Short-cut denitrification-anaerobic ammonia oxidation system and intelligent regulation and control method thereof

Abstract

The invention discloses a short-cut denitrification-anaerobic ammonia oxidation system and an intelligent regulation and control method thereof, and belongs to the technical field of intelligent regulation and control of sewage treatment. Comprising the following steps: constructing and processing a machine learning data set to obtain a training set and a test set; based on the training set, a prediction model is established through a machine learning method, and prediction performance is evaluated to select an optimal prediction model; performing importance analysis on the data in the data set as feature data, and identifying key features; and taking the key features as optimization regulation and control parameters, and constructing an optimal control strategy through a particle swarm optimization algorithm. Compared with the prior art, the method has the beneficial effects that a system denitrification performance prediction model is constructed and optimized by utilizing a machine learning method by utilizing a large number of system operation parameters, microbial community structures and other multi-dimensional data, the operation characteristics of the system are fully reflected, and a unique optimal control strategy is designed and formed aiming at a specific scene; and the adaptability of the strategy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent regulation and control of sewage treatment, and more specifically, to a short-range denitrification-anaerobic ammonia oxidation system and an intelligent regulation and control method thereof. Background Art

[0002] Among the many processes of sewage treatment, biological denitrification has always occupied an important position. However, with the improvement of environmental awareness and the increasingly stringent requirements for energy conservation and emission reduction, traditional biological denitrification processes face the dual challenges of low energy consumption and low carbon emissions. Against this background, the discovery of the anaerobic ammonium oxidation biological denitrification pathway has brought revolutionary changes to the field of biological denitrification of sewage. Anaerobic ammonium oxidation technology has quickly become a research hotspot in the field of sewage treatment due to its high efficiency and low consumption. The anaerobic ammonium oxidation process relies on a stable supply of nitrite substrate to achieve efficient removal of ammonia nitrogen. However, how to continuously and stably provide nitrite substrate has become a key factor restricting the promotion and application of anaerobic ammonium oxidation technology. In recent years, through in-depth research, researchers have discovered that the short-term denitrification process has an extremely high nitrite accumulation efficiency. This discovery provides an ideal source of nitrite for anaerobic ammonium oxidation technology. Combining short-term denitrification with anaerobic ammonium oxidation technology has formed a new biological denitrification process-short-term denitrification-anaerobic ammonium oxidation process. This coupled system not only improves the denitrification efficiency, but also significantly reduces energy consumption and carbon emissions, meeting the current high requirements for sewage treatment processes in the environmental protection field. However, the complexity of the short-cut denitrification-anaerobic ammonium oxidation coupling system also brings considerable challenges. In actual operation, the denitrification performance of the system is affected by a variety of factors, including the cumulative efficiency of nitrite in the short-cut denitrification process, the denitrification rate in the anaerobic ammonium oxidation process, and the synergistic effect between the two. The interaction between these factors makes it difficult to ensure the stability of the system. Once fluctuations or even collapses occur, the denitrification effect and operating efficiency will be seriously affected. In order to meet this challenge, researchers began to try to model the sewage treatment process to simulate and optimize the biological treatment process.

[0003] However, traditional modeling methods need to consider complex dynamics and a large number of chemical reaction parameters, which not only increases the difficulty of modeling, but also limits the versatility of the model in different application scenarios. In addition, the process of adjustment and parameter verification for different systems also increases the application cost of the model. In recent years, with the rapid development of big data and machine learning technology, machine learning-based models have gradually become an effective tool for predicting the performance of biological denitrification of sewage. Compared with traditional modeling methods, machine learning models do not require an in-depth understanding of the complex biological denitrification mechanism, and can only rely on the existing operating parameters and denitrification performance data samples of the system for prediction and optimization. Applying big data-driven machine learning to short-range denitrification-anaerobic ammonium oxidation systems can achieve accurate prediction and intelligent regulation of system performance, thereby improving the stability and denitrification efficiency of the system.

