Operation parameter setting method, device and equipment of sewage treatment system and medium

Abstract

The invention discloses an operation parameter setting method and device of a sewage treatment system, equipment and a medium, and belongs to the technical field of sewage treatment. The operation parameter setting method of the sewage treatment system comprises the following steps: establishing a sewage direct characteristic gas emission mechanism model according to an association relationship between direct sewage production footprint nodes and microorganism operation parameters; determining numerical values of a plurality of optimal operation parameters according to a sewage discharge standard; constructing a database according to the operating parameter value range and the sewage direct characteristic gas emission mechanism model; training a decontamination, carbon reduction and consumption reduction model by using the database and the optimized operation parameters; and after training of the pollution-removing, carbon-reducing and consumption-reducing model is completed, inputting the actual operation parameters of the sewage treatment system into the pollution-removing, carbon-reducing and consumption-reducing model to obtain target operation parameters so as to control the sewage treatment system to operate according to the target operation parameters. The running parameters of the sewage treatment system can be reasonably set, and carbon reduction and energy consumption reduction are realized on the premise of ensuring the effluent quality.

Description

Technical Field

[0001] The present application relates to the technical field of sewage treatment, and particularly relates to a method, device, equipment and medium for setting operating parameters of a sewage treatment system. Background Technique

[0002] Sewage treatment is a process of using physical, chemical and biological methods to remove or reduce pollutants in sewage, in order to protect the environment and promote the recycling of water resources.

[0003] Conventional sewage treatment technologies often focus on optimizing a single pollutant emission target, often overly pursuing extremely low pollutant emissions, adding excessive carbon sources during operation, and increasing nitrification liquid reflux excessively, resulting in extremely high energy consumption. For example, some sewage treatment plants blindly raise the drainage standard to ensure the environmental quality of the receiving water body, leading to excessive power consumption, chemical consumption and carbon emissions during the sewage treatment process.

[0004] Therefore, how to reasonably set the operating parameters of the sewage treatment system to achieve carbon reduction and energy consumption reduction on the premise of ensuring the effluent water quality is a technical problem that needs to be solved by those skilled in the art at present. Summary of the Invention

[0005] The purpose of the present application is to provide a method, device, equipment and medium for setting operating parameters of a sewage treatment system, which can reasonably set the operating parameters of the sewage treatment system to achieve carbon reduction and energy consumption reduction on the premise of ensuring the effluent water quality.

[0006] To solve the above technical problems, the present application provides a method for setting operating parameters of a sewage treatment system, including: determining the correlation between the direct pollution footprint nodes and the microbial operating parameters during the sewage treatment process, and establishing a sewage direct characteristic gas emission mechanism model by using the correlation; determining the numerical values of multiple preferred operating parameters according to the sewage discharge standard; constructing a database according to the operating parameter value range and the sewage direct characteristic gas emission mechanism model; training a pollution removal, carbon reduction and energy consumption reduction model by using the database and the preferred operating parameters; after the pollution removal, carbon reduction and energy consumption reduction model is trained, inputting the actual operating parameters of the sewage treatment system into the pollution removal, carbon reduction and energy consumption reduction model to obtain target operating parameters, so as to control the sewage treatment system to operate according to the target operating parameters.

[0007] Optionally, a sewage direct characteristic gas emission mechanism model is established by using the association relationship, including: establishing the sewage direct characteristic gas emission mechanism model based on the association relationship, the mechanism of microbial growth and death, and the sewage microorganism ratio calculation formula; wherein, the sewage direct characteristic gas emission mechanism model includes a first sub-mechanism model, a second sub-mechanism model, and a third sub-mechanism model; the first sub-mechanism model is used to simulate the mechanism of characteristic gas emission during the endogenous respiration of sewage microorganisms, the second sub-mechanism model is used to simulate the mechanism of sewage organic matter carbonization emission, and the third sub-mechanism model is used to simulate the mechanism of sewage microorganism fixed characteristic gas.

[0008] Optionally, before determining the numerical values of multiple preferred operating parameters according to the sewage discharge standard, it further includes: using a mediation effect model or a causal relationship model to determine the influence degree of each operating parameter on the total sewage direct characteristic gas emission amount during the sewage treatment process, and setting the operating parameters with an influence degree greater than a preset value as the preferred operating parameters.

[0009] Optionally, the preferred operating parameters include any one or a combination of any several of a preferred sludge age, a preferred microbial growth rate, a preferred carbon source addition concentration, and a preferred sewage microorganism ratio.

[0010] Optionally, determining the numerical values of multiple preferred operating parameters according to the sewage discharge standard includes: determining a first reference value and a second reference value according to the sewage discharge standard, and setting the maximum value of the first reference value and the second reference value as the numerical value of the preferred sludge age; wherein, the first reference value is the sludge age value that meets the sewage microorganism growth rate requirement, and the second reference value is the sludge age value that makes the effluent concentration of sewage characteristic pollutants reach the standard; determining a third reference value, a fourth reference value, and a fifth reference value according to the sewage discharge standard, and setting the maximum value of the third reference value, the fourth reference value, and the fifth reference value as the preferred total microorganism concentration, and setting the ratio of the microbial growth concentration to the preferred total microorganism concentration as the preferred microbial growth rate; wherein, the third reference value is the total microorganism concentration that makes the concentration of sewage characteristic pollutants reach the standard; the fourth reference value is the total microorganism concentration that makes the denitrification efficiency reach the standard under anoxic conditions; the fifth reference value is the total microorganism concentration that makes the reflux denitrification efficiency reach the standard; dynamically adjusting the relationship between the microbial growth absorption amount and the carbon and nitrogen consumption amount based on a first calculation formula and a second calculation formula to make the ratio of the dissolved biochemical oxygen demand to the dissolved nitrate nitrogen amount reach a target ratio; calculating the preferred carbon source addition concentration according to the dissolved biochemical oxygen demand and the dissolved nitrate nitrogen amount when the ratio reaches the target ratio; wherein, the first calculation formula is a formula for calculating the dissolved biochemical oxygen demand, and the second calculation formula is a formula for calculating the dissolved nitrate nitrogen amount.

[0011] Optionally, the decontamination, carbon reduction, and energy consumption reduction model includes a first sub-model, a second sub-model, a third sub-model, a fourth sub-model, a fifth sub-model, a sixth sub-model, and a decontamination algorithm sub-model.

[0012] Correspondingly, training the decontamination, carbon reduction, and energy consumption reduction model using the database and the optimal operating parameters includes: extracting alternative operating parameters from the database; wherein the alternative operating parameters include any one or a combination of several of temperature, dissolved oxygen, pH, influent index values of sewage characteristic pollutants, and effluent index values of sewage characteristic pollutants; using the alternative operating parameters as inputs and the optimal carbon source addition concentration as the target value, and iteratively training the first sub-model using the backpropagation neural network classification algorithm; using the alternative operating parameters as inputs and the proportion of sewage microorganisms in the database as the target value, and iteratively training the second sub-model using the backpropagation neural network classification algorithm. Using the alternative operating parameters and the proportion of sewage microorganisms output by the second sub-model as inputs and the optimal sludge age as the target value, and iteratively training the third sub-model using the backpropagation neural network classification algorithm; using the alternative operating parameters and the proportion of sewage microorganisms output by the second sub-model as inputs and the optimal microorganism growth rate as the target value, and iteratively training the fourth sub-model using the adaptive boosting regression algorithm; using the alternative operating parameters, the proportion of sewage microorganisms output by the second sub-model, the sludge age output by the third sub-model, and the microorganism growth rate output by the fourth sub-model as inputs and the direct emission amount of characteristic gas in the database as the target value, and iteratively training the fifth sub-model using the backpropagation neural network classification algorithm; using the alternative operating parameters, the proportion of sewage microorganisms output by the second sub-model, the microorganism growth rate output by the fourth sub-model, and the characteristic gas emission amount output by the fifth sub-model as inputs and the reflux denitrification ratio in the database as the target value, and iteratively training the sixth sub-model using the machine learning regression algorithm; using the alternative operating parameters as inputs and the maximum concentration of the optimal microorganism metabolism pollutants reaching the standard effluent in the database as the target value, and iteratively training the decontamination algorithm sub-model using the machine regression algorithm.

[0013] Optionally, constructing a database according to the operating parameter value range and the sewage direct characteristic gas emission mechanism model includes: performing a non-fixed step size value-taking operation within the operating parameter value range according to the sensitivity of microorganisms to operating parameters to obtain multiple groups of initial operating parameters; calculating the initial operating parameters using the sewage direct characteristic gas emission mechanism model to obtain the parameter calculation results corresponding to each group of the initial operating parameters; constructing the database including the initial operating parameters and the parameter calculation results.

[0014] The present application also provides an operating parameter setting device for a sewage treatment system, which includes: a modeling module for determining the correlation between the direct pollutant generation footprint nodes and the microbial operating parameters during the sewage treatment process, and establishing a sewage direct characteristic gas emission mechanism model using the correlation; an optimal parameter determination module for determining the values of multiple optimal operating parameters according to the sewage discharge standard; a database construction module for constructing a database based on the operating parameter value range and the sewage direct characteristic gas emission mechanism model; a model training module for training a pollution removal, carbon reduction, and energy consumption reduction model using the database and the optimal operating parameters; and a parameter setting module for, after the pollution removal, carbon reduction, and energy consumption reduction model is trained, inputting the actual operating parameters of the sewage treatment system into the pollution removal, carbon reduction, and energy consumption reduction model to obtain target operating parameters, so as to control the sewage treatment system to operate according to the target operating parameters.

[0015] The present application also provides a storage medium, on which a computer program is stored, and when the computer program is executed, the steps performed by the above-mentioned operating parameter setting method for the sewage treatment system are realized.

[0016] The present application also provides an electronic device, including a memory and a processor, where a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps performed by the above-mentioned operating parameter setting method for the sewage treatment system are realized.

[0017] The present application provides an operating parameter setting method for a sewage treatment system. In this solution, a sewage direct characteristic gas emission mechanism model is established based on the correlation between the direct pollutant generation footprint nodes and the microbial operating parameters, and then a database is constructed in combination with the operating parameter value range and the sewage direct characteristic gas emission mechanism model to provide data support for model training. The present application also determines the values of multiple optimal operating parameters according to the sewage discharge standard, and trains a pollution removal, carbon reduction, and energy consumption reduction model based on the constructed database and the optimal operating parameters. The trained pollution removal, carbon reduction, and energy consumption reduction model learns the setting strategy of the operating parameters, and inputs the actual operating parameters of the sewage treatment system into the model to obtain target operating parameters, so that the sewage treatment system operates according to the target operating parameters. In the present application, the database used to train the pollution removal, carbon reduction, and energy consumption reduction model is constructed based on the direct sewage direct characteristic gas emission mechanism model and the sewage discharge standard. The operating parameters output by the pollution removal, carbon reduction, and energy consumption reduction model can not only ensure the effluent quality, but also maximize carbon reduction and energy consumption reduction. The present application also provides an operating parameter setting device for a sewage treatment system, a storage medium, and an electronic device at the same time, which have the above-mentioned beneficial effects and will not be elaborated here. Description of the Drawings

[0018] To more clearly illustrate the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a flowchart of a method for setting operating parameters of a sewage treatment system provided by an embodiment of the present application.

[0020] Figure 2 It is a schematic structural diagram of a device for setting operating parameters of a sewage treatment system provided by an embodiment of the present application. Detailed implementation manners

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0022] Please refer to the following Figure 1 , Figure 1 It is a flowchart of a method for setting operating parameters of a sewage treatment system provided by an embodiment of the present application.

[0023] The specific steps may include.

