Intelligent carbon source dosing method, system and storage medium for sewage treatment

Abstract

The present invention provides a method, system and storage medium for intelligent carbon source dosing in sewage treatment, and relates to the field of intelligent planning technology. The present invention comprehensively analyzes the effects of target heavy metals and target fungicides, and utilizes regression and optimization techniques to accurately control the carbon source dosing process. At the same time, it provides an intelligent neutralizer and carbon source adjustment strategy based on actual error judgment to maximize denitrification efficiency and optimize the configuration of system resources. This improves the accuracy and stability of carbon source dosing, and lays a technical foundation for the long-term sustainable operation of sewage treatment.

Description

Technical Field

[0001] The present invention relates to the field of intelligent planning technology, and in particular to a method, system and storage medium for intelligent carbon source addition in sewage treatment. Background Art

[0002] Denitrifying biological filters are widely used in the treatment of nitrogen-containing wastewater. Denitrifying bacteria convert nitrate nitrogen into nitrogen gas and release it to reduce the harm of nitrogen pollution in wastewater to the ecological environment. However, the pollutants in wastewater are complex, especially heavy metals and fungicides, which can have adverse effects on microbial activity and directly weaken the denitrification effect. Therefore, it is an important research direction for wastewater treatment to maintain the functional bacteria of the system at an efficient activity level by precisely controlling the amount of carbon source added during the denitrification process. Traditional carbon source addition methods are usually based on empirical rules and lack sufficient scientific basis. Their addition strategies often have problems such as resource waste, insufficient treatment or microbial metabolic imbalance. In recent years, with the development of sensor monitoring technology, machine learning algorithms and refined control technology, the construction of data modeling methods based on the operating conditions of sewage systems has provided the possibility of achieving precise control of carbon source addition.

[0003] In the prior art, the publication number is CN117892970A, and the name is a carbon source intelligent dosing method, system and storage medium, which involves the field of intelligent planning. The method includes: constructing a multi-parameter prediction model for carbon source dosing based on historical water quality parameters and historical operating parameters in historical data; real-time detection of real-time water quality parameters and real-time operating parameters in the sewage treatment process to obtain a real-time detection data set; inputting the real-time detection data set into the multi-parameter prediction model to obtain an optimized carbon source dosage; when the difference between the optimized carbon source dosage and the current actual dosage is within the allowable error range, maintaining the current carbon source dosage; when the difference between the optimized carbon source dosage and the current actual dosage exceeds the allowable error range, gradually adjusting the current carbon source dosage in a step-by-step manner. Implementing this method, the carbon source dosage is dynamically adjusted according to actual working conditions, rather than simply fixed addition, which improves the flexibility of dosage control and achieves better treatment effects.

[0004] Although there are some advanced carbon source dosing control methods, existing technologies are still insufficient in dealing with complex influencing factors (such as the inhibitory effects of heavy metals and fungicides on microorganisms). On the one hand, most technologies ignore the dynamic effects of heavy metals or fungicides on microbial activity and fail to fully capture the complex relationship between them and carbon source demand. On the other hand, existing methods for dynamic carbon source dosing control mainly rely on linear or empirical deductions and fail to combine multi-dimensional dynamic constraints (such as dosing dosage and the neutralization effect of heavy metals and fungicides). This results in low carbon source utilization and may even cause secondary pollution or decreased microbial activity due to excessive or insufficient dosing. Existing technologies lack effective solutions.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a method, system and storage medium for intelligently adding carbon sources to sewage treatment to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The intelligent carbon source dosing method for sewage treatment includes the following specific steps:

[0009] Step S1: determining target heavy metals and target fungicides that are strongly correlated with the microbial activity evaluation index, obtaining the microbial activity evaluation index, target heavy metal concentration, and target fungicide concentration of the current denitrifying biological filter at different times during the monitoring period, wherein the microbial activity evaluation index is determined based on the microbial respiration rate and the microbial denitrification rate, and summarizing the target heavy metal concentration, target fungicide concentration, and microbial activity evaluation index to form a historical data set;

[0010] Step S2: Based on the historical data set, the target heavy metal concentration and target fungicide concentration are used as independent variables, and the microbial activity evaluation index is used as the dependent variable, and a multivariate linear regression is used to construct a microbial activity prediction model;

[0011] Step S3: Based on the constructed microbial activity prediction model and in combination with the target heavy metal concentration and target fungicide concentration obtained in real time, the predicted value of the microbial activity evaluation index at the current moment is calculated;

[0012] Based on the calculated predicted values ​​of microbial activity evaluation indicators, the carbon source dosage requirement in the sewage treatment process is determined using a linear optimization equation;

[0013] Step S4: Compare the calculated carbon source dosage requirement with the actual carbon source dosage currently added to determine whether the error is within a preset allowable threshold, and then obtain an error judgment result for providing an adjustment addition strategy for the actual carbon source dosage.

