Carbon neutralization regulation and control method and system for sewage plant

Abstract

The invention relates to the technical field of sewage plant-oriented carbon neutralization regulation and control scheme design, in particular to a sewage plant-oriented carbon neutralization regulation and control method and a sewage plant-oriented carbon neutralization regulation and control system. The method comprises the steps of collecting water quality, energy consumption and gas emission data in real time through a multi-source sensor, inputting the data into a space-time diagram convolutional network to predict a carbon emission trend after edge computing node cleaning, and dynamically optimizing an aeration rate and a sludge reflux ratio based on a fuzzy PID controller. A whole-process carbon footprint is tracked by adopting a life cycle evaluation method, a multi-target compensation strategy is generated in combination with an improved NSGA-III algorithm, and photovoltaic, biogas and green power resources are scheduled preferentially. A digital twin platform and a block chain evidence storage module are innovatively integrated, the former calibrates model parameters in real time, and the latter generates a non-tampering carbon neutralization voucher. According to the method, the problems of one-sided data, regulation and control lag and insufficient credibility of a traditional method are solved, and minute-level sensing, prediction and offset closed-loop control of carbon emission in the sewage treatment process is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon neutrality regulation scheme design for sewage treatment plants, and particularly to a carbon neutrality regulation method and system for sewage treatment plants. Background Art

[0002] The current carbon neutrality regulation technology for sewage treatment plants has the following bottlenecks: Defects in data perception and processing: Traditional methods rely on single sensors or off-line monitoring, insufficiently capture dynamic characteristics such as sudden changes in influent load and uneven spatial distribution of dissolved oxygen (DO), and lack the ability to clean real-time data at the edge side, resulting in outliers interfering with the accuracy of prediction models. For example, the aeration volume regulation often uses fixed thresholds, which are difficult to adapt to water quality fluctuations, leading to over-aeration (increased energy consumption) or insufficient DO (decreased denitrification efficiency).

[0003] One-sidedness in carbon emission accounting: Existing carbon tracking mostly focuses on direct emissions (CH4, N20), ignores the full-life cycle impact of indirect emissions (such as chemical agent production, purchased electricity), and the compensation strategy relies on a single energy source (such as only photovoltaic), without achieving multi-source collaborative optimization.

[0004] Lag in regulation strategies: Static models based on historical data cannot predict the coupled impact of external variables such as meteorological and power grid factors on carbon emissions. Process adjustment and compensation decisions often lag for several hours, making it difficult to achieve minute-level dynamic carbon neutrality rate tracking.

[0005] Lack of credibility and traceability: Carbon offset amounts rely on manual records or centralized storage, there is a risk of tampering, and it cannot meet the rigid requirements of the carbon trading market for data auditability.

[0006] The above problems make it difficult for the existing technology to support the real-time and accurate regulation of sewage treatment plants under complex working conditions, restricting the achievement of carbon neutrality goals.

[0007] Therefore, the existing technology still needs to be further developed. Summary of the Invention

[0008] The purpose of the present invention is to overcome the above technical deficiencies, and provide a carbon neutrality regulation method and system for sewage treatment plants to solve the problems existing in the existing technology.

[0009] To achieve the above technical objectives, according to the first aspect of the present invention, a carbon neutrality regulation method for sewage treatment plants is provided, including: S100. Real-time monitor the operation parameters of the sewage treatment plant through multi-source sensors, including influent water quality, aeration volume, sludge concentration, energy consumption data, and greenhouse gas emissions; S200. Preprocess the monitored data based on edge computing nodes, eliminate outliers, and generate a standardized data stream; S300. Input the standardized data into the artificial intelligence prediction model to predict the energy consumption and carbon emission trends of sewage treatment within the next 24 hours; S400. Dynamically adjust the sewage treatment process parameters according to the prediction results, including optimizing the aeration volume, regulating the sludge return ratio, and matching the output of renewable energy power generation equipment; S500. Calculate the real-time carbon neutralization rate after process adjustment through the carbon footprint full life cycle tracking module; S600. If the carbon neutralization rate is lower than the preset threshold, trigger a multi-objective optimization algorithm to generate a compensation strategy, and preferentially call the in-plant photovoltaic energy storage system or the external green power trading interface.

[0010] Specifically, the pretreatment in step S200 includes: Denoise the sensor data using the sliding time window algorithm and fill in the missing values through the long short-term memory network.

[0011] Specifically, the artificial intelligence prediction model is a spatio-temporal graph convolutional network integrating the attention mechanism, and its inputs include historical energy consumption data, weather forecast information, and grid carbon emission factors.

[0012] Specifically, the dynamic adjustment includes: According to the spatio-temporal distribution characteristics of the dissolved oxygen concentration in the aeration tank, use a fuzzy PID controller to achieve precise regulation of the partitioned aeration volume.

[0013] Specifically, the renewable energy power generation equipment includes: A coordinated scheduling system for photovoltaic power generation units, biogas combined heat and power units, and micro hydropower turbines.

[0014] Specifically, the carbon footprint tracking module uses the life cycle assessment method to cover the direct and indirect emissions of the entire sewage treatment process, including the embodied carbon emissions of chemical agent production and transportation.

[0015] Specifically, the multi-objective optimization algorithm is an improved NSGA-III algorithm, and the objective function simultaneously minimizes the operating cost, carbon emissions, and the risk of effluent water quality exceeding the standard.

