Intelligent control type artificial wetland denitrification and phosphorus removal control method

Abstract

The present application relates to sewage treatment technical field, and disclose a kind of intelligent control type artificial wetland denitrification and phosphorus removal control method, the method includes S1, artificial wetland multidimensional operating parameter data is collected, generates water quality dynamic monitoring data, plant physiological state data and microbial activity characteristic data;S2, based on the water quality dynamic monitoring data, calculate pollutant removal efficiency index, generate nitrogen and phosphorus removal efficiency evaluation data;By integrating multidimensional operating parameter acquisition, real-time obtain water quality, plant physiological state and microbial activity data, realize the overall perception of wetland system operating state, ensure the integrity and real-time of system monitoring, simultaneously based on multi-source data collaborative analysis and intelligent decision-making, identify pollutant removal efficiency, improve the evaluation accuracy of wetland system operating state, provide basis for subsequent regulation.

Description

Technical Field

[0001] This invention relates to the field of wastewater treatment technology, specifically to an intelligent control method for nitrogen and phosphorus removal in constructed wetlands. Background Technology

[0002] Constructed wetlands are artificially built and controlled wetlands similar to marshes. Wastewater and sludge are systematically distributed onto these artificially constructed wetlands. As the wastewater and sludge flow in a certain direction, the technology mainly utilizes the physical, chemical, and biological synergistic effects of soil, artificial media, plants, and microorganisms to treat the wastewater and sludge.

[0003] Currently, constructed wetlands mainly rely on natural purification and human experience-based regulation in the process of nitrogen and phosphorus removal. They lack the ability to perceive water quality parameters, plant physiological status, and microbial activity in a multi-dimensional and coordinated manner, making it difficult to accurately assess pollutant removal efficiency in real time and to ensure that water quality meets standards in the long term.

[0004] Therefore, an intelligent control method for nitrogen and phosphorus removal in constructed wetlands is proposed to solve the above problems. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an intelligent control method for nitrogen and phosphorus removal in constructed wetlands, which solves the problems mentioned in the background technology, namely, the difficulty in accurately assessing pollutant removal efficiency in real time and the difficulty in ensuring long-term stable compliance of water quality.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an intelligent control method for nitrogen and phosphorus removal in constructed wetlands, the method comprising the following steps:

[0007] S1. Collect multi-dimensional operational parameter data of constructed wetlands and generate dynamic water quality monitoring data, plant physiological status data and microbial activity characteristic data;

[0008] S2. Calculate pollutant removal efficiency indicators based on the water quality dynamic monitoring data, and generate nitrogen and phosphorus removal efficiency assessment data;

[0009] S3. Based on the nitrogen and phosphorus removal efficiency assessment data and the preset water quality standard threshold, perform compliance status judgment processing to generate pollutant removal compliance status identifier. If compliance is achieved, proceed to step S7.

[0010] S4. When the standard is not met, multi-parameter collaborative regulation is performed based on the water quality dynamic monitoring data, plant physiological state data and microbial activity characteristic data to generate a set of wetland operation parameter optimization instructions.

[0011] S5. Construct a dynamic control strategy matrix, optimize the instruction set based on the wetland operation parameters to match the best control strategy, and generate target control strategy feature data.

[0012] S6. Map physical execution devices according to the target control strategy feature data to generate wetland equipment control parameter configuration data;

[0013] S7 integrates real-time environmental parameters and control strategy data to drive constructed wetland actuators to perform precise control of nitrogen and phosphorus removal, and outputs pollutant concentration calibration data.

[0014] Preferably, the collection of multi-dimensional operational parameter data of the constructed wetland in S1 includes:

[0015] S11. Collect waveforms of ammonia nitrogen, nitrate nitrogen, and total phosphorus concentration changes in water bodies by deploying a multispectral sensor array in the wetland inlet area, matrix layer, and plant root zone to generate dynamic water quality monitoring data.

