A method for identifying new pollutant reduction pathways in sludge-based modular anti-clogging constructed wetlands

Abstract

The present invention relates to the field of environmental protection technology, and in particular to a method for identifying new pollutant reduction pathways in sludge-based modular anti-clogging artificial wetlands, which is applied to a control unit of a wetland system, wherein the wetland system further comprises: a plurality of artificial wetland modules connected in series. The present application provides a method for identifying new pollutant reduction pathways in a sludge-based modular anti-clogging artificial wetland, which collects data for a new type of modular anti-clogging artificial wetland with layered baffles, predicts the amount of pollutant reduction through the time series data processing capability of a prediction model, and then optimizes a pre-built prediction model based on the analysis and processing of the sampled data, and then continues to add new pollutants to obtain a concentration distribution model of the new pollutant. The identification of the new pollutant reduction pathway is then determined based on the microbial characteristics of each partition, which facilitates subsequent control and adjustment of the wetland system and improves the pollutant treatment capability.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for identifying new pollutant reduction pathways in sludge-based modular anti-clogging artificial wetlands. Background Art

[0002] Traditional constructed wetlands typically use dense stone fillers and planted plants to treat wastewater. However, when treating wastewater containing emerging pollutants (such as microplastics), these wetlands suffer from substrate clogging, low purification efficiency, and difficulty identifying and quantifying emerging pollutants. In contrast, the new modular, anti-clogging constructed wetland utilizes a baffled flow (alternating upper and lower baffles) and a top-bottom layered design. The upper layer consists of sludge-based lightweight suspended filler, the middle layer consists of lightweight ceramsite, the lower layer consists of traditional filler, and the bottom layer consists of sediment. While this design improves the wetland system's purification efficiency, it also complicates the identification and quantification of emerging pollutants. Therefore, a new identification method is needed to accurately reflect the distribution and reduction patterns of emerging pollutants within the new modular, anti-clogging constructed wetland system. Summary of the Invention

[0003] In view of this, the object of the present invention is to provide a method for identifying new pollutant reduction pathways in a sludge-based modular anti-clogging constructed wetland.

[0004] In a first aspect, an embodiment of the present invention provides a method for identifying new pollutant reduction pathways in a sludge-based modular anti-clogging constructed wetland, which is applied to a control unit of a wetland system. The wetland system further includes: a plurality of constructed wetland modules connected in series, the constructed wetland modules including: a plurality of partitions arranged in sequence along the height direction; the upper partition is filled with a sludge-based lightweight suspended filler, the middle partition is filled with lightweight ceramsite, the lower partition is filled with lightweight ceramsite, and the bottom partition is a sediment zone; the method includes:

[0005] According to the specified pollutant concentration and pollutant content, new pollutants are added to the upstream side of the wetland system. At the same time, the pollutant concentration and pollutant content of the new pollutants are input into the pre-built prediction model to output the predicted pollutant content of each zone;

[0006] Obtain sampling data from each zone during the operation of the wetland system and conduct quantitative analysis of the sampling data to determine the content of new pollutants in each zone;

[0007] For each partition, the difference between the new pollutant content and the predicted pollutant content is calculated to obtain the difference result of the partition;

[0008] Combine all the difference results and adjust the key parameters of the prediction model;

[0009] New pollutants are again added to the upstream side of the wetland system and new pollutant sampling is performed periodically to establish a new pollutant concentration distribution model;

[0010] Based on the concentration distribution model of new pollutants and combined with the number and type of microbial populations in the zones, the reduction pathways for new pollutants are determined.

[0011] In combination with the first aspect, and in combination with all the difference results, the steps for adjusting the key parameters of the prediction model include:

[0012] Based on the difference results, identify the factors affecting the association of new pollutants;

[0013] Adjusting key parameters of a pre-built prediction model based on influencing factors to obtain a first prediction model;

[0014] Use the first prediction model to perform simulation and obtain simulation results;

[0015] Comparing the simulation results with the actual sampling data and conducting sensitivity analysis on the adjusted parameters to determine the first number of target key parameters;

[0016] The first prediction model is adjusted based on the target key parameters until a target prediction model that meets the preset requirements is obtained.

