Modular unit sewage treatment method and system

Abstract

The invention relates to the technical field of water treatment engineering, in particular to a modular unit sewage treatment method and system.The constructed wetland is divided into three layers of treatment units including a flow guide layer, a reaction layer and a water collection layer in the water flow direction, and key data are monitored in real time; comprise water quality parameters, water flow velocity, hydraulic retention time, water flow pressure and microbial activity; constructing a blockage prediction model and a pollution prediction model by using the data, and respectively predicting a blockage degree value and a pollution score value of the water flow; determining risk levels of blockage and pollution by comparing the predicted value with a preset threshold value; according to the risk level, operation parameters of the sewage treatment system are dynamically adjusted, intelligent regulation and control are achieved, the treatment effect is optimized, and stable and efficient operation of the system is ensured. The method can predict and prevent the risks of blockage and pollution in advance, reduce the maintenance cost, prolong the service life of the system, and ensure that the effluent quality is stable and reaches the standard.

Description

Technical Field

[0001] This invention relates to the field of water treatment engineering technology, and in particular to a modular unit wastewater treatment method and system. Background Technology

[0002] With the increasing severity of global water scarcity and water pollution, wastewater treatment technology has become a key area for environmental protection and sustainable resource utilization. Constructed wetlands, as an eco-friendly and cost-effective wastewater treatment technology, are widely used in scenarios such as advanced treatment of municipal wastewater effluent and ecological restoration of polluted rivers. Constructed wetlands remove pollutants from wastewater by simulating the ecological processes of natural wetlands and utilizing the synergistic effects of packing materials, plants, and microorganisms.

[0003] The existing technology has the following drawbacks:

[0004] 1. Traditional constructed wetlands generally adopt a crude, bulk filling method, which leads to disordered hydraulic channels, easily forming short-flow zones and stagnant water zones, resulting in a purification efficiency reduction rate of up to 40% (see measured data from Environmental Science in 2021).

[0005] 2. When blockage occurs, a full-section excavation is required to replace the fill material, and the cost of a single maintenance exceeds 30% of the construction cost.

[0006] 3. During the reconstruction of the packing layer, the biofilm system collapses, and the ecological recovery cycle can take as long as 6-8 months.

[0007] 4. Currently, vertical subsurface flow ecological fillers are mostly laid by direct dumping, which is simple, direct, and crude. The types, particle sizes, and combinations of fillers are too indiscriminate, and when localized blockages occur in the wetland fillers, it often affects the overall effluent quality and is detrimental to the overall operation of the wetland. Existing technologies lack intelligent monitoring and early warning systems, making it impossible to predict and resolve potential problems in advance, and thus difficult to ensure the long-term stable and efficient operation of the wetland system. Summary of the Invention

[0008] Therefore, the present invention provides a modular unit wastewater treatment method and system to overcome the aforementioned problems existing in the prior art.

[0009] To achieve the above objectives, the present invention provides a modular unit wastewater treatment method, comprising:

[0010] Step S1: Divide the constructed wetland into a three-layer treatment unit along the water flow direction: a flow guiding layer, a reaction layer, and a water collection layer.

[0011] Step S2: Real-time acquisition of water quality parameters, water flow velocity, hydraulic retention time, water flow pressure, and microbial activity data of the treatment unit;

[0012] Step S3: Construct a blockage prediction model based on the water flow velocity, the hydraulic residence time, and the water flow pressure to predict the degree of blockage in the treatment unit;

[0013] Step S4: Compare the blockage degree value with the preset blockage level threshold to obtain a comparison result;

[0014] Step S5: Construct a pollution prediction model based on the water quality parameters and the microbial activity data to predict the pollution score of the water flow;

[0015] Step S6: Compare the pollution score value with the preset pollution score threshold to obtain a comparison result;

[0016] Step S7: Determine the parameter adjustment strategy based on the comparison results and the contrast results.

[0017] Furthermore, the process of step S3 includes:

[0018] The water flow velocity, the hydraulic residence time, and the water flow pressure are serialized to obtain a time series;

[0019] The time series data is used as input to the congestion prediction model to predict the congestion level.