[0014] A sewage treatment carbon source intelligent dosing system, the system is used to implement the sewage treatment carbon source intelligent dosing method, comprising:

[0015] Range value determination module: used to determine the target heavy metals and target fungicides that are strongly correlated with the microbial activity evaluation index, obtain the microbial activity evaluation index, target heavy metal concentration, and target fungicide concentration of the current denitrification biofilter at different times during the monitoring period. The microbial activity evaluation index is determined based on the microbial respiration rate and microbial denitrification rate, and the target heavy metal concentration, target fungicide concentration, and microbial activity evaluation index are aggregated to form a historical data set;

[0016] Prediction model building module: used to build a microbial activity prediction model based on historical data sets, with target heavy metal concentrations and target fungicide concentrations as independent variables and microbial activity evaluation indicators as dependent variables, using multiple linear regression;

[0017] Calculation and analysis module: used to calculate the predicted value of the microbial activity evaluation index at the current moment based on the constructed microbial activity prediction model and combined with the real-time acquired target heavy metal concentration and target fungicide concentration;

[0018] Based on the calculated predicted values ​​of microbial activity evaluation indicators, the carbon source dosage requirement in the sewage treatment process is determined using a linear optimization equation;

[0019] Judgment and adjustment module: used to compare the calculated carbon source addition demand with the actual carbon source addition amount currently put in to determine whether the error is within the preset allowable threshold, and then obtain the error judgment result used to provide an adjustment addition strategy for the actual carbon source addition amount.

[0020] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the intelligent carbon source addition method for sewage treatment.

[0021] Compared with the existing technology, the beneficial effects of the present invention are: by comprehensively analyzing the effects of target heavy metals and target fungicides, and using regression and optimization techniques, the carbon source addition process is accurately controlled, and at the same time, combined with actual error judgment, an intelligent neutralizer and carbon source adjustment strategy is provided to maximize denitrification efficiency and optimize the configuration of system resources; it improves the accuracy and stability of carbon source addition, and lays a technical foundation for the long-term sustainable operation of sewage treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic diagram of the process of the intelligent carbon source dosing method for sewage treatment according to the present invention;

[0023] Figure 2 This is a system module block logic diagram of the intelligent carbon source addition method for sewage treatment using the present invention. DETAILED DESCRIPTION

[0024] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0025] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0026] Example 1:

[0027] See also Figure 1 , the present invention provides a technical solution:

[0028] The intelligent carbon source dosing method for sewage treatment includes the following specific steps:

[0029] Step S1: determining target heavy metals and target fungicides that are strongly correlated with the microbial activity evaluation index, obtaining the microbial activity evaluation index, target heavy metal concentration, and target fungicide concentration of the current denitrifying biological filter at different times during the monitoring period, wherein the microbial activity evaluation index is determined based on the microbial respiration rate and the microbial denitrification rate, and summarizing the target heavy metal concentration, target fungicide concentration, and microbial activity evaluation index to form a historical data set;

[0030] Further explanation: First, the target heavy metals and target fungicides are determined as follows:

[0031] For target heavy metals, including: lead (Pb), cadmium (Cd), chromium (Cr), mercury (Hg), copper (Cu);

[0032] For target fungicides, they include: chlorine, sodium hypochlorite, ozone, and various antibiotics (such as penicillin, tetracycline, etc.);

[0033] The above-mentioned target heavy metals and target fungicides were screened and determined by the following methods;

[0034] In the current denitrifying biofilter, a target heavy metal with the greatest impact on microbial activity is selected from lead (Pb), cadmium (Cd), chromium (Cr), mercury (Hg), and copper (Cu);

[0035] Select a target fungicide that has the greatest impact on microbial activity from chlorine, sodium hypochlorite, ozone, and multiple antibiotics (such as penicillin, tetracycline, etc.);

[0036] Expert experience and literature research:

[0037] Learn from the experience of experts in related fields or academic literature to understand which heavy metals and fungicides have typically had significant effects on microbial activity in previous studies or case studies.

[0038] Visual observation of microbial activity:

[0039] Based on the records of observing changes in microbial activity, it is possible to determine which heavy metals or fungicides have obvious inhibitory effects on microbial activity when their concentrations change. This "observation-judgment" approach can quickly identify problematic substances.

[0040] An atomic absorption spectrometer is configured for online monitoring of target heavy metal concentrations in wastewater.