[0016] S12. Use a chlorophyll fluorescence imager and a root scanner to obtain parameters of photosynthetic efficiency and root development status of wetland plants, and generate plant physiological status data.

[0017] S13. Real-time detection of biofilm metabolic activity intensity in the aerobic and anaerobic zones of the substrate layer using microbial electrochemical sensors, generating microbial activity characteristic data.

[0018] Preferably, the nitrogen and phosphorus removal efficiency evaluation data generated in S2 includes:

[0019] S21. Extract the pollutant concentration change curve within a 24-hour period from the water quality dynamic monitoring data;

[0020] S22. Calculate the nitrogen and phosphorus removal load per unit area based on the pollutant mass balance model, and generate a dynamic evaluation coefficient of removal efficiency by combining the hydraulic retention time parameter.

[0021] S23. Generate a biological synergistic compensating factor by associating root exudate indicators in plant physiological state data with enzyme reaction intensity in microbial activity characteristic data.

[0022] S24. The removal efficiency dynamic evaluation coefficient and the biological synergistic compensation factor are combined to generate nitrogen and phosphorus removal efficiency evaluation data.

[0023] Preferably, the compliance status determination process in S3 includes:

[0024] S31. Preset compliance benchmark ranges for ammonia nitrogen concentration threshold ≤ 0.5 mg / L and total phosphorus concentration threshold ≤ 0.3 mg / L;

[0025] S32. When all pollutant concentrations in the nitrogen and phosphorus removal efficiency assessment data fall within the benchmark range, the pollutant removal compliance status is output as "compliant".

[0026] S33. When the concentration of any pollutant exceeds the standard range, output the pollutant removal compliance status as "not compliant" and trigger the pollutant type code.

[0027] Preferably, the multi-parameter coordinated control processing in S4 includes:

[0028] S41. When the pollutant removal compliance status is marked as "not compliant", analyze the pollutant type code that exceeds the standard;

[0029] S42. For scenarios where ammonia nitrogen exceeds the standard, generate instructions to increase dissolved oxygen concentration, enhance plant root aeration, and activate nitrifying bacteria.

[0030] S43. For scenarios where total phosphorus exceeds the standard, generate instructions for adjusting the pH of the matrix layer, controlling the iron salt addition gradient, and enriching polyphosphate bacteria.

[0031] S44. Integrate multi-dimensional control instructions to form a set of wetland operation parameter optimization instructions.

[0032] Preferably, the target regulation strategy feature data generated in S5 includes:

[0033] S51. Construct a dynamic regulation strategy matrix encompassing three dimensions: chemical enhancement, biostimulation, and hydraulic regulation.

[0034] ;

[0035] in For chemical enhancement strategy vectors, For biological stimulus strategy vectors, For hydraulic control strategy vector, The total number of strategy dimensions is 3;

[0036] S52. A biomimetic optimization algorithm is used to match the wetland operation parameter optimization instruction set with the dynamic control strategy matrix:

[0037] S521. Initialize the position of the osprey population in the n-dimensional solution space under the wetland regulation strategy;

[0038] S522. During the exploration phase, simulate the global search behavior of the population and calculate the fitness value of the strategy matching.

[0039] S523, during the development phase, simulate local fine-grained optimization and update the optimal strategy position;

[0040] S524. Output the feature vector of the strategy with the highest matching degree to generate target regulation strategy feature data.

[0041] Preferably, the target regulation strategy feature data generated in S6 includes:

[0042] S61. Establish the mapping relationship between regulation strategy and equipment: dissolved oxygen regulation strategy corresponds to the frequency conversion parameter of aerator, chemical dosing strategy corresponds to the flow parameter of dosing pump, and plant regulation strategy corresponds to the light compensation intensity.

[0043] S62. Based on the target regulation strategy feature data indexing device control parameter mapping table, generate wetland device control parameter configuration data containing device address codes and control thresholds.