[0020] Furthermore, the process of using the time series as input to the congestion prediction model to predict the congestion level includes:

[0021] The time series is divided into several time windows of equal size;

[0022] The water flow velocity, the hydraulic residence time, and the water flow pressure are normalized to obtain the processing result;

[0023] The processing results are divided into a training dataset and a validation dataset;

[0024] The congestion prediction model is trained based on the data in the time window and the data validation set to obtain a first training model;

[0025] The first trained model is validated using the validation dataset to obtain the congestion level value.

[0026] Furthermore, the process of step S4 includes:

[0027] The congestion level threshold is obtained by setting a level range for the congestion level value based on historical data.

[0028] The congestion level is obtained by comparing the congestion severity value with the congestion level threshold range.

[0029] The current processing unit's blockage status is determined based on the blockage level to obtain the corresponding comparison result.

[0030] Furthermore, the process of step S5 includes:

[0031] The water quality parameters and the microbial activity data are subjected to feature extraction of the rate of change of water quality parameters and the fluctuation of microbial activity to obtain the extraction results;

[0032] Historical water quality parameters and historical microbial activity data were used as training and validation sets.

[0033] The extraction results are used as input parameters, and the pollution prediction model is trained using the training set to obtain a second training model;

[0034] The second training model is validated using the validation set to obtain the target contamination training model;

[0035] The water quality parameters and the microbial activity data are input into the target pollution training model for prediction to obtain the pollution score.

[0036] Furthermore, step S6 includes the following process:

[0037] A range of pollution score levels is set to obtain the pollution score threshold.

[0038] The pollution score value and the pollution score threshold are compared to obtain the pollution score level;

[0039] The current pollution status is determined based on the pollution rating level to obtain the corresponding comparison results.

[0040] Furthermore, the process of step S7 includes:

[0041] Based on the system operation goals and priorities, weights are assigned to the blockage degree value and the pollution score value to construct a risk assessment model, thereby obtaining a comprehensive risk value;

[0042] Adjust the operating parameters of the wastewater treatment system based on the comprehensive risk value.

[0043] Furthermore, the process of assigning weights to the congestion level value and the pollution score value according to the system operation objectives and priorities to construct a comprehensive risk assessment model, and then obtaining the comprehensive risk value, includes:

[0044] Collect historical data on congestion levels and pollution levels;

[0045] Different weighting combinations are set based on the blockage level value and the pollution score value;

[0046] The risk assessment model is constructed using a weighted average method based on the blockage level value and the pollution score value.

[0047] The risk assessment model is validated using the historical blockage levels and historical pollution data to obtain validation results;

[0048] The risk assessment model is optimized based on the verification results to obtain the comprehensive risk value.

[0049] Furthermore, the process of adjusting the operating parameters of the wastewater treatment system based on the comprehensive risk value includes:

[0050] Set comprehensive risk thresholds for different levels;

[0051] The overall risk value and the overall threshold are compared to obtain the current risk level;

[0052] Execute the corresponding parameter adjustment strategy based on the risk level.

[0053] On the other hand, the present invention provides a modular unit wastewater treatment system, comprising:

[0054] The unit division module is used to divide the constructed wetland into three treatment units along the water flow direction: a flow guiding layer, an influent layer, and a reaction layer.

[0055] The data acquisition module is connected to the unit division module and is used to collect water quality parameters, water flow velocity, hydraulic retention time, water flow pressure and microbial activity data of the treatment unit in real time.

[0056] A blockage prediction module, connected to the data acquisition module, is used to construct a blockage prediction model based on the water flow velocity, the hydraulic residence time, and the water flow pressure to predict the degree of blockage in the treatment unit.

[0057] A congestion assessment module, connected to the congestion prediction module, is used to compare the congestion severity value with a preset congestion level threshold to obtain a comparison result;

[0058] A pollution prediction module, connected to the data acquisition module, is used to construct a pollution prediction model based on the water quality parameters and the microbial activity data to predict the pollution score of the water flow.

[0059] A pollution assessment module, connected to the pollution prediction module, is used to compare the pollution score value with a preset pollution score threshold to obtain a comparison result.

[0060] The parameter adjustment module is connected to the blockage assessment module and the pollution assessment module respectively, and is used to determine the parameter adjustment strategy based on the comparison results and the contrast results.