[0016] Specifically, the method further includes: Construct a virtual mirror of the sewage treatment plant through the digital twin platform, compare the operation deviation between the physical system and the virtual model in real time, and update the prediction model parameters based on the deviation value.

[0017] Specifically, the execution effect of the compensation strategy is recorded by the blockchain evidence storage module to generate an immutable carbon neutralization performance certificate.

[0018] According to the second aspect of the present invention, there is provided a carbon neutralization regulation system for a sewage treatment plant, including: An acquisition module, including multi-source sensors, is used to monitor the operating parameters of the sewage treatment plant in real time, including influent water quality, aeration volume, sludge concentration, energy consumption data, and greenhouse gas emissions; A control module is used to preprocess the monitoring data based on edge computing nodes, eliminate outliers and generate a standardized data stream; input the standardized data into an artificial intelligence prediction model to predict the energy consumption and carbon emission trends of sewage treatment within the next 24 hours; dynamically adjust the sewage treatment process parameters according to the prediction results, including aeration volume optimization, sludge return ratio regulation, and output matching of renewable energy power generation equipment; calculate the real-time carbon neutralization rate after process adjustment through a carbon footprint full-life cycle tracking module. If the carbon neutralization rate is lower than the preset threshold, trigger a multi-objective optimization algorithm to generate a compensation strategy, and preferentially call the in-plant photovoltaic energy storage system or external green power trading interface.

[0019] Beneficial effects: The present invention significantly improves the intelligence and reliability of carbon neutralization regulation in sewage treatment plants through systematic innovation: Multi-source perception and edge collaboration: The multi-dimensional sensor network captures the dynamic characteristics of water quality, energy consumption, and gas emissions in real time. Combined with the efficient preprocessing of edge computing nodes, data noise is eliminated and information integrity is ensured, providing high-precision input for subsequent models.

[0020] Space-time coupling prediction ability: The spatio-temporal graph convolutional network based on the attention mechanism integrates the process topology and external variables (such as meteorology, power grid factors) to accurately analyze the spatio-temporal evolution law of carbon emissions, breaking through the bottleneck of traditional models in representing complex correlation relationships.

[0021] Adaptive dynamic regulation: The fuzzy PID controller is used to achieve refined zoning regulation of the aeration volume, adapt to water quality fluctuations and equipment state changes, optimize energy consumption distribution while ensuring nitrogen removal efficiency, and significantly improve process stability.

[0022] Full-life cycle carbon tracking: A full-process accounting system covering direct emissions, indirect emissions, and carbon offsets accurately quantifies the collaborative emission reduction effect of process adjustment and renewable energy scheduling, supporting scientific decision-making.

[0023] Multi-objective collaborative optimization: The improved optimization algorithm balances operating costs, environmental risks, and carbon neutralization goals, dynamically generates a multi-energy collaborative scheduling strategy, and improves the overall energy efficiency and anti-interference ability of the system.

[0024] Trusted traceability and self-calibration mechanism: The digital twin platform realizes online update of model parameters through virtual mirrors, ensuring a high degree of consistency between prediction and the physical system; blockchain technology solidifies carbon offset data to build a traceable and tamper-proof trust system.

[0025] The present invention constructs a closed-loop control link of "perception - prediction - regulation - verification", providing a complete technical framework for the sewage treatment plant to achieve dynamic carbon neutrality. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a schematic flowchart of the carbon neutrality regulation method for a sewage treatment plant provided in a specific embodiment of the present invention; Figure 2 is a schematic diagram of the system composition of the carbon neutrality regulation system for a sewage treatment plant provided in a specific embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Based on the embodiments in this application, other similar embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application. In addition, the directional terms mentioned in the following embodiments, such as "upper", "lower", "left", "right", etc., are only references to the directions in the drawings. Therefore, the directional terms used are for illustration rather than limitation of the present invention.

[0028] The present invention will be further described below in conjunction with the drawings and preferred embodiments.

[0029] Please refer to Figure 1 , the present invention provides a carbon neutrality regulation method for a sewage treatment plant, including: S100. Real-time monitor the operation parameters of the sewage treatment plant through multi-source sensors, including influent water quality, aeration volume, sludge concentration, energy consumption data and greenhouse gas emissions.

[0030] Specifically, the multi-source sensors are composed of Internet of Things sensors deployed in the grille chamber, aeration tank, secondary sedimentation tank and outlet, and real-time collect water quality, gas and equipment status data.

[0031] It should be further noted that regarding the layout of the multi-source sensors, the design solution of the present invention is as follows: COD, ammonia nitrogen and pH value sensors (accuracy ±0.1 mg / L) are deployed at the inlet.

[0032] Dissolved oxygen (DO) sensors (range 0 - 15 mg / L) are arranged at intervals of 5 m in the aeration tank. It can be understood that based on the typical size of the aeration tank (length 50 - 100 m) and the experimental data of the oxygen diffusion gradient, a 5 m spacing can ensure that the spatial resolution of the dissolved oxygen concentration field ≤ 10% error, covering the oxygen transfer differences at the head, middle and end of the tank body.