[0041] A liquid chromatography-mass spectrometry system was set up for online monitoring of the target fungicide concentration.

[0042] Start the atomic absorption spectrometer to measure and record the target heavy metal concentration in the sewage in real time, and record the target heavy metal concentration as C metal ;

[0043] Start the liquid chromatography-mass spectrometry system to measure and record the target fungicide concentration data in the sewage in real time, and record the target fungicide concentration as C drug ;

[0044] The monitoring data C metal and C drug Automatically transmit to the monitoring center database;

[0045] Determining target heavy metals and target fungicides that are strongly correlated with microbial activity evaluation indicators includes: obtaining the microbial activity evaluation indicators of the current denitrifying biological filter at different times during the monitoring period, as well as the concentrations of various heavy metals and fungicides, and using these obtained data as a data set. Based on the calculation results of the Pearson correlation coefficient, the heavy metal concentrations and fungicide concentrations that are strongly correlated with the microbial activity evaluation indicators are screened out to determine them as the target heavy metal concentrations and target fungicide concentrations;

[0046] Based on the calculation results of the Pearson correlation coefficient, it specifically includes: determining that the collected data set contains data on three variables: microbial activity evaluation index, heavy metal concentration, and fungicide concentration;

[0047] Calculate the Pearson correlation coefficient:

[0048] The Pearson correlation coefficient was calculated for each pair of variables (microbial activity evaluation index and heavy metal concentration, microbial activity evaluation index and fungicide concentration). The Pearson correlation coefficient (r) is a statistic used to measure the strength and direction of the linear relationship between two variables. The value ranges from -1 to 1, as follows:

[0049] r = 1 indicates a perfect positive correlation;

[0050] r = -1 indicates a perfect negative correlation;

[0051] r = 0 means no correlation;

[0052] Screening for highly correlated variables: Set a strong correlation threshold of |r| > 0.5 to determine which heavy metal concentrations and fungicide concentrations have significant correlations with the microbial activity evaluation index. Based on the calculated Pearson correlation coefficient, select the heavy metal concentrations and fungicide concentrations that meet the threshold condition and have the largest |r| as the target heavy metal concentrations and target fungicide concentrations.

[0053] The microbial activity evaluation index is defined as MAI i , the calculation formula is as follows:

[0054] MAI i =a1×SOUR i +a2×NUR i

[0055] Among them, SOUR i is the respiration rate of microorganisms in the denitrifying biofilter at the i-th moment in the monitoring period, NUR i is the denitrification rate of microorganisms in the denitrifying biological filter at the i-th moment in the monitoring period, a1 and a2 are the weight values ​​of the corresponding parameters, and a1+a2=1, and the values ​​of a1 and a2 are both in the interval (0,1).

[0056] It should be noted that when SOUR i or NUR i The larger the value, the higher the respiration rate and denitrification rate, which in turn means greater microbial activity.

[0057] SOUR i The calculation formula is as follows:

[0058]

[0059] Among them, O 2xh,i Is the denitrification biological filter in {C metal,i ,C drug,i The amount of oxygen consumed per unit time under the combination, O 2xh,ixh represents “consumption”; t is the time (hours) used to consume oxygen; M1 is the total amount of microorganisms in the activated sludge; C metal,i1 is the target heavy metal concentration at the current moment; C drug,i1 is the target fungicide concentration at the current moment;

[0060] NUR i The calculation formula is as follows:

[0061]

[0062] Among them, Nq xh,i Is the denitrification biological filter in {C metal,i ,C drug,i}The amount of nitrogen removed per unit time under this combination.

[0063] It is further explained that the target heavy metal concentration range values ​​and the target fungicide concentration range values ​​are divided into multiple impact levels, and the impact level judgment results are comprehensively obtained. The higher the impact level, the greater the impact on the microbial activity evaluation index;

[0064] In the current denitrifying biological filter, a first neutralizer and a second neutralizer are respectively determined for reducing the target heavy metal concentration and the target fungicide concentration;

[0065] Setting the expected reduction ratio of the target heavy metal concentration by the first neutralizer at a preset addition amount; and the expected reduction ratio of the target fungicide concentration by the second neutralizer at a preset addition amount;

[0066] The first neutralizing agent is defined as being capable of reacting with the target heavy metal to form an insoluble precipitate;

[0067] For example, calcium-based compounds such as lime are used for precipitation treatment of lead, copper, etc.

[0068] Sulfide sodium sulfide, etc.: used to form sulfide precipitation with target heavy metals (mercury, cadmium);

[0069] The second neutralizing agent is defined as being capable of reducing or oxidizing the target fungicide, rendering the target fungicide inactive;

[0070] For example: sodium sulfite or sodium thiosulfate: used to neutralize the residual chlorine in the target fungicide.