[0017] In conjunction with the first aspect, based on the concentration distribution model of the new pollutant and in combination with the number and type of microbial populations in the zones, the steps for determining the reduction pathway for the new pollutant include:

[0018] Determine the spatial distribution of new pollutants based on their concentration distribution models;

[0019] Obtain the number and type of microbial populations in the partitions to obtain the characteristics of the microbial populations;

[0020] Combining all key target parameters, determine the reduction pathways for multiple new pollutants;

[0021] Determine the priority of each reduction pathway based on the spatial distribution of new pollutants, microbial population characteristics, and the reduction effects of all reduction pathways;

[0022] Combine all reduction pathways to determine the target reduction pathway.

[0023] In combination with the first aspect, before the step of adding new pollutants to the upstream side of the wetland system according to the specified pollutant concentration and pollutant content, and inputting the pollutant concentration and pollutant content of the new pollutants into a pre-established prediction model and outputting the predicted pollutant content of each partition, the method further includes:

[0024] Obtain the time series data and corresponding operating parameters within the preset historical period of each partition;

[0025] Preprocessing of time series data and operating parameters;

[0026] Use the preprocessed time series data and operating parameters to train the regression model and output the prediction results;

[0027] Based on the long short-term memory network (LSTM), the regression model is optimized, and the residuals between the prediction results and the actual pollutant time series data corresponding to the historical period are used to compensate for the errors of the regression model to obtain a trained prediction model.

[0028] In conjunction with the first aspect, the steps of preprocessing the time series data and operating parameters include:

[0029] Clean the time series data corresponding to each partition;

[0030] Perform data conversion on the cleaned time series data;

[0031] Normalize the time series data after data conversion.

[0032] In combination with the first aspect, after optimizing the regression model based on the long short-term memory network LSTM, the following steps are also included:

[0033] A long short-term memory network (LSTM) is added between the input layer and the transformer of the regression model to obtain an optimized regression model.

[0034] In combination with the first aspect, the step of using the residual between the prediction result and the actual pollutant time series data corresponding to the historical period to compensate the regression model for errors to obtain a trained prediction model also includes:

[0035] Obtain actual pollutant time series data corresponding to historical periods;

[0036] Calculate residuals based on actual pollutant time series data and prediction results;

[0037] The residual is used to compensate the error of the regression model, obtain the trained prediction model, and output the target prediction result.

[0038] In a second aspect, the present application provides a sludge-based modular anti-clogging artificial wetland new pollutant reduction pathway identification device, which is applied to a control unit of a wetland system, wherein the wetland system further comprises: a plurality of artificial wetland modules connected in series, the artificial wetland modules comprising: a plurality of partitions arranged in sequence along the height direction; the upper partition is filled with sludge-based lightweight suspended filler, the middle partition is filled with lightweight ceramsite, the lower partition is filled with lightweight ceramsite, and the bottom partition is a sediment zone; the device further comprises:

[0039] The content prediction module is used to add new pollutants to the upstream side of the wetland system according to the specified pollutant concentration and pollutant content. At the same time, the pollutant concentration and pollutant content of the new pollutants are input into the pre-built prediction model to output the predicted pollutant content of each partition.

[0040] The content determination module is used to obtain sampling data of each partition during the operation of the wetland system and perform quantitative analysis on the sampling data to determine the content of new pollutants in each partition.

[0041] The calculation module is used to calculate the difference between the new pollutant content and the predicted pollutant content in each partition, and obtain the difference result of the partition.

[0042] The parameter adjustment module is used to adjust the key parameters of the prediction model based on all the difference results.

[0043] A model building module is used to add new pollutants to the upstream side of the wetland system again and periodically sample the new pollutants to establish a concentration distribution model of the new pollutants;

[0044] The reduction pathway determination module is used to determine the reduction pathway for new pollutants based on the concentration distribution model of the new pollutants and in combination with the number and type of microbial populations in the partitions.

[0045] In a third aspect, the present application provides an electronic device, which includes a memory and a processor. 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.

[0046] 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-mentioned method is executed.