[0061] Compared with existing technologies, the advantages of this invention lie in its ability to proactively prevent and mitigate blockage and pollution risks by constructing predictive models, thereby shifting from reactive response to proactive prevention and effectively extending the system's lifespan. Based on risk assessment results, operating parameters are intelligently adjusted to ensure the wastewater treatment system is always in optimal operating condition, improving treatment efficiency and reducing energy and material consumption. Real-time tracking of water quality changes and dynamic optimization of the treatment process enhance the system's adaptability to water quality fluctuations, ensuring stable effluent quality and reducing environmental pollution risks.

[0062] In particular, by segmenting time-series data into uniformly sized time windows and normalizing them, the dynamic changes in water flow velocity, hydraulic retention time, and water pressure can be effectively captured, improving the accuracy of blockage prediction. Early prediction of blockage risks allows for preventative measures to be taken, reducing system maintenance needs and frequency, effectively extending system lifespan, and ensuring the stable operation of the wastewater treatment system.

[0063] In particular, by setting clear congestion level thresholds, the degree of congestion can be quantified into specific levels, providing intuitive assessment results and helping operations and maintenance personnel quickly understand the system status. Based on the congestion level, the system automatically triggers corresponding warnings and maintenance suggestions, achieving intelligent decision support and improving operational efficiency.

[0064] In particular, the integrated feature vector, which combines rate of change and fluctuation, can more accurately predict pollution scores and identify potential risks in advance. By cleaning and organizing historical data and rationally dividing the training and validation sets, the model's adaptability and generalization ability to new data are improved.

[0065] In particular, by setting clearly defined pollution rating ranges, the degree of pollution can be quantified into specific levels, providing intuitive assessment results and helping maintenance personnel quickly understand the water quality status. Based on the pollution rating level, the system automatically triggers corresponding early warnings and treatment suggestions, achieving intelligent decision support and improving maintenance efficiency.

[0066] In particular, a weighted averaging method is used to comprehensively consider both congestion and contamination risks, providing a more comprehensive system risk assessment. Weights are dynamically adjusted, and the model is flexibly optimized based on system operational goals and priorities, ensuring the accuracy and usability of the assessment results. Different threshold levels are set based on the comprehensive risk value, enabling refined management of the system's operational status. Through clear adjustment strategies, corresponding measures are taken for different risk levels to ensure efficient system operation. System risks are monitored and assessed in real time, allowing for rapid response and measures to reduce system failures and maintenance costs. Continuous optimization of adjustment strategies enhances the system's adaptability and long-term stability. Attached Figure Description

[0067] Figure 1A schematic diagram of a modular unit wastewater treatment method provided by the present invention;

[0068] Figure 2 A schematic diagram of the process of step S3 in a modular unit wastewater treatment method provided by the present invention;

[0069] Figure 3 This is a schematic diagram of step S4 in a modular unit wastewater treatment method provided by the present invention;

[0070] Figure 4 This is a schematic diagram of a modular unit sewage treatment system provided by the present invention. Detailed Implementation

[0071] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0072] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0073] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0074] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0075] Please see Figure 1 As shown, the present invention provides a modular unit wastewater treatment method, comprising:

[0076] Step S1: Divide the constructed wetland into a three-layer treatment unit along the water flow direction: a flow guiding layer, a reaction layer, and a water collection layer.

[0077] Step S2: Real-time acquisition of water quality parameters, water flow velocity, hydraulic retention time, water flow pressure, and microbial activity data of the treatment unit;

[0078] Step S3: Construct a blockage prediction model based on the water flow velocity, the hydraulic residence time, and the water flow pressure to predict the degree of blockage in the treatment unit;

[0079] Step S4: Compare the blockage degree value with the preset blockage level threshold to obtain a comparison result;

[0080] Step S5: Construct a pollution prediction model based on the water quality parameters and the microbial activity data to predict the pollution score of the water flow;

[0081] Step S6: Compare the pollution score value with the preset pollution score threshold to obtain a comparison result;

[0082] Step S7: Determine the parameter adjustment strategy based on the comparison results and the contrast results.