[0071] The expected reduction ratio of the target heavy metal concentration by the first neutralizer at a preset addition amount is set to A1%;

[0072] The expected reduction ratio of the target fungicide concentration by the second neutralizer at a preset addition amount is set to A2%;

[0073] Impact level determination results include:

[0074] The threshold interval of target heavy metal concentration is set as [C metal,min ,C metal,max ]; C metal,min ,C metal,max are the lower and upper limits of the threshold interval corresponding to the target heavy metal concentration;

[0075] will be below the threshold interval [C metal,min ,C metal,max ]’s target heavy metal concentration is classified as heavy metal low impact level L1;

[0076] will be in the threshold interval [C metal,min ,C metal,max ]’s target heavy metal concentration is classified as impact level L2 among heavy metals;

[0077] will be above the threshold interval [C metal,min ,C metal,max ]’s target heavy metal concentration is classified as heavy metal high impact level L3;

[0078] Among them, L1, L2 and L3 represent the marks of low impact level of heavy metals, medium impact level of heavy metals and high impact level of heavy metals respectively;

[0079] The threshold interval of target fungicide concentration is set as [C drug,min ,C drug,max ]; C drug,min ,C drug,max are the lower and upper limits of the threshold interval corresponding to the target fungicide concentration;

[0080] will be below the threshold interval [C drug,min ,C drug,max ]’s target fungicide concentration is classified as fungicide low impact level L4;

[0081] will be in the threshold interval [C drug,min ,C drug,max ]’s target fungicide concentration is classified as impact level L5 among fungicides;

[0082] will be above the threshold interval [C drug,min ,C drug,max ]’s target fungicide concentration is classified as fungicide high impact level L6;

[0083] Among them, L4, L5 and L6 represent the marks of low impact level of fungicide, medium impact level of fungicide and high impact level of fungicide respectively.

[0084] Step S2: Based on the historical data set, the target heavy metal concentration and target fungicide concentration are used as independent variables, and the microbial activity evaluation index is used as the dependent variable, and a multivariate linear regression is used to construct a microbial activity prediction model;

[0085] Further explanation: The calculation formula for defining the microbial activity prediction model is as follows:

[0086] MAI′ i =b1×C metal,i +b2×C drug,i +μ1

[0087] Among them, MAI′ i represents the predicted value of the microbial activity evaluation index of the microorganisms in the denitrifying biological filter at the i-th moment; b1 and b2 are the weight coefficients of the corresponding parameters, and b1+b2=1, and the values ​​of b1 and b2 are both in the interval (0,1); μ1 is the bias of the microbial activity prediction model; based on the historical data set and experimental data, the specific values ​​of b1, b2 and bias μ1 are determined;

[0088] C metal,i is the target heavy metal concentration at the i-th moment; C drug,i is the target fungicide concentration at the i-th moment.

[0089] It should be noted that: in this embodiment, b1 is set to be less than b2. Although the target heavy metal concentration will affect the microbial activity, the target fungicide concentration will have a greater impact on the microbial activity. Therefore, in the distribution of the weight ratio, b1 needs to be less than b2. In this example, b1 and b2 are set to 0.4 and 0.6.

[0090] Step S3: Based on the constructed microbial activity prediction model and in combination with the target heavy metal concentration and target fungicide concentration obtained in real time, the predicted value of the microbial activity evaluation index at the current moment is calculated;

[0091] Based on the calculated predicted values ​​of microbial activity evaluation indicators, the carbon source dosage requirement in the sewage treatment process is determined using a linear optimization equation;

[0092] Further explanation: Obtain the carbon source addition requirements corresponding to the microbial activity evaluation indicators at different times in the historical data set;

[0093] The carbon source addition requirement and the microbial activity evaluation index were correlated and analyzed, and the following linear correlation calculation formula was obtained:

[0094] Q carbon,i =k1×MAI i +μ2

[0095] Among them, Q carbon,i Represents the MAI of microorganisms in the denitrifying biofilter at the i-th moment in the monitoring period ik1 is the proportional coefficient; μ2 is the system adjustment coefficient; it is used to fine-tune the stability of process regulation. The values ​​of k1 and μ2 are obtained by fitting historical operating data, and are specifically determined by using the linear regression function in Python or Matlab.

[0096] Q carbon,i Determined by expert systems using experimental data or by sewage treatment workers based on historical data and standard manuals;

[0097] The predicted value of the microbial activity evaluation index MAI′ at the current moment i1 i1 Input to Q carbon,i1 =k1×MAI′ i1 +μ2 in;

[0098] Q carbon,i1 It is the carbon source dosage requirement of microorganisms in the denitrifying biological filter at the current time i1.