[0033] An ultrasonic sludge concentration meter (resolution 0.1%) is installed in the sludge return pipeline; the sampling frequency of the sludge concentration meter is preferably 1 time / minute. It is understandable that the response time constant of the sludge return system is 5-10 minutes, and 1Hz sampling can capture transient fluctuations (such as sudden sludge expansion) while avoiding high-frequency noise interference.

[0034] S200: Preprocess the monitoring data based on the edge computing node, remove outliers and generate a standardized data stream.

[0035] Specifically, the preprocessing in step S200 includes: The sensor data is denoised using a sliding time window algorithm, and missing values ​​are filled using a long short-term memory network.

[0036] It should be further explained that, regarding step S200, the solution designed by the present invention includes: 1. The length of the sliding time window is set to 60 seconds. When the standard deviation of the data in the window exceeds 3 times the historical data, it is judged as an outlier. It is understandable that the water flow change cycle of a sewage treatment plant is about 30-120 seconds (such as pump start-stop impact). The 60-second window can cover a complete fluctuation cycle. When the standard deviation threshold is set to 3 times the historical value, the detection sensitivity for sudden water quality impacts (such as industrial wastewater mixing) reaches 95%.

[0037] 2. LSTM (Long Short-Term Memory Network) Missing Value Filling Model: The network structure is: input layer (30 time steps), LSTM layer (128 neurons, tanh activation), output layer; Training data: Use the normal operating data of the sewage plant for one year, 80% as the training set and 20% as the validation set; Hyperparameters: learning rate 0.001, batch size 32, iteration 200 cycles; Filling effect: When the number of missing consecutive data points does not exceed 3 sampling points (15 minutes), the error rate is <2%.

[0038] It is understandable that regarding the number of neurons (128): after grid search verification (64 / 128 / 256 comparison), the 128-layer has the smallest error difference between the training set (RMSE=0.12) and the validation set (RMSE=0.15), indicating that the risk of overfitting is controllable.

[0039] It is understandable that regarding the training cycle (200 times): the loss function curve enters a plateau period at 150-200 cycles, and continued training causes the validation set error to increase by 0.3%.

[0040] It is understandable that regarding the learning rate (0.001): when using the Adam optimizer, 0.001 is the recommended initial value for the NVIDIA GPU computing library for LSTM, which can balance the convergence speed and stability.

[0041] S300. Input the standardized data into the artificial intelligence prediction model to predict the energy consumption and carbon emission trends of sewage treatment within the next 24 hours.

[0042] Specifically, the artificial intelligence prediction model is a spatio-temporal graph convolutional network integrating an attention mechanism, and its input includes historical energy consumption data, weather forecast information, and grid carbon emission factors.

[0043] It should be further noted that the present invention designs the following spatio-temporal graph convolutional network (ST-GCN) architecture: 1. Input layer: Time dimension: Historical 24-hour data (sampling interval of 5 minutes); Spatial topology: The sewage treatment plant process units (bar screen tank → aeration tank ← secondary sedimentation tank) are defined as directed graph nodes.

[0044] 2. Spatio-temporal convolution formula: In the formula: : The node feature matrix of the l-th layer; : K sub-matrices divided from the adjacency matrix (K = 3 in this embodiment); : The convolution kernel weight of the k-th sub-graph; : GELU activation function.

[0045] It is understandable that the reason for choosing the time step (24 hours, 5-minute interval) is as follows: The nitrification / denitrification cycle of the sewage treatment process is about 6 - 24 hours, and the 5-minute interval can analyze the DO regulation lag effect (such as the effluent ammonia nitrogen decreases 30 - 40 minutes after the aeration volume changes).

[0046] It is understandable that the reason for choosing the adjacency matrix division (K = 3) is as follows: Due to the mass transfer relationship corresponding to the mainstream process units of the sewage treatment plant (pretreatment → biological treatment → sedimentation), the weight distribution is pretreatment → biological treatment (weight 0.6), biological treatment self-circulation (weight 0.3), and biological treatment → sedimentation (weight 0.1).

[0047] It is understandable that the reason for choosing the GELU activation function is as follows: Compared with ReLU, GELU achieves a better balance between gradient vanishing and non-linear representation ability. After testing, it can reduce the model prediction error by 2.1%.

[0048] 3. Attention mechanism design: Calculation of time attention weights: : They are the state vectors of the current moment and the historical moment respectively.

[0049] : Feature dimension (set to =64 in this embodiment). It can be understood that a 64-dimensional vector can encode the interaction relationships of key process states (such as DO, MLSS, temperature). When it exceeds 128 dimensions, the calculation time increases by 50% while the accuracy only increases by 0.7%.

[0050] Prediction output: Prediction error: The total energy consumption prediction error in the next 24 hours ≤ 5%, and the carbon emission error ≤ 8%; Training data augmentation: Add ±10% Gaussian noise to the influent flow rate to improve the model robustness. It can be understood that the typical error range (±8%-12%) of the influent flow rate sensor is simulated, and the probability that the model prediction error ≤ 5% under noise interference is increased to 92%.

[0051] S400. Dynamically adjust the sewage treatment process parameters according to the prediction results, including aeration volume optimization, sludge return ratio regulation, and output matching of renewable energy power generation equipment.

[0052] Specifically, the dynamic adjustment includes: According to the spatio-temporal distribution characteristics of the dissolved oxygen concentration in the aeration tank, use a fuzzy PID controller to achieve precise regulation of the partition aeration volume.