[0024] S101: Determine the correlation between the direct pollution footprint nodes and the microbial operating parameters in the sewage treatment process, and establish a sewage direct characteristic gas emission mechanism model using the correlation.

[0025] Among them, this embodiment can be applied to an electronic device with data processing capabilities. Before this step, the sewage treatment process can be analyzed to obtain the direct pollution footprint nodes in the sewage treatment process. The direct pollution footprint node refers to: the key link or step that directly causes pollutant emissions.

[0026] In an alternative embodiment, the above direct pollution footprint node can be a direct carbon footprint node, and the direct carbon footprint node is the key link or step that directly generates carbon emissions. The above carbon emissions can be carbon dioxide emissions.

[0027] After determining the direct pollution footprint nodes, this step can determine the correlation between the direct pollution footprint nodes and the microbial operating parameters in the sewage treatment process, and this correlation reflects the relationship between microbial activities and carbon emissions in the sewage treatment process.

[0028] Based on the above correlation, in this embodiment, a corresponding direct sewage characteristic gas emission mechanism model is established. The direct sewage characteristic gas emission mechanism model is a mathematical model used to describe the direct sewage characteristic gas in the sewage treatment process.

[0029] S102: Determine the values of multiple preferred operating parameters according to the sewage discharge standard.

[0030] Among them, before this step, the sewage discharge standard can be obtained. The sewage discharge standard is used to stipulate the pollutant concentration limit in the sewage to ensure that the discharged water quality meets the environmental protection and health requirements.

[0031] In this embodiment, multiple preferred operating parameters can be selected from all the operating parameters of the sewage treatment system. These preferred operating parameters have a greater impact on the total direct sewage characteristic gas (such as the total carbon dioxide emissions) in the sewage treatment process. This step determines the values of multiple preferred operating parameters according to the sewage discharge standard, which can ensure the reduction of energy consumption and carbon emissions on the premise of meeting the water quality discharge requirements.

[0032] Specifically, before determining the values of multiple preferred operating parameters according to the sewage discharge standard, this embodiment can also use the mediating effect model or the causal relationship model to determine the influence degree of each operating parameter on the total direct sewage characteristic gas emissions (such as the total carbon dioxide emissions) in the sewage treatment process, and set the operating parameters with the influence degree greater than the preset value as the preferred operating parameters.

[0033] S103: Construct a database according to the operating parameter value range and the direct sewage characteristic gas emission mechanism model.

[0034] Among them, in this step, the value range of each operating parameter in the sewage treatment system, that is, the operating parameter value range, can be obtained. According to the operating parameter value range and the direct sewage characteristic gas emission mechanism model, the possible values of all operating parameters in the sewage treatment system are determined, and then the database is constructed. The above database includes multiple groups of alternative operating parameters.

[0035] Before this step, the operating conditions of multiple sewage treatment systems in each region can be obtained. By statistically analyzing the above operating conditions, the above operating parameter value range can be obtained. Specifically, in this step, non-fixed step-size value-taking operations can be performed within the operating parameter value range according to the sensitivity of microorganisms to the operating parameters to obtain multiple groups of initial operating parameters; use the direct sewage characteristic gas emission mechanism model to calculate the initial operating parameters, and obtain the parameter calculation results corresponding to each group of the initial operating parameters; construct the database including the initial operating parameters and the parameter calculation results.

[0036] The above sensitivity refers to the sensitivity of any sewage microorganism (such as nitrifying bacteria, etc.) to operating parameters (such as temperature, dissolved oxygen, etc.); in the interval with low sensitivity, a larger step length is used to take values; in the interval with high sensitivity, a smaller step length is used to take values; that is, the value taking step length in this application is negatively correlated with the sensitivity. For different types of operating parameters, this embodiment can select corresponding specific microorganisms, and then perform non-fixed step length value taking operations within the operating parameter value range based on the sensitivity of the specific microorganisms to the operating parameters.

[0037] Specifically, this embodiment can establish an association relationship between operating parameters, classification standards, and asymmetric preset step sizes of preferred microorganisms, use the actual growth rate of nitrifying bacteria to calculate the second-order derivative of temperature to obtain the nitrifying bacteria activity mutation threshold, and use the following non-equivalent segmentation strategy for operating parameters: break through the conventional equidistant temperature segmentation mode, and set 10 to 12 degrees Celsius as a high-sensitivity narrow interval (step size 0.5 degrees Celsius) based on the nitrifying bacteria activity mutation temperature threshold, and set 12 to 25 degrees Celsius as a low-sensitivity wide interval (step size 1 degree Celsius).

[0038] S104: Using the database and the preferred operating parameters to train a pollution removal, carbon reduction and energy consumption reduction model.

[0039] Among them, this step uses the constructed database and the determined preferred operating parameters to train the pollution removal, carbon reduction and consumption reduction model, so that the pollution removal, carbon reduction and consumption reduction model learns the optimal operating parameter setting strategy under different operating conditions in sewage treatment.

[0040] S105: After the pollution removal, carbon reduction and consumption reduction model is trained, the actual operating parameters of the sewage treatment system are input into the pollution removal, carbon reduction and consumption reduction model to obtain target operating parameters, so as to control the sewage treatment system to operate according to the target operating parameters.

[0041] After the pollution removal, carbon reduction and consumption reduction model is trained, the actual operating parameters of the sewage treatment system can be input into the pollution removal, carbon reduction and consumption reduction model. The pollution removal, carbon reduction and consumption reduction model can calculate and output target operating parameters, which can reduce energy consumption and carbon emissions while ensuring that the effluent quality meets the standard.

[0042] This embodiment provides a method for setting operating parameters of a sewage treatment system. According to the correlation between the direct pollution footprint nodes and the microbial operating parameters, a sewage direct characteristic gas emission mechanism model is established. Then, a database is constructed by combining the operating parameter value ranges and the sewage direct characteristic gas emission mechanism model to provide data support for model training. This embodiment also determines the values of multiple preferred operating parameters according to the sewage discharge standards, and trains the pollution reduction, carbon reduction and energy consumption reduction model based on the constructed database and the preferred operating parameters. The trained pollution reduction, carbon reduction and energy consumption reduction model learns the setting strategy of the operating parameters, and inputs the actual operating parameters of the sewage treatment system into the model to obtain the target operating parameters, so that the sewage treatment system operates according to the target operating parameters. In this embodiment, the database used to train the pollution reduction, carbon reduction and energy consumption reduction model is constructed based on the direct sewage direct characteristic gas emission mechanism model and the sewage discharge standards. The operating parameters output by the pollution reduction, carbon reduction and energy consumption reduction model can not only ensure the effluent quality, but also maximize carbon reduction and energy consumption reduction.

[0043] As for Figure 1 As a further introduction to the corresponding embodiment, this embodiment can establish the sewage direct characteristic gas emission mechanism model in the following way: establish the sewage direct characteristic gas emission mechanism model based on the correlation, the microbial growth and death mechanism, and the sewage microorganism ratio calculation formula. The sewage microorganism ratio calculation formula can be the ratio of the sludge amount generated by specific sewage microorganisms to the total sludge amount generated in the sewage treatment system.

[0044] As a feasible implementation manner, the above sewage microorganism ratio calculation formula can specifically be the autotrophic bacteria ratio calculation formula. The microbial growth and death mechanism includes the autotrophic bacteria growth-death mechanism and the heterotrophic bacteria growth-death mechanism. The autotrophic bacteria ratio calculation formula is the ratio of the sludge amount generated by autotrophic bacteria to the total sludge amount generated in the sewage treatment system.

[0045] The above sewage direct characteristic gas emission mechanism model includes a first sub-mechanism model, a second sub-mechanism model and a third sub-mechanism model; the first sub-mechanism model is used to simulate the mechanism of characteristic gas emission during the endogenous respiration process of sewage microorganisms, the second sub-mechanism model is used to simulate the mechanism of sewage organic matter carbonization emission, and the third sub-mechanism model is used to simulate the mechanism of sewage microorganism fixed characteristic gas.

[0046] As for Figure 1 As a further introduction to the corresponding embodiment, the selected preferred operating parameters can include any one or a combination of several of the preferred sludge age, the preferred microbial growth rate, the preferred carbon source addition concentration, and the preferred sewage microorganism ratio. On the basis of selecting the above preferred operating parameters, the values of multiple preferred operating parameters can be determined in the following way.

[0047] The process of determining the value of the preferred sludge age is as follows: Determine the first reference value and the second reference value according to the sewage discharge standard, and set the maximum value of the first reference value and the second reference value as the value of the preferred sludge age; wherein, the first reference value is the sludge age value that meets the requirement of the sewage microorganism growth rate , and the second reference value is the sludge age value that enables the effluent concentration of the sewage characteristic pollutants to meet the standard. The above-mentioned second reference value includes the sludge age value that enables the ammonia nitrogen effluent concentration to meet the standard , and the sludge age value that enables the total biochemical oxygen demand effluent concentration to meet the standard . On this basis, the value of the above-mentioned preferred sludge age can be , and the maximum value among them.

[0048] The process of determining the preferred microorganism proliferation rate is as follows.

[0049] Determine the third reference value, the fourth reference value and the fifth reference value according to the sewage discharge standard, and set the maximum value of the third reference value, the fourth reference value and the fifth reference value as the preferred total microorganism concentration, and set the ratio of the microorganism proliferation concentration to the preferred total microorganism concentration as the preferred microorganism proliferation rate; wherein, the third reference value is the total microorganism concentration that enables the sewage characteristic pollutant concentration to meet the standard; the fourth reference value is the total microorganism concentration that enables the denitrification efficiency under anoxic conditions to meet the standard; the fifth reference value is the total microorganism concentration that enables the reflux denitrification efficiency to meet the standard. The above-mentioned third reference value can be the total microorganism concentration that enables the total biochemical oxygen demand effluent concentration and the ammonia nitrogen effluent concentration to meet the standard ; the above-mentioned fourth reference value can be the total microorganism concentration that enables the denitrification efficiency under anoxic conditions to meet the standard ; the above-mentioned fifth reference value can be the total microorganism concentration that enables the reflux denitrification efficiency to meet the standard .

[0050] The process of determining the preferred carbon source addition concentration is as follows: Dynamically adjust the relationship between the microorganism proliferation absorption amount and the carbon-nitrogen consumption amount based on the first calculation formula and the second calculation formula, so that the ratio of the dissolved biochemical oxygen demand to the dissolved nitrate nitrogen amount reaches the target ratio; Calculate the preferred carbon source addition concentration according to the dissolved biochemical oxygen demand and the dissolved nitrate nitrogen amount when the ratio reaches the target ratio ; wherein, the first calculation formula is the formula for calculating the dissolved biochemical oxygen demand, and the second calculation formula is the formula for calculating the dissolved nitrate nitrogen amount.

[0051] As for Figure 1For a further introduction to the corresponding embodiment, the decontamination, carbon reduction and energy consumption reduction model includes a first sub-model, a second sub-model, a third sub-model, a fourth sub-model, a fifth sub-model, a sixth sub-model and a decontamination algorithm sub-model; the first sub-model is a model for calculating the carbon source addition concentration, the second sub-model is a model for calculating the proportion of autotrophic bacteria, the third sub-model is a model for calculating the sludge age, the fourth sub-model is a model for calculating the microbial growth rate, the fifth sub-model is a model for calculating the carbon dioxide emission, the sixth sub-model is a model for calculating the reflux denitrification ratio, and the decontamination algorithm sub-model is a model for calculating the maximum concentration of the preferred microorganisms to metabolize pollutants to meet the effluent standards. Specifically, in this embodiment, alternative operating parameters can be extracted from the database, and then the decontamination, carbon reduction and energy consumption reduction model can be trained using the alternative operating parameters; among them, the alternative operating parameters include any one or a combination of several of temperature, dissolved oxygen, pH, influent index values of sewage characteristic pollutants and effluent index values of sewage characteristic pollutants.