[0044] Preferably, the pollutant concentration calibration data output in S7 includes:

[0045] S71. Real-time collection of ambient temperature, light intensity and rainfall parameters to generate environmental disturbance compensation coefficient;

[0046] S72. Superimpose the environmental disturbance compensation coefficient and the wetland equipment control parameter configuration data to generate anti-interference equipment control commands;

[0047] S73. Drive the aeration system, dosing device, and water level regulating valve to perform actions through the Internet of Things control gateway;

[0048] S74. Collect pollutant concentration data at the outlet every 30 minutes to verify the control effect and output pollutant concentration calibration data.

[0049] Preferred options also include:

[0050] S8. When the pollutant concentration calibration data fails to meet the standard for three consecutive times, the abnormal handling mechanism will be activated:

[0051] S81. Tracing back the historical execution path of control strategies and marking failed control nodes;

[0052] S82. Invoke the expert knowledge base to generate a system-level repair solution;

[0053] S83, activate the matrix layer flushing procedure and microbial reset procedure.

[0054] Preferably, the activation matrix layer flushing procedure and microbial reset procedure further include:

[0055] S831, Employs a pulse gradient water flow impact mode to flush out blockages in the matrix layer in stages;

[0056] S832. Based on the coding of pollutant types exceeding the standard, selectively inoculate with nitrifying bacteria and polyphosphate-accumulating bacteria to rebuild the microbial community;

[0057] S833. Real-time monitoring of matrix permeability changes after flushing; if the permeability increase is less than 30%, a second flushing cycle is triggered.

[0058] S834, dynamically adjust the inoculant dosing rate based on ambient temperature parameters.

[0059] Beneficial effects

[0060] Compared with existing technologies, this invention provides an intelligent control method for nitrogen and phosphorus removal in constructed wetlands, which has the following beneficial effects:

[0061] 1. In this invention, when conducting intelligent control of nitrogen and phosphorus removal in constructed wetlands, multi-dimensional operating parameter acquisition is integrated to obtain real-time data on water quality, plant physiological status, and microbial activity, thereby achieving comprehensive perception of the wetland system's operating status, ensuring the integrity and real-time nature of system monitoring, and simultaneously conducting collaborative analysis and intelligent decision-making based on multi-source data to identify pollutant removal efficiency, improve the accuracy of wetland system operating status assessment, and provide a basis for subsequent control.

[0062] 2. In this invention, when performing intelligent control of nitrogen and phosphorus removal in constructed wetlands, a dynamic control strategy matrix is ​​constructed and the optimal control strategy is matched to adaptively respond to different exceedance scenarios and operating conditions, thereby enhancing the adaptability to load fluctuations and changes in influent water quality. This makes the control strategy more targeted and effective, thereby improving the stability and removal efficiency of nitrogen and phosphorus removal.

[0063] 3. In this invention, when performing intelligent control of nitrogen and phosphorus removal in constructed wetlands, an anomaly handling mechanism and a system-level repair scheme are established. When control fails, the problem is quickly located and the corresponding recovery procedure is initiated, which enhances the system's self-repair capability and fault tolerance, reduces the need for manual intervention, ensures the long-term stable operation of the wetland system, and extends the service life of the facilities. Attached Figure Description

[0064] Figure 1 This is a flowchart of the intelligent control method for nitrogen and phosphorus removal in constructed wetlands according to the present invention. Detailed Implementation

[0065] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0066] Specific embodiment: Intelligent regulation-type constructed wetland nitrogen and phosphorus removal control method, the method includes the following steps:

[0067] S1. Collect multi-dimensional operational parameter data of constructed wetlands and generate dynamic water quality monitoring data, plant physiological status data and microbial activity characteristic data;

[0068] S2. Calculate pollutant removal efficiency indicators based on the water quality dynamic monitoring data, and generate nitrogen and phosphorus removal efficiency assessment data;

[0069] S3. Based on the nitrogen and phosphorus removal efficiency assessment data and the preset water quality standard threshold, perform compliance status judgment processing to generate pollutant removal compliance status identifier. If compliance is achieved, proceed to step S7.