[0053] Specifically, the renewable energy power generation equipment includes: A coordinated scheduling system for a photovoltaic power generation unit, a biogas combined heat and power unit, and a micro-hydro turbine.

[0054] It should be further noted that the present invention designs the following fuzzy PID controller: Input variable error e(t) = DO set value (preset to 2.0mg / L) - measured value; Fuzzy rule table: 49 rules (7×7) are formulated according to e(t) and its change rate Δe(t); Specifically, regarding the fuzzy rule table, the solution designed by the present invention includes: 1. Definition of input / output variables: Input variable 1: Dissolved oxygen error e(t) = DO set value (2.0 mg / L) - measured DO value; Fuzzy set partition (unit: mg / L): NL (Negative Large): [-5, -3], NM (Negative Medium): [-3, -1], NS (Negative Small): [-1, 0], ZE (Zero): [-0.5, 0.5], PS (Positive Small): [0, 1], PM (Positive Medium): [1, 3], PL (Positive Large): [3, 5].

[0055] Input variable 2: Error change rate Δe(t) = e(t) - e(t - 1); Fuzzy set partition (unit: mg / L / min): NL: [-0.5, -0.3], NM: [-0.3, -0.1], NS: [-0.1, 0], ZE: [-0.05, 0.05], PS: [0, 0.1], PM: [0.1, 0.3], PL: [0.3, 0.5].

[0056] Output variable: Percentage adjustment of aeration volume ΔQ (relative to the reference aeration volume).

[0057] Fuzzy set partition: NL: -20%, NM: -12%, NS: -5%, ZE: 0%, PS: +5%, PM: +12%, PL: +20%.

[0058] 2. The fuzzy rule table designed by the present invention is shown in Table 1: Table 1 Fuzzy rule table 3. Detailed explanation of rule logic: 3.1 Rule design principles: Diagonal symmetry: When the directions of e(t) and Δe(t) are opposite (such as e = PL and Δe = NL), the maximum correction amount (PL or NL) is adopted to quickly eliminate the deviation.

[0059] Steady-state regulation: When e(t) = ZE, if Δe(t) = ZE, maintain the current aeration volume (output ZE); if Δe(t) ≠ ZE, suppress overshoot in advance according to the trend.

[0060] Nonlinear compensation: In the extreme regions of e(t) (such as PL / NL), even if Δe(t) is small, a large adjustment is required to break through the process inertia.

[0061] 3.2 Typical rule examples: Rule 1: (e = PL, Δe = NL), output PL(+20%); Applicable scenario: The measured DO is much lower than the set value (e = PL) and the deviation continues to increase (Δe = NL, that is, the error change rate is negative large).

[0062] Action logic: The aeration volume needs to be increased to the maximum extent to quickly increase the DO concentration and avoid the collapse of nitrification reaction.

[0063] Rule 13: (e = ZE, Δe = PS), the output is NM (-12%); Applicable scenario: DO is close to the set value (e = ZE), but there is an upward trend (Δe = PS, that is, the rate of change of error is a small positive value).

[0064] Action logic: Reduce the aeration volume in advance to prevent energy consumption waste caused by DO overshoot.

[0065] Rule 28: (e = NS, Δe = ZE), the output is NL (-20%); Applicable scenario: DO is slightly higher than the set value (e = NS) and the trend is stable (Δe = ZE).

[0066] Action logic: Although the deviation is small, because it is in the sludge sedimentation sensitive interval, it is necessary to aggressively reduce the aeration volume to avoid mud turning in the secondary sedimentation tank.

[0067] 4. Membership function and defuzzification: 4.1 Membership function of input variable (triangle): Membership function parameters of e(t) (unit: mg / L): NL: [-5, -3, -1]; NM: [-3, -1, 0]; NS: [-1, 0, 1]; ZE: [-0.5, 0, 0.5]; PS: [0, 1, 3]; PM: [1, 3, 5]; PL: [3, 5, 7].

[0068] Note: The interval extension is used to handle out-of-limit values.

[0069] 4.2 The defuzzification of the output variable uses the center of gravity method (COG) to calculate the accurate output value: Activation degree of the i-th rule (take the minimum value of the input membership degree); : Output value of the i-th rule.

[0070] 5. Verification of actual control effect: In the step response test of the aeration tank (DO set value rises from 1.5 to 2.0 mg / L): Overshoot: ≤3% (15 - 20% for traditional PID); Adjustment time: 18 minutes (40 - 50 minutes for traditional PID); Steady - state error: ±0.1 mg / L (meeting the process requirement of effluent ammonia nitrogen < 1 mg / L); Basis for parameter selection of the rule table: 7 - level division (not 5 or 9 levels): 7 fuzzy sets can cover the non - linear characteristics of the sewage treatment process (such as nitrification / denitrification thresholds), and at the same time avoid rule explosion (49 vs 25 or 81 rules).

[0071] Output amplitude (±20%): Based on the maximum adjustment ability of the variable - frequency fan (conventional models allow ±25% flow adjustment), a 5% safety margin is reserved.

[0072] ZE interval (±0.5 mg / L): Matched with the DO sensor accuracy (±0.1 mg / L), the influence of measurement noise is limited to the non - action area.