[0052] The training process of the first sub-model is as follows: taking the alternative operating parameters as the input and the preferred carbon source addition concentration as the target value, the first sub-model is iteratively trained using the backpropagation neural network classification algorithm. Specifically, the alternative operating parameters participating in the training process of the first sub-model are the first type of alternative operating parameters. In this embodiment, taking the first type of alternative operating parameters in the database as the input and the preferred carbon source addition concentration as the target value, the first sub-model is iteratively trained using the backpropagation neural network classification algorithm. Among them, the first type of alternative operating parameters includes dissolved oxygen DO, pH and the first effluent index value of sewage characteristic pollutants. The first effluent index value of sewage characteristic pollutants includes: ammonia nitrogen effluent concentration , influent biochemical oxygen demand , influent total nitrogen , effluent total biochemical oxygen demand and total nitrogen change .

[0053] The training process of the second sub-model is as follows: taking the alternative operating parameters as the input and the proportion of sewage microorganisms in the database as the target value, the second sub-model is iteratively trained using the backpropagation neural network classification algorithm. Specifically, the alternative operating parameters participating in the training process of the second sub-model are the second type of alternative operating parameters. In this embodiment, taking the second type of alternative operating parameters in the database as the input and the proportion of autotrophic bacteria AO in the database as the target value, the second sub-model is iteratively trained using the backpropagation neural network classification algorithm. Among them, the second type of alternative operating parameters includes temperature T, dissolved oxygen DO, pH and the second effluent index value of sewage characteristic pollutants. The second effluent index value of sewage characteristic pollutants includes total influent biochemical oxygen demand and influent total nitrogen .

[0054] The training process of the third sub-model is as follows: Using the alternative operating parameters and the sewage microorganism ratio output by the second sub-model as inputs, and the preferred sludge age as the target value, the third sub-model is iteratively trained using the backpropagation neural network classification algorithm. Specifically, the alternative operating parameters involved in the training process of the third sub-model are the third type of alternative operating parameters. In this embodiment, the third type of alternative operating parameters in the database and the autotrophic bacteria ratio output by the second sub-model are used as inputs, and the preferred sludge age is used as the target value, and the third sub-model is iteratively trained using the backpropagation neural network classification algorithm; among them, the third type of alternative operating parameters includes dissolved oxygen DO, pH value, and temperature T.

[0055] The training process of the fourth sub-model is as follows: Using the alternative operating parameters and the sewage microorganism ratio output by the second sub-model as inputs, and the preferred microorganism growth rate as the target value, the fourth sub-model is iteratively trained using the adaptive boosting regression algorithm. Specifically, the alternative operating parameters involved in the training process of the fourth sub-model are the fourth type of alternative operating parameters. In this embodiment, the fourth type of alternative operating parameters in the database and the autotrophic bacteria ratio output by the second sub-model are used as inputs, and the preferred microorganism growth rate is used as the target value, and the fourth sub-model is iteratively trained using the adaptive boosting regression algorithm; among them, the fourth type of alternative operating parameters includes dissolved oxygen DO, pH value, and the effluent index value of the fourth sewage characteristic pollutant; the effluent index value of the fourth sewage characteristic pollutant includes: ammonia nitrogen effluent concentration , total influent biochemical oxygen demand , influent total nitrogen , effluent total biochemical oxygen demand and total nitrogen change .

[0056] The training process of the fifth sub-model is as follows: Using the alternative operating parameters, the proportion of sewage microorganisms output by the second sub-model, the sludge age output by the third sub-model, and the microbial growth rate output by the fourth sub-model as inputs, and using the direct emission of characteristic gas in the database as the target value, the fifth sub-model is iteratively trained using the backpropagation neural network classification algorithm. Specifically, the alternative operating parameters participating in the training process of the fourth sub-model are the fifth type of alternative operating parameters. In this embodiment, the fifth type of alternative operating parameters in the database, the proportion of autotrophic bacteria output by the second sub-model, the sludge age output by the third sub-model, and the microbial growth rate output by the fourth sub-model are used as inputs, and the carbon dioxide emission in the database is used as the target value, and the fifth sub-model is iteratively trained using the backpropagation neural network classification algorithm; among them, the fifth alternative operating parameters include: temperature T, dissolved oxygen DO, pH value, and the effluent index value of the fifth sewage characteristic pollutant. The effluent index value of the fifth sewage characteristic pollutant is the total influent biochemical oxygen demand .

[0057] The training process of the sixth sub-model is as follows: Using the alternative operating parameters, the proportion of sewage microorganisms output by the second sub-model, the microbial growth rate output by the fourth sub-model, and the characteristic gas emission amount output by the fifth sub-model as inputs, and using the reflux denitrification ratio in the database as the target value, the sixth sub-model is iteratively trained using the machine learning regression algorithm. Specifically, the alternative operating parameters participating in the training process of the fourth sub-model are the sixth type of alternative operating parameters. In this embodiment, the sixth type of alternative operating parameters in the database, the proportion of autotrophic bacteria output by the second sub-model, the microbial growth rate output by the fourth sub-model, and the carbon dioxide emission amount output by the fifth sub-model are used as inputs, and the reflux denitrification ratio in the database is used as the target value, and the sixth sub-model is iteratively trained using the machine learning regression algorithm; among them, the sixth type of alternative operating parameters includes temperature T, dissolved oxygen DO, pH value, and the effluent index value of the sixth sewage characteristic pollutant. The effluent index value of the sixth sewage characteristic pollutant includes: ammonia nitrogen effluent concentration , the total influent biochemical oxygen demand , influent total nitrogen , and effluent total biochemical oxygen demand .

[0058] Using the alternative operating parameters as inputs and using the maximum concentration of the preferred microbial metabolism pollutant reaching the standard effluent in the database as the target value, the decontamination algorithm sub-model is iteratively trained using the machine regression algorithm.

[0059] The above decontamination algorithm submodels include a seventh submodel, an eighth submodel, and a ninth submodel. The specific training process is as follows: Using the seventh type of alternative operating parameters in the database as input and the maximum effluent concentration of dissolved organic matter in the database as the target value, iteratively train the seventh submodel using the decision tree regression algorithm; wherein, the seventh type of alternative operating parameters includes temperature T, pH value, and influent biochemical oxygen demand . The seventh submodel is a model for calculating the maximum effluent concentration of dissolved organic matter.

[0060] Using the eighth type of alternative operating parameters in the database as input and the maximum effluent concentration of ammonia nitrogen in the database as the target value, iteratively train the eighth submodel using the decision tree regression algorithm; wherein, the eighth type of alternative operating parameters includes temperature T, pH value, dissolved oxygen DO, influent biochemical oxygen demand and influent total nitrogen . The eighth submodel is a model for calculating the maximum effluent concentration of ammonia nitrogen.

[0061] Using the ninth type of alternative operating parameters in the database and the maximum effluent concentration of dissolved organic matter output by the seventh submodel as input and the minimum total nitrogen removal concentration of the sewage treatment system in the database as the target value, iteratively train the ninth submodel using the adaboost (adaptive boosting) regression algorithm; wherein, the ninth type of alternative operating parameters includes the ammonia nitrogen effluent concentration , influent biochemical oxygen demand and influent total nitrogen . The ninth submodel is a model for calculating the minimum total nitrogen removal concentration of the sewage treatment system.

[0062] The following illustrates the process described in the above embodiments through examples in practical applications.

[0063] Existing sewage treatment technologies often focus on optimizing single pollutant emission targets, often overly pursuing extremely low concentrations of pollutants. During operation, excessive amounts of carbon sources are added, and the recirculation of nitrified liquid is overly increased, resulting in extremely high energy consumption. In existing technologies, only the inherent MLVSS (Mixed Liquor Volatile Suspended Solids) in the sewage system is regarded as an indicator of microbial health, but the proliferation of MLVSS and the proportion of autotrophic bacteria are also of profound significance for sewage treatment. Currently, most sewage treatment plants blindly raise the drainage standards to ensure the environmental quality of the receiving water body, resulting in higher power consumption, chemical consumption, and more carbon emissions during the sewage treatment process, which seriously conflicts with the carbon emission reduction strategy. Therefore, based on the division of environmental function areas and environmental capacity of the discharged water body, a reasonable effluent quality standard should be formulated with a combination of strictness and leniency, which can not only ensure the compliance of the receiving water body but also help reduce carbon emissions and energy consumption during sewage treatment. In existing solutions, usually only microorganisms and pollutants in water are concerned, and the emissions of air pollutants are not deeply considered. However, this solution correlates microorganisms, operating parameters, water pollutants, and air pollutants to achieve precise coordinated control of sewage treatment for pollution removal, carbon reduction, and energy consumption reduction, and to achieve the effect of coordinated optimization of sewage parameters.

[0064] In view of the technical problems existing in the above-mentioned related technologies, this embodiment adopts the closed-loop thinking of "mechanism revelation data-driven algorithm integration optimization project" to provide an optimization scheme for sewage treatment operating parameters driven by direct low carbon footprint. Existing sewage operation technologies establish a rough control of the mechanism model through simple microbial treatment principles, without considering process parameters such as sludge age, MLVSS, and carbon source addition, which are mainly related to direct carbon dioxide emissions and are optimized based on pollutant classification drainage standards and sewage operation conditions. However, this solution uses a mechanism model of microbial growth and death to construct a one-to-one correspondence between sewage operation conditions - pollutant (substrate) removal - direct carbon dioxide generation, and feedback-correlates the control of process parameters related to direct carbon dioxide emissions; while ensuring the compliance of the effluent, it can reduce direct carbon dioxide emissions during the sewage process as much as possible, and can also take into account reducing chemical consumption, energy consumption, etc., so as to achieve the coordination of pollution reduction and carbon reduction. Based on the above mechanism model, this solution creates an algorithm model to realize the sewage treatment during the optimization process. After establishing the mechanism model, this solution correlates multiple objectives and parameters, deeply explores parameters such as the proliferation of MLVSS and the proportion of autotrophic bacteria, optimizes the sewage treatment process, and establishes an intelligent algorithm model based on the sludge age, MLVSS, and minimum concentration of added carbon source, which can not only ensure the compliance of the sewage effluent but also keep the direct carbon dioxide emissions at a relatively low level, achieving "coordinated pollution reduction and carbon reduction".

[0065] This solution establishes a nitrification (autotrophic) - denitrification (heterotrophic) sewage system operation parameter - pollutant removal - carbon reduction mechanism model based on the principle of microbial water treatment; based on the investigation of basic parameters such as the sewage microbial operation parameters, pollutant (microbial growth substrate) influent concentration, engineering operation parameters, and microbial nutrient parameters of multiple sewage treatment plants, as well as the sewage discharge standards, after orthogonalization of factor levels, the direct carbon dioxide emissions and pollutant effluent concentration are calculated by substituting into the mechanism model, and a database containing basic parameters, process parameters, direct carbon dioxide emissions, and pollutant effluent concentration is constructed. This solution also mines and optimizes potential indicators such as carbon source addition, autotrophic bacteria ratio, nitrification liquid reflux ratio, and microbial proliferation based on direct carbon emissions and pollutant compliance, and trains and optimizes parameters such as carbon source addition, autotrophic bacteria ratio, nitrification liquid reflux ratio, and microbial proliferation based on machine regression algorithms and machine classification algorithms, so as to set the actual operation parameters of the sewage treatment system. This solution includes the following steps 1 to step 5.