[0004] However, although machine learning models have shown great potential in the field of biological denitrification of sewage, how to carry out targeted intelligent regulation based on the characteristics of short-range denitrification-anaerobic ammonium oxidation systems remains a technical problem that needs to be solved urgently. In addition, there are obvious differences in the key functional bacteria in different systems, and their requirements for optimal environmental conditions are also different. If regulation is only carried out from the perspective of operating parameters, the differences between microbial communities in each system may be ignored, resulting in poor results of the regulation strategy. In addition, different actual operating environments may also lead to differences in adjustable parameters, further reducing the adaptability of the optimization regulation strategy.

[0005] In the related technology, for example, Chinese patent CN114790039A provides a method and system for intelligent nitrogen removal control of aquaculture wastewater, which includes obtaining different water quality indicators for different wastewater treatment units according to the wastewater treatment process; using big data calculation and deep learning algorithm to predict the control parameters in sewage treatment based on the obtained water quality indicators according to the microbial dynamics model, and the control parameters include carbon source amount, internal reflow ratio and external reflow ratio; according to the prediction results and the set four-level early warning control measures, the unstable condition is warned and adjusted, and the dosage and aeration volume are finely controlled to ensure that the effluent is stable and meets the standards. This solution is based on the establishment of a microbial dynamics model, and uses big data calculation and platform deep learning to achieve automatic (semi-automatic) remote control of sewage treatment plants. However, the shortcoming of this solution is that it does not eliminate the impact of dynamic changes in microbial communities on system stability.

[0006] From the above, it can be seen that the relevant technology does not provide any technical inspiration on how to solve the problems of performance fluctuation and collapse that may be encountered during the operation of the short-range denitrification-anaerobic ammonium oxidation system. Summary of the invention

[0007] 1. Technical issues to be solved In view of the problem in the prior art that the microbial community in the short-range denitrification-anaerobic ammonium oxidation system changes due to fluctuations in the system operating conditions, thereby leading to unstable system denitrification performance, the present invention provides a short-range denitrification-anaerobic ammonium oxidation system and an intelligent control method thereof, which can build and screen an optimal model for predicting the system's denitrification performance, and identify key influencing factors for efficient denitrification based on feature importance analysis, thereby using a particle swarm optimization algorithm to design an optimal control strategy for a specific system, thereby achieving precise control of the system and efficient denitrification.

[0008] 2. Technical solution The purpose of the present invention is achieved through the following technical solutions.

[0009] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0010] Some embodiments of the present application propose a short-range denitrification-anaerobic ammonium oxidation system and an intelligent control method thereof to solve the technical problems mentioned in the above background technology section.

[0011] As the first aspect of the present application, some embodiments of the present application provide an intelligent control method for a short-term denitrification-anaerobic ammonium oxidation system, including the following steps: obtaining sample point data of the short-term denitrification-anaerobic ammonium oxidation system, including operation data, operating parameters and microbial community structure data, and constructing a data set for machine learning; performing outlier processing, category information conversion, data standardization, correlation analysis and data set splitting on the data set to obtain a training set and a test set; based on the training set, establishing a prediction model through a machine learning method, and evaluating the prediction performance of each prediction model on the test set to select the optimal prediction model; using the data in the data set as feature data, performing feature data importance analysis, and identifying key parameters that affect the total nitrogen removal rate of the system; using the key parameters as the optimization control parameters of the short-term denitrification-anaerobic ammonium oxidation system, and constructing an optimal control strategy through a particle swarm optimization algorithm.

[0012] Furthermore, outlier processing includes calculating the mean and standard deviation of the feature data of all sample points and making a judgment on each feature data. The judgment process is as follows: Take the data in the data set as feature data, calculate the mean and standard deviation of each feature data of all sample points; take the mean value of the feature data of the current sample point minus the standard deviation as the minimum value, and take the mean value of the feature data of the current sample point plus the standard deviation as the maximum value, and define the current range; determine whether the feature data of the current sample point is within the current range. If not, it is regarded as an outlier, and the outlier is replaced by the mean value of the feature data of the current sample point.