[0083] Specifically, the guide layer is located at the upstream end, and its main function is to evenly distribute the incoming water and reduce the interference of hydraulic shock on the system. This layer uses larger particle size packing material (such as 30-50mm zeolite) with high porosity (approximately 42%) to ensure uniform water infiltration. The reaction layer is located in the middle and is the main pollutant degradation zone. This layer uses smaller particle size packing material (such as a mixture of 2-5mm volcanic rock, ceramsite, and gravel) with a C / N ratio of 12:1, providing abundant attachment surface and a suitable growth environment for microorganisms. The collection layer is located at the downstream end, and its main function is to collect the treated water. This layer uses a quartz sand filter layer with small particle size and moderate porosity, which can further filter and collect the water treated by the reaction layer. Multi-parameter water quality sensors are installed at the outlet of each treatment unit to monitor water quality parameters such as COD, ammonia nitrogen, and pH value in real time. A flow velocity sensor is installed at the junction of the guide layer and the reaction layer to monitor the water flow velocity. The hydraulic retention time is calculated by calculating the water flow velocity and the length of the treatment unit. Pressure sensors are installed at the inlet and outlet of each treatment unit to monitor water flow pressure. Biofilm samples are periodically collected from the reaction layer packing material to analyze microbial activity (such as ATP content, respiration rate, etc.).

[0084] Specifically, by building predictive models to anticipate blockage and pollution risks, the system shifts from reactive response to proactive prevention, effectively extending its lifespan. Operating parameters are intelligently adjusted based on risk assessment results to ensure the wastewater treatment system is always in optimal condition, improving treatment efficiency and reducing energy and material consumption. Real-time tracking of water quality changes and dynamic optimization of the treatment process enhance the system's adaptability to water quality fluctuations, ensuring stable effluent quality and reducing environmental pollution risks.

[0085] Specifically, such as Figure 2 As shown, the process of step S3 includes:

[0086] Step S31: Serialize the water flow velocity, the hydraulic residence time, and the water flow pressure to obtain a time series;

[0087] Step S32: Use the time series as input to the congestion prediction model to predict the congestion level value.

[0088] Specifically, the process of using the time series as input to the congestion prediction model to predict the congestion level includes:

[0089] The time series is divided into several time windows of equal size;

[0090] The water flow velocity, the hydraulic residence time, and the water flow pressure are normalized to obtain the processing result;

[0091] The processing results are divided into a training dataset and a validation dataset;

[0092] The congestion prediction model is trained based on the data in the time window and the data validation set to obtain a first training model;

[0093] The first trained model is validated using the validation dataset to obtain the congestion level value.

[0094] Specifically, the collected data is arranged chronologically to form a time-series dataset. For example, data can be sampled in minutes, hours, or days. The time-series data is stored in a database for subsequent processing and analysis. The time-series data is divided into several time windows of equal size. For example, each window can contain data from the past 10 time points. Using a sliding window technique, the windows are moved sequentially to generate multiple training samples. The water flow velocity, hydraulic residence time, and water flow pressure data in each time window are normalized, mapping the data to the [0,1] interval. The normalized data results are obtained. The normalized dataset is divided into a training set and a validation set. Typically, earlier data can be used as the training set and newer data as the validation set in chronological order to ensure that the model only uses past information during training. A Long Short-Term Memory (LSTM) network is used as the congestion prediction model, as LSTM can effectively capture long-term dependencies in the time series. An LSTM model is constructed, including an input layer, hidden layers, and an output layer. The dimension of the input layer is consistent with the size of the time window and the number of features, and the output layer predicts the degree of congestion. Using mean squared error (MSE) as the loss function, a suitable optimizer (such as Adam) is selected for model compilation. The training set is input into the model for training, and the model parameters are adjusted using the backpropagation algorithm until the loss function on the training set reaches its minimum. The trained model is then validated using a validation set to evaluate its predictive performance. The mean squared error (MSE) and other relevant metrics (such as R-squared) on the validation set are calculated. 2 (Score). Based on the validation results, adjust the model's hyperparameters (such as learning rate, hidden layer size, time window size, etc.) to improve the model's generalization ability and prediction accuracy. Input the real-time collected time series data into the trained model to predict the current congestion level.

[0095] Specifically, by segmenting time-series data into uniformly sized time windows and normalizing them, the dynamic changes in water flow velocity, hydraulic retention time, and water pressure can be effectively captured, improving the accuracy of blockage prediction. Early prediction of blockage risks allows for preventative measures to be taken, reducing system maintenance needs and frequency, effectively extending system lifespan, and ensuring the stable operation of the wastewater treatment system.