[0066] Step 1: Obtain the basic parameters of multiple sewage treatment plants and the sewage discharge standards, and preliminarily screen and classify the pollutant influent and effluent ranges based on the sewage discharge standards and temperature.

[0067] Specifically, this step can determine the operating conditions of each sewage treatment system and the pollutant influent and effluent concentration levels, so as to determine the suitable growth conditions of autotrophic bacteria and heterotrophic bacteria. This step can obtain the basic parameters of sewage treatment plants in each region, and then determine the value range of operating parameters. For example, the value range of dissolved oxygen DO: 2.0~3.5mg / L; the value range of pH: 7~8.5; T: 10~25 ; Total nitrogen influent concentration Value range: 35~55mg / L, total suspended solids influent concentration Value range: 230mg / L; influent biochemical oxygen demand Value range: 50~200mg / L. The above mg represents milligram, L represents liter, represents degree Celsius.

[0068] This embodiment can also obtain the sewage discharge standards, and preliminarily screen and classify the pollutant influent and effluent ranges based on the sewage discharge standards and temperature. For example, the first-class A discharge standard: ammonia nitrogen effluent standard NH effluent standard: 5 (8) mg / L (temperature 10~12 Execute 5mg / L, temperature greater than 12 Execute 8mg / L), five-day biochemical oxygen demand : 10mg / L, total suspended solids TSS: 10mg / L, total nitrogen TN: 15mg / L; the first-class B discharge standard: ammonia nitrogen effluent standard NH effluent standard: 8 (15) mg / L (temperature 10~12 Execute 8mg / L, temperature greater than 12 Execute (at 15 mg / L), five-day biochemical oxygen demand : 20 mg / L, total suspended solids TSS: 20 mg / L, total nitrogen TN: 20 mg / L.

[0069] Step 2: Sort out the direct carbon footprint nodes, correlate the microbial operation parameters with the emissions of the direct carbon footprint nodes, and establish a direct carbon dioxide emission mechanism model based on the autotrophic and heterotrophic microbial growth-death mechanism. In this embodiment, a carbon dioxide emission mechanism model is established by coupling the thermodynamic and kinetic parameters of water treatment.

[0070] Since autotrophic bacteria and heterotrophic bacteria are related to the sewage treatment and sewage pollutants , TN, ammonia nitrogen, TSS influent and effluent concentrations (mg / L), influent water volume Q ( ), where m represents meters and d represents days, and are also closely related to the appropriate dissolved oxygen DO (mg / L), pH value (dimensionless), temperature T ( ), etc. sewage operation parameters. Based on the C (carbon) material balance method of the sewage chemical process under the reaction kinetic conditions of different operation parameters and pollutant influent and effluent concentrations, a direct carbon dioxide emission mechanism model is established. In this embodiment, by analyzing the dynamic changes of the operation parameters and the influent and effluent concentrations of pollutants in the sewage treatment process, a quantitative relationship between engineering microbial kinetics and carbon dioxide generation thermodynamics is established, and a direct emission model is constructed based on the carbon material balance principle. The direct carbon dioxide emission mechanism model is divided into 3 sub-mechanism models. The first sub-mechanism model is used to describe the endogenous respiration emission (carbon dioxide) of autotrophic bacteria and heterotrophic bacteria, the second sub-mechanism model is used to describe the carbonization emission of sewage organic matter , and the third sub-mechanism model is used to describe the fixation of autotrophic bacteria . The direct carbon footprint is the direct carbon dioxide emission step in the biological sewage treatment system.

[0071] The description of the direct carbon footprint of the sewage biological treatment system is as follows: In the sewage treatment system, autotrophic bacteria and heterotrophic bacteria grow. Autotrophic bacteria use as a carbon source, mainly nitrifying bacteria and nitrosifying bacteria, which convert ammonium nitrogen into nitrate nitrogen in the aeration tank (aerobic nitrification tank). Autotrophic bacteria net proliferate themselves and simultaneously fix . Heterotrophic bacteria use the carbon-containing organic matter in the sewage as a carbon source. Heterotrophic bacteria proliferate themselves and decompose the carbon-containing organic matter into . In addition, a certain concentration of inherent endogenous respiration emissions of autotrophic bacteria and heterotrophic bacteria will be maintained within the sludge age cycle . In the anoxic denitrification tank, heterotrophic bacteria proliferate themselves and simultaneously denitrify the refluxed nitrate nitrogen into nitrogen gas, and at the same time emit carbon dioxide.

[0072] The potential operating parameters of sewage refer to: in the process of sewage treatment, sludge age, MLVSS (Mixed Liquor Volatile Suspended Solids concentration), and carbon source addition are key parameters that affect sewage treatment efficiency and carbon footprint. The following is a detailed analysis of these parameters and their roles in sewage treatment.

[0073] Sludge age refers to the average time that activated sludge stays in the system, usually measured in days. It is an important parameter to measure the stability of sludge activity and sewage treatment effect. Roles: Pollutant removal efficiency: When the sludge age is short, autotrophic microorganisms are difficult to complete nitrogen treatment, and nitrogen emissions are likely to exceed the standard. Proportion of autotrophic bacteria in sludge: If the sludge age is too short, autotrophic microorganisms may not fully adapt to the environment and are difficult to grow; if it is too long, it may lead to sludge aging and reduce activity. Direct carbon emissions: Sludge age is closely related to aeration volume. A longer sludge age usually requires more aeration volume, which may lead to an increase in direct carbon emissions. At the same time, the increase in aeration volume increases the treatment energy consumption. In this embodiment, by adjusting the sludge age, the pollutant removal efficiency and carbon emissions are balanced. For example, on the premise of ensuring that pollutants meet the discharge standards, the sludge age is appropriately shortened to reduce aeration energy consumption and carbon emissions.

[0074] MLVSS refers to the concentration of biologically active organic substances in activated sludge, usually used to measure the number and activity of microorganisms in activated sludge. Roles: Treatment capacity: A higher MLVSS usually means that more microorganisms are involved in pollutant degradation, which can improve the treatment efficiency. Energy consumption and carbon emissions: Maintaining a higher MLVSS requires more aeration and carbon source addition, which may lead to an increase in energy consumption and carbon emissions. In this embodiment, the MLVSS is controlled within a reasonable range to avoid being too high or too low. For example, by optimizing the sludge return ratio and aeration volume, the balance between treatment efficiency and energy consumption is achieved.

[0075] Carbon source addition means that in the biological denitrification process, the carbon source is an important substrate for microbial metabolism. When the carbon source in sewage is insufficient, external carbon sources (such as methanol, sodium acetate, etc.) usually need to be added to promote the denitrification process. Roles: Denitrification efficiency: Sufficient carbon source can improve the denitrification efficiency. Direct carbon emissions: The addition of carbon source may directly lead to an increase in carbon emissions, especially when using organic carbon sources such as methanol. Operating cost: The addition of external carbon sources increases the operating cost, and excessive addition may cause secondary pollution. This embodiment is used to accurately control the amount of carbon source addition to avoid overuse.

[0076] The nitrification liquid reflow ratio is a key operating parameter in the sewage treatment process, especially in the biological denitrification process. It refers to the ratio of the nitrification liquid flow rate from the nitrification tank to the denitrification tank to the raw water flow rate entering the denitrification tank. Impact on denitrification efficiency: When the reflow is relatively low, the nitrate in the nitrification liquid cannot fully enter the denitrification tank, resulting in a decrease in denitrification efficiency. When the reflow is relatively high, although the denitrification efficiency is improved, an excessively high reflow ratio may lead to insufficient carbon source in the denitrification tank, which in turn reduces the denitrification efficiency. Impact on energy consumption: The nitrification liquid reflow needs to be achieved by a pump, and increasing the reflow ratio will significantly increase the energy consumption of the pump. Impact on carbon emissions: Increasing the reflow ratio not only increases energy consumption, but may also lead to an increase in the amount of carbon source added during the denitrification process, further increasing carbon emissions.

[0077] The proportion of autotrophic bacteria is the proportion of autotrophic bacteria (nitrifying bacteria) in MLVSS. Autotrophic bacteria refer to microorganisms that can use inorganic substances (such as carbon dioxide) as carbon sources and use light energy or chemical energy to convert inorganic substances into organic matter. The proportion of autotrophic bacteria in an ecosystem is one of the important indicators for evaluating the structure and function of microbial communities. Autotrophic bacteria and heterotrophic bacteria compete for DO in the aerobic stage. Compared with heterotrophic bacteria, autotrophic bacteria grow slowly and are more sensitive to water quality fluctuations. If the proportion of autotrophic bacteria is too low, it may cause insufficient nitrification in the sewage system and excessive ammonia nitrogen emissions. At the same time, a low proportion of autotrophic bacteria means a high proportion of heterotrophic bacteria. Excessive growth of heterotrophic bacteria can easily cause large amounts of residual sludge to be discharged and high energy consumption for subsequent treatment.

[0078] Competitive relationship between autotrophic bacteria and heterotrophic bacteria: Autotrophic bacteria (nitrifying bacteria): mainly responsible for converting ammonia nitrogen Converted to nitrate , but they grow slowly, have a long generation cycle, and are sensitive to DO and water quality fluctuations (such as temperature, pH, and toxic substances). Heterotrophic bacteria: They are mainly responsible for decomposing organic matter, have a fast growth rate, a short generation cycle, and are more competitive with DO. Competition results: When DO is limited, heterotrophic bacteria preferentially use DO to degrade organic matter, resulting in insufficient DO for autotrophic bacteria, thereby inhibiting the nitrification process and causing a decrease in the efficiency of ammonia nitrogen removal.

[0079] The impacts of too low proportion of autotrophic bacteria are as follows: insufficient nitrification and excessive ammonia nitrogen discharge: too low proportion of autotrophic bacteria will lead to incomplete nitrification, and ammonia nitrogen in sewage cannot be effectively converted into nitrate, ultimately resulting in excessive ammonia nitrogen concentration in the effluent and affecting the water environment. Overgrowth of heterotrophic bacteria and increased sludge yield: too high proportion of heterotrophic bacteria will accelerate the degradation of organic matter, but at the same time will also lead to a significant increase in the yield of excess sludge. This not only increases the difficulty and cost of sludge treatment, but also may lead to an increase in energy consumption in subsequent treatment processes (such as dewatering, incineration). Decline in system stability: autotrophic bacteria are sensitive to water quality fluctuations. In a system dominated by heterotrophic bacteria, autotrophic bacteria may gradually decrease due to competitive disadvantages, further weakening the system's ability to withstand shock loads. Autotrophic bacteria themselves assimilate carbon dioxide, and too low proportion results in a decline in carbon sequestration capacity. To optimize the proportion of autotrophic bacteria and heterotrophic bacteria and improve the sewage treatment effect, the following measures can be taken in this embodiment: optimize DO control: increase the DO concentration in the aerobic tank to provide sufficient dissolved oxygen for autotrophic bacteria; extend the sludge age; reduce the addition of carbon sources: inhibit the growth of heterotrophic bacteria; adjust the pH to promote the growth of autotrophic bacteria.

[0080] In the sewage treatment system, the competitive relationship between autotrophic bacteria and heterotrophic bacteria directly affects the ammonia nitrogen removal efficiency and sludge yield. By reasonably controlling measures such as DO, sludge age, and carbon source addition, the proportion of autotrophic bacteria can be optimized, the nitrification ability can be improved, the excess sludge yield can be reduced, and ultimately a more efficient and stable sewage treatment effect can be achieved.