[0070] S4. When the standard is not met, multi-parameter collaborative regulation is performed based on the water quality dynamic monitoring data, plant physiological state data and microbial activity characteristic data to generate a set of wetland operation parameter optimization instructions.

[0071] S5. Construct a dynamic control strategy matrix, optimize the instruction set based on the wetland operation parameters to match the best control strategy, and generate target control strategy feature data.

[0072] S6. Map physical execution devices according to the target control strategy feature data to generate wetland equipment control parameter configuration data;

[0073] S7 integrates real-time environmental parameters and control strategy data to drive constructed wetland actuators to perform precise control of nitrogen and phosphorus removal, and outputs pollutant concentration calibration data.

[0074] The multi-dimensional operational parameter data of the constructed wetland collected in S1 include:

[0075] S11. Collect waveforms of ammonia nitrogen, nitrate nitrogen, and total phosphorus concentration changes in water bodies by deploying a multispectral sensor array in the wetland inlet area, matrix layer, and plant root zone to generate dynamic water quality monitoring data.

[0076] S12. Use a chlorophyll fluorescence imager and a root scanner to obtain parameters of photosynthetic efficiency and root development status of wetland plants, and generate plant physiological status data.

[0077] S13. Real-time detection of biofilm metabolic activity intensity in the aerobic and anaerobic zones of the substrate layer using microbial electrochemical sensors, generating microbial activity characteristic data.

[0078] The evaluation data on nitrogen and phosphorus removal efficiency in S2 includes:

[0079] S21. Extract the pollutant concentration change curve within a 24-hour period from the water quality dynamic monitoring data;

[0080] S22. Calculate the nitrogen and phosphorus removal load per unit area based on the pollutant mass balance model, and generate a dynamic evaluation coefficient of removal efficiency by combining the hydraulic retention time parameter.

[0081] Pollutant removal load :

[0082] ;

[0083] in This refers to the inlet water flow rate. , The concentration of pollutants in the influent and effluent, The area of ​​the wetland unit. For monitoring time periods;

[0084] Removal efficiency dynamic evaluation coefficient :

[0085] ;

[0086] in The hydraulic residence time, The matrix adsorption coefficient;

[0087] S23. Generate a biological synergistic compensating factor by associating root exudate indicators in plant physiological state data with enzyme reaction intensity in microbial activity characteristic data.

[0088] S24. The removal efficiency dynamic evaluation coefficient and the biological synergistic compensation factor are combined to generate nitrogen and phosphorus removal efficiency evaluation data.

[0089] The compliance status determination process in S3 includes:

[0090] S31. Preset compliance benchmark ranges for ammonia nitrogen concentration threshold ≤ 0.5 mg / L and total phosphorus concentration threshold ≤ 0.3 mg / L;

[0091] S32. When all pollutant concentrations in the nitrogen and phosphorus removal efficiency assessment data fall within the benchmark range, the pollutant removal compliance status is output as "compliant".

[0092] S33. When the concentration of any pollutant exceeds the standard range, output the pollutant removal compliance status as "not compliant" and trigger the pollutant type code.

[0093] The multi-parameter coordinated control process in S4 includes:

[0094] S41. When the pollutant removal compliance status is marked as "not compliant", analyze the pollutant type code that exceeds the standard;

[0095] S42. For scenarios where ammonia nitrogen exceeds the standard, generate instructions to increase dissolved oxygen concentration, enhance plant root aeration, and activate nitrifying bacteria.

[0096] S43. For scenarios where total phosphorus exceeds the standard, generate instructions for adjusting the pH of the matrix layer, controlling the iron salt addition gradient, and enriching polyphosphate bacteria.

[0097] S44. Integrate multi-dimensional control instructions to form a set of wetland operation parameter optimization instructions.