[0047] The embodiments of the present invention bring the following beneficial effects: the present application provides a method for identifying new pollutant reduction pathways in a sludge-based modular anti-clogging artificial wetland, which is applied to a control unit of a wetland system. The wetland system also includes: a plurality of artificial wetland modules connected in series, and the artificial wetland module includes: a plurality of partitions arranged in sequence along the height direction; the upper partition is filled with sludge-based lightweight suspended filler, the middle partition is filled with lightweight ceramsite, the lower partition is filled with lightweight ceramsite, and the bottom partition is a sediment area; the method includes: adding new pollutants to the upstream side of the wetland system according to the specified pollutant concentration and pollutant content, and at the same time, inputting the pollutant concentration and pollutant content of the new pollutants into a pre-constructed The prediction model outputs the predicted pollutant content of each partition; obtains sampling data of each partition during the operation of the wetland system, and conducts quantitative analysis on the sampling data to determine the new pollutant content of each partition; for each partition, calculates the difference between the new pollutant content and the predicted pollutant content of the partition to obtain the difference result of the partition; combines all the difference results to adjust the key parameters of the prediction model; adds new pollutants to the upstream side of the wetland system again, and periodically samples new pollutants to establish a concentration distribution model for new pollutants; based on the concentration distribution model of new pollutants and combined with the number and type of microbial populations in the partitions, determines the reduction path of new pollutants.

[0048] The present application provides a method for identifying new pollutant reduction pathways in sludge-based modular anti-clogging artificial wetlands. Data is collected for a new layered baffled modular anti-clogging artificial wetland, and the pollutant reduction amount is predicted through the time series data processing capability of the prediction model. The new pollutant is then added to optimize the pre-built prediction model based on the analysis and processing of the sampling data to obtain a concentration distribution model of the new pollutant. The reduction pathway of the new pollutant is then determined based on the microbial characteristics of each partition, which facilitates subsequent control and adjustment of the wetland system and improves the pollutant treatment capacity.

[0049] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the present invention. The purposes and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0050] 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

[0051] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 A schematic flow chart of a method for identifying new pollutant reduction pathways in a sludge-based modular anti-clogging constructed wetland provided in this application;

[0053] Figure 2 A schematic diagram of a sludge-based modular anti-clogging constructed wetland new pollutant reduction pathway identification device provided in this application;

[0054] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0055] Reference numerals:

[0056] 10-content prediction module, 20-content determination module, 30-calculation module, 40-parameter adjustment module, 50-model building module, 60-reduction path determination module;

[0057] 130 - processor, 131 - memory, 132 - bus, 133 - communication interface. DETAILED DESCRIPTION

[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0059] To facilitate understanding of this embodiment, the following is a brief introduction to the technical terms used in this application.

[0060] A baffled constructed wetland (also known as a multi-stage or cascade constructed wetland) is an ecologically engineered system designed for wastewater treatment. It purifies wastewater by directing water through multiple wetland units of varying types, each with a specific function and plant configuration to optimize pollutant removal.

[0061] Sludge-based lightweight suspended filler is a new environmentally friendly material made from treated sludge through a specific process. This filler features low density, large specific surface area, high mechanical strength, and good biocompatibility. It is widely used in biofilm bioreactors (MBBRs) for wastewater treatment and other water treatment technologies.

[0062] After introducing the technical terms involved in this application, the application scenarios and design concepts of the embodiments of this application are briefly introduced.

[0063] Existing artificial wetlands cannot quickly and effectively identify pollutant reduction patterns, which is not conducive to improving pollutant treatment efficiency.

[0064] Based on this, an embodiment of the present application provides a method for identifying new pollutant reduction pathways in a sludge-based modular anti-clogging constructed wetland.

[0065] Example 1

[0066] The present application provides a method for identifying new pollutant reduction pathways in a sludge-based modular anti-clogging artificial wetland, which is applied to a control unit of a wetland system. The wetland system also includes: a plurality of artificial wetland modules connected in series, and the artificial wetland modules include: a plurality of partitions arranged in sequence along the height direction; the upper partition is filled with sludge-based lightweight suspended filler, the middle partition is filled with lightweight ceramsite, the lower partition is filled with lightweight ceramsite, and the bottom partition is a sediment area.

[0067] Combine Figure 1 As shown, the method includes:

[0068] S110, according to the specified pollutant concentration and pollutant content, new pollutants are added to the upstream side of the wetland system. At the same time, the pollutant concentration and pollutant content of the new pollutants are input into a pre-built prediction model, and the predicted pollutant content of each partition is output.