[0081] Microorganisms are the main executors of degrading organic pollutants and removing nutrients such as nitrogen and phosphorus during the sewage treatment process, especially in biological treatment processes (such as activated sludge process, biofilm process, etc.). The level of microorganism proliferation concentration directly affects the sewage treatment efficiency.

[0082] The microorganism proliferation concentration is of great significance to the sewage treatment process. High concentration of microorganisms: can rapidly degrade pollutants, shorten the treatment time, and improve the effluent quality. Low concentration of microorganisms: may lead to a decline in treatment efficiency and excessive concentration of pollutants in the effluent. Controlling the microorganism proliferation concentration can optimize the energy consumption and operating costs in the sewage treatment process. Excessive proliferation: may lead to an increase in oxygen consumption and an increase in aeration energy consumption. Insufficient proliferation: requires additional addition of microorganisms or extension of the treatment time, increasing the operating costs.

[0083] The calculation formula for the maximum specific growth rate of autotrophic bacteria is: ; the unit of the maximum specific growth rate is 1 / d (per day). represents the maximum specific growth rate of autotrophic bacteria.

[0084] The calculation formula for the endogenous respiration coefficient of autotrophic bacteria is: , the unit of the endogenous respiration coefficient is 1 / d, represents the endogenous respiration coefficient of autotrophic bacteria.

[0085] The calculation formula for the half-rate constant of autotrophic bacteria based on substrate growth is: , and the unit of the half-rate constant based on substrate growth is mg / L. represents the half-rate constant of autotrophic bacteria based on the specific substrate of ammonia nitrogen.

[0086] The calculation formula for the actual specific growth rate of autotrophic bacteria based on aeration operating conditions is: ; the unit of the actual specific growth rate based on aeration operating conditions is 1 / d. represents the actual specific growth rate of autotrophic bacteria based on aeration operating conditions. represents the maximum specific growth rate of autotrophic bacteria. represents the standard concentration of ammonia nitrogen in the effluent. represents the dissolved oxygen (i.e., the dissolved oxygen concentration). represents the half-saturation constant of dissolved oxygen. represents the pH value. represents the endogenous respiration coefficient of autotrophic bacteria.

[0087] The calculation formula for the apparent sludge production coefficient of autotrophic bacteria is: ; the unit of the apparent sludge production coefficient is and , where kg represents kilograms and VSS represents the concentration of mixed liquor volatile suspended solids. represents ammonia nitrogen. represents the five-day biochemical oxygen demand. represents the apparent sludge production coefficient of autotrophic bacteria. represents the sludge age. The apparent sludge production coefficient of autotrophic bacteria can also be the theoretical yield coefficient of nitrifying bacteria, 0.12 .

[0088] The calculation formula for the sludge production of autotrophic bacteria is: ; the unit of the sludge production of autotrophic bacteria is kg / d. represents the amount of sludge produced by autotrophic bacteria. represents the flow rate of sewage entering the sewage treatment system. represents the total nitrogen concentration in the influent. represents the amount of sludge produced by heterotrophic bacteria. represents the apparent sludge production coefficient of autotrophic bacteria.

[0089] The calculation formula for the autotrophic bacteria ratio (dimensionless) is: , represents the total sludge production in the system.

[0090] The calculation formula for the maximum specific growth rate of heterotrophic bacteria is: , and the unit of the maximum specific growth rate is 1 / d. Represents the maximum specific growth rate of heterotrophic bacteria.

[0091] The calculation formula for the endogenous respiration coefficient of heterotrophic bacteria is: , and the unit of the endogenous respiration coefficient is 1 / d. Represents the endogenous respiration coefficient of heterotrophic bacteria.

[0092] The calculation formula for the half-rate constant of heterotrophic bacteria based on substrate growth is: , Represents the half-rate constant of autotrophic bacteria based on this specific substrate. The unit of the half-rate constant based on substrate growth is mg / L.

[0093] The calculation formula for the actual specific growth rate of heterotrophic bacteria based on the aeration operating conditions is: , Represents the actual specific growth rate of heterotrophic bacteria based on the aeration operating conditions. Represents the maximum specific growth rate of heterotrophic bacteria. Represents the total influent biochemical oxygen demand. The endogenous respiration coefficient of heterotrophic bacteria. The unit of the actual specific growth rate based on the aeration operating conditions is 1 / d.

[0094] The calculation formula for the apparent sludge production coefficient of heterotrophic bacteria is: , Represents the apparent sludge production coefficient of heterotrophic bacteria. The unit of the apparent sludge production coefficient is and , kg represents kilograms, VSS represents the mixed liquor volatile suspended solid concentration. Represents ammonia nitrogen. Represents the five-day biochemical oxygen demand. The apparent sludge production coefficient of heterotrophic bacteria can also be the theoretical yield coefficient of heterotrophic bacteria, 0.67 .

[0095] The calculation formula for the sludge production of heterotrophic bacteria is: , and the unit of the sludge production of heterotrophic bacteria is kg / d. Represents the effluent dissolved concentration. Represents the apparent sludge production coefficient of heterotrophic bacteria.

[0096] Total sludge production .

[0097] The calculation formula for the anoxic denitrification rate of autotrophic and heterotrophic bacteria is: , Represents the anoxic tank (denitrification) dissolved oxygen concentration (unit: mg / L). The unit of the anoxic denitrification rate is: / (mgVSS·d). mgNO₃-N represents nitrate nitrogen per milligram, mgVSS represents the concentration of mixed liquor volatile suspended solids per milligram, and d represents day.

[0098] The half-rate constant for the aeration DO operating conditions of autotrophic and heterotrophic bacteria is 0.5 mg / L.

[0099] The calculation method for the effluent concentration of influent pollutants (growth substrates) is as follows.

[0100] The formula for calculating the effluent ammonia nitrogen concentration is: ; represents the effluent ammonia nitrogen concentration, represents the half-rate constant (ammonia nitrogen saturation constant) of autotrophic bacteria based on ammonia nitrogen as a specific substrate.

[0101] The formula for calculating the effluent total nitrogen concentration is: ; represents the effluent total nitrogen concentration, represents the influent total nitrogen concentration, represents the concentration of mixed liquor volatile suspended solids, represents the endogenous respiration coefficient of total nitrogen, represents the nitrogen concentration absorbed by microbial growth.

[0102] The formula for calculating the minimum total nitrogen concentration to be removed is: , represents the minimum total nitrogen concentration to be removed, represents the standard that the total nitrogen concentration in the effluent after sewage treatment needs to reach.

[0103] The formula for calculating the nitrogen concentration absorbed by microbial growth is: .

[0104] Effluent dissolved The concentration formula is: .

[0105] Effluent non-dissolved The concentration formula is: , represents the effluent non-dissolved concentration, represents the effluent total suspended solids concentration, represents the proportion of VSS in TSS in the effluent, VSS represents the concentration of mixed liquor volatile suspended solids, and TSS represents the total suspended solids.

[0106] Effluent total The concentration formula is: , represents the effluent total concentration, represents the effluent dissolved Concentration.

[0107] The calculation formula for the carbon concentration absorbed by microbial growth is: , represents the carbon concentration absorbed by microbial growth, and 1.416 is the conversion carbon equivalent of biochemical oxygen demand.

[0108] The formula corresponding to the third sub-mechanism model for describing the carbon dioxide emission fixed by autotrophic bacteria (unit: kg / d, kilograms per day) is: . represents the amount of carbon dioxide fixed by autotrophic bacteria through chemosynthesis during sewage treatment, represents the amount of sludge produced by autotrophic bacteria.

[0109] The formula corresponding to the second sub-mechanism model for describing the carbon dioxide emission from sewage organic matter carbonization (unit: kg / d) is: , represents the amount of carbon dioxide released during the decomposition of organic matter in sewage, c / d represents a preset coefficient, represents the amount of sludge produced by heterotrophic bacteria.

[0110] The formula corresponding to the first sub-mechanism model for describing the carbon dioxide emission from the endogenous respiration of autotrophic and heterotrophic bacteria (unit: kg / d) is: .

[0111] represents the amount of carbon dioxide released during the endogenous respiration of autotrophic and heterotrophic bacteria, represents the hydraulic retention time, AO represents the proportion of autotrophic bacteria. MLVSS represents the total microbial concentration, represents the microbial proliferation concentration, The ratio of is used to characterize the growth of microorganisms in the water treatment system.

[0112] The formula corresponding to the direct carbon dioxide emission mechanism model for describing the total carbon dioxide emission is: ; represents the total amount of directly released carbon dioxide.

[0113] The formula for describing the decomposition process of organic matter in sewage under the action of microorganisms is: ;

[0114] represents the chemical formula of organic matter in sewage, represents the amount of ammonia nitrogen consumed in the reaction, represents the amount of oxygen consumed in the reaction, represents the chemical formula of microbial cells generated in the reaction, Indicates the amount of carbon dioxide released in the reaction, Indicates the amount of water generated in the reaction. The molecular weight of the organic matter in the sewage is 393, the molecular weight of the generated microbial cells is 113, b represents the amount of generated microbial cells, c represents the amount of carbon dioxide released calculated based on the amount of generated microbial cells b, a represents the amount of ammonia nitrogen consumed in the reaction calculated based on the amount of generated microbial cells b, e represents the amount of water generated calculated based on the hydrogen content of the organic matter in the sewage, the amount of ammonia nitrogen consumed, and the amount of generated microbial cells, and d represents the amount of oxygen consumed in the reaction calculated based on the amount of generated microbial cells, the amount of carbon dioxide released, and the amount of water generated. , , , , .

[0115] The preset coefficient c / d is equal to the ratio of the amount of carbon dioxide released calculated based on the amount of generated microbial cells b to the amount of oxygen consumed in the reaction calculated based on the amount of generated microbial cells, the amount of carbon dioxide released, and the amount of water generated.

[0116] In this embodiment, a full-process analytical system for carbon metabolism based on sewage treatment is constructed, and its core logic is to accurately calculate through the source quantification of the microbial metabolic pathway Emissions. This system includes the following key parts:

[0117] Source analysis of carbon footprint: Decompose the Emissions into the carbon fixation offset of autotrophic bacteria, the carbonization emissions of organic matter, and the endogenous respiration emissions of bacteria. This method breaks through the extensiveness of traditional total estimation and realizes a more refined carbon footprint analysis.

[0118] Coupling of metabolic pathways: Based on the utilization of substrates by heterotrophic bacteria and autotrophic bacteria (including BOD degradation and ammonia oxidation) and the dynamic process of endogenous respiration ( / ), a carbon flow balance equation describing the growth and decay process of microorganisms is established.

[0119] Quantitative deduction mechanism for the carbon fixation effect of autotrophic bacteria: Through the formula , quantitatively deduct the carbon fixation effect of autotrophic bacteria and reveal the carbon sink potential in the sewage treatment process.

[0120] Dynamic characterization of endogenous respiration carbon emissions: Combine the sludge age and population structure to dynamically characterize the endogenous respiration carbon emissions to improve the accuracy of accounting.

[0121] Chemical stoichiometry innovation: Construct a degradation reaction formula with elemental conservation for complex organic matter ( ), and observe the yield ( ) Directly associate organic matter transformation with microbial proliferation ( ), and achieve accurate inversion of parameters such as oxygen consumption and generation.

[0122] Step 3: Based on the same temperature and drainage standard, classify and establish a mechanical algorithm training database and a prediction database, and optimize the carbon source addition concentration , microbial proliferation rate and sludge age .