[0013] Furthermore, data standardization includes using the Standardscaler standard method to normalize the sample point data. The process is expressed as: ; in, Represents sample feature data, is the average value of each feature data, is the standard deviation of each feature data.

[0014] Furthermore, the process of splitting the data set is as follows: according to the five-fold cross-validation method in the machine learning model evaluation method, the data set is randomly split into two mutually exclusive data sets in a ratio of 8:2, of which 80% of the data is used as a training set for model training; and 20% of the data is used as a test set for model testing.

[0015] Furthermore, the operating data include ammonia nitrogen concentration, nitrate nitrogen concentration, nitrite concentration, COD concentration, pH, carbon nitrogen ratio and nitrate ammonia nitrogen ratio; the operating parameters include system type, system volume, reflow ratio, hydraulic retention time, temperature, inoculated sludge type and carbon source type; The microbial community structure data are presented in matrix form, with each column representing a species, each row representing a sample, and the element value being the relative abundance of the corresponding species.

[0016] Furthermore, based on the operating data and operating parameters in the training set, a machine learning method is selected to establish a prediction model; Coefficient of determination , mean square error and mean absolute error The indicators are used to compare the prediction performance of the prediction models and select the optimal prediction model.

[0017] Furthermore, the process of comparing the prediction performance of the prediction models is expressed as: ; ; ; in, The sample index in the test set is The actual total nitrogen removal rate value, The sample index in the test set is The total nitrogen removal rate value predicted by the prediction model is is the average of the actual total nitrogen removal rates of all samples in the test set, is the sample size.

[0018] Furthermore, the process of feature data importance analysis includes using Python's SHAP package to calculate the SHAP value of each feature data; analyzing the SHAP value of the feature data, and taking features with high SHAP values ​​as key parameters.

[0019] Furthermore, the process of constructing the optimal control strategy includes: selecting one or more of the key parameters as control parameters, using the particle swarm optimization algorithm to find the optimization parameters, and constructing the optimal control strategy for a specific scenario.

[0020] As a second aspect of the present application, some embodiments of the present application provide a short-range denitrification-anaerobic ammonium oxidation system, including a data module: obtaining sample point data of the short-range denitrification-anaerobic ammonium oxidation system, including operation data, operation parameters, and microbial community structure data, and constructing a data set for machine learning; Processing module: performs outlier processing, category information conversion, data standardization, correlation analysis, and data set splitting on the data set to obtain training sets and test sets; Model module: Based on the training set, a prediction model is established through machine learning methods, and the prediction performance of each prediction model on the test set is evaluated to select the optimal prediction model; Analysis module: Take the data in the data set as feature data, perform feature data importance analysis, and identify key parameters that affect the total nitrogen removal rate of the system; Building module: Using key parameters as the optimization and regulation parameters of the short-range denitrification-anaerobic ammonium oxidation system, the optimal control strategy is constructed through the particle swarm optimization algorithm.