[0099] Step S4: Compare the calculated carbon source dosage requirement with the actual carbon source dosage currently added to determine whether the error is within a preset allowable threshold, thereby obtaining an error judgment result for providing an adjustment strategy for the actual carbon source dosage;

[0100] Further explanation: Set the target heavy metal concentration C of microorganisms in the denitrification biofilter at the current moment metal,i1 and target fungicide concentration C drug,i1 The preset allowable threshold corresponding to the combination is Wc i1 ; and set the actual carbon source dosage at the current moment as Q1 carbon In this embodiment, Wc i1 Set to Wc i1 =Q carbon,i1 ×0.1;

[0101] Ruo Dang|Q1 carbon -Q carbon,i1 |>Wc i1 When the error judgment result indicates that the error is outside the preset allowable threshold, there are two specific situations:

[0102] Case 1: If Q1 carbon >Q carbon,i1 When the carbon source dosage is too large relative to the carbon source dosage requirement, excessive carbon source addition will lead to rapid microbial reproduction, exceeding the management capacity of the system, causing expansion of biofilm or activated sludge, and easily leading to failure of the sewage treatment system.

[0103] Case 2: If Q1 carbon carbon,i1 ​When , it means that the actual amount of carbon source added is too small relative to the required amount of carbon source addition. Insufficient carbon source addition will limit the growth and metabolic activities of microorganisms, resulting in low efficiency in removing pollutants.

[0104] If|Q1 carbon -Q carbon,i1 |≤Wc i1 When , the error judgment result indicates that the error is within the preset allowable threshold, indicating that the actual carbon source addition amount is close to the carbon source addition demand amount, which meets the carbon source addition requirement.

[0105] The impact level judgment results and the error judgment results are combined for analysis to formulate adjustment and addition strategies for the actual carbon source dosage, the first neutralizer, and the second neutralizer.

[0106] Further explanation: For the adjustment and addition strategy of the actual carbon source dosage:

[0107] When |Q1 carbon -Q carbon,i1 |>Wc i1 And Q1 carbon >Q carbon,i1 When , it means there is excess carbon source, and it is necessary to adjust the temperature, pH and nutrients in the denitrification biofilter to improve the efficiency of microbial carbon source utilization until |Q1 carbon,d -Q carbon,i1 |≤Wc i1 until;

[0108] Temperature regulation: The metabolic rate of microorganisms is closely related to temperature. Within a suitable temperature range (e.g., 20°C-30°C), the enzyme activity of denitrifying bacteria increases, which can significantly accelerate the denitrification process and convert excess carbon sources into carbon dioxide and water, thereby reducing the carbon source concentration.

[0109] pH optimization: Microorganisms can maintain optimal growth and metabolic activity within a specific pH range (e.g., 6.5-8.5). Maintaining an appropriate pH ensures optimal activity of denitrifying bacterial enzymes, improves their carbon source utilization efficiency, promotes carbon source consumption, and reduces excess load in the system.

[0110] Nutrient Ratio Adjustment: A reasonable carbon-nitrogen ratio (C:N ratio) is crucial to the denitrification process. Increasing the amount of nitrogen added can improve the microbial utilization of carbon sources, allowing microorganisms to effectively utilize excess carbon sources during denitrification. The ideal C:N ratio is typically 5:1 to 10:1, ensuring that denitrifying bacteria can efficiently convert nitrogen in the presence of a relatively sufficient carbon source.

[0111] When |Q1 carbon -Q carbon,i1 |>Wc i1 And Q1carbon carbon,i1 When the actual carbon source dosage is increased, the actual carbon source dosage after the increase is defined as Q1 carbon,s =Q1 carbon +h2×η2;

[0112] Q1 carbon,s is the actual amount of carbon source added after the increase, η2 is the increase in carbon source addition each time, h2 is the number of times the carbon source is added until |Q1 carbon,s -Q carbon,i1 |≤Wc i1 until;

[0113] The setting of η2 is used to indicate that the carbon source is added in batches, so as to avoid excessive addition of carbon source at one time, which may cause the microorganisms in the denitrifying biofilter to be unable to adapt quickly.