[0096] Specifically, such as Figure 3 As shown, the process of step S4 includes:

[0097] Step S41: Set the level range of the congestion level value based on historical data to obtain the congestion level threshold;

[0098] Step S42: Compare the congestion level value with the congestion level threshold range to obtain the congestion level.

[0099] Step S43: Determine the current blockage status of the processing unit based on the blockage level to obtain the corresponding comparison result.

[0100] Specifically, congestion level data for a past period (e.g., the past year) is extracted from the database. This data can be obtained using the congestion prediction model in step S3. The extracted historical data is cleaned to remove outliers and missing values, ensuring data accuracy and completeness. Level ranges are defined: Low risk (unimpeded): congestion level value between 0 and 0.3; Medium risk (mild congestion): congestion level value between 0.3 and 0.6; High risk (severe congestion): congestion level value between 0.6 and 1.0. The rationality of the defined level ranges is verified through statistical analysis (e.g., calculating the frequency of occurrence of each range) and expert experience, and adjustments are made as necessary. The congestion level value of the current processing unit is obtained from the congestion prediction model. If the congestion level value is between 0 and 0.3, it is classified as "unimpeded". If the congestion level value is between 0.3 and 0.6, it is classified as "mild congestion". If the congestion level value is between 0.6 and 1.0, it is classified as "severe congestion". The comparison results are recorded in the database for subsequent analysis and decision-making. Based on the degree of blockage, the blockage status of the current processing unit is mapped to a specific description: Unobstructed: The system is operating normally, requiring no action. Slight Blockage: System operation is slightly affected; minor maintenance (such as local flushing) is recommended. Severe Blockage: System operation is significantly affected; immediate maintenance (such as replacing packing or performing a full flush) is required. The blockage status description is output to the central control system so that maintenance personnel can take appropriate measures in a timely manner. When the blockage level reaches "Severe Blockage," an early warning mechanism is triggered to remind maintenance personnel to take immediate action.

[0101] Specifically, by setting clear congestion level thresholds, the degree of congestion can be quantified into specific levels, providing intuitive assessment results and helping operations and maintenance personnel quickly understand the system status. Based on the congestion level, the system automatically triggers corresponding alerts and maintenance suggestions, achieving intelligent decision support and improving operational efficiency.

[0102] Specifically, step S5 includes the following process:

[0103] The water quality parameters and the microbial activity data are subjected to feature extraction of the rate of change of water quality parameters and the fluctuation of microbial activity to obtain the extraction results;

[0104] Historical water quality parameters and historical microbial activity data were used as training and validation sets.

[0105] The extraction results are used as input parameters, and the pollution prediction model is trained using the training set to obtain a second training model;

[0106] The second training model is validated using the validation set to obtain the target contamination training model;

[0107] The water quality parameters and the microbial activity data are input into the target pollution training model for prediction to obtain the pollution score.

[0108] Specifically, real-time collected water quality parameters and microbial activity data are processed to calculate the rate of change of water quality parameters and the fluctuation of microbial activity. The rate of change and fluctuation data are fused to form a comprehensive feature vector, reflecting the dynamic changes of water quality and microbial activity from multiple dimensions. Historical water quality parameter and microbial activity data are acquired and a data reserve is established. Historical data is cleaned to remove outliers and missing data. The cleaned data is divided into training and validation sets in chronological order. A pollution prediction model is constructed using a Long Short-Term Memory (LSTM) network. The model is trained using the training set, and its performance is optimized by adjusting parameters. The model's predictive ability is evaluated using the validation set, and indicators such as mean squared error (MSE) are calculated. Real-time water quality parameters and microbial activity data are input into the model to predict pollution scores. The prediction results are output to provide a basis for water quality management.

[0109] Specifically, the integrated feature vector combines rate of change and fluctuation, enabling more accurate prediction of pollution scores and early detection of potential risks. By cleaning and organizing historical data and rationally dividing the training and validation sets, the model's adaptability and generalization ability to new data are improved.

[0110] Specifically, step S6 includes the following process:

[0111] A range of pollution score levels is set to obtain the pollution score threshold.