[0098] The target regulation strategy feature data generated in S5 includes:

[0099] S51. Construct a dynamic regulation strategy matrix encompassing three dimensions: chemical enhancement, biostimulation, and hydraulic regulation.

[0100] ;

[0101] in For chemical enhancement strategy vectors, For biological stimulus strategy vectors, For hydraulic control strategy vector, The total number of strategy dimensions is 3;

[0102] S52. A biomimetic optimization algorithm is used to match the wetland operation parameter optimization instruction set with the dynamic control strategy matrix:

[0103] S521. Initialize the position of the osprey population in the n-dimensional solution space under the wetland regulation strategy;

[0104] Population initialization is achieved by randomly generating the position vectors of policy solutions:

[0105] ;

[0106] ;

[0107] in For the first The position vectors of individual ospreys, where , Population size; For the first The individual in the first Component values ​​in the solution space; For the dimensions of the dynamic control strategy matrix; For a uniformly distributed random function, and The first The lower and upper bounds of a dimension;

[0108] S522. During the exploration phase, simulate the global search behavior of the population and calculate the fitness value of the strategy matching.

[0109] ;

[0110] in:

[0111] Let the fitness value of the i-th osprey individual be denoted by (0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 1, 1, 1, 2 ...2, 1, 2, 1, 2, 3, 1], the larger the value, the higher the strategy matching degree;

[0112] This is a dynamic control strategy matrix;

[0113] The dot product of a matrix and a vector is used to output a vector predicting the control effect.

[0114] S523, during the development phase, simulate local fine-grained optimization and update the optimal strategy position;

[0115] S524. Output the feature vector of the strategy with the highest matching degree to generate target regulation strategy feature data.

[0116] The target regulation strategy feature data generated in S6 includes:

[0117] S61. Establish the mapping relationship between regulation strategy and equipment: dissolved oxygen regulation strategy corresponds to the frequency conversion parameter of aerator, chemical dosing strategy corresponds to the flow parameter of dosing pump, and plant regulation strategy corresponds to the light compensation intensity.

[0118] S62. Based on the target regulation strategy feature data indexing device control parameter mapping table, generate wetland device control parameter configuration data containing device address codes and control thresholds.

[0119] The pollutant concentration calibration data output in S7 includes:

[0120] S71. Real-time collection of ambient temperature, light intensity and rainfall parameters to generate environmental disturbance compensation coefficient;

[0121] S72. Superimpose the environmental disturbance compensation coefficient and the wetland equipment control parameter configuration data to generate anti-interference equipment control commands;

[0122] S73. Drive the aeration system, dosing device, and water level regulating valve to perform actions through the Internet of Things control gateway;

[0123] S74. Collect pollutant concentration data at the outlet every 30 minutes to verify the control effect and output pollutant concentration calibration data.

[0124] Also includes:

[0125] S8. When the pollutant concentration calibration data fails to meet the standard for three consecutive times, the abnormal handling mechanism will be activated:

[0126] S81. Tracing back the historical execution path of control strategies and marking failed control nodes;

[0127] S82. Invoke the expert knowledge base to generate a system-level repair solution;

[0128] S83, activate the matrix layer flushing procedure and microbial reset procedure.

[0129] Activating the substrate flushing procedure and microbial reset procedure further includes:

[0130] S831, Employs a pulse gradient water flow impact mode to flush out blockages in the matrix layer in stages;

[0131] S832. Based on the coding of pollutant types exceeding the standard, selectively inoculate with nitrifying bacteria and polyphosphate-accumulating bacteria to rebuild the microbial community;

[0132] S833. Real-time monitoring of matrix permeability changes after flushing; if the permeability increase is less than 30%, a second flushing cycle is triggered.

[0133] Penetration rate increase:

[0134] ;

[0135] in The matrix permeability before flushing. This represents the matrix permeability after rinsing.