[0073] Asymmetric rule distribution: When e(t) is negative (DO is too high), the rules are more aggressive (e.g., rule 28 outputs NL), because too high DO is likely to cause sludge bulking and needs to be quickly suppressed.

[0074] Example rule: If e(t)=Positive Large and Δe(t)=Negative Medium, the aeration volume increases by 15%.

[0075] Quantization parameters: Proportional coefficient Kp = 0.8 (for fast response); Integral time Ti = 120 s (to suppress steady - state error); Derivative time Td = 20 s (to suppress overshoot).

[0076] It can be understood that the reasons for parameter selection of the fuzzy PID controller: DO set value (2.0 mg / L): Based on the research of nitrifying bacteria activity, when DO < 1.5 mg / L, the ammonia nitrogen removal rate decreases by 30%, when DO > 2.5 mg / L, the energy consumption increases sharply and sludge disintegration may occur, and 2.0 mg / L is a typical compromise value.

[0077] Proportional coefficient (Kp = 0.8): Through step - response testing, Kp = 0.8 can make the overshoot of the system ≤5% (15% overshoot for traditional PID), and the adjustment time is shortened to 20 minutes.

[0078] Integral time (Ti = 120 s): The integral action is used to eliminate the steady-state error of the aeration system (such as the attenuation of fan efficiency). 120 s corresponds to 1 / 120 of the sludge retention time (SRT) to avoid integral saturation.

[0079] Derivative time (Td = 20 s): It suppresses the DO oscillation caused by the sudden change of the influent load. 20 s is twice the response time of the dissolved oxygen sensor (10 s) to effectively filter out high-frequency noise.

[0080] Optimization formula for aeration volume: : Area weight of the i-th partition of the aeration tank (Σ = 1).

[0081] It should be noted here that the preferred weight in the present invention = 0.5. The reason for the selection is that the BOD load at the head end of the aeration tank accounts for 60% - 70% of the total, and 50% of the aeration volume needs to be allocated to ensure sufficient carbon oxidation; the weight at the end = 0.2 is used to maintain the nitrification reaction.

[0082] Implementation effect: Compared with the traditional PID, the energy consumption is reduced by 12% - 18%.

[0083] S500. Calculate the real-time carbon neutralization rate after process adjustment through the carbon footprint full-life cycle tracking module.

[0084] Specifically, the carbon footprint tracking module adopts the life cycle assessment method, covering the direct emissions and indirect emissions of the whole process of sewage treatment, including the embodied carbon emissions in the production and transportation of chemical agents.

[0085] It should be further noted that regarding carbon footprint tracking and compensation, the solution designed in the present invention includes: Design the life cycle assessment (LCA) calculation formula: ① Design the total carbon emission formula: Among them: : Total carbon emissions of the sewage treatment plant over the full life cycle (unit: kgCOze), that is, the net carbon emissions after direct emissions, indirect emissions and carbon offset measures.

[0086] : Direct carbon emissions, from the greenhouse gases directly released during sewage treatment (CH4, N20, etc.); : Indirect carbon emissions, covering the embodied carbon emissions in related links such as purchased energy, production and transportation of chemical agents; Carbon offset: The amount of carbon emissions offset through renewable energy sources (such as photovoltaic and biogas power generation) or carbon sink projects, with a negative value (reducing net emissions).

[0087] ② Design the direct carbon emission formula: Where: : Methane emissions (unit: kg), mainly from the decomposition of organic matter in oxygen-deficient links such as anaerobic digesters and sludge storage ponds; : Methane global warming potential value (IPCC AR6 standard is 27.9), indicating that the greenhouse effect of 1 kg of CH4 is equivalent to 27.9 kg of CO2; : Nitrous oxide emissions (unit: kg), mainly from by-products of the nitrogen removal process (such as nitrification / denitrification); : Nitrous oxide global warming potential value (IPCC AR6 standard is 273), reflecting the long lifespan (about 121 years) and strong radiative forcing effect of N2O.

[0088] The GWP value adopts the IPCC AR6 standard (CH4 = 27.9, N2O = 273).

[0089] It can be understood that the GWP of CH4 = 27.9 (IPCC AR6): Using the data from the latest AR6 assessment report (replacing 28 - 36 of AR5), reflecting the latest research results on the shortened residence time of methane in the atmosphere.

[0090] It can be understood that the GWP of N2O = 273: The radiative forcing effect of N2O dominates in sewage treatment emissions. Using 273 can avoid underestimating emissions during the nitrogen removal process (traditional values 265 - 298).

[0091] ③ Design the indirect carbon emission formula: Where: : Purchased grid electricity (unit: kWh), covering the energy consumption of equipment such as water pumps and aeration blowers; : Grid carbon emission factor (example value 0.55 ), representing the embodied carbon emissions per 1 kWh of electricity consumed; Data source: Using regional real-time factors (such as 0.55 for China Southern Power Grid and 0.75 for Northwest Power Grid) to reflect the differences in different energy structures (proportion of coal-fired power). It can be understood that based on dynamic design, this invention uses time-of-use factors (such as a high proportion of coal-fired power during peak hours, EFgrid can reach 0.8; when hydropower is mainly used at night, EFgrid≈0.2) to guide the sewage treatment plant to concentrate electricity consumption during low-carbon periods.