[0114] Based on the expected reduction ratio of the first neutralizer and the second neutralizer, the following adjustment addition strategy description is made for the first neutralizer and the second neutralizer:

[0115] If the "target heavy metal concentration" and / or "target fungicide concentration" are at the low impact level L1 or L4, add the "first neutralizer" and / or "second neutralizer" lower than the preset addition amount to the current denitrifying biological filter;

[0116] If the "target heavy metal concentration" and / or "target fungicide concentration" is at the medium impact level L2 or L5, add the preset amount of "first neutralizer" and / or "second neutralizer" to the current denitrifying biological filter;

[0117] If the "target heavy metal concentration" and / or "target fungicide concentration" are at the high impact level L3 or L6, add the "first neutralizer" and / or "second neutralizer" higher than the preset addition amount to the current denitrifying biological filter;

[0118] The adjustment target of the preset addition amount is set as follows: until the "target heavy metal concentration" and "target fungicide concentration" after neutralization are respectively at the corresponding low impact levels L1 and L4.

[0119] It should be noted that in this embodiment, the addition of the corresponding neutralizer "higher than the preset addition amount" or "lower than the preset addition amount" needs to be determined based on the expected decrease ratio A1% of the first neutralizer and the expected decrease ratio A2% of the second neutralizer.

[0120] Example 2:

[0121] See also Figure 2 ​, a sewage treatment carbon source intelligent dosing system, the system is used to implement the sewage treatment carbon source intelligent dosing method, comprising:

[0122] Range value determination module: used to determine the target heavy metals and target fungicides that are strongly correlated with the microbial activity evaluation index, obtain the microbial activity evaluation index, target heavy metal concentration, and target fungicide concentration of the current denitrification biofilter at different times during the monitoring period. The microbial activity evaluation index is determined based on the microbial respiration rate and microbial denitrification rate, and the target heavy metal concentration, target fungicide concentration, and microbial activity evaluation index are aggregated to form a historical data set;

[0123] Prediction model building module: used to build a microbial activity prediction model based on historical data sets, with target heavy metal concentrations and target fungicide concentrations as independent variables and microbial activity evaluation indicators as dependent variables, using multiple linear regression;

[0124] Calculation and analysis module: used to calculate the predicted value of the microbial activity evaluation index at the current moment based on the constructed microbial activity prediction model and combined with the real-time acquired target heavy metal concentration and target fungicide concentration;

[0125] Based on the calculated predicted values ​​of microbial activity evaluation indicators, the carbon source dosage requirement in the sewage treatment process is determined using a linear optimization equation;

[0126] Judgment and adjustment module: used to compare the calculated carbon source addition demand with the actual carbon source addition amount currently put in to determine whether the error is within the preset allowable threshold, and then obtain the error judgment result used to provide an adjustment addition strategy for the actual carbon source addition amount.

[0127] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the intelligent carbon source addition method for sewage treatment.

[0128] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0129] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0130] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, and may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment as needed.

[0131] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for intelligently adding carbon sources to sewage treatment, characterized in that: The specific steps include: Step S1: determining target heavy metals and target fungicides that are strongly correlated with the microbial activity evaluation index, obtaining the microbial activity evaluation index, target heavy metal concentration, and target fungicide concentration of the current denitrifying biological filter at different times during the monitoring period, wherein the microbial activity evaluation index is determined based on the microbial respiration rate and the microbial denitrification rate, and summarizing the target heavy metal concentration, target fungicide concentration, and microbial activity evaluation index to form a historical data set; Step S2: Based on the historical data set, the target heavy metal concentration and target fungicide concentration are used as independent variables, and the microbial activity evaluation index is used as the dependent variable, and a microbial activity prediction model is constructed using multiple linear regression; Step S3: Based on the constructed microbial activity prediction model and in combination with the target heavy metal concentration and target fungicide concentration obtained in real time, the predicted value of the microbial activity evaluation index at the current moment is calculated; Based on the calculated predicted values ​​of microbial activity evaluation indicators, the carbon source dosage requirement in the sewage treatment process is determined based on the linear optimization equation; specifically: Obtain the carbon source dosage requirements corresponding to the microbial activity evaluation indicators at different times in the historical data set; The carbon source addition requirement and the microbial activity evaluation index were correlated and analyzed, and the following linear correlation calculation formula was obtained: Q carbon,i =k1×MAI i +μ2 Among them, the microbial activity evaluation index is defined as MAI i , Q carbon,i Represents the MAI of microorganisms in the denitrifying biofilter at the i-th moment in the monitoring period i The carbon source addition requirement under the condition of θ is θ; k1 is the proportional coefficient; μ2 is the system adjustment coefficient; it is used to fine-tune the stability of process regulation. The values ​​of k1 and μ2 are obtained by fitting the historical operation data, specifically using the linear regression function in Python or Matlab to fit and determine; the microbial activity evaluation index prediction value MAI′ of i1 at the current moment is i1 Input to Q carbon,i1 =k1×MAI′ i1 +μ2, MAI′ i represents the predicted value of the microbial activity evaluation index of the denitrifying biological filter at the i-th moment, Q carbon,i1 is the carbon source dosage requirement of the microorganisms in the denitrifying biological filter at the current time i1; Step S4: Compare the calculated carbon source dosage requirement with the actual carbon source dosage currently added to determine whether the error is within a preset allowable threshold, and then obtain an error judgment result for providing an adjustment addition strategy for the actual carbon source dosage.