[0112] The pollution score value and the pollution score threshold are compared to obtain the pollution score level;

[0113] The current pollution status is determined based on the pollution rating level to obtain the corresponding comparison results.

[0114] Specifically, pollution score data for a past period (e.g., the past year) is extracted from the database. The extracted historical data is cleaned to remove outliers and missing values, ensuring accuracy and completeness. Level ranges are defined: Low pollution: pollution score between 0 and 0.3; Medium pollution: pollution score between 0.3 and 0.6; High pollution: pollution score between 0.6 and 1.0. The pollution score of the current water flow is obtained from the pollution prediction model. If the pollution score is between 0 and 0.3, it is classified as "low pollution." If the pollution score is between 0.3 and 0.6, it is classified as "medium pollution." If the pollution score is between 0.6 and 1.0, it is classified as "high pollution." Based on the pollution score level, the current water flow's pollution status is mapped to a specific description: Low pollution: Good water quality, no action required. Medium pollution: Slightly polluted water quality, minor treatment recommended (e.g., increasing aeration intensity). High pollution: Severely polluted water quality, immediate treatment required (e.g., adjusting influent flow rate, increasing return ratio). The pollution status description is output to the central control system so that maintenance personnel can take appropriate measures in a timely manner. When the pollution score reaches "high pollution", an early warning mechanism is triggered to remind maintenance personnel to take immediate action.

[0115] Specifically, by setting clear pollution rating ranges, the degree of pollution can be quantified into specific levels, providing intuitive assessment results and helping maintenance personnel quickly understand the water quality status. Based on the pollution rating level, the system automatically triggers corresponding early warnings and treatment suggestions, achieving intelligent decision support and improving maintenance efficiency.

[0116] Specifically, step S7 includes the following process:

[0117] Based on the system operation goals and priorities, weights are assigned to the blockage degree value and the pollution score value to construct a risk assessment model, thereby obtaining a comprehensive risk value;

[0118] Specifically, the process of assigning weights to the congestion level value and the pollution score value according to system operation goals and priorities to construct a comprehensive risk assessment model, and then obtaining a comprehensive risk value, includes:

[0119] Collect historical data on congestion levels and pollution levels;

[0120] Different weighting combinations are set based on the blockage level value and the pollution score value;

[0121] The risk assessment model is constructed using a weighted average method based on the blockage level value and the pollution score value.

[0122] The risk assessment model is validated using the historical blockage levels and historical pollution data to obtain validation results;

[0123] The risk assessment model is optimized based on the verification results to obtain the comprehensive risk value.

[0124] Specifically, the blockage severity and pollution score values ​​for a past period (e.g., the past year) are extracted from the database. Different weighting combinations are assigned to the blockage severity and pollution score values ​​based on the system's operational goals and priorities. For example, if the system prioritizes water quality, the pollution score value can be weighted at 70%, and the blockage severity value at 30%. A weighted average method is used to construct a comprehensive risk assessment model, with the formula: Comprehensive Risk Value = (Blockage Weight × Blockage Severity Value) + (Pollution Weight × Pollution Score Value). The model is ensured to comprehensively reflect the overall risk status of the system. The blockage severity and pollution score values ​​from historical data are input into the model to calculate the comprehensive risk value. The comprehensive risk value predicted by the model is compared with the actual system operating status to verify the model's accuracy and reliability. The predictive performance of the model is evaluated by calculating the mean squared error (MSE) and other relevant indicators (such as R²). 2 (Score). Based on the validation results, adjust the weights or optimize the model structure to improve the model's prediction accuracy and practicality. For example, use methods such as grid search or genetic algorithms to find the optimal weight combination.

[0125] Adjust the operating parameters of the wastewater treatment system based on the comprehensive risk value.

[0126] Specifically, the process of adjusting the operating parameters of the wastewater treatment system based on the comprehensive risk value includes:

[0127] Set comprehensive risk thresholds for different levels;

[0128] The overall risk value and the overall threshold are compared to obtain the current risk level;

[0129] Execute the corresponding parameter adjustment strategy based on the risk level.