[0092] : Chemical agent dosage (unit: kg), such as polyaluminum chloride (PAC), carbon source (sodium acetate), etc.; : Chemical agent emission factor (example value PAC = 1.2 ), covering the whole-process carbon emissions of chemical agent production, transportation, and packaging, specifically including: Bauxite mining (0.3 ); Hydrochloric acid synthesis (0.5 ); Transportation (0.2 ); Packaging (0.2 ).

[0093] Data source: Based on the Ecoinvent database, for example: PAC (polyaluminum chloride): 1.2 (including bauxite mining and hydrochloric acid synthesis energy consumption); Sodium acetate: 2.8 (including fermentation production and distillation purification carbon emissions).

[0094] The grid emission factor EF_grid uses regional real-time data (example value: 0.55 ); The chemical agent emission factor EF_chem is based on the Ecoinvent database (such as PAC = 1.2 ).

[0095] Application examples are as follows: Data of a certain sewage treatment plant: = 50 kg / d, = 5 kg / d• = 1000 kWh / d, = 200 kg / d• = -300 (offset by photovoltaic power generation).

[0096] Calculation: Direct emissions: Indirect emissions: Total emissions: ④ Design the calculation formula for the real-time carbon neutralization rate: S600. If the carbon neutralization rate is lower than the preset threshold, trigger the multi-objective optimization algorithm to generate a compensation strategy, and preferentially call the in-plant photovoltaic energy storage system or the external green power trading interface.

[0097] Specifically, the multi-objective optimization algorithm is the improved NSGA-III algorithm, and the objective function simultaneously minimizes the operating cost, carbon emissions, and the risk of effluent water quality exceeding the standard.

[0098] Specifically, if the real-time η carbon neutralization < 95%, trigger multi-level compensation, including: The first level: Call the in-plant photovoltaic energy storage (when SOC ≥ 30%, the maximum offset = energy storage capacity × 0.85 ) The second level: Increase the load of the biogas generator set to 85% (it is necessary to monitor NOx < 50 ppm); The third level: Purchase green power through the blockchain API (select the time period when EF_grid < 0.1); Weight allocation: Photovoltaic: Biogas: Green power = 6:3:1 (optimized according to economy).

[0099] The following is demonstrated through a specific example: Scenario: After optimizing the aeration volume of a sewage treatment plant, it is necessary to calculate the real-time carbon neutralization rate; Original data (benchmark before adjustment): , , ; Benchmark carbon emissions .

[0100] Data after process adjustment: Reduced to (improvement in aeration efficiency), (10% power saving); (new photovoltaic panels added).

[0101] Calculation: Net emissions ; Carbon neutralization rate (excessive neutralization); Conclusion: Process adjustment has increased the carbon neutrality rate from 75% (150 / 200) to 105%. It is necessary to reduce the purchase of green electricity to optimize costs.

[0102] Specifically, it needs to be further explained that regarding the trigger threshold of the compensation strategy: It can be understood that due to considering the monitoring error (±3%) and the carbon offset cost, the 95% threshold can balance the environmental benefits and economy, which is higher than the EU carbon trading market compliance standard (93%). In the present invention, the carbon neutrality rate threshold is preferably set at 95% (compensation is triggered if it is lower).

[0103] Compensation priority: On-site photovoltaic energy storage system (discharging when SOC≥30%). It can be understood that based on historical extreme weather data (continuous 3 days of rain), 30% SOC can maintain the operation of key equipment (blower, reflux pump) for 48 hours.

[0104] The load rate of the biogas generator set is increased to 85%-90%. It can be understood that this load range corresponds to the best efficiency point of the biogas engine (the thermoelectric ratio is 1.2-1.5). When the load > 90%, the risk of NOx emission exceeding the standard increases by 50%; External green electricity purchase (selecting the time period when the real-time EFgrid≤0.1kgCO2e / kWh).

[0105] Specifically, the method further includes: Constructing a virtual mirror of the sewage treatment plant through a digital twin platform, comparing the operation deviation between the physical system and the virtual model in real time, and updating the prediction model parameters based on the deviation value.

[0106] It needs to be further explained that the present invention designs the following virtual mirror construction process: 1. Data synchronization layer: Hardware: Deploy an edge gateway (NVIDIA Jetson AGX Xavier) and an OPC UA protocol server, and synchronize the physical system data (DO, MLSS, energy consumption, etc.) every 5 seconds.

[0107] Data preprocessing: Filter noise using a sliding window (60 seconds), standardize the data format (JSON Schema), and then transmit it to the cloud twin engine.

[0108] 2. Model architecture: Hybrid modeling: Physical model: Based on the activated sludge process (ASM1), construct a mass balance equation to describe the dynamic changes of COD, ammonia nitrogen, and DO.

[0109] (X: sludge concentration, μ: specific growth rate, Q: sludge discharge flow rate); Data-driven model: Stacked LSTM network (64 neurons in the hidden layer), compensating for unmodeled dynamics (such as the impact of sudden changes in water temperature).

[0110] 3. Real-time deviation calculation: Indicator: Using the normalized root mean square error (NRMSE) to compare key parameters (DO, effluent ammonia nitrogen): y_i: Measured value of the physical system, _i: Output value of the virtual model.

[0111] Threshold setting: When NRMSE > 15%, it is determined as a significant deviation (triggering model update).

