economic indicators and gas emission flux. For example, training sample a: COD removal rate = 80%; ammonia nitrogen removal rate parameter = 95%, total nitrogen removal rate = 92%; reflow ratio = b; aeration = c; CH4 = d, NO = e, CO2 = f.

[0055] Then, for each adjustment indicator, other indicators when the adjustment indicator is adjusted to a preset value are obtained to obtain a target sample set.

[0056] Specifically, for any of the above-mentioned adjustment indicators (such as increasing the COD removal rate to 90%), the water quality indicator is adjusted. The adjustment method includes changing the influent water volume, adjusting the influent water quality, and opening one or more of a certain return pipeline, so as to obtain other water quality indicators, economic indicators and gas emission flux indicators after the COD removal rate is increased to 90%; and then obtain a target sample.

[0057] Then, multiple target samples are combined for linear regression processing to draw a fitting curve.

[0058] Combining multiple target samples, we find the adjustment rules and then draw the fitting curve.

[0059] Finally, based on the multi-objective optimization algorithm, the target adjustment index and target adjustment are determined.

[0060] Combined with the above examples, it can be seen that if the target adjustment index is the gas emission flux index, then the purpose of adjusting the gas emission flux can be achieved by adjusting the water intake, reflux ratio and aeration volume, and similarly, if the target adjustment index is an economic index, then the optimization purpose can also be achieved by adjusting the water intake, reflux ratio and aeration volume, etc. In this embodiment, the optimal solution that meets the expected adjustment efficiency is selected as the initial adjustment strategy through a multi-objective optimization algorithm.

[0061] For example, in this embodiment, the target adjustment index determined by the multi-objective optimization algorithm is an economic index, and the corresponding initial adjustment strategy is to change the recirculation ratio and the aeration volume.

[0062] In combination with the first aspect, step S135 specifically includes: 1351, the strategy evaluation model is used to evaluate the comprehensive indicators corresponding to the opening and closing angles of each reflux pipeline and each reflux pump in the initial adjustment strategy to determine the target adjustment strategy.

[0063] It can be understood that, after the target adjustment index has been determined and the initial adjustment strategy has been obtained, the adjustment strategy is further accurately calculated based on the pre-trained strategy evaluation model to determine which specific reflux pipeline should be opened and the opening and closing of the reflux pump corresponding to the reflux pipeline, that is, to which specific purification module the water should flow back.

[0064] In summary, the present application monitors the water quality removal rate of the water purification system, performs multi-level data processing through a pre-trained adjustment model, first calculates the comprehensive indicator prediction results of the preset indicators, and when the comprehensive indicator prediction results do not meet the process requirements, first determines the target adjustment index based on the multi-objective optimization model to determine the preliminary adjustment strategy, and then further refines the preliminary adjustment strategy based on the strategy evaluation model, so as to determine the target adjustment strategy, and then realize intelligent and accurate adjustment of the water purification system to obtain the target adjustment strategy that meets the preset purification requirements.

[0065] Furthermore, the water purification system also includes a voice interaction model; the method also includes: Receive voice or text command information from users; Recognize voice or text command information and generate control instructions; Based on the control instruction, the target adjustment strategy is corrected to obtain a corrected target adjustment strategy.

[0066] In the present application, the pre-trained voice interaction model recognizes the voice and text information input by the user to correct and readjust the target adjustment strategy to facilitate the optimization of human-computer interaction and water purification system.

[0067] In the second aspect, the present application provides a modular artificial wetland optimization device, combined with Figure 2 As shown, it is applied to a water purification system; the device includes an acquisition module 10, a calculation module 20, an output module 30 and an optimization module 40.

[0068] The acquisition module 10 is used to obtain the inlet water volume, inlet water quality and outlet water quality.

[0069] The calculation module 20 is used to calculate the water removal rate according to the inlet water quality and the outlet water quality.

[0070] The output module 30 is used to input the influent water volume and water quality removal rate into a pre-trained adjustment model and output a target adjustment strategy.

[0071] The optimization module 40 is used to optimize the water purification system according to the target adjustment strategy.

[0072] Among them, the adjustment model includes a prediction model, a multi-objective optimization model and a strategy evaluation model which are connected in sequence.