[0069] S120, obtaining sampling data of each partition during the operation of the wetland system, and performing quantitative analysis on the sampling data to determine the content of new pollutants in each partition.

[0070] S130 , for each partition, calculating the difference between the new pollutant content of the partition and the predicted pollutant content to obtain a difference result for the partition.

[0071] S140, combining all the difference results, and adjusting the key parameters of the prediction model.

[0072] S150, new pollutants are again added to the upstream side of the wetland system, and new pollutant sampling is periodically performed to establish a concentration distribution model of the new pollutants.

[0073] S160, based on the concentration distribution model of new pollutants and combined with the number and type of microbial populations in the zones, determines the reduction path for new pollutants.

[0074] The present application provides a method for identifying new pollutant reduction pathways in a sludge-based modular anti-clogging artificial wetland. New pollutants of specified pollutant concentrations and pollutant contents are added to the upstream side of the wetland system, and the new pollutant contents in each partition are obtained through sampling. The new pollutant contents are compared with the predicted pollutant contents output by the prediction model to optimize the key parameters of the prediction model. Subsequently, the new pollutant distribution model of each partition, the number and type of microbial populations in each partition are combined to determine the new pollutant reduction pathways, so as to facilitate subsequent control and adjustment of the wetland system and improve the pollutant treatment capacity.

[0075] Among them, the baffled waterway structure and layered structure design can effectively prevent the matrix from being blocked, improve the reliability and stability of the wetland system operation, and help improve the purification efficiency of the wetland system. In this embodiment, the output end of the previous artificial wetland module is connected to the input end of the current artificial wetland module, and the input ends of the two adjacent artificial wetland modules are set in opposite directions, thereby forming a baffled waterway structure. For example, the input end of the first artificial wetland module is at the top and the output end is at the bottom; correspondingly, the input end of the adjacent second artificial wetland module is at the bottom and the output end is at the top; the third artificial wetland module is the same as the first artificial wetland module, with the input end at the top and the output end at the bottom... In this way, the sewage flow enters the first artificial wetland module from the top and flows downward along the input end at the bottom into the second artificial wetland module, and the water level rises until it is output to the third artificial wetland along the output end at the top... until it is output along the output end of the last artificial wetland module. In order to achieve a diverting water flow path, two adjacent artificial wetland modules are separated by a partition wall or barrier, forcing the water to flow back and forth between these units. Furthermore, guide plates can be installed on the partition wall or barrier to help the water turn and flow more smoothly.

[0076] In this embodiment, the wetland system is divided into multiple partitions along the front, back, left and right sides according to the diverted water flow pattern, and each wetland module includes an upper partition, a middle partition, a lower partition and a bottom partition formed by separation along the height direction.

[0077] It is understandable that the above data processing process involves a deep learning model. Before actual application, the prediction model (i.e., the hydrodynamic-water quality model of the anti-clogging artificial wetland system) should be constructed, trained, and optimized until a model that meets the use requirements is obtained and applied.

[0078] Among them, new pollutants such as microplastics, antibiotics, and PFAS (per- or polyfluoroalkyl substances) are calculated based on the specified pollutant concentration and pollutant content, and sufficient pure water is prepared in combination with the total volume of the wetland system. Then, the new pollutant solution is prepared, and one or more of the above-mentioned new pollutant solutions are mixed. A flow meter and pump are installed at the entrance of the wetland system to control the water flow rate and flow rate so that the new pollutant solution is evenly added to the wetland system.

[0079] In combination with the first aspect, before step S110, the method further includes:

[0080] S010, obtaining time series data and corresponding operating parameters within a preset historical period of each partition.

[0081] For each zone (a zone refers to one of the upper, middle, lower, and bottom zones), acquire time-series data for that zone's historical period, along with the operating parameters of the wetland system during that period. The wetland system can be installed on the surface or semi-buried, and sediment removal from the bottom sediment zone can be performed by either emptying or suction, with regular sediment removal.

[0082] S020, preprocessing the time series data and operating parameters.

[0083] In combination with the first aspect, step S020 specifically includes:

[0084] S021: Clean the time series data corresponding to each partition.