[0112] 4. Parameter update mechanism: Online learning: When NRMSE exceeds the threshold, start the Bayesian optimization algorithm to adjust the LSTM weights, preferentially updating neurons related to the deviation (such as the DO prediction module).

[0113] Update frequency: At most once every 10 minutes to avoid high-frequency calculation overload.

[0114] Specifically, the execution effect of the compensation strategy is recorded by the blockchain evidence storage module, generating an immutable carbon neutrality performance certificate.

[0115] 5. Implementation case: Scenario: The measured value of DO in the aeration tank is continuously lower than the model prediction (NRMSE = 18%).

[0116] Action: The Bayesian optimizer adjusts the learning rate of the DO prediction branch of LSTM from 0.001 to 0.002.

[0117] After the update, NRMSE drops to 8%, and the model realigns.

[0118] It should be further noted that the present invention designs the following virtual mirror construction process: 1. Blockchain architecture: Type: Consortium blockchain (Hyperledger Fabric 2.4), and the participating nodes include wastewater treatment plants, environmental protection bureaus, and third-party auditing agencies.

[0119] 2. Node roles: Wastewater treatment plant node: Submit compensation data (photovoltaic power generation, biogas utilization).

[0120] Auditing node: Verify the authenticity of the data (based on the digital signature of the sensor).

[0121] Supervision Node: Issue vouchers and store the evidence on the blockchain.

[0122] 2.1 Data Upload Process to the Blockchain: Data Encapsulation: Fields: Timestamp, Photovoltaic Power Generation (kWh), Biogas CH4 Volume (m³), Hash Value (SHA-256).

[0123] Signature: Sign the data packet using the in-plant private key (RSA-2048) to ensure the credibility of the source.

[0124] 2.2 Smart Contract Logic: Voucher Generation (Chaincode Example): func generateCarbonCredits(stub shim.ChaincodeStubInterface, args []string) { / / Input: Photovoltaic power generation solar, biogas volume biogas / / Calculate the carbon offset offset := solar * 0.85 + biogas * 0.67 * 27.9 / / Generate voucher ID: Timestamp + first 8 digits of the hash certificateID := timestamp + SHA256(solar|biogas)[0:8] / / Write to the blockchain stub.PutState(certificateID, offset) } Verification Logic: Check if the sensor ID is in the registration list and if the data hash matches the historical record.

[0125] 2.3 Carbon Neutrality Performance Voucher: The voucher structure is as follows: { "certificateID": "20231001-3A5F", "timestamp": "2023-10-01T14:30:00Z", "offsetAmount": 150.2, / / Unit: kgCO2e "source": {"solar": 120, "biogas": 30}, "signature": "E2C3A5...", "auditor": "EPB_Shanghai" } Query interface: Provide a REST API for third-party verification. Input the voucher ID to return all the deposited evidence data.

[0126] It should be noted here that the preferred parameter values and the basis are shown in Table 2: Table 2 Basis of Preferred Parameter Values It can be understood that the time from voucher generation to verifiability in blockchain evidence deposit < 10 seconds, which supports real-time auditing by the environmental protection bureau and avoids Greenwashing. Through hybrid modeling and online learning, the present invention realizes self-calibration of the virtual model to adapt to water quality fluctuations and equipment aging. The consortium chain architecture designed by the present invention takes into account both efficiency and regulatory compliance. The hash chain + digital signature ensures the immutability of data, meeting the requirements of the carbon trading market for data traceability.

[0127] Please refer to Figure 2 , the present invention provides another embodiment. The present embodiment provides a carbon neutrality regulation system for a sewage treatment plant, and the carbon neutrality regulation system for a sewage treatment plant includes: An acquisition module 100, including multi-source sensors, for real-time monitoring of the operating parameters of the sewage treatment plant, including influent water quality, aeration volume, sludge concentration, energy consumption data, and greenhouse gas emissions; A control module 200, for preprocessing the monitoring data based on edge computing nodes, removing outliers and generating a standardized data stream; for inputting the standardized data into an artificial intelligence prediction model to predict the energy consumption and carbon emission trends of sewage treatment within the next 24 hours; for dynamically adjusting the sewage treatment process parameters according to the prediction results, including aeration volume optimization, sludge return ratio regulation, and output matching of renewable energy power generation equipment; for calculating the real-time carbon neutrality rate after process adjustment through a carbon footprint full-life cycle tracking module, and if the carbon neutrality rate is lower than a preset threshold, triggering a multi-objective optimization algorithm to generate a compensation strategy, and preferentially calling the in-plant photovoltaic energy storage system or an external green power trading interface.

[0128] In a preferred embodiment, the present application also provides an electronic device, and the electronic device includes: A memory; and a processor, wherein computer-readable instructions are stored on the memory, and when the computer-readable instructions are executed by the processor, the carbon-neutral regulation method for a sewage treatment plant is implemented. The computer device can be broadly a server, a terminal, or any other electronic device with necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, a memory, a network interface, a communication interface, etc. connected through a system bus. The processor of the computer device can be used to provide necessary computing, processing, and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. An operating system, a computer program, etc. may be stored in or on the non-volatile storage medium. The internal memory can provide an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface and the communication interface of the computer device can be used to connect and communicate with external devices through a network. When the computer program is executed by the processor, the steps of the method of the present invention are executed.