[0136] S834, dynamically adjust the inoculant dosing rate based on ambient temperature parameters.

[0137] The steps of this method are as follows:

[0138] Step 1: Dynamic Sensing of Multi-Dimensional Operating Parameters

[0139] By deploying a multispectral sensor array in the wetland inlet area, substrate layer, and plant root zone, the system collects real-time waveforms of ammonia nitrogen, nitrate nitrogen, and total phosphorus concentrations in the water. Simultaneously, chlorophyll fluorescence imaging technology is used to obtain the photosynthetic efficiency of wetland plants, and a root scanner is used to capture the root development status. At the same time, microbial electrochemical sensors are used to monitor the metabolic activity intensity of biofilms in the aerobic and anaerobic zones of the substrate layer, forming a multi-source fusion sensing system of dynamic water quality monitoring data, plant physiological status data, and microbial activity characteristic data, thus constructing a panoramic view of the wetland's operational status.

[0140] Step 2: Intelligent Assessment of Pollutant Removal Efficiency

[0141] Based on the mass balance model, the pollutant concentration change curve within a 24-hour period was analyzed, and the dynamic correlation parameters between nitrogen and phosphorus removal load per unit area and hydraulic retention time were calculated. The indicators of plant root exudates and the intensity of microbial enzymatic reactions were correlated to quantify the contribution rate of biological synergy to pollutant removal. By combining the dynamic evaluation coefficient of removal efficiency and the biological synergy compensation factor, nitrogen and phosphorus removal efficiency evaluation data with spatiotemporal characteristics were generated to accurately reflect the nitrogen and phosphorus removal efficiency of the system.

[0142] Step 3: Self-assessment of water quality compliance status

[0143] The system presets compliance benchmark ranges of ≤0.5mg / L for ammonia nitrogen concentration and ≤0.3mg / L for total phosphorus concentration, and compares real-time assessment data with the benchmark thresholds. When all pollutant concentrations are within the compliance range, the system triggers a continuous operation mode. If any pollutant exceeds the standard, a non-compliance label containing the type of exceedance code is immediately generated, and a multi-parameter collaborative control mechanism is activated.

[0144] Step 4: Collaborative Optimization Decision of Operating Parameters

[0145] For scenarios with excessive ammonia nitrogen, instructions to increase dissolved oxygen concentration, enhance plant root aeration, and activate nitrifying bacteria are generated simultaneously. For scenarios with excessive total phosphorus, instructions to adjust the pH of the substrate layer, control the gradient addition of iron salts, and implement strategies for enriching polyphosphate-accumulating bacteria are dynamically triggered. Through the intelligent combination and priority ranking of multi-dimensional instructions, a set of optimized wetland operation parameters adapted to the current pollution characteristics is formed.

[0146] Step 5: Dynamic matching of control strategy matrix

[0147] A dynamic regulation strategy matrix library with three dimensions of chemical enhancement, biostimulation, and hydraulic regulation is constructed. A biomimetic optimization algorithm is used to intelligently match the parameter optimization instruction set with the strategy matrix: the strategy population position is initialized in the solution space, and the strategy fitness is calculated and the optimal solution is iteratively updated through a two-stage optimization of global exploration and local development. The target regulation strategy feature data with the highest matching degree with the current working condition is output.

[0148] Step Six: Perform precise parameter mapping for the equipment.

[0149] Establish a dynamic mapping database between regulation strategies and physical equipment: convert dissolved oxygen regulation strategies into aerator frequency conversion parameters, chemical dosing strategies into dosing pump flow curves, and plant regulation strategies into light compensation intensity; based on the target strategy feature data index, generate an executable instruction set containing equipment address codes, action timing, and control thresholds.

[0150] Step 7: Real-time compensation control for environmental disturbances

[0151] The system collects ambient temperature, light intensity, and rainfall parameters in real time, overlays compensation coefficients onto the equipment control parameter configuration data, and generates dynamic execution commands with anti-interference capabilities. Through the Internet of Things control gateway, it drives the aeration system, dosing device, and water level regulating valve to perform precise actions, achieving stable control in complex environments.