[0073] In a third aspect, the present application provides an electronic device, Figure 3 As shown, the electronic device includes a memory 131 and a processor 130. The memory 131 is used to store computer programs, and the processor 130 runs the computer programs to enable the electronic device to perform the above method.

[0074] Furthermore, combined with Figure 3 The electronic device shown further includes a bus 132 and a communication interface 133 , and the processor 130 , the communication interface 133 and the memory 131 are connected via the bus 132 .

[0075] The memory 131 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 133 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 132 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0076] The processor 130 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 130. The above processor 130 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 131, and the processor 130 reads the information in the memory 131 and completes the steps of the method of the above embodiment in combination with its hardware.

[0077] In a fourth aspect, an embodiment of the present application provides a readable storage medium, in which computer program instructions are stored. When the computer program instructions are read and executed by a processor, the above method is executed.

[0078] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0079] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0080] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0081] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0082] Finally, it should be noted that the above embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A modular artificial wetland optimization method, characterized in that: Applied to a water purification system, the method comprises: Obtain inlet water volume, inlet water quality and outlet water quality; Calculating a water removal rate according to the influent water quality and the effluent water quality; Input the influent water volume and the water quality removal rate into a pre-trained adjustment model, and output a target adjustment strategy; Optimizing the water purification system according to the target adjustment strategy; The adjustment model includes a prediction model, a multi-objective optimization model and a strategy evaluation model which are connected in sequence.

2. The method according to claim 1, characterized in that The steps of inputting the influent water volume and the water quality removal rate into a pre-trained adjustment model and outputting a target adjustment strategy include: Input the influent water volume and the water quality removal rate into the prediction model, and output the comprehensive index prediction result of multiple indicators; Determine whether the prediction result of the comprehensive index meets the preset requirements; If not, the comprehensive index prediction result is input into the multi-objective optimization model, and the target adjustment index and the initial adjustment strategy are output; The strategy evaluation model is called, and a target adjustment strategy is determined according to the strategy evaluation model, the initial adjustment strategy, each reflux pipeline and each reflux pump. The target adjustment strategy includes the opening and closing angles of the reflux pipeline and the target reflux pump.

3. The method according to claim 1, characterized in that: The step of inputting the influent water volume and the water quality removal rate into the prediction model and outputting the comprehensive index prediction result comprises: Inputting the influent water volume and the water quality removal rate into the prediction model to obtain multiple prediction results corresponding to multiple indicators; Combine the multiple prediction results and the weight coefficient corresponding to each indicator to calculate and output the comprehensive indicator prediction result.

4. The method according to claim 3, characterized in that The step of inputting the comprehensive index prediction result into the multi-objective optimization model and outputting the target adjustment index and the initial adjustment strategy comprises: The multi-objective optimization model is trained by using the comprehensive index prediction result, and the target adjustment index is determined based on the multi-objective optimization algorithm; Based on the target adjustment indicator, an initial adjustment strategy corresponding to the target adjustment indicator is determined.

5. The method according to claim 4, characterized in that The step of calling the strategy evaluation model and determining the target adjustment strategy according to the strategy evaluation model, the initial adjustment strategy, each reflux pipeline and each reflux pump comprises: The strategy evaluation model is used to evaluate the comprehensive indicators corresponding to the opening and closing angles of each reflux pipeline and each reflux pump in the initial adjustment strategy to determine the target adjustment strategy.

6. The method according to claim 1, characterized in that The step of calculating the water removal rate according to the influent water quality and the effluent water quality comprises: The difference between the outlet water quality and the inlet water quality is calculated to obtain the water quality removal rate.

7. The method according to claim 3, characterized in that After the step of determining whether the comprehensive index prediction result meets the preset requirements, the method further includes: If so, the water purification system is controlled to continue operating with the current control strategy.

8. A modular artificial wetland optimization device, characterized in that: Applied to a water purification system, the device comprises: An acquisition module is used to obtain the inlet water volume, inlet water quality and outlet water quality; A calculation module, used for calculating a water removal rate according to the influent water quality and the effluent water quality; An output module, used for inputting the influent water volume and the water quality removal rate into a pre-trained adjustment model, and outputting a target adjustment strategy; An optimization module, for optimizing the water purification system according to the target adjustment strategy; The adjustment model includes a prediction model, a multi-objective optimization model and a strategy evaluation model which are connected in sequence.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the method according to any one of claims 1 to 7 is executed.

Images