[0085] S022: Perform data conversion processing on the cleaned time series data.

[0086] S023, standardize the time series data after data conversion.

[0087] It can be understood that step S021 pre-processes the data collected in step S010 to eliminate abnormal data, check and supplement missing values, and mark abnormal values, thereby improving the quality of the data and enhancing the model performance.

[0088] Step S022 converts the format of the cleaned time series data to convert data from different sources into a unified format. Then, step S023 standardizes the converted time series data. This is an important step to ensure that different features have the same scale, which helps improve the performance and explanatory power of the model.

[0089] S030: Use the preprocessed time series data and operating parameters to train the regression model and output the prediction results.

[0090] It is understandable that the target variable to be predicted (e.g., water quality index, equipment performance, etc.) and the features to be used for prediction (e.g., temperature, pH value, timestamp, etc.) are first clearly defined. In this embodiment, the target variable to be predicted is the pollutant content.

[0091] Collect multiple preprocessed time series data and operating parameters as training samples and divide them into training and test sets. Use the training set data to train the selected regression model, perform predictions on the test set, and evaluate model performance. Common evaluation metrics include mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and coefficient of determination (R²).

[0092] S040, based on the long short-term memory network LSTM, optimizes the regression model and uses the residuals between the prediction results and the actual pollutant time series data corresponding to the historical period to compensate for the error of the regression model to obtain the trained prediction model.

[0093] In combination with the first aspect, step S040 is a step of optimizing the regression model based on a long short-term memory network (LSTM), including:

[0094] S041, add a long short-term memory network LSTM between the input layer and the transformer of the regression model to obtain an optimized regression model.

[0095] LSTM is a special type of recurrent neural network (RNN) that can learn long-term dependencies and is well-suited for processing time series data. By adding a long short-term memory (LSTM) network to this regression model, the LSTM processes time series data, while the transformer in the regression model captures more complex sequence patterns or dependencies between features, thereby constructing an optimized hybrid model. This model combines the LSTM's excellent processing capabilities for time series data with the transformer's powerful feature learning capabilities, making it suitable for a variety of complex prediction tasks.

[0096] In step S040, the residual between the prediction result and the actual pollutant time series data corresponding to the historical period is used to compensate the regression model for errors, thereby obtaining a trained prediction model. Specifically, the following steps are performed:

[0097] S042: Obtaining actual pollutant reduction time series data corresponding to the historical period.

[0098] S043, calculate the residual based on the actual pollutant time series data and the prediction results.

[0099] S044, using the residual to compensate for the error of the regression model, obtain the trained prediction model, and output the target prediction result.

[0100] To improve the accuracy of model predictions, the regression model uses the residuals between the predicted results and the actual pollutant time series data corresponding to the historical period to compensate for errors. In step S042, the actual pollutant reduction time series data for the historical period is obtained. Based on the existing regression model (i.e., a hybrid model with an LSTM layer added between the input layer and the transformer), predicted values ​​are generated using the data in the test set. The differences between these predicted values ​​and the actual observed values, or residuals, are calculated. Next, the residuals are analyzed to understand the pattern of the prediction errors. For example, methods such as plotting residuals and autocorrelations can be used to examine the presence of systematic biases or cyclical variations. A residual model is then constructed, and based on the characteristics of the residuals, a new model is constructed to predict these residuals. Commonly used models include linear regression, ARIMA (autoregressive integrated moving average), and even another LSTM model. Finally, error compensation is applied. The original prediction results are added to the residuals predicted by the residual model to obtain the final prediction value, thereby achieving error compensation and evaluating the model performance. If the prediction results need to be denormalized, repeat the above steps and use these residuals to adjust and compensate for the errors in the regression model to obtain a more accurate prediction model, which is used to output the pollutant content prediction results for each partition in the specified time period.

[0101] In combination with the first aspect, step S140 includes:

[0102] S141, based on the difference results, identify the factors affecting the association of new pollutants.

[0103] S142, adjusting key parameters of the pre-built prediction model in combination with the influencing factors to obtain an updated first prediction model.

[0104] S143, using the first prediction model to perform simulation and obtain simulation results.

[0105] S144 , comparing the simulation results with the actual sampling data, and performing a sensitivity analysis on the adjusted parameters to determine a first number of target key parameters.