[0123] The method for optimizing the sludge age is as follows: Based on different actual influent ammonia nitrogen concentrations, actual conditions of supplementary carbon source, and discharge compliance standards, different autotrophic bacteria (heterotrophic bacteria) growth sludge ages are required. Therefore, calculate the sludge age (i.e., the second reference value) based on the ammonia nitrogen effluent compliance standard, and calculate the sludge age (i.e., the third reference value) based on the effluent compliance standard / supplementary carbon source / actual conditions of heterotrophic bacteria growth. Secondly, autotrophic bacteria are more sensitive to operating conditions such as dissolved oxygen DO, pH value, and temperature T of sewage, and grow slower than heterotrophic bacteria. Therefore, the sludge age needs to meet the requirements of the actual specific growth rate of autotrophic bacteria, and calculate the sludge age (i.e., the first reference value) based on the growth of autotrophic bacteria. Optimize the sludge age , where max represents taking the maximum value.

[0124] The sludge age based on the growth of autotrophic bacteria .

[0125] The sludge age based on ammonia nitrogen effluent compliance , represents the maximum allowable concentration of ammonia nitrogen specified in the sewage discharge standard.

[0126] The sludge age based on total effluent compliance: , represents the maximum allowable concentration specified in the sewage discharge standard.

[0127] Where ; ( represents that no supplementary carbon source is required), represents the total effluent standard, represents the proportion of volatile suspended solids VSS in the total suspended solids TSS in the effluent, represents the total suspended solids TSS effluent standard.

[0128] ; ( Supplementary carbon source is required because the substrate saturation constant Ks is relatively large. Therefore, the effluent concentration is too low, which affects the growth of heterotrophic bacteria. Thus, according to the semi-empirical coefficient, the minimum value is taken as 5 mg / L.

[0129] Optimization The method is as follows: Under the same temperature condition, the higher the total microbial concentration MLVSS, the higher the microbial proliferation concentration, and the greater the total biological carbon dioxide emissions. Therefore, the optimal microbial concentration in the sewage system is based on the ammonia nitrogen under aerobic nitrification conditions, meeting the standard, TN meeting the standard under anoxic denitrification conditions, and the reasonable reflux denitrification efficiency , to optimize the total microbial concentration . Finally, the ratio of the optimized proliferating microbial concentration to the total microbial concentration (i.e., the preferred microbial proliferation rate) is obtained .

[0130] This solution optimizes MLVSS through a multi-objective collaborative threshold determination, adopts a dual-path driving method, and calculates the MLVSS thresholds that meet the standard, ammonia nitrogen meeting the standard, and total nitrogen meeting the standard (denitrification demand) respectively. Under the constraint of denitrification efficiency, the denitrification rate ( = / ) is introduced to dynamically adjust the denitrification MLVSS demand. When ≤ 85%, the total nitrogen meeting the standard threshold is directly adopted; when > 85%, the MLVSS demand is increased through the denitrification efficiency compensation factor (1 / ) to break through the limitations of the traditional fixed reflux ratio assumption. During global optimization, the maximum threshold of each path (nitrification demand, denitrification demand, high denitrification rate compensation demand) is taken for MLVSS, to ensure that the system simultaneously meets the requirements of organic matter removal, nitrification, and deep denitrification.

[0131] It can be seen that this embodiment adopts the following multi-objective threshold coupling mechanism: Incorporate the degradation of BOD and ammonia nitrogen, total nitrogen removal, and denitrification efficiency engineering constraints into a unified calculation framework, and dynamically select the MLVSS control factor through competitive threshold comparison (max function) to solve the problem of carbon-nitrogen metabolic imbalance caused by traditional single-objective design.

[0132] During the above process, a two-way feedback of sludge proliferation - carbon source iteration is established: The microbial proliferation amount ( ) and the carbon source demand ( ) form a closed-loop optimization through iteration calculation to achieve the coordinated control of sludge concentration and the amount of externally added carbon source.

[0133] Proliferating microbial concentration 。

[0134] Based on and ammonia nitrogen (aerobic nitrification) reaching the standard 。 Indicates the mixed liquor volatile suspended solid concentration based on and ammonia nitrogen reaching the standard.

[0135] Based on TN (anoxic denitrification) reaching the standard 。 Indicates the mixed liquor volatile suspended solid concentration based on total nitrogen reaching the standard, Indicates the minimum total nitrogen concentration that needs to be removed, Indicates the endogenous respiration coefficient.

[0136] Based on reasonable return denitrification efficiency , Indicates the return denitrification efficiency, Indicates the minimum total nitrogen concentration that needs to be removed, Indicates the influent total nitrogen.

[0137] ; Indicates the mixed liquor volatile suspended solid concentration when the return denitrification efficiency is less than or equal to 0.85.

[0138] In the above process, the following dynamic mapping of denitrification efficiency - microbial concentration was established: Establish The MLVSS compensation formula when > 85% ( ), converting the high return ratio constraint that is actually difficult to achieve into the microbial concentration increment requirement, and avoiding the risk of nitrogen removal failure caused by idealized hydrodynamics assumptions. Indicates the mixed liquor volatile suspended solid concentration when the return denitrification efficiency is greater than 0.85.

[0139] Because in actual engineering, the nitrogen removal rate of pre - denitrification is related to the internal return and external return ratios. The higher the denitrification efficiency, the larger the return ratio, and it is difficult to achieve a denitrification efficiency greater than 85%.

[0140] Optimizing the method of adding carbon source: The sources of dissolved carbon in sewage include influent concentration and microbial autotrophic carbon source can also be used as the dissolved carbon source in sewage. In the sewage system, in addition to being dissolved in water, carbon and nitrogen can also form non - dissolved microbial , based on the thermodynamics principle of sewage treatment denitrification, the ratio of dissolved in sewage to dissolved nitrogen (nitrate nitrogen) is 2.86 (all in this plan are calculated based on nitrate nitrogen). The dissolved in sewage is the total influent concentration and microbial autotrophic carbon source and the effluent concentration, microbial proliferation and absorption Difference in concentration. The dissolved nitrogen (nitrate nitrogen) in the sewage is the difference between the influent concentration and the effluent concentration of TN in the sewage and the concentration of TN absorbed by the microbial proliferation. This process requires iterative calculation to complete.

[0141] Using the microbial operation parameters, pollutant influent and effluent concentrations, and engineering operation parameters to cross-form data, and substituting them into the mechanism model in sequence to calculate the output parameters.

[0142] The optimization calculation of the minimum concentration of carbon source added for denitrification (mg / L) is as follows.

[0143] Autotrophic carbon source of microorganisms .

[0144] represents the amount of carbon source produced by autotrophic microorganisms through autotrophication, MLVSS represents the concentration of mixed liquor volatile suspended solids, AO represents the proportion of autotrophic bacteria, represents the endogenous respiration coefficient of autotrophic bacteria, represents the endogenous respiration coefficient of heterotrophic bacteria.

[0145] Minimum carbon-nitrogen ratio .

[0146] represents the minimum carbon-nitrogen ratio, represents the total influent biochemical oxygen demand, represents the effluent biochemical oxygen demand, represents the amount of carbon source absorbed by microbial proliferation, represents the minimum total nitrogen change.

[0147] , represents the calculated amount of carbon source to be added, represents the influent biochemical oxygen demand.

[0148] .

[0149] represents the carbon source addition concentration, and IF{..., ..., ...} represents a conditional judgment statement.

[0150] , represents the actual carbon-nitrogen ratio.

[0151] ( is the nitrate nitrogen concentration in mg / L. In this plan, all nitrate nitrogen is taken, X = 2.86). X represents the theoretical demand ratio of carbon source to nitrate nitrogen in the denitrification process, represents nitrite nitrogen, represents nitrate nitrogen.

[0152] Since it is known that can WC, WN, etc. be calculated, and etc., and , which involves iterative calculations and is completed by Excel (spreadsheet software). In the first step, use the influent water to calculate up to and In the second step, use to calculate up to ; upon completion of the iteration step,[ and The relative error is less than 2%.

[0153] represents the total influent biochemical oxygen demand, WC represents the concentration of carbon absorbed by microbial growth, WN represents the concentration of nitrogen absorbed by microbial growth, represents the carbon source addition concentration, represents the influent biochemical oxygen demand.

[0154] , , and represent the iterative results of the total influent biochemical oxygen demand at the 1st, 2nd, nth, and (n + 1)th steps respectively.

[0155] In this embodiment, a denitrification optimization model that couples the utilization of endogenous carbon sources by microorganisms and the dynamic carbon-nitrogen balance is constructed. Specifically, the generated by the self-decay of activated sludge is used as the denitrification carbon source for quantitative calculation, and the cyclic dependence problem between the total influent BOD and the supplementary carbon source is solved through an iterative algorithm, breaking through the static limitation of the traditional empirical carbon-nitrogen ratio design. In this embodiment, a carbon source hierarchical call mechanism is established to preferentially utilize endogenous carbon to reduce the demand for externally added carbon, and then dynamically trigger carbon source supplementation through condition determination ( > 0) to achieve precise regulation of the carbon-nitrogen ratio; the autotrophic / heterotrophic bacteria decay difference coefficients (AO, , ) are introduced to finely characterize the contribution differences of sludge populations to carbon release, providing a theoretical basis and an engineering optimization path for the denitrification of low carbon-nitrogen ratio sewage.

[0156] This embodiment uses the endogenous carbon source of microorganisms to reduce the demand for externally added carbon sources; approaches the true total influent BOD through iteration until the result is stable; the ultimate goal is to achieve efficient denitrification at the lowest cost.

[0157] The database constructed in this embodiment includes: a first-class A discharge standard database with a temperature between 10 and 12 , and a temperature between 12 and 25 The first-class A discharge standard database between, temperature at 10~12 The first-class B discharge standard database between, and temperature at 12~25 The first-class B discharge standard database between.

[0158] The row labels of the above database include: basic parameters, parameter names, first-class A (10~12 ) parameter values, first-class B (10~12 ) parameter values, and the number of values.

[0159] The column labels of the above database include: microbial operation parameters, pollutant (microbial growth substrate) influent and effluent concentrations / discharge standards, engineering operation parameters, and microbial nutrition parameters.

[0160] Indicates the dissolved oxygen concentration, Indicates the pH value, Indicates the temperature, Indicates the influent total suspended solids, Indicates the influent biochemical oxygen demand, Indicates the total nitrogen influent concentration, Indicates the ammonia nitrogen effluent standard, Indicates the total nitrogen effluent standard, Indicates the biochemical oxygen demand effluent standard, Indicates the total suspended solids effluent standard, Indicates the effluent dissolved Concentration, Indicates the effluent non-dissolved Concentration, Indicates the total effluent biochemical oxygen demand, Indicates the ammonia nitrogen effluent concentration, Indicates the total nitrogen effluent concentration, Indicates the carbon source addition concentration, Indicates the total influent biochemical oxygen demand, Indicates the microbial proliferation concentration, Indicates the total microbial concentration, Indicates the total sludge production in the system, Indicates the influent water volume, Indicates the hydraulic retention time, Indicates the dimensionless parameter, Indicates the autotrophic bacteria ratio, Indicates the reflux denitrification efficiency, Indicates the carbon-nitrogen ratio, Indicates the concentration of nitrogen absorbed by microbial growth, Indicates the concentration of carbon absorbed by microbial growth, Indicates the minimum total nitrogen change.

[0161] Step 4: Train the pollution removal, carbon reduction, and energy consumption reduction model.

[0162] The pollution removal, carbon reduction, and energy consumption reduction model includes a first sub-model, a second sub-model, a third sub-model, a fourth sub-model, a fifth sub-model, a sixth sub-model, a seventh sub-model, an eighth sub-model, and a ninth sub-model.