2. The method for intelligently adding carbon sources for sewage treatment according to claim 1, characterized in that: Determining the target heavy metals and target fungicides that are strongly correlated with the microbial activity evaluation index includes: obtaining the microbial activity evaluation index of the current denitrifying biological filter at different times during the monitoring period, as well as the concentrations of various heavy metals and fungicides, and screening out the heavy metal concentrations and fungicide concentrations that are strongly correlated with the microbial activity evaluation index based on the calculation results of the Pearson correlation coefficient, and determining them as the target heavy metal concentrations and target fungicide concentrations; The microbial activity evaluation index is defined as MAI i , the calculation formula is as follows: MIA i =a1×SOUR i +a2×NUR i Among them, SOUR i is the respiration rate of microorganisms in the denitrifying biofilter at the i-th moment in the monitoring period, NUR i is the denitrification rate of microorganisms in the denitrifying biological filter at the i-th moment in the monitoring period, a1 and a2 are the weight values ​​of the corresponding parameters, and a1+a2=1, and the values ​​of a1 and a2 are both in the interval (0,1).

3. The method for intelligently adding carbon sources for sewage treatment according to claim 2, characterized in that: The calculation formula for defining the microbial activity prediction model is as follows: MAY' i =b1×C metal,i +b2×C drug,i +μ1 Among them, MAI′ i represents the predicted value of the microbial activity evaluation index of microorganisms in the denitrifying biological filter at the i-th moment; b1 and b2 are the weight coefficients of the corresponding parameters, and b1+b2=1, and the values ​​of b1 and b2 are both in the interval (0,1); μ1 is the bias of the microbial activity prediction model; C metal,i is the target heavy metal concentration at the i-th moment; C drug,i is the target fungicide concentration at the i-th moment.

4. The method for intelligently adding carbon sources for sewage treatment according to claim 3, characterized in that: The threshold interval of target heavy metal concentration is set as [C metal,min ,C metal,max ]; C metal,min ,C metal,max are the lower and upper limits of the threshold interval corresponding to the target heavy metal concentration; will be below the threshold interval [C metal,min ,C metal,max ]’s target heavy metal concentration is classified as heavy metal low impact level L1; will be in the threshold interval [C metal,min ,C metal,max ]’s target heavy metal concentration is classified as impact level L2 among heavy metals; will be above the threshold interval [C metal,min ,C metal,max ]’s target heavy metal concentration is classified as heavy metal high impact level L3; Among them, L1, L2 and L3 represent the marks of low impact level of heavy metals, medium impact level of heavy metals and high impact level of heavy metals respectively; The threshold interval of target fungicide concentration is set as [C drug,min ,C drug,max ]; C drug,min ,C drug,max are the lower and upper limits of the threshold interval corresponding to the target fungicide concentration; will be below the threshold interval [C drug,min ,C drug,max ]’s target fungicide concentration is classified as fungicide low impact level L4; will be in the threshold interval [C drug,min ,C drug,max ]’s target fungicide concentration is classified as impact level L5 among fungicides; will be above the threshold interval [C drug,min ,C drug,max ]’s target fungicide concentration is classified as fungicide high impact level L6; Among them, L4, L5 and L6 represent the marks of low impact level of fungicide, medium impact level of fungicide and high impact level of fungicide respectively.

5. The method for intelligently adding carbon sources for sewage treatment according to claim 4, characterized in that: The calculated carbon source dosage requirement is compared with the actual carbon source dosage currently added to determine whether the error is within a preset allowable threshold. The specific logic includes: Set the target heavy metal concentration C of microorganisms in the denitrification biofilter at the current moment metal,i1 and target fungicide concentration C drug,i1 The preset allowable threshold corresponding to the combination is Wc i1 ; and set the actual carbon source dosage at the current moment as Q1 carbon ; Ruo Dang|Q1 carbon -Q carbon,i1 |>Wc i1 When the error judgment result indicates that the error is outside the preset allowable threshold, there are two specific situations: The first case: If Q1 carbon >Q carbon,i1 When , it means that the actual carbon source dosage is too large relative to the carbon source dosage requirement; The second case: If Q1 carbon carbon,i1 When , it means that the actual carbon source dosage is too small relative to the carbon source dosage requirement;​ Ruo Dang|Q1 carbon -Q carbon,i1 |≤Wc i1 When , the error judgment result indicates that the error is within the preset allowable threshold, indicating that the actual carbon source addition amount is close to the carbon source addition demand amount, which meets the carbon source addition requirement.