[0106] S145 , adjusting the first prediction model based on the target key parameters until a target prediction model that meets preset requirements is obtained.

[0107] It is understandable that after sampling and quantitative analysis of each partition to determine the content of the new pollutant in that partition, and calculating the difference between the new pollutant content and the predicted pollutant content output by the prediction model, the difference results of each partition are combined to first identify the influencing factors associated with the new pollutant, and then adjust the pre-configured key parameters of the prediction model based on the specific influencing factors to initially update the first prediction model. The updated first prediction model is then simulated and output to output simulation results. The simulation results are compared with the actual sampling data, and parameter sensitivity analysis is performed to evaluate the first number of target key parameters that are strongly associated with the new pollutant. Based on these target key parameters, the first prediction model is further adjusted to optimize the prediction model again to obtain a target prediction model that can meet the purification needs of the new pollutant.

[0108] Among them, the influencing factors include at least one of: hydrodynamic parameters, physical factors, chemical factors and biological factors; the difference results include at least the concentration difference results of new pollutants, spatial distribution difference results and time series difference results.

[0109] It can be understood that in this embodiment, the hydrodynamic parameters may include flow velocity, flow direction, and turbulence intensity, among which the speed and direction of the water flow directly affect the transmission path and diffusion rate of pollutants, and the turbulent motion in the water body can increase the mixing efficiency between pollutants and other substances, thereby affecting their chemical reaction rate and biological degradation process.

[0110] Physical factors refer to physical phenomena that occur during the wastewater purification process, such as sedimentation, suspension, adsorption, or desorption. Sedimentation and suspension can, understandably, characterize the vertical migration of new pollutants within a water column; adsorption and desorption can also cause changes in the concentration of these new pollutants when environmental conditions change.

[0111] Chemical factors refer to changes in the form or chemical properties of new pollutants due to chemical reactions, or changes in the environmental pH that affect the existence and stability of new pollutants. For example, some heavy metal ions can be converted to less soluble forms through redox reactions.

[0112] Biological factors refer to the metabolic decomposition or accumulation and amplification of new pollutants by microorganisms. For example, specific types of microorganisms can metabolize and decompose certain types of pollutants, converting them into harmless compounds. This natural purification mechanism is of great significance for controlling environmental pollution.

[0113] After determining the factors influencing the new pollutant content in step S141, the model parameters are adjusted based on the determined factors in step S142, and a simulation run is performed in step S143 to output the simulation results. Furthermore, in step S144, the simulation results are compared with the currently sampled data, and key parameter evaluation is performed to verify whether each influencing parameter actually affects the new pollutant content, thereby determining a first number of target key parameters that can have a substantial impact on the new pollutant. Furthermore, in step S145, the model's target key parameters are adjusted to obtain a predictive model that meets the requirements for new pollutant removal.

[0114] In combination with the first aspect, step S160 includes:

[0115] S161, determine the spatial distribution of the new pollutant based on the concentration distribution model of the new pollutant.

[0116] S162, obtaining the number and type of microbial populations in the partition to obtain microbial population characteristics.

[0117] S163, combine all target key parameters to determine the reduction pathways for multiple new pollutants.

[0118] S164: Determine the target reduction pathway based on the spatial distribution of new pollutants, microbial population characteristics, and the reduction effects of all reduction pathways.

[0119] In this embodiment, based on the new pollutant concentration distribution model and microbial population characteristics, rationally select and optimize reduction pathways, thereby effectively reducing the risk of new pollutants in the environment. Specifically, the new pollutant concentration distribution model is used to understand the concentration differences of pollutants in different zones, identifying high and low pollution areas. Then, based on time series analysis, the changing trends of pollutant concentrations over time are analyzed to understand their dynamics (such as seasonal fluctuations and long-term changes), thereby identifying the factors that significantly affect the concentration of new pollutants. The principle behind this is the same as step S141.

