Sewage treatment intelligent aeration control method and system based on real-time carbon emission feedback

Abstract

The invention discloses a sewage treatment intelligent aeration control method and system based on real-time carbon emission feedback. The method comprises the following steps: acquiring an inflow water quality parameter, a process state parameter, an inflow water flow, aeration equipment power consumption and an external agent dosage of a sewage treatment system in real time; calculating real-time carbon emission intensity per ton of water by combining a preset carbon emission factor based on the power consumption of the aeration equipment and the dosage of the external medicament; inputting the inlet water quality parameter and the process state parameter into a pre-trained Transform time sequence prediction model, and outputting a theoretical oxygen demand in a future set time window; calculating a theoretical gas flow set value according to the theoretical oxygen demand; optimizing the gas flow set value based on the theoretical gas flow set value, the real-time carbon emission intensity per ton of water and the factory carbon emission standard; and the optimized final gas flow set value serves as a set point, and the opening degree of the electric adjusting valve is adjusted through the flow closed-loop controller. According to the invention, accurate regulation and control of the aeration process are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wastewater treatment process control and industrial artificial intelligence, and particularly relates to a wastewater treatment intelligent aeration control method and system based on real-time carbon emission feedback. BACKGROUND

[0002] In the activated sludge process of wastewater treatment, the aeration process of the aerobic biochemical tank is the highest energy consumption link, accounting for about 50%-70% of the total energy consumption of the whole plant. The goal of aeration is to provide a suitable amount of dissolved oxygen to microorganisms to ensure the smooth progress of biochemical reactions. At present, most wastewater treatment plants use simple PID feedback control to adjust the blower or valve according to the fixed dissolved oxygen set value.

[0003] In the activated sludge process of wastewater treatment, the aeration system is a key link for microorganisms to degrade pollutants and provides oxygen, and its energy consumption accounts for 50%-70% of the total energy consumption of the whole plant, which is the main source of carbon emissions of wastewater treatment plants. At present, most wastewater treatment plants use PID control strategy based on fixed dissolved oxygen set value, which has obvious limitations.

[0004] Firstly, the fixed dissolved oxygen set value cannot adapt to the dynamic changes of the influent load, resulting in either insufficient aeration affecting the treatment effect or excessive aeration causing energy waste. Secondly, the traditional control method only focuses on energy consumption indicators and cannot directly respond to the carbon emission control target of the whole plant. More importantly, the existing method lacks the predictive consideration of the risk of effluent water quality caused by improper control and the implicit carbon emissions it causes.

[0005] With the deepening of the national strategy, wastewater treatment plants are facing urgent carbon emission reduction pressure. Although some researches have tried to introduce feedforward control or simple machine learning models to improve control effect, these methods have shortcomings in capturing complex spatiotemporal dependencies among multiple variables and have failed to establish a direct link from control decisions to carbon emissions.

[0006] Therefore, the present application is proposed. SUMMARY

[0007] The technical problem to be solved by the present application is that the existing method has shortcomings in capturing complex spatiotemporal dependencies among multiple variables and has failed to establish a direct link from control decisions to carbon emissions, which cannot achieve precise regulation and control of the aeration process. The present application aims to provide a wastewater treatment intelligent aeration control method and system based on real-time carbon emission feedback. The present application directly links the control of aeration quantity to the carbon emission intensity standard of the plant, and through real-time carbon accounting and intelligent optimization, it realizes precise regulation and control of the aeration process, ensuring that the operation process meets the process requirements while meeting the carbon emission target.