[0152] Step 8: Closed-loop verification and anomaly self-repair

[0153] Every 30 minutes, the pollutant concentration at the outlet is collected to verify the control effect and generate pollutant concentration calibration data. When the calibration fails to meet the standard for three consecutive times, the historical control path is traced back to mark the failure node, and the pulse gradient water flow flushing program is started to remove the matrix blockage. Based on the code of the excessive type, the microbial agent is selectively inoculated, and the colonization rate is dynamically adjusted in combination with temperature parameters to complete the reconstruction of the microbial community and the restoration of system function.

[0154] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0155] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart control method for nitrogen and phosphorus removal in constructed wetlands, characterized by: The method includes the following steps: S1. Collect multi-dimensional operational parameter data of constructed wetlands and generate dynamic water quality monitoring data, plant physiological status data and microbial activity characteristic data; The multi-dimensional operational parameter data of the constructed wetland collected in S1 include: S11. Collect waveforms of ammonia nitrogen, nitrate nitrogen, and total phosphorus concentration changes in water bodies by deploying a multispectral sensor array in the wetland inlet area, matrix layer, and plant root zone to generate dynamic water quality monitoring data. S12. Use a chlorophyll fluorescence imager and a root scanner to obtain parameters of photosynthetic efficiency and root development status of wetland plants, and generate plant physiological status data. S13. Real-time detection of biofilm metabolic activity intensity in the aerobic and anaerobic zones of the substrate layer using a microbial electrochemical sensor, generating microbial activity characteristic data; S2. Calculate pollutant removal efficiency indicators based on the water quality dynamic monitoring data, and generate nitrogen and phosphorus removal efficiency assessment data; The nitrogen and phosphorus removal efficiency evaluation data generated in S2 includes: S21. Extract the pollutant concentration change curve within a 24-hour period from the water quality dynamic monitoring data; S22. Calculate the nitrogen and phosphorus removal load per unit area based on the pollutant mass balance model, and generate a dynamic evaluation coefficient of removal efficiency by combining the hydraulic retention time parameter. S23. Generate a biological synergistic compensating factor by associating root exudate indicators in plant physiological state data with enzyme reaction intensity in microbial activity characteristic data. S24. Integrate the aforementioned dynamic evaluation coefficient for removal efficiency with the biological synergistic compensation factor to generate nitrogen and phosphorus removal efficiency evaluation data. S3. Based on the nitrogen and phosphorus removal efficiency assessment data and the preset water quality standard threshold, perform compliance status judgment processing to generate pollutant removal compliance status identifier. If compliance is achieved, proceed to step S7. S4. When the standard is not met, multi-parameter collaborative regulation is performed based on the water quality dynamic monitoring data, plant physiological state data and microbial activity characteristic data to generate a set of wetland operation parameter optimization instructions. The multi-parameter coordinated control process in S4 includes: S41. When the pollutant removal compliance status is marked as "not compliant", analyze the pollutant type code that exceeds the standard; S42. For scenarios where ammonia nitrogen exceeds the standard, generate instructions to increase dissolved oxygen concentration, enhance plant root aeration, and activate nitrifying bacteria. S43. For scenarios where total phosphorus exceeds the standard, generate instructions for adjusting the pH of the matrix layer, controlling the iron salt addition gradient, and enriching polyphosphate bacteria. S44. Integrate multi-dimensional control instructions to form a wetland operation parameter optimization instruction set. S5. Construct a dynamic control strategy matrix, optimize the instruction set based on the wetland operation parameters to match the best control strategy, and generate target control strategy feature data. S6. Map physical execution devices according to the target control strategy feature data to generate wetland equipment control parameter configuration data; S7. Integrates real-time environmental parameters and control strategy data to drive constructed wetland actuators to perform precise control of nitrogen and phosphorus removal, and outputs pollutant concentration calibration data; S8. When the pollutant concentration calibration data fails to meet the standard for three consecutive times, the abnormal handling mechanism will be activated: S81. Tracing back the execution path of historical control strategies and marking failed control nodes; S82. Invoke the expert knowledge base to generate a system-level repair solution; S83, activate the matrix layer flushing procedure and microbial reset procedure.