[0021] 3. Beneficial effects Compared with the prior art, the advantages of the present invention are: (1) The technical solution of the present invention makes full use of a large amount of multi-dimensional data such as the operating parameters of the short-range denitrification-anaerobic ammonium oxidation system and the structure of the microbial community, and uses machine learning methods to construct and optimize the system denitrification performance prediction model to identify the key factors affecting the system performance. The prediction model can fully reflect the operating characteristics of the system; (2) The technical solution of the present invention can simultaneously consider the key factors identified based on machine learning and the unique operating scenarios of different systems, and design a unique optimal control strategy for each scenario, thereby improving the high adaptability of the strategy; (3) By constructing a multidimensional data set that integrates operating parameters, operation parameters and microbial community structure, a high-precision prediction model was established using the gradient boosting algorithm (the test set R² reached 0.958). The key regulatory factors such as temperature, pH and carbon-nitrogen ratio were accurately identified by combining the SHAP feature importance analysis. A scenario-adaptive control strategy was generated based on the particle swarm optimization algorithm, which increased the total nitrogen removal rate of the short-range denitrification-anaerobic ammonia oxidation system from 80.7% to 93.5%. The removal rate fluctuation range was reduced under the condition of a ±50% fluctuation in the total nitrogen concentration in the influent. At the same time, the operating cost was reduced by optimizing the carbon source addition amount. This effectively solved the problem of system instability caused by ignoring the dynamic changes of the microbial community in the traditional method. The system has the technical advantages of high multi-source data fusion, strong model generalization ability and excellent adaptability of the control strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a schematic flow chart of a smart control method for a short-range denitrification-anaerobic ammonium oxidation system in one embodiment of the present invention; Figure 2 is a correlation coefficient diagram between features in one embodiment of the present invention; Figure 3 A schematic diagram of ranking the importance of features in one embodiment of the present invention; Figure 4 The figure is a schematic diagram for verifying the intelligent control method in one embodiment of the present invention; wherein (a) is the total nitrogen removal rate of the system before intelligent control and its predicted value; (b) is the total nitrogen removal rate of the system after intelligent control for scenario one and its predicted value; (c) is the total nitrogen removal rate of the system after intelligent control for scenario two and its predicted value; (d) is the average value of the total nitrogen removal rate and its predicted value before and after intelligent control. DETAILED DESCRIPTION

[0023] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0024] Combination Figures 1 to 4 The invention provides a smart control method for a short-range denitrification-anaerobic ammonium oxidation system, comprising the following steps: Obtain sample point data of the short-range denitrification-anaerobic ammonium oxidation system and construct a data set for machine learning; Perform outlier processing, category information conversion, data standardization, correlation analysis, and data set splitting on the data set to obtain training sets and test sets; Based on the training set, a prediction model is established through machine learning methods, and the prediction performance of each prediction model on the test set is evaluated to select the optimal prediction model; The data in the dataset are used as characteristic data, and the importance analysis of characteristic data is performed to identify the key parameters that affect the total nitrogen removal rate of the system; The operation data, operating parameters and community structure data of the short-range denitrification-anaerobic ammonium oxidation system were obtained, and the key parameters were used as the optimization and regulation parameters of the short-range denitrification-anaerobic ammonium oxidation system. The optimal control strategy was constructed through the particle swarm optimization algorithm.

[0025] In a specific embodiment, the specific process of the intelligent control method of the short-range denitrification-anaerobic ammonium oxidation system is as follows: S1. Building a dataset Obtain data from a short-range denitrification-anaerobic ammonium oxidation system and construct a machine learning dataset by fusing multi-source data.

[0026] Specifically, WebPlotDigidizer is used to obtain the short-range denitrification-anaerobic ammonium oxidation system data, which consists of all sample point data in the short-range denitrification-anaerobic ammonium oxidation system.

[0027] More specifically, the sample point data include operational data, operating parameters, and microbial community structure data.

[0028] Among them, the operating data include ammonia nitrogen concentration, nitrate nitrogen concentration, nitrite concentration, COD concentration, pH, carbon-nitrogen ratio and nitrate-ammonia nitrogen ratio.

[0029] Operating parameters include system type, system volume, recirculation ratio, hydraulic retention time, temperature, inoculum sludge type, and carbon source type.

[0030] The microbial community structure data include matrix data of the relative abundance of different genera of microorganisms at each sample point. More precisely, in the form of microbial community structure data, it is presented in matrix form, with each column representing a genus (species), each row representing a sample, and the element value being the relative abundance of the corresponding species.

[0031] All system data obtained through the above process are merged according to the sample point names to form a matrix containing all the necessary information. This matrix will serve as the data set required to build the machine learning model.