[0008] The present application is achieved by the following technical solutions:

[0009] In a first aspect, the present application provides a sewage treatment intelligent aeration control method based on real-time carbon emission feedback, which comprises:

[0010] Real-time multi-element parameters of the sewage treatment system are obtained to form a multi-element time series data set; the multi-element parameters include influent water quality parameters, process state parameters, influent flow, aeration equipment power consumption, and external reagent dosage;

[0011] Based on the aeration equipment power consumption and the external reagent dosage, the real-time ton of water carbon emission intensity is calculated in combination with a preset carbon emission factor;

[0012] The influent water quality parameters and the process state parameters are input into a pre-trained Transformer time series prediction model, and the theoretical oxygen demand in a future set time window is output; and the theoretical gas flow set value is calculated according to the theoretical oxygen demand;

[0013] Based on the theoretical gas flow set value, the real-time ton of water carbon emission intensity, and the factory carbon emission standard, the gas flow set value is optimized to obtain a final gas flow set value;

[0014] The final gas flow set value is taken as a set point, and the opening of the electric regulating valve is adjusted by a flow closed-loop controller to realize precise aeration control.

[0015] Further, based on the aeration equipment power consumption and the external reagent dosage, the real-time ton of water carbon emission intensity is calculated in combination with a preset carbon emission factor, which comprises:

[0016] Based on the aeration equipment power consumption and the external reagent dosage, the total carbon emission of the sewage treatment system is calculated in real time in combination with a preset carbon emission factor;

[0017] The real-time ton of water carbon emission intensity is calculated according to the total carbon emission and the influent flow.

[0018] Further, the calculation formula of the real-time ton of water carbon emission intensity is:

[0019] Real-time ton of water carbon emission intensity = total carbon emission / influent flow = (direct carbon emission + indirect carbon emission) / influent flow;

[0020] Direct carbon emission = real-time power of the fan × local power grid carbon emission factor;

[0021] Indirect carbon emission = instantaneous dosage of the carbon source × sodium acetate implicit carbon factor.

[0022] Further, based on the theoretical gas flow set value, the real-time ton of water carbon emission intensity, and the factory carbon emission intensity standard, the gas flow set value is optimized to obtain a final gas flow set value, which comprises:

[0023] Based on the theoretical gas flow set value, within a predefined process safety range, the optimization is solved to minimize the real-time ton of water carbon emission intensity or to meet the factory carbon emission intensity standard value, and the final gas flow set value with optimal carbon emission is output.

[0024] Further, the optimization is solved by evaluating the predicted carbon emissions corresponding to different candidate gas flow set values; the predicted carbon emissions are the sum of the predicted energy consumption carbon emissions and the predicted reagent addition carbon emissions due to the effluent risk under the candidate set value;

[0025] Wherein, the effluent risk is predicted by an auxiliary output head of the Transformer time series prediction model, which outputs the probability of exceeding the effluent quality in the future set time window.

[0026] Further, the predefined process safety range is determined in advance based on historical operation data, mechanism model simulation and expert experience, and is used to limit the allowed floating interval of the final gas flow set value relative to the theoretical gas flow set value.

[0027] Further, the gas flow set value optimization is realized by a model predictive controller, which takes the factory carbon emission intensity standard value as the set point and the real-time ton of water carbon emission intensity as the feedback, and the output is the dynamic correction amount of the theoretical gas flow set value, so that the real-time ton of water carbon emission intensity tracks the factory carbon emission intensity standard value.

[0028] In a second aspect, the present application further provides a sewage treatment intelligent aeration control system based on real-time carbon emission feedback, which comprises:

[0029] A data acquisition module is used to acquire multi-element parameters of the sewage treatment system in real time to form a multi-element time series data set; the multi-element parameters include influent water quality parameters, process state parameters, influent flow, aeration equipment power consumption and external reagent addition amount;

[0030] A carbon accounting module is used to calculate the total carbon emission of the sewage treatment system in real time based on the aeration equipment power consumption and the external reagent addition amount, combined with the preset carbon emission factor; and calculate the real-time ton of water carbon emission intensity according to the total carbon emission and the influent flow;

[0031] A set value optimization module is used to input the influent water quality parameters and the process state parameters into a pre-trained Transformer time series prediction model to output the theoretical oxygen demand in the future set time window; calculate the theoretical gas flow set value according to the theoretical oxygen demand; perform gas flow set value optimization based on the theoretical gas flow set value, the real-time ton of water carbon emission intensity and the factory carbon emission standard to obtain the final gas flow set value;

[0032] The control and regulation module is used to take the final gas flow rate setpoint as the set point and adjust the opening of the electric regulating valve through the flow closed-loop controller to achieve precise aeration control.