[0129] The present invention can be implemented as a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method of the embodiments of the present invention are caused to be executed. In one embodiment, the computer program is distributed on a plurality of network-coupled computer devices or processors, so that the computer program is stored, accessed, and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, can be executed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations can be executed by one or more computer devices or processors, and one or more other method steps / operations can be executed by one or more other computer devices or processors. One or more computer devices or processors can execute a single method step / operation, or execute two or more method steps / operations.

[0130] Those of ordinary skill in the art can understand that the method steps of the present invention can be completed by a computer program instructing relevant hardware such as a computer device or a processor, and the computer program can be stored in a non-transitory computer-readable storage medium, and when the computer program is executed, the steps of the present invention are caused to be executed. Depending on the situation, any reference to a memory, a storage, a database, or other medium herein may include non-volatile and / or volatile memories. Examples of non-volatile memories include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk, etc. Examples of volatile memories include random access memory (RAM), external cache memory, etc.

[0131] The various technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification, as long as there is no contradiction in such a combination.

[0132] The specific embodiments of the present invention described above do not constitute a limitation on the protection scope of the present invention. Any other corresponding changes and deformations made according to the technical concept of the present invention should be included within the protection scope of the claims of the present invention.

Claims

1. A carbon neutral regulation method for sewage treatment plants, characterized in that It includes the following steps: S100. Real-time monitor the operation parameters of the sewage treatment plant through multi-source sensors, including influent water quality, aeration volume, sludge concentration, energy consumption data and greenhouse gas emissions; S200. Preprocess the monitored data based on the edge computing node, remove outliers and generate a standardized data stream; S300. Input the standardized data into the artificial intelligence prediction model to predict the energy consumption and carbon emission trends of sewage treatment within the next 24 hours; S400. Dynamically adjust the sewage treatment process parameters according to the prediction results, including optimizing the aeration volume, regulating the sludge return ratio and matching the output of renewable energy power generation equipment; S500. Calculate the real-time carbon neutralization rate after process adjustment through the carbon footprint full life cycle tracking module; S600. If the carbon neutralization rate is lower than the preset threshold, trigger a multi-objective optimization algorithm to generate a compensation strategy, and preferentially call the in-plant photovoltaic energy storage system or the external green power trading interface.

2. The carbon neutrality regulation method for sewage treatment plants according to claim 1, wherein In the step S200, the preprocessing includes: Use the sliding time window algorithm to denoise the sensor data and fill in the missing values through the long short-term memory network.

3. The carbon neutrality regulation method for sewage treatment plants according to claim 1, wherein, The artificial intelligence prediction model is a spatio-temporal graph convolutional network integrating an attention mechanism, and its inputs include historical energy consumption data, weather forecast information and grid carbon emission factors.

4. The carbon neutrality regulation method for sewage treatment plants according to claim 1, characterized in that The dynamic adjustment includes: According to the spatio-temporal distribution characteristics of the dissolved oxygen concentration in the aeration tank, use a fuzzy PID controller to achieve precise regulation of the partition aeration volume.

5. The carbon neutrality regulation method for sewage treatment plants according to claim 1, wherein The renewable energy power generation equipment includes: A coordinated scheduling system for photovoltaic power generation units, biogas combined heat and power units and micro hydropower turbines.

6. The carbon neutrality regulation method for sewage treatment plants according to claim 1, characterized in that The carbon footprint tracking module uses the life cycle assessment method to cover the direct and indirect emissions of the entire sewage treatment process, including the embodied carbon emissions of chemical agent production and transportation.

7. The carbon neutrality regulation method for sewage treatment plants according to claim 1, wherein The multi-objective optimization algorithm is an improved NSGA-III algorithm, and the objective function simultaneously minimizes the operating cost, carbon emissions and the risk of effluent water quality exceeding the standard.

8. The carbon neutrality regulation method for sewage treatment plants according to any one of claims 1-7, characterized in that The method further includes: Construct a virtual mirror of the sewage treatment plant through the digital twin platform, compare the operation deviation between the physical system and the virtual model in real time, and update the prediction model parameters based on the deviation value.

9. The carbon neutrality regulation method for sewage treatment plants according to claim 7, characterized in that The execution effect of the compensation strategy is recorded by the blockchain evidence storage module to generate an immutable carbon neutralization performance certificate.

10. A carbon neutral regulation system for sewage treatment plants, characterized in that, It includes: An acquisition module, including multi-source sensors, for real-time monitoring of the operation parameters of the sewage treatment plant, including influent water quality, aeration volume, sludge concentration, energy consumption data and greenhouse gas emissions; A control module, for preprocessing the monitored data based on the edge computing node, removing outliers and generating a standardized data stream; For inputting the standardized data into the artificial intelligence prediction model to predict the energy consumption and carbon emission trends of sewage treatment within the next 24 hours; For dynamically adjusting the sewage treatment process parameters according to the prediction results, including optimizing the aeration volume, regulating the sludge return ratio and matching the output of renewable energy power generation equipment; For calculating the real-time carbon neutralization rate after process adjustment through the carbon footprint full life cycle tracking module, and if the carbon neutralization rate is lower than the preset threshold, triggering a multi-objective optimization algorithm to generate a compensation strategy, and preferentially calling the in-plant photovoltaic energy storage system or the external green power trading interface.

Images