[0130] Specifically, based on system design standards and historical operating data, different comprehensive risk threshold ranges are set: low risk: 0-0.3; medium risk: 0.3-0.6; high risk: 0.6-1.0. The real-time calculated comprehensive risk value is compared with the preset threshold ranges to determine the current risk level. If the current risk level is low, the system is operating normally and no adjustment is needed. Maintain the current operating parameters and continue monitoring the system status. If the current risk level is medium, adjust the operating parameters appropriately to reduce the risk. Reduce the influent flow rate by 10%-20%; increase the aeration intensity by 10%-20%; increase the return ratio by 5%-10%. If the current risk level is high, significantly adjust the operating parameters and take emergency measures. Reduce the influent flow rate by 30%-50%; increase the aeration intensity by 30%-50%; increase the return ratio by 15%-30%. Initiate emergency maintenance procedures (such as partial flushing or replacement of packing material). Continuously monitor the system's operating status and dynamically adjust the operating parameters based on real-time data. Regularly reassess and optimize strategies to ensure stable system operation.

[0131] Specifically, a weighted average method is used to comprehensively consider both congestion and contamination risks, providing a more comprehensive system risk assessment. Weights are dynamically adjusted, and the model is flexibly optimized based on system operational goals and priorities to ensure the accuracy and usability of the assessment results. Different threshold levels are set based on the comprehensive risk value to achieve refined management of the system's operational status. Through clear adjustment strategies, corresponding measures are taken for different risk levels to ensure efficient system operation. System risks are monitored and assessed in real time, enabling rapid response and action to reduce system failures and maintenance costs. Continuous optimization of the adjustment strategy enhances the system's adaptability and long-term stability.

[0132] On the other hand, such as Figure 4 As shown, the present invention provides a modular unit wastewater treatment system, comprising:

[0133] Unit division module 10 is used to divide the constructed wetland into three treatment units along the water flow direction: a flow guiding layer, an inlet layer, and a reaction layer.

[0134] The data acquisition module 20 is connected to the unit division module 10 and is used to collect water quality parameters, water flow velocity, hydraulic retention time, water flow pressure and microbial activity data of the treatment unit in real time.

[0135] The blockage prediction module 30 is connected to the data acquisition module 20 and is used to construct a blockage prediction model based on the water flow velocity, the hydraulic residence time and the water flow pressure to predict the degree of blockage of the treatment unit.

[0136] The congestion assessment module 40 is connected to the congestion prediction module 30 and is used to compare the congestion degree value with a preset congestion level threshold to obtain a comparison result.

[0137] The pollution prediction module 50 is connected to the data acquisition module 20 and is used to construct a pollution prediction model based on the water quality parameters and the microbial activity data to predict the pollution score of the water flow.

[0138] The pollution assessment module 60 is connected to the pollution prediction module 50 and is used to compare the pollution score value with a preset pollution score threshold to obtain a comparison result.

[0139] The parameter adjustment module 70 is connected to the blockage assessment module 40 and the pollution assessment module 60 respectively, and is used to determine the parameter adjustment strategy based on the comparison results and the contrast results.

[0140] Specifically, the modular unit sewage treatment system provided in this embodiment of the invention can execute the modular unit sewage treatment method in this embodiment of the invention and achieve the same technical effect, which will not be described in detail here.

[0141] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0142] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A modular unit wastewater treatment method, characterized in that, include: Step S1: Divide the constructed wetland into a three-layer treatment unit along the water flow direction: a flow guiding layer, a reaction layer, and a water collection layer. Step S2: Real-time acquisition of water quality parameters, water flow velocity, hydraulic retention time, water flow pressure, and microbial activity data of the treatment unit; Step S3: Construct a blockage prediction model based on the water flow velocity, the hydraulic residence time, and the water flow pressure to predict the degree of blockage in the treatment unit; Step S4: Compare the blockage degree value with the preset blockage level threshold to obtain a comparison result; Step S5: Construct a pollution prediction model based on the water quality parameters and the microbial activity data to predict the pollution score of the water flow; Step S6: Compare the pollution score value with the preset pollution score threshold to obtain a comparison result; Step S7: Determine the parameter adjustment strategy based on the comparison results and the contrast results.

2. The modular unit wastewater treatment method according to claim 1, characterized in that, The process of step S3 includes: The water flow velocity, the hydraulic residence time, and the water flow pressure are serialized to obtain a time series; The time series data is used as input to the congestion prediction model to predict the congestion level.