[0033] Furthermore, based on the theoretical gas flow rate setpoint, real-time carbon emission intensity per ton of water, and the plant's carbon emission intensity standard, the gas flow rate setpoint is optimized to obtain the final gas flow rate setpoint, including:

[0034] Based on the theoretical gas flow rate setpoint, within the predefined process safety range, the optimization objective is to minimize the real-time carbon emission intensity per ton of water or to make it meet the plant's carbon emission intensity standard. The optimization solution is then performed to output the final gas flow rate setpoint with optimal carbon emission.

[0035] Furthermore, the setpoint optimization module is deployed on an edge computing platform and has a built-in model update service, which supports fine-tuning the parameters of the Transformer time series prediction model using newly collected multivariate time series data.

[0036] Thirdly, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described intelligent aeration control method for wastewater treatment based on real-time carbon emission feedback.

[0037] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0038] This invention discloses an intelligent aeration control method and system for wastewater treatment based on real-time carbon emission feedback. It directly links the control of aeration volume to the plant's carbon emission intensity standards. Through real-time carbon accounting and intelligent optimization, it achieves precise control of the aeration process, ensuring that the operation meets both process requirements and carbon emission targets. Specifically:

[0039] (1) Direct carbon target orientation: The optimization target of aeration control is directly defined as "real-time carbon emission intensity per ton of water", which is linked with the carbon emission standards of the factory in real time, so that the control behavior directly serves the carbon emission reduction strategy and realizes the paradigm shift from "energy consumption control" to "carbon emission control".

[0040] (2) Global carbon optimal decision: By introducing real-time carbon accounting and Transformer time series prediction model, the system can make intelligent decisions with the lowest global carbon emissions by dynamically balancing "carbon emissions from aeration energy consumption" and "carbon emissions from chemical addition caused by effluent risk" while ensuring process safety.

[0041] (3) Strong forward-looking control capability: By utilizing the multi-head self-attention mechanism of the Transformer time series prediction model, it effectively captures the long-range dependence between multiple variables, realizes accurate prediction of oxygen demand and effluent risk, and provides a reliable basis for forward control.

[0042] (4) The system is safe and reliable: By setting the process safety range, the optimization process is always carried out within the safety boundary of biochemical treatment, and the effluent quality is guaranteed to meet the standards while actively reducing carbon.

[0043] (5) Excellent adaptive performance: It supports online model updates, can adapt to the time-varying characteristics of water quality and process, and maintain long-term prediction accuracy and control effect. Attached Figure Description

[0044] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings:

[0045] Figure 1 This is a flowchart of an intelligent aeration control method for wastewater treatment based on real-time carbon emission feedback, according to the present invention.

[0046] Figure 2 This is a detailed flowchart of an intelligent aeration control method for wastewater treatment based on real-time carbon emission feedback, according to the present invention.

[0047] Figure 3 This is a flowchart of the gas flow rate setpoint optimization in step S4 of Embodiment 1 of the present invention;

[0048] Figure 4 This is a structural block diagram of an intelligent aeration control system for wastewater treatment based on real-time carbon emission feedback, according to the present invention.

[0049] Figure 5 This is a detailed structural diagram of an intelligent aeration control system for wastewater treatment based on real-time carbon emission feedback, according to the present invention. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0051] Existing methods fall short in capturing complex spatiotemporal dependencies among multiple variables and fail to establish a direct link between control decisions and carbon emissions, thus hindering precise control of the aeration process. Therefore, there is an urgent need in this field for a novel intelligent control method that directly links aeration control to the carbon emission standards of wastewater treatment plants, enabling carbon sensing, carbon decision-making, and carbon execution. This invention directly links the control of aeration volume to the plant's carbon emission intensity standards. Through real-time carbon accounting and intelligent optimization, it achieves precise control of the aeration process, ensuring that the operation meets both process requirements and carbon emission targets.