[0163] The training process of the first sub-model includes: training the minimum concentration of carbon source added to the water treatment system to obtain the total organic matter concentration of the water treatment system : According to the influent and TN water quality concentration, drainage standards (for secondary / level B / level A, establish training databases and prediction databases according to temperature respectively), calculate the carbon source to be added (in terms of converted ), and the sum of the two is the total influent organic matter concentration of the sewage treatment system . Round to the integer place, and in the SPSSPRO (an online statistical analysis platform) software, convert it into categorical data. Using the BP (BackPropagation, feedforward) neural network machine classification algorithm, based on DO, pH, , , , , , total nitrogen change , recall rate 0.902, average absolute error of the test set 0.89%.

[0164] The above BP neural network machine classification algorithm is a multi-layer feedforward network trained by the error backpropagation algorithm and is one of the most widely used neural network models at present. The learning rule of the BP neural network is to use the steepest descent method and continuously adjust the weights and thresholds of the network through backpropagation to minimize the classification error rate of the network.

[0165] The training process of the second sub-model includes: training the optimal proportion of autotrophic bacteria AO in the water treatment system. Using the BP neural network machine classification algorithm, based on T, DO, pH, , , train the proportion of autotrophic bacteria , recall rate 0.967, average relative error of the test set 0.42%.

[0166] The training process of the third sub-model includes: training the optimized sludge age for the simultaneous attainment of carbon-containing pollutants and nitrogen-containing pollutants , round to two decimal places, and in the SPSSPRO software, convert it into categorical data. Using the BP neural network machine classification algorithm, based on DO, pH, T, AO, recall rate 1, average absolute error of the test set 0%.

[0167] The training process of the fourth sub-model includes: training the growth concentration of water treatment microorganisms , using the adaboost machine regression algorithm, based on DO, pH, , , , , , AO, , training , with a goodness of fit of 1 and an average relative error of 1.62% in the test set.

[0168] The above adaboost is a machine learning regression algorithm that can be implemented and calculated through the SPSSPRO statistical software. Adaboost gives a high weight to the learner with a low error rate and a low weight to the learner with a high error rate, and combines the weak learner and the corresponding weights to generate a strong learner. The difference between the regression problem and the classification problem algorithms lies in the different ways of calculating the error rate. The classification problem generally uses the 0 / 1 loss function, while the regression problem generally uses the squared loss function or the linear loss function. The independent variable X is one or more categorical or quantitative variables, and the dependent variable Y is a quantitative variable.

[0169] The training process of the fifth sub-model includes: training the carbon dioxide emissions in the biological treatment process of autotrophic and heterotrophic bacteria: using the BP neural network machine regression algorithm, based on T, DO, pH, AO, , , , training the carbon dioxide emissions, with a goodness of fit of 0.997 and an average relative error of 1.48%.

[0170] The training process of the sixth sub-model includes: training the optimal reflux denitrification ratio : using the lighGBM (Lightweight Gradient Boosting Machine) machine regression algorithm, based on T, DO, pH, AO, , , carbon dioxide emissions, training the reflux denitrification ratio , with a goodness of fit of 0.999 and an average relative error of 0.39%.

[0171] LightGBM is a machine learning regression algorithm that can be implemented and calculated through SPSSPRO statistical software. LightGBM is an efficient implementation of XGBoost (Extreme Gradient Boosting). Its idea is to discretize continuous floating-point features into k discrete values and construct a histogram with a width of k. Traverse the training data and calculate the cumulative statistics of each discrete value in the histogram. When performing feature selection, only need to traverse and find the optimal splitting point according to the discrete values of the histogram; and use the leaf-wise strategy with depth limit, which saves a lot of time and space overhead. The independent variable is one or more categorical or quantitative variables, and the dependent variable Y is a quantitative variable.

[0172] The training process of the seventh sub-model includes: based on suspended solids SS (Suspended Solids) and achieving the maximum concentration of dissolved organic matter in the effluent meeting the standard Using the decision tree regression algorithm, based on T, pH, , training the maximum concentration The goodness of fit is 0.998, and the average absolute error of the test set is 0.12%.

[0173] The training process of the eighth sub-model includes: achieving the maximum concentration of ammonia nitrogen in the effluent based on meeting the standard , using the decision tree regression algorithm, based on T, pH, DO, , , training the maximum concentration The goodness of fit is 0.999, and the average absolute error of the test set is 6.8%.

[0174] The training process of the ninth sub-model includes: achieving the minimum total nitrogen removal concentration of the sewage treatment system based on TN and ammonia nitrogen meeting the standard , using the adaboost regression algorithm, based on , , , , training the minimum total nitrogen removal concentration , the goodness of fit is 1, and the average absolute error of the test set is 0.55%.

[0175] Step 5: Optimize the actual operation of the sewage based on the above steps.

[0176] Biological methods for removing nitrogen from sewage require alternating aerobic nitrification and anoxic denitrification environments. During this process, the carbon-nitrogen ratio needs to be maintained at a certain proportion. If it is too low, the carbon source in the system is insufficient, and when denitrification is required, additional carbon sources need to be added, resulting in additional carbon dioxide emissions. Therefore, when optimizing the process, it is better to add less or no carbon source.

[0177] The process parameter control steps in this embodiment include: (1) determining a reasonable carbon source addition concentration based on the optimized carbon-nitrogen ratio, operating conditions, and inlet and outlet pollutant concentrations; (2) based on the graded drainage standards at different temperatures, biochemical oxygen demand (BOD), suspended solids concentration (SS), ammonia nitrogen, and TN inlet concentrations, and on the principle of "all pollutants meet the standards at the same time and do not blindly increase the drainage standards", optimizing the sludge age, mixed liquor volatile suspended solids concentration (MLVSS), total reflux ratio, and reasonable effluent concentrations of each pollutant.

[0178] Traditional sewage treatment technologies often focus on single-target optimization, such as blindly improving treatment efficiency or reducing energy consumption, but ignore the synergistic effects between multiple targets. For example, while improving treatment efficiency, energy consumption increases significantly; or segmented management is adopted to separate carbon reduction and pollution removal, lacking a systematic solution. In addition, existing technologies focus too much on indirect carbon footprints and ignore the significant impact of direct carbon emissions. In fact, direct carbon emissions from sewage treatment are closely related to aeration, nitrification liquid reflux, denitrification carbon source addition and other links, and are in urgent need of in-depth research and optimization. This embodiment focuses on the direct carbon footprint emission nodes of biological sewage treatment. By constructing a classic model of carbon footprint nodes, establishing an algorithm database, screening and mining traditional and potential sewage parameters, and intelligently optimizing operating conditions. While ensuring that pollutants are discharged in compliance with standards, the direct carbon footprint emissions are significantly reduced, and the operating energy consumption is reduced, so as to achieve the coordinated optimization of the triple goals of "pollution removal, carbon reduction, and consumption reduction."

[0179] See also Figure 2 , Figure 2 A schematic diagram of a device for setting operating parameters of a sewage treatment system provided in an embodiment of the present application includes:

[0180] The modeling module 201 is used to determine the correlation between the direct pollution footprint nodes and the microbial operation parameters in the sewage treatment process, and use the correlation to establish a sewage direct characteristic gas emission mechanism model.

[0181] The preferred parameter determination module 202 is used to determine the values of multiple preferred operating parameters according to the sewage discharge standard.

[0182] The database construction module 203 is used to construct a database according to the range of operating parameter values and the sewage direct characteristic gas emission mechanism model.

[0183] The model training module 204 is used to train the pollution removal, carbon reduction and energy consumption reduction model using the database and the preferred operating parameters.

[0184] The parameter setting module 205 is configured to input the actual operating parameters of the sewage treatment system into the sewage treatment, carbon reduction, and energy consumption reduction model after the model training is completed, so as to obtain target operating parameters, and control the sewage treatment system to operate according to the target operating parameters.

[0185] This embodiment provides a method for setting the operating parameters of a sewage treatment system. According to the correlation between the direct pollution footprint nodes and the microbial operating parameters, a sewage direct characteristic gas emission mechanism model is established. Then, in combination with the operating parameter value range and the sewage direct characteristic gas emission mechanism model, a database is constructed to provide data support for model training. This embodiment also determines the values of multiple preferred operating parameters according to the sewage discharge standards, and trains the sewage treatment, carbon reduction, and energy consumption reduction model based on the constructed database and the preferred operating parameters. The trained sewage treatment, carbon reduction, and energy consumption reduction model learns the setting strategy of the operating parameters. By inputting the actual operating parameters of the sewage treatment system into the model, target operating parameters are obtained, so that the sewage treatment system operates according to the target operating parameters. In this embodiment, the database used to train the sewage treatment, carbon reduction, and energy consumption reduction model is constructed based on the direct sewage direct characteristic gas emission mechanism model and the sewage discharge standards. The operating parameters output by the sewage treatment, carbon reduction, and energy consumption reduction model can not only ensure the effluent quality but also maximize carbon reduction and energy consumption reduction.

[0186] Further, the process of the modeling module 201 establishing the sewage direct characteristic gas emission mechanism model using the correlation includes: establishing the sewage direct characteristic gas emission mechanism model based on the correlation, the microbial growth and death mechanism, and the sewage microorganism ratio calculation formula; wherein, the sewage direct characteristic gas emission mechanism model includes a first sub-mechanism model, a second sub-mechanism model, and a third sub-mechanism model; the first sub-mechanism model is used to simulate the mechanism of the sewage microorganisms emitting characteristic gases during endogenous respiration, the second sub-mechanism model is used to simulate the mechanism of sewage organic matter carbonization and emission, and the third sub-mechanism model is used to simulate the mechanism of sewage microorganisms fixing characteristic gases.

[0187] Further, it further includes: a preferred operating parameter determination module, configured to determine the influence degree of each operating parameter on the total sewage direct characteristic gas emission amount during the sewage treatment process using a mediation effect model or a causal relationship model before determining the values of multiple preferred operating parameters according to the sewage discharge standards, and set the operating parameters with an influence degree greater than a preset value as the preferred operating parameters.

[0188] Further, the preferred operating parameters include any one or a combination of several of a preferred sludge age, a preferred microbial growth rate, a preferred carbon source addition concentration, and a preferred sewage microorganism ratio.

[0189] Further, the process of the preferred operating parameter determination module determining the values of multiple preferred operating parameters according to the sewage discharge standard includes: determining a first reference value and a second reference value according to the sewage discharge standard, and setting the maximum value of the first reference value and the second reference value as the value of the preferred sludge age; wherein, the first reference value is the sludge age value that meets the sewage microorganism growth rate requirement, and the second reference value is the sludge age value that enables the effluent concentration of the sewage characteristic pollutants to meet the standard.

[0190] Determine a third reference value, a fourth reference value and a fifth reference value according to the sewage discharge standard, and set the maximum value of the third reference value, the fourth reference value and the fifth reference value as the preferred total microorganism concentration, and set the ratio of the microorganism proliferation concentration to the preferred total microorganism concentration as the preferred microorganism proliferation rate; wherein, the third reference value is the total microorganism concentration that enables the concentration of the sewage characteristic pollutants to meet the standard; the fourth reference value is the total microorganism concentration that enables the denitrification efficiency to meet the standard under anoxic conditions; the fifth reference value is the total microorganism concentration that enables the reflux denitrification efficiency to meet the standard.

[0191] Dynamically adjust the relationship between the microorganism proliferation absorption amount and the carbon and nitrogen consumption amount based on the first calculation formula and the second calculation formula so that the ratio of the dissolved biochemical oxygen demand to the dissolved nitrate nitrogen amount reaches the target ratio; calculate the preferred carbon source addition concentration according to the dissolved biochemical oxygen demand and the dissolved nitrate nitrogen amount when the ratio reaches the target ratio; wherein, the first calculation formula is the formula for calculating the dissolved biochemical oxygen demand, and the second calculation formula is the formula for calculating the dissolved nitrate nitrogen amount.