[0120] Afterwards, the current microbial population characteristics are obtained in step S162, and the determined target key parameters that can produce substantial impact are combined with the microbial population characteristics in step S163 to formulate multiple reduction pathways. Afterwards, the multiple reduction pathways are integrated based on the reduction effects that can be produced by each reduction pathway to obtain a target reduction pathway that can meet the new pollutant reduction requirements. After the pollutant reduction pathway is determined in step S160, a working parameter adjustment direction is provided for the wetland system, for example, increasing the aeration volume. At this point, the working parameters can be adjusted based on the provided working parameter adjustment direction to determine the target working parameters, and then the operation of the wetland system is controlled to reduce pollutants and improve purification efficiency.

[0121] In the second aspect, the present application provides a sludge-based modular anti-clogging artificial wetland new pollutant reduction path identification device, which is applied to the control unit of the wetland system. The wetland system also includes: a plurality of artificial wetland modules connected in series, and the artificial wetland module includes: a plurality of partitions arranged in sequence along the height direction; the upper partition is filled with sludge-based lightweight suspended filler, the middle partition is filled with lightweight ceramsite, the lower partition is filled with lightweight ceramsite, and the bottom partition is a sediment area; such as Figure 2 As shown, the device further includes: a content prediction module 10 , a content determination module 20 , a calculation module 30 , a parameter adjustment module 40 , a model building module 50 and a reduction path determination module 60 .

[0122] The content prediction module 10 is used to add new pollutants to the upstream side of the wetland system according to the specified pollutant concentration and pollutant content. At the same time, the pollutant concentration and pollutant content of the new pollutants are input into a pre-built prediction model to output the predicted pollutant content of each partition.

[0123] The content determination module 20 is used to obtain sampling data of each partition during the operation of the wetland system and perform quantitative analysis on the sampling data to determine the content of new pollutants in each partition.

[0124] The calculation module 30 is used to calculate the difference between the new pollutant content and the predicted pollutant content in each partition, and obtain a difference result for the partition.

[0125] The parameter adjustment module 40 is used to adjust key parameters of the prediction model based on all the difference results.

[0126] The model building module 50 is used to add new pollutants to the upstream side of the wetland system again, and periodically sample the new pollutants to establish a concentration distribution model of the new pollutants.

[0127] The reduction pathway determination module 60 is used to determine a reduction pathway for new pollutants based on a concentration distribution model of the new pollutants and in combination with the number and type of microbial populations in the partitions.

[0128] 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.

[0129] Further, 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 .

[0130] The memory 131 may include high-speed random access memory (RAM) and may also include 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 achieved 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. 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 one type of bus.

[0131] The processor 130 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor 130 or by software instructions. The processor 130 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may 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 gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in memory 131, and processor 130 reads information in memory 131 and, in conjunction with its hardware, completes the steps of the method of the aforementioned embodiment.

[0132] 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-mentioned method is executed.

[0133] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems and devices can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0134] In addition, in the description of the embodiments of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to mechanical connections or electrical connections; they may refer to direct connections or indirect connections through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0135] If the functions are implemented as 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 portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0136] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0137] Finally, it should be noted that the above embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for identifying new pollutant reduction pathways in a sludge-based modular anti-clogging constructed wetland, characterized in that: A control unit applied to a wetland system, the wetland system further comprising: a plurality of artificial wetland modules connected in series, the artificial wetland modules comprising: a plurality of partitions arranged in sequence along a height direction; an upper partition filled with sludge-based lightweight suspended filler, a middle partition filled with lightweight ceramsite, a lower partition filled with lightweight ceramsite, and a bottom partition being a sediment zone; the method comprising: According to the specified pollutant concentration and pollutant content, new pollutants are added to the upstream side of the wetland system, and at the same time, the pollutant concentration and pollutant content of the new pollutants are input into a pre-built prediction model to output the predicted pollutant content of each zone; Acquiring sampling data of each of the partitions during the operation of the wetland system, and performing quantitative analysis on the sampling data to determine the content of new pollutants in each of the partitions; For each of the partitions, calculating the difference between the new pollutant content and the predicted pollutant content in the partition to obtain a difference result for the partition; Combining all of the difference results, adjusting key parameters of the prediction model; adding the new pollutant to the upstream side of the wetland system again, and periodically sampling the new pollutant to establish a concentration distribution model of the new pollutant; Based on the concentration distribution model of the new pollutant and in combination with the number and type of microbial populations in the partitions, a reduction approach for the new pollutant is determined.