[0052] Example 1

[0053] like Figure 1 and Figure 2 As shown, this invention discloses an intelligent aeration control method for wastewater treatment based on real-time carbon emission feedback. The method includes:

[0054] S1 acquires multivariate parameters of the wastewater treatment system in real time to form a multivariate time-series dataset. The multivariate parameters include influent water quality parameters, process state parameters, influent flow rate, power consumption of aeration equipment and dosage of external reagents, environmental parameters, etc.

[0055] In this embodiment, various devices installed in the sensor network layer acquire multi-dimensional parameters of the wastewater treatment system in real time, including:

[0056] Influent water quality parameters, such as chemical oxygen demand (COD) and ammonia nitrogen, are obtained in real time by an online water quality analyzer installed in the intake channel.

[0057] Process status parameters, such as sludge concentration (MLSS), dissolved oxygen (DO), and water temperature, are acquired in real time by process instruments installed in the biochemical reaction tank.

[0058] The inlet flow rate is obtained in real time by an electromagnetic flow meter installed on the main inlet pipe;

[0059] The power consumption of the aeration equipment is obtained in real time by a smart meter installed in the power distribution cabinet of the aeration blower.

[0060] The dosage of external reagents, such as carbon sources, is obtained in real time through the communication interface connected to the PLC of the dosing system.

[0061] The aeration volume is obtained in real time by a gas flow meter installed on the aeration branch pipe.

[0062] S2, based on the power consumption of the aeration equipment and the amount of external reagents added, combined with the preset carbon emission factor, calculates the real-time carbon emission intensity per ton of water;

[0063] In this embodiment, step S2 specifically includes:

[0064] S21, based on the power consumption of the aeration equipment and the dosage of external reagents, combined with preset carbon emission factors, calculates the total carbon emissions of the wastewater treatment system in real time; specifically:

[0065] Using local power grid carbon emission factors Calculate direct carbon emissions; Direct carbon emissions = Real-time power of wind turbine × ;

[0066] Using sodium acetate with hidden carbon factor Calculate indirect carbon emissions; Indirect carbon emissions = Instantaneous carbon source input × ;

[0067] The total carbon emissions are obtained by adding direct and indirect carbon emissions together.

[0068] S22, calculate the real-time carbon emission intensity per ton of water based on total carbon emissions and influent flow rate; specifically:

[0069] Real-time carbon emission intensity per ton of water = Total carbon emissions / Influent flow rate = (Direct carbon emissions + Indirect carbon emissions) / Influent flow rate.

[0070] S3: Input the influent water quality parameters and process state parameters into the pre-trained Transformer time series prediction model, and output the theoretical oxygen demand within the future set time window; calculate the theoretical gas flow rate setpoint based on the theoretical oxygen demand;

[0071] In this embodiment, the Transformer time-series prediction model adopts an encoder-decoder architecture. It effectively captures the complex nonlinear relationship between influent load, influent water quality parameters, and oxygen demand through a multi-head self-attention mechanism, outputting the theoretical oxygen demand prediction value for the next two hours. Then, the theoretical gas flow rate setpoint Fsp is calculated using the standard oxygen transfer function. theoretical .

[0072] The standard oxygen transfer function is a well-known function and will not be described in detail here.

[0073] S4. Based on the theoretical gas flow rate setpoint, real-time carbon emission intensity per ton of water and factory carbon emission standards, the gas flow rate setpoint is optimized to obtain the final gas flow rate setpoint.

[0074] In this embodiment, step S4 includes:

[0075] Based on the theoretical gas flow rate setpoint, within the predefined process safety range, the optimization objective is to minimize the real-time carbon emission intensity per ton of water or to make it meet the plant's carbon emission intensity standard. The optimization solution is then performed to output the final gas flow rate setpoint with optimal carbon emission.

[0076] In this embodiment, the optimization solution is achieved by evaluating the predicted carbon emissions corresponding to different candidate gas flow rate settings; the predicted carbon emissions are the sum of the predicted energy consumption carbon emissions under the candidate setting value and the predicted reagent addition carbon emissions due to water discharge risk.