2. The intelligent control method for nitrogen and phosphorus removal in constructed wetlands according to claim 1, characterized in that: The compliance status determination process in S3 includes: S31. Preset compliance benchmark ranges for ammonia nitrogen concentration threshold ≤ 0.5 mg / L and total phosphorus concentration threshold ≤ 0.3 mg / L; S32. When all pollutant concentrations in the nitrogen and phosphorus removal efficiency assessment data fall within the benchmark range, the pollutant removal compliance status is output as "compliant". S33. When the concentration of any pollutant exceeds the standard range, output the pollutant removal compliance status as "not compliant" and trigger the pollutant type code.

3. The intelligent control method for nitrogen and phosphorus removal in constructed wetlands according to claim 1, characterized in that: The target regulation strategy feature data generated in S5 includes: S51. Construct a dynamic regulation strategy matrix encompassing three dimensions: chemical enhancement, biostimulation, and hydraulic regulation. ； in For chemical enhancement strategy vectors, For biological stimulus strategy vectors, For hydraulic control strategy vector, The total number of strategy dimensions, where ; S52. A biomimetic optimization algorithm is used to match the wetland operation parameter optimization instruction set with the dynamic control strategy matrix: S521. Initialize the position of the osprey population in the n-dimensional solution space under the wetland regulation strategy; S522. During the exploration phase, simulate the global search behavior of the population and calculate the fitness value of the strategy matching. S523, during the development phase, simulate local fine-grained optimization and update the optimal strategy position; S524. Output the feature vector of the strategy with the highest matching degree to generate target regulation strategy feature data.

4. The intelligent control method for nitrogen and phosphorus removal in constructed wetlands according to claim 1, characterized in that: The target regulation strategy feature data generated in S6 includes: S61. Establish the mapping relationship between regulation strategy and equipment: dissolved oxygen regulation strategy corresponds to the frequency conversion parameter of aerator, chemical dosing strategy corresponds to the flow parameter of dosing pump, and plant regulation strategy corresponds to the light compensation intensity. S62. Based on the target regulation strategy feature data indexing device control parameter mapping table, generate wetland device control parameter configuration data containing device address codes and control thresholds.

5. The intelligent control method for nitrogen and phosphorus removal in constructed wetlands according to claim 1, characterized in that: The pollutant concentration calibration data output in S7 includes: S71. Real-time collection of ambient temperature, light intensity and rainfall parameters to generate environmental disturbance compensation coefficient; S72. Superimpose the environmental disturbance compensation coefficient and the wetland equipment control parameter configuration data to generate anti-interference equipment control commands; S73. Drive the aeration system, dosing device, and water level regulating valve to perform actions through the Internet of Things control gateway; S74. Collect pollutant concentration data at the outlet every 30 minutes to verify the control effect and output pollutant concentration calibration data.

6. The intelligent control method for nitrogen and phosphorus removal in constructed wetlands according to claim 1, characterized in that: The activation matrix layer flushing procedure and microbial reset procedure include: S831, Employs a pulse gradient water flow impact mode to flush out blockages in the matrix layer in stages; S832. Based on the coding of pollutant types exceeding the standard, selectively inoculate with nitrifying bacteria and polyphosphate-accumulating bacteria to rebuild the microbial community; S833. Real-time monitoring of matrix permeability changes after flushing; if the permeability increase is less than 30%, a second flushing cycle is triggered. S834, dynamically adjust the inoculant dosing rate based on ambient temperature parameters.

Images