2. The method according to claim 1, characterized in that The step of adjusting key parameters of the prediction model based on all the difference results includes: Based on the difference results, identifying factors influencing the association of the new pollutant; Adjusting key parameters of the pre-built prediction model in combination with the influencing factors to obtain an updated first prediction model; Run a simulation using the first prediction model to obtain a simulation result; Comparing the simulation results with actual sampling data, and performing sensitivity analysis on the adjusted parameters to determine a first number of target key parameters; The first prediction model is adjusted based on the target key parameters until a target prediction model that meets preset requirements is obtained.

3. The method according to claim 2, characterized in that The step of determining a reduction approach for the new pollutant based on the concentration distribution model of the new pollutant and in combination with the microbial population quantity and microbial population type of the partition comprises: Determining the spatial distribution of the new pollutant based on the concentration distribution model of the new pollutant; Obtaining the number and type of microbial populations in the partitions to obtain microbial population characteristics; Combining all the target key parameters, determining reduction pathways for multiple new pollutants; The target reduction pathway is determined based on the spatial distribution of the new pollutants, the characteristics of the microbial population, and the reduction effects corresponding to all of the reduction pathways.

4. The method according to claim 1, wherein Before the step of adding new pollutants to the upstream side of the wetland system according to the specified pollutant concentration and pollutant content, and inputting the pollutant concentration and pollutant content of the new pollutants into a pre-built prediction model to output the predicted pollutant content of each zone, the method further includes: Obtain the time series data and corresponding operating parameters within the preset historical period of each partition; Preprocessing the time series data and the operating parameters; Using the preprocessed time series data and the operating parameters to train a regression model, and output a prediction result; Based on the long short-term memory network (LSTM), the regression model is optimized, and the residual between the prediction result and the actual pollutant time series data corresponding to the historical period is used to compensate for the error of the regression model, thereby obtaining a trained prediction model.

5. The method according to claim 4, characterized in that The step of preprocessing the time series data and the operating parameters includes: Cleaning the time series data corresponding to each partition; Perform data conversion on the cleaned time series data; The time series data after data conversion is standardized.

6. The method according to claim 4, characterized in that The steps of optimizing the regression model based on the long short-term memory network (LSTM) include: A long short-term memory network (LSTM) is added between the input layer and the transformer of the regression model to obtain the optimized regression model.

7. The method according to claim 4, characterized in that The step of performing error compensation on the regression model using the residual between the prediction result and the actual pollutant time series data corresponding to the historical period to obtain a trained prediction model further includes: Obtaining actual pollutant time series data corresponding to the historical period; Calculating residuals based on the actual pollutant time series data and the prediction results; The residual is used to perform error compensation on the regression model to obtain a trained prediction model and output the target prediction result.

8. A sludge-based modular anti-clogging constructed wetland new pollutant reduction pathway identification device, characterized in that: A control unit for a wetland system, the wetland system further comprising: a plurality of artificial wetland modules connected in series, the artificial wetland modules comprising: a plurality of partitions arranged in sequence along the height direction; the upper partition being filled with sludge-based lightweight suspended filler, the middle partition being filled with lightweight ceramsite, the lower partition being filled with lightweight ceramsite, and the bottom partition being a sediment zone; the device further comprising: a content prediction module, configured to add new pollutants to the upstream side of the wetland system according to the specified pollutant concentration and pollutant content, and input the pollutant concentration and pollutant content of the new pollutants into a pre-built prediction model to output the predicted pollutant content of each partition; a content determination module, configured to obtain sampling data of each of the partitions during the operation of the wetland system, and perform quantitative analysis on the sampling data to determine the content of new pollutants in each of the partitions; a calculation module, configured to calculate, for each partition, a difference between the new pollutant content and the predicted pollutant content in the partition, and obtain a difference result for the partition; A parameter adjustment module, configured to adjust key parameters of the prediction model based on all the difference results; A model building module, configured to add the new pollutant to the upstream side of the wetland system again, and periodically sample the new pollutant to establish a concentration distribution model of the new pollutant; The reduction pathway determination module is configured to determine a reduction pathway for the new pollutant based on a concentration distribution model of the new pollutant and in combination with the number and type of microbial populations in the partitions.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, 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