[0077] Among them, the risk of effluent discharge is predicted by an auxiliary output head of the Transformer time series prediction model, which outputs the probability of effluent water quality exceeding the standard within a set time window in the future.

[0078] In this embodiment, the predefined process safety range is determined in advance based on historical operating data, mechanism model simulation and expert experience, and is used to limit the allowable fluctuation range of the final gas flow rate setpoint relative to the theoretical gas flow rate setpoint.

[0079] In this embodiment, the optimization of the gas flow rate setpoint is achieved by a model predictive controller. The model predictive controller uses the factory carbon emission intensity standard value as the setpoint and the real-time carbon emission intensity per ton of water as feedback. Its output is a dynamic correction amount to the theoretical gas flow rate setpoint, so that the real-time carbon emission intensity per ton of water tracks the factory carbon emission intensity standard value.

[0080] In practice, Figure 3 The flowchart for optimizing the gas flow rate setpoint in step S4; the optimizer in the optimization solution uses Fsp theoretical Within a baseline safety range of ±15% (determined based on historical data analysis and mechanism simulation), multiple candidate setpoints are generated using a discretization search strategy. For each candidate value:

[0081] The predicted probability of ammonia nitrogen exceeding the standard in effluent is obtained through the auxiliary output head of the Transformer time series prediction model.

[0082] Calculate the predicted energy consumption carbon emissions, i.e., direct carbon emissions, under this candidate value;

[0083] Carbon emissions from pesticide application, predicted based on the probability of exceeding the standard, i.e., indirect carbon emissions;

[0084] The predicted total carbon emissions for this candidate value are obtained by summing them up, i.e., the total carbon emissions.

[0085] The optimizer selects the candidate value with the lowest predicted total carbon emissions as the final gas flow setpoint Fsp. optimized Output.

[0086] S5 uses the final gas flow rate setpoint as the set point and adjusts the opening of the electric regulating valve through the flow closed-loop controller to achieve precise aeration control.

[0087] In this embodiment, the final gas flow rate setpoint Fsp is... optimizedThe flow rate is sent to the PID controller, which forms a closed loop with the actual value fed back from the gas flow meter to precisely control the opening of the electric regulating valve and achieve accurate aeration.

[0088] This invention directly links aeration control with carbon emission targets, realizing a shift from energy consumption control to carbon emission control. While ensuring effluent quality, it effectively reduces the carbon emission intensity of the wastewater treatment process and achieves precise aeration.

[0089] Example 2

[0090] like Figure 4 and Figure 5 As shown, the difference between this embodiment and Embodiment 1 is that this embodiment provides a wastewater treatment intelligent aeration control system based on real-time carbon emission feedback. This system corresponds one-to-one with the wastewater treatment intelligent aeration control method based on real-time carbon emission feedback in Embodiment 1. The system includes:

[0091] The data acquisition module is used to acquire multivariate parameters of the wastewater treatment system in real time and form a multivariate time-series dataset. The multivariate parameters include influent water quality parameters, process status parameters, influent flow rate, power consumption of aeration equipment, and external reagent dosage.

[0092] The carbon accounting module is used to calculate the total carbon emissions of the wastewater treatment system in real time based on the power consumption of the aeration equipment and the dosage of external reagents, combined with the preset carbon emission factors; and to calculate the real-time carbon emission intensity per ton of water based on the total carbon emissions and the influent flow rate.

[0093] The setpoint optimization module is used to input the influent water quality parameters and process state parameters into the pre-trained Transformer time series prediction model, output the theoretical oxygen demand within the future set time window; calculate the theoretical gas flow setpoint based on the theoretical oxygen demand; and optimize the gas flow setpoint based on the theoretical gas flow setpoint, real-time carbon emission intensity per ton of water and plant carbon emission standards to obtain the final gas flow setpoint.

[0094] The control and regulation module is used to take the final gas flow rate setpoint as the set point and adjust the opening of the electric regulating valve through the flow closed-loop controller to achieve precise aeration control.