6. The method for intelligently adding carbon sources for sewage treatment according to claim 5, characterized in that: Explanation of the adjustment strategy for the actual carbon source dosage: When |Q1 carbon -Q carbon,i1 |>Wc i1 And Q1 carbon >Q carbon,i1 When , it means there is excess carbon source, and it is necessary to adjust the temperature, pH and nutrients in the denitrification biofilter to improve the efficiency of microbial carbon source utilization until |Q1 carbon,d -Q carbon,i1 |≤Wc i1 until; When |Q1 carbon -Q carbon,i1 |>Wc i1 And Q1 carbon carbon,i1 When the actual carbon source dosage is increased, the actual carbon source dosage after the increase is defined as Q1 carbon,s =Q1 carbon +h2×η2;​ Q1 carbon,s is the actual amount of carbon source added after the increase, η2 is the increase in carbon source addition each time, h2 is the number of times the carbon source is added until |Q1 carbon,s -Q carbon,i1 |≤Wc i1 until.

7. The method for intelligently adding carbon sources for sewage treatment according to claim 6, characterized in that: In the current denitrifying biological filter, a first neutralizer and a second neutralizer are respectively determined for reducing the target heavy metal concentration and the target fungicide concentration; Setting the expected reduction ratio of the target heavy metal concentration by the first neutralizer at a preset addition amount; and the expected reduction ratio of the target fungicide concentration by the second neutralizer at a preset addition amount; The first neutralizing agent is defined as being capable of reacting with the target heavy metal to form an insoluble precipitate; The second neutralizing agent is defined as being capable of reducing or oxidizing the target fungicide, rendering the target fungicide inactive; The expected reduction ratio of the target heavy metal concentration by the first neutralizer at a preset addition amount is set to A1%; The expected reduction ratio of the target fungicide concentration by the second neutralizer at a preset addition amount is set to A2%; Based on the impact level judgment results, the following adjustments and addition strategies are made to the first and second neutralizers: If the "Target Heavy Metal Concentration" and / or "Target Fungicide Concentration" are at the low impact level L1 or L4, add a "First Neutralizer" and / or "Second Neutralizer" below the preset dosage to the current denitrifying biological filter; If the "Target Heavy Metal Concentration" and / or "Target Fungicide Concentration" are at the medium impact level L2 or L5, add the preset amount of "First Neutralizer" and / or "Second Neutralizer" to the current denitrifying biological filter; If the "Target Heavy Metal Concentration" and / or "Target Fungicide Concentration" are at the high impact level L3 or L6, add a higher than preset amount of "First Neutralizer" and / or "Second Neutralizer" to the current denitrifying biofilter; The adjustment target of the preset addition amount is set as follows: until the "target heavy metal concentration" and "target fungicide concentration" after neutralization are respectively at the corresponding low impact levels L1 and L4.

8. An intelligent carbon source dosing system for sewage treatment, characterized by: The system is used to implement the intelligent carbon source addition method for sewage treatment according to any one of claims 1 to 7, comprising: Range value determination module: used to determine the target heavy metals and target fungicides that are strongly correlated with the microbial activity evaluation index, obtain the microbial activity evaluation index, target heavy metal concentration, and target fungicide concentration of the current denitrification biofilter at different times during the monitoring period. The microbial activity evaluation index is determined based on the microbial respiration rate and microbial denitrification rate, and the target heavy metal concentration, target fungicide concentration, and microbial activity evaluation index are aggregated to form a historical data set; Prediction model building module: used to build a microbial activity prediction model based on historical data sets, with target heavy metal concentrations and target fungicide concentrations as independent variables and microbial activity evaluation indicators as dependent variables, using multiple linear regression; Calculation and analysis module: used to calculate the predicted value of the microbial activity evaluation index at the current moment based on the constructed microbial activity prediction model and combined with the real-time acquired target heavy metal concentration and target fungicide concentration; Based on the calculated predicted values ​​of microbial activity evaluation indicators, the carbon source dosage requirement in the sewage treatment process is determined using a linear optimization equation; Judgment and adjustment module: used to compare the calculated carbon source addition demand with the actual carbon source addition amount currently put in to determine whether the error is within the preset allowable threshold, and then obtain the error judgment result used to provide an adjustment addition strategy for the actual carbon source addition amount.

9. A readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the intelligent carbon source addition method for sewage treatment as described in any one of claims 1 to 7 are implemented.

Images