[0192] Further, the pollution removal, carbon reduction and energy consumption reduction model includes a first sub-model, a second sub-model, a third sub-model, a fourth sub-model, a fifth sub-model, a sixth sub-model and a pollution removal algorithm sub-model.

[0193] Correspondingly, the process of the model training module 204 training the pollution removal, carbon reduction and energy consumption reduction model by using the database and the preferred operating parameters includes: extracting alternative operating parameters from the database; wherein, the alternative operating parameters include any one or a combination of several of temperature, dissolved oxygen, pH, sewage characteristic pollutant inlet index value and sewage characteristic pollutant outlet index value.

[0194] Taking the alternative operating parameters as the input and the preferred carbon source addition concentration as the target value, iteratively train the first sub-model by using the backpropagation neural network classification algorithm.

[0195] Taking the alternative operating parameters as the input and the sewage microorganism ratio in the database as the target value, iteratively train the second sub-model by using the backpropagation neural network classification algorithm.

[0196] Taking the alternative operating parameters and the proportion of sewage microorganisms output by the second sub-model as inputs, and taking the preferred sludge age as the target value, the third sub-model is iteratively trained using the backpropagation neural network classification algorithm.

[0197] Taking the alternative operating parameters and the proportion of sewage microorganisms output by the second sub-model as inputs, and taking the preferred microorganism growth rate as the target value, the fourth sub-model is iteratively trained using the adaptive boosting regression algorithm.

[0198] Taking the alternative operating parameters, the proportion of sewage microorganisms output by the second sub-model, the sludge age output by the third sub-model, and the microorganism growth rate output by the fourth sub-model as inputs, and taking the direct emission amount of characteristic gas in the database as the target value, the fifth sub-model is iteratively trained using the backpropagation neural network classification algorithm.

[0199] Taking the alternative operating parameters, the proportion of sewage microorganisms output by the second sub-model, the microorganism growth rate output by the fourth sub-model, and the characteristic gas emission amount output by the fifth sub-model as inputs, and taking the reflux denitrification ratio in the database as the target value, the sixth sub-model is iteratively trained using the machine learning regression algorithm.

[0200] Taking the alternative operating parameters as inputs, and taking the maximum concentration of the preferred microorganism metabolizing pollutants reaching the standard effluent in the database as the target value, the decontamination algorithm sub-model is iteratively trained using the machine regression algorithm.

[0201] Further, the process of the database construction module 203 constructing the database according to the operating parameter value range and the sewage direct characteristic gas emission mechanism model includes: performing a non-fixed step size value-taking operation within the operating parameter value range according to the sensitivity of microorganisms to operating parameters to obtain multiple groups of initial operating parameters; using the sewage direct characteristic gas emission mechanism model to calculate the initial operating parameters to obtain the parameter calculation results corresponding to each group of the initial operating parameters; constructing the database including the initial operating parameters and the parameter calculation results.

[0202] Since the embodiments of the device part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the device part, and will not be elaborated here.

[0203] The present application also provides a storage medium on which a computer program is stored, and when the computer program is executed, the steps provided by the above embodiments can be implemented. The storage medium may include: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0204] The present application also provides an electronic device, which may include a memory and a processor. A computer program is stored in the memory. When the processor calls the computer program in the memory, the steps provided in the above embodiments can be implemented. Of course, the electronic device may further include various network interfaces, power supplies and other components.

[0205] The various embodiments in the specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For the relevant parts, reference can be made to the description in the method part. It should be noted that for those of ordinary skill in the art in the technical field of the present application, without departing from the principle of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope of the present application.

[0206] It should also be noted that in this specification, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including the element.

Claims

1. A method for setting operating parameters of a sewage treatment system, characterized in that, Including: Determine the correlation between the direct pollutant generation footprint nodes and the microbial operation parameters in the sewage treatment process, and establish a sewage direct characteristic gas emission mechanism model using the correlation; Determine the numerical values of multiple preferred operation parameters according to the sewage discharge standard; Construct a database based on the operation parameter value range and the sewage direct characteristic gas emission mechanism model; Train the sewage treatment and carbon reduction and energy consumption reduction model using the database and the preferred operation parameters; After the sewage treatment and carbon reduction and energy consumption reduction model is trained, input the actual operation parameters of the sewage treatment system into the sewage treatment and carbon reduction and energy consumption reduction model to obtain the target operation parameters, so as to control the sewage treatment system to operate according to the target operation parameters.

2. The method for setting the operating parameters of the sewage treatment system according to claim 1, wherein Establishing the sewage direct characteristic gas emission mechanism model using the correlation includes: Establish the sewage direct characteristic gas emission mechanism model based on the correlation, the microbial growth and death mechanism, and the sewage microorganism ratio calculation formula; Among them, the sewage direct characteristic gas emission mechanism model includes a first sub-mechanism model, a second sub-mechanism model, and a third sub-mechanism model; the first sub-mechanism model is used to simulate the mechanism of characteristic gas emission during the endogenous respiration of sewage microorganisms, the second sub-mechanism model is used to simulate the mechanism of sewage organic matter carbonization emission, and the third sub-mechanism model is used to simulate the mechanism of sewage microorganism fixed characteristic gas.

3. The method for setting the operating parameters of the sewage treatment system according to claim 1, wherein, Before determining the numerical values of multiple preferred operation parameters according to the sewage discharge standard, it also includes: Use the mediating effect model or causal relationship model to determine the influence degree of each operation parameter on the total sewage direct characteristic gas emission amount during the sewage treatment process, and set the operation parameters with an influence degree greater than the preset value as the preferred operation parameters.

4. The method for setting the operating parameters of the sewage treatment system according to claim 1, characterized in that The preferred operation parameters include any one or a combination of any several of the preferred sludge age, preferred microbial proliferation rate, preferred carbon source addition concentration, and preferred sewage microorganism ratio.

5. The method for setting the operating parameters of the sewage treatment system according to claim 1, characterized in that Determining the numerical values of multiple preferred operation parameters according to the sewage discharge standard includes: Determine a first reference value and a second reference value according to the sewage discharge standard, and set the maximum value of the first reference value and the second reference value as the numerical value of the preferred sludge age; among them, the first reference value is the sludge age value that meets the sewage microorganism growth rate requirement, and the second reference value is the sludge age value that makes the effluent concentration of sewage characteristic pollutants reach the standard; Determine a third reference value, a fourth reference value, and a fifth reference value according to the sewage discharge standard, and set the maximum value of the third reference value, the fourth reference value, and the fifth reference value as the preferred total microorganism concentration, and set the ratio of the microbial proliferation concentration to the preferred total microorganism concentration as the preferred microbial proliferation rate; among them, the third reference value is the total microorganism concentration that makes the sewage characteristic pollutant concentration reach the standard; the fourth reference value is the total microorganism concentration that makes the denitrification efficiency reach the standard under anoxic conditions; the fifth reference value is the total microorganism concentration that makes the reflux denitrification efficiency reach the standard. Dynamically adjust the relationship between the microbial proliferation absorption amount and the carbon and nitrogen consumption amounts based on the first calculation formula and the second calculation formula, so that the ratio of the dissolved biochemical oxygen demand to the dissolved nitrate nitrogen amount reaches the target ratio; calculate the preferred carbon source addition concentration according to the dissolved biochemical oxygen demand and the dissolved nitrate nitrogen amount when the ratio reaches the target ratio; wherein, the first calculation formula is the formula for calculating the dissolved biochemical oxygen demand, and the second calculation formula is the formula for calculating the dissolved nitrate nitrogen amount.

6. The method for setting the operating parameters of the sewage treatment system according to claim 5, characterized in that, The sewage treatment, carbon reduction and energy consumption reduction model includes a first sub-model, a second sub-model, a third sub-model, a fourth sub-model, a fifth sub-model, a sixth sub-model and a sewage treatment algorithm sub-model; Correspondingly, training the sewage treatment, carbon reduction and energy consumption reduction model by using the database and the preferred operating parameters includes: Extracting alternative operating parameters from the database; wherein, the alternative operating parameters include any one or a combination of several of temperature, dissolved oxygen, pH, influent index values of sewage characteristic pollutants and effluent index values of sewage characteristic pollutants; Using the alternative operating parameters as the input and the preferred carbon source addition concentration as the target value, iteratively training the first sub-model by using the backpropagation neural network classification algorithm; Using the alternative operating parameters as the input and the sewage microbial proportion in the database as the target value, iteratively training the second sub-model by using the backpropagation neural network classification algorithm; Using the alternative operating parameters and the sewage microbial proportion output by the second sub-model as the input and the preferred sludge age as the target value, iteratively training the third sub-model by using the backpropagation neural network classification algorithm; Using the alternative operating parameters and the sewage microbial proportion output by the second sub-model as the input and the preferred microbial proliferation rate as the target value, iteratively training the fourth sub-model by using the adaptive boosting regression algorithm; Using the alternative operating parameters, the sewage microbial proportion output by the second sub-model, the sludge age output by the third sub-model and the microbial proliferation rate output by the fourth sub-model as the input and the direct emission amount of characteristic gas in the database as the target value, iteratively training the fifth sub-model by using the backpropagation neural network classification algorithm; Using the alternative operating parameters, the sewage microbial proportion output by the second sub-model, the microbial proliferation rate output by the fourth sub-model and the characteristic gas emission amount output by the fifth sub-model as the input and the reflux denitrification ratio in the database as the target value, iteratively training the sixth sub-model by using the machine learning regression algorithm; Using the alternative operating parameters as the input and the maximum concentration of the preferred microbial metabolism of pollutants reaching the standard effluent in the database as the target value, iteratively training the sewage treatment algorithm sub-model by using the machine regression algorithm.

7. The method for setting the operating parameters of the sewage treatment system according to claim 1, wherein, Construct a database according to the operating parameter value range and the sewage direct characteristic gas emission mechanism model, including: Performing a value-taking operation with a non-fixed step size within the operating parameter value range according to the sensitivity of the microorganism to the operating parameters to obtain multiple groups of initial operating parameters; Calculating the initial operating parameters by using the direct characteristic gas emission mechanism model of the sewage to obtain the parameter calculation results corresponding to each group of the initial operating parameters; Constructing the database including the initial operating parameters and the parameter calculation results.

8. An operating parameter setting device for a sewage treatment system, characterized in that, Comprising: A modeling module, configured to determine the correlation between the direct pollution generation footprint nodes and the microbial operating parameters in the sewage treatment process, and establish a direct characteristic gas emission mechanism model of the sewage by using the correlation; An optimal parameter determination module, configured to determine the values of a plurality of optimal operating parameters according to the sewage discharge standard; A database construction module, configured to construct a database according to the operating parameter value range and the direct characteristic gas emission mechanism model of the sewage; A model training module, configured to train the pollution removal, carbon reduction and energy consumption reduction model by using the database and the optimal operating parameters; A parameter setting module, configured to, after the pollution removal, carbon reduction and energy consumption reduction model is trained, input the actual operating parameters of the sewage treatment system into the pollution removal, carbon reduction and energy consumption reduction model to obtain the target operating parameters, so as to control the sewage treatment system to operate according to the target operating parameters.

9. An electronic device, characterized in that, Comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps of the method for setting the operating parameters of the sewage treatment system according to any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that, Computer-executable instructions are stored in the storage medium, and when the computer-executable instructions are loaded and executed by a processor, the steps of the method for setting the operating parameters of the sewage treatment system according to any one of claims 1 to 7 are implemented.

Images