[0095] The data acquisition module is deployed at the sensor network layer, the carbon accounting module, the carbon accounting module and the setpoint optimization module are all deployed at the edge computing platform, and the control and regulation module is deployed at the actuator layer.

[0096] In this embodiment, the data acquisition module obtains multi-dimensional parameters of the wastewater treatment system in real time through various devices installed in the sensor network layer.

[0097] In this embodiment, the carbon accounting module is deployed on an edge computing platform to perform the real-time carbon emission intensity per ton of water step.

[0098] In this embodiment, the setpoint optimization module is deployed on an edge computing platform, integrating a Transformer time series prediction model and optimization algorithm; and has a built-in model update service to support fine-tuning of the parameters of the Transformer time series prediction model using newly collected multivariate time series data.

[0099] Specifically, the setpoint optimization module optimizes the gas flow setpoint based on the theoretical gas flow setpoint, real-time carbon emission intensity per ton of water, and the factory's carbon emission intensity standard to obtain the final gas flow setpoint, including:

[0100] Based on the theoretical gas flow rate setpoint, within the predefined process safety range, the optimization objective is to minimize the real-time carbon emission intensity per ton of water or to make it meet the plant's carbon emission intensity standard. The optimization solution is then performed to output the final gas flow rate setpoint with optimal carbon emission.

[0101] In this embodiment, the actuators of the control and regulation module include an electric regulating valve, a flow closed-loop controller, and a gas flow meter.

[0102] In this embodiment, the control and adjustment module sets the final gas flow rate Fsp. optimized The flow rate PID controller receives a signal, which, together with the actual value fed back from the gas flow meter, forms a closed loop to precisely control the opening of the electric regulating valve, achieving accurate aeration. The flow rate PID controller is also deployed on an edge computing platform.

[0103] The execution process of each unit can be carried out according to the process steps of the intelligent aeration control method for wastewater treatment based on real-time carbon emission feedback in Example 1, and will not be described in detail in this example.

[0104] The entire system of this invention achieves a leap from traditional experience-based control to data-driven intelligent control of the aeration process through a closed loop of "perception-decision-execution," significantly improving the level of carbon emission control while ensuring the quality of the effluent.

[0105] Meanwhile, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned intelligent aeration control method for wastewater treatment based on real-time carbon emission feedback.

[0106] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0107] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0108] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0109] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0110] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A smart aeration control method for wastewater treatment based on real-time carbon emission feedback, characterized in that, The method includes: The system acquires multivariate parameters of the wastewater treatment system in real time to form a multivariate time-series dataset. The multivariate parameters include influent water quality parameters, process state parameters, influent flow rate, power consumption of aeration equipment, and external reagent dosage. Based on the power consumption of the aeration equipment and the amount of external reagents added, combined with the preset carbon emission factor, the real-time carbon emission intensity per ton of water is calculated. The influent water quality parameters and process state parameters are input into a pre-trained Transformer time series prediction model, which outputs the theoretical oxygen demand within a future set time window; the theoretical gas flow rate setpoint is calculated based on the theoretical oxygen demand. Based on the theoretical gas flow rate setpoint, the real-time carbon emission intensity per ton of water, and the factory carbon emission standards, the gas flow rate setpoint is optimized to obtain the final gas flow rate setpoint. Using the final gas flow rate setpoint as the set point, the opening of the electric regulating valve is adjusted by the flow closed-loop controller to achieve aeration control.

2. The intelligent aeration control method for wastewater treatment based on real-time carbon emission feedback according to claim 1, characterized in that, Based on the power consumption of the aeration equipment and the dosage of external reagents, and in conjunction with a preset carbon emission factor, the real-time carbon emission intensity per ton of water is calculated, including: Based on the power consumption of the aeration equipment and the amount of external reagents added, combined with the preset carbon emission factor, the total carbon emissions of the wastewater treatment system are calculated in real time. The real-time carbon emission intensity per ton of water is calculated based on the total carbon emissions and the influent flow rate.