3. The modular unit wastewater treatment method according to claim 2, characterized in that, The process of using the time series as input to the congestion prediction model to predict the congestion level includes: The time series is divided into several time windows of equal size; The water flow velocity, the hydraulic residence time, and the water flow pressure are normalized to obtain the processing result; The processing results are divided into a training dataset and a validation dataset; The congestion prediction model is trained based on the data in the time window and the data validation set to obtain a first training model; The first trained model is validated using the validation dataset to obtain the congestion level value.

4. The modular unit wastewater treatment method according to claim 3, characterized in that, The process of step S4 includes: The congestion level threshold is obtained by setting a level range for the congestion level value based on historical data. The congestion level is obtained by comparing the congestion severity value with the congestion level threshold range. The current processing unit's blockage status is determined based on the blockage level to obtain the corresponding comparison result.

5. A modular unit wastewater treatment method according to claim 4, characterized in that, The process of step S5 includes: The water quality parameters and the microbial activity data are subjected to feature extraction of the rate of change of water quality parameters and the fluctuation of microbial activity to obtain the extraction results; Historical water quality parameters and historical microbial activity data were used as training and validation sets. The extraction results are used as input parameters, and the pollution prediction model is trained using the training set to obtain a second training model; The second training model is validated using the validation set to obtain the target contamination training model; The water quality parameters and the microbial activity data are input into the target pollution training model for prediction to obtain the pollution score.

6. The modular unit wastewater treatment method according to claim 5, characterized in that, The process of step S6 includes: A range of pollution score levels is set to obtain the pollution score threshold. The pollution score value and the pollution score threshold are compared to obtain the pollution score level; The current pollution status is determined based on the pollution rating level to obtain the corresponding comparison results.

7. A modular unit wastewater treatment method according to claim 6, characterized in that, The process of step 7 includes: Based on the system operation goals and priorities, weights are assigned to the blockage degree value and the pollution score value to construct a risk assessment model, thereby obtaining a comprehensive risk value; Adjust the operating parameters of the wastewater treatment system based on the comprehensive risk value.

8. A modular unit wastewater treatment method according to claim 7, characterized in that, The process of assigning weights to the congestion level value and the pollution score value according to the system operation goals and priorities to construct a comprehensive risk assessment model and obtain a comprehensive risk value includes: Collect historical data on congestion levels and pollution levels; Different weighting combinations are set based on the blockage level value and the pollution score value; The risk assessment model is constructed using a weighted average method based on the blockage level value and the pollution score value. The risk assessment model is validated using the historical blockage levels and historical pollution data to obtain validation results; The risk assessment model is optimized based on the verification results to obtain the comprehensive risk value.

9. A modular unit wastewater treatment method according to claim 8, characterized in that, The process of adjusting the operating parameters of the wastewater treatment system based on the comprehensive risk value includes: Set comprehensive risk thresholds for different levels; The overall risk value and the overall threshold are compared to obtain the current risk level; Execute the corresponding parameter adjustment strategy based on the risk level.

10. A modular unit wastewater treatment system based on the modular unit wastewater treatment method according to any one of claims 1-9, characterized in that, include: The unit division module is used to divide the constructed wetland into three treatment units along the water flow direction: a flow guiding layer, an influent layer, and a reaction layer. The data acquisition module is connected to the unit division module and is used to collect water quality parameters, water flow velocity, hydraulic retention time, water flow pressure and microbial activity data of the treatment unit in real time. A blockage prediction module, connected to the data acquisition module, is used to construct a blockage prediction model based on the water flow velocity, the hydraulic residence time, and the water flow pressure to predict the degree of blockage in the treatment unit. A congestion assessment module, connected to the congestion prediction module, is used to compare the congestion severity value with a preset congestion level threshold to obtain a comparison result; A pollution prediction module, connected to the data acquisition module, is used to construct a pollution prediction model based on the water quality parameters and the microbial activity data to predict the pollution score of the water flow. A pollution assessment module, connected to the pollution prediction module, is used to compare the pollution score value with a preset pollution score threshold to obtain a comparison result. The parameter adjustment module is connected to the blockage assessment module and the pollution assessment module respectively, and is used to determine the parameter adjustment strategy based on the comparison results and the contrast results.

Images