[0032] S2. Data preprocessing The data preprocessing process includes outlier processing, category information conversion, data standardization, correlation analysis, and data set splitting.

[0033] (1) Outlier processing: First, before conducting machine learning model analysis, the operating data, operating parameters and community structure data in the above data set are used as feature data, the mean and standard deviation of each feature data of all sample points are calculated, and the feature data of each sample point is judged.

[0034] Specifically, the judgment process is: the current minimum value is taken as the average value of the current sample point feature data minus the standard deviation, the current maximum value is taken as the average value of the current sample point feature data plus the standard deviation, and the range defined by the current minimum value and the current maximum value as the boundary value is taken as the current range; Then, it is determined whether the current sample point feature data is within the current range. If it is not within the current range, the current sample point feature data is an outlier, and the average value of the current sample point feature data is used to replace the outlier.

[0035] (2) Category information conversion: In a specific embodiment, since the system type, sludge type and carbon source type in the operating parameters are all string type category information, they cannot be directly used for the construction of subsequent machine learning models. Therefore, for the string type category information such as system type, sludge type and carbon source type in the operating parameters, the get_dummies function in the program package pandas is used to perform one-hot encoding on the string class features, and a new binary (0 or 1) column is created for each possible category. If a sample is in this category, the corresponding column is 1, otherwise it is 0. Thereby converting the string category information into digital information. In this embodiment, this data set includes a total of 4863 sample point data.

[0036] get_dummies is a function in the Pandas library that converts categorical data into one-hot encoded dummy variables. In machine learning and data processing, categorical data are often encountered, which cannot be directly used for training most models because they are non-numeric. One-hot encoding can convert these categorical data into a digital form that the model can process.

[0037] (3) Data standardization: After the category information is converted, data standardization is performed.

[0038] Specifically, the Standardscaler standard method is used to normalize the sample point data, and the calculation formula is:

[0039] in, Represents sample feature data, is the average value of each feature data, is the standard deviation of each feature data.

[0040] (4) Correlation analysis: The Pearson correlation between different feature data was calculated using the SciPy package in Python. Pearson correlation is a statistical method to measure the linear relationship between two continuous variables.

[0041] In this example, Pearson correlation coefficients were calculated between 14 features in the operational data and operating parameters.

[0042] The Pearson correlation coefficient is used to measure the strength and direction of the linear relationship between two continuous variables. The value range of the Pearson correlation coefficient is between -1 and 1. When the Pearson correlation coefficient is equal to 1, it means that the two variables are completely positively correlated, that is, when one variable increases, the other variable also increases, showing a completely linear positive correlation. When the Pearson correlation coefficient is equal to -1, it means that the two variables are completely negatively correlated, that is, when one variable increases, the other variable decreases, showing a completely linear negative correlation. When the Pearson correlation coefficient is equal to 0, it means that there is no linear relationship between the two variables, that is, there is no linear correlation between the two.

[0043] like Figure 2 As shown, the correlation between the characteristic data is judged based on the correlation coefficient. The result shows that the correlation coefficient between the influent ammonia nitrogen concentration and the influent total nitrogen concentration is 0.93, and its absolute value exceeds the significant correlation threshold of 0.8. Therefore, there is a significant positive correlation between the two characteristic data.

[0044] In this embodiment, since the influent ammonia nitrogen and total nitrogen concentrations directly determine the important control indicators of the short-range denitrification-anaerobic ammonium oxidation system operating performance, the two key characteristic data of the influent ammonia nitrogen concentration and the influent total nitrogen concentration are retained. There is no significant correlation between the other characteristic data.

[0045] (5) Dataset splitting: According to the five-fold cross-validation method in the machine learning model evaluation method, the data set is randomly split into two mutually exclusive data sets in a ratio of 8:2, of which 80% of the data is used as the training set for model training; and 20% of the data is used as the test set for model testing.

[0046] The above data preprocessing process is an important step before building a machine learning model, which aims to improve data quality and ensure