3. The intelligent aeration control method for wastewater treatment based on real-time carbon emission feedback according to claim 2, characterized in that, The formula for calculating the real-time carbon emission intensity per ton of water is as follows: Real-time carbon intensity per ton of water = Total carbon emissions / Influent flow rate = (Direct carbon emissions + Indirect carbon emissions) / Influent flow rate; Direct carbon emissions = Real-time power of wind turbine × Local power grid carbon emission factor; Indirect carbon emissions = Instantaneous carbon source addition × Carbon factor implied by sodium acetate.

4. The intelligent aeration control method for wastewater treatment based on real-time carbon emission feedback according to claim 1, characterized in that, Based on the theoretical gas flow rate setpoint, the real-time carbon emission intensity per ton of water, and the factory carbon emission intensity standard, the gas flow rate setpoint is optimized to obtain the final gas flow rate setpoint, including: Based on the theoretical gas flow rate setpoint, within the predefined process safety range, with the optimization objective of minimizing the real-time carbon emission intensity per ton of water or making it meet the factory's carbon emission intensity standard, the optimization solution is performed, and the final gas flow rate setpoint with optimal carbon emission is output.

5. The intelligent aeration control method for wastewater treatment based on real-time carbon emission feedback according to claim 4, characterized in that, The optimization solution is achieved by evaluating the predicted carbon emissions corresponding to different candidate gas flow rate settings; the predicted carbon emissions are the sum of the predicted energy consumption carbon emissions under the candidate setting and the predicted reagent addition carbon emissions due to water discharge risk. The risk of effluent discharge is predicted by an auxiliary output head of the Transformer time-series prediction model, which outputs the probability of effluent water quality exceeding the standard within a set time window in the future.

6. The intelligent aeration control method for wastewater treatment based on real-time carbon emission feedback according to claim 4, characterized in that, The predefined process safety range is determined in advance based on historical operating data, mechanism model simulation, and expert experience, and is used to limit the allowable fluctuation range of the final gas flow rate setpoint relative to the theoretical gas flow rate setpoint.

7. The intelligent aeration control method for wastewater treatment based on real-time carbon emission feedback according to claim 4, characterized in that, The optimization of the gas flow setpoint is achieved by a model predictive controller. This model predictive controller uses the factory carbon emission intensity standard value as the setpoint and the real-time carbon emission intensity per ton of water as feedback. Its output is a dynamic correction to the theoretical gas flow setpoint, so that the real-time carbon emission intensity per ton of water tracks the factory carbon emission intensity standard value.

8. A smart aeration control system for wastewater treatment based on real-time carbon emission feedback, characterized in that, The system includes: The data acquisition module is used to acquire multivariate parameters of the wastewater treatment system in real time and form a multivariate time-series dataset. The multivariate parameters include influent water quality parameters, process status parameters, influent flow rate, power consumption of aeration equipment, and external reagent dosage. The carbon accounting module is used to calculate the total carbon emissions of the wastewater treatment system in real time based on the power consumption of the aeration equipment and the dosage of external reagents, combined with a preset carbon emission factor; and to calculate the real-time carbon emission intensity per ton of water based on the total carbon emissions and the influent flow rate. The setpoint optimization module is used to input the influent water quality parameters and process state parameters into a pre-trained Transformer time series prediction model, output the theoretical oxygen demand within a future set time window; calculate the theoretical gas flow rate setpoint based on the theoretical oxygen demand; and optimize the gas flow rate setpoint based on the theoretical gas flow rate setpoint, the real-time carbon emission intensity per ton of water, and the plant carbon emission standards to obtain the final gas flow rate setpoint. The control and adjustment module is used to take the final gas flow rate setpoint as the set point and adjust the opening of the electric regulating valve through the flow closed-loop controller to achieve aeration control.

9. A smart aeration control system for wastewater treatment based on real-time carbon emission feedback as described in claim 8, characterized in that, The setpoint optimization module is deployed on an edge computing platform and has a built-in model update service, which supports fine-tuning the parameters of the Transformer time series prediction model using newly collected multivariate time series data.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements a smart aeration control method for wastewater treatment based on real-time carbon emission feedback as described in any one of claims 1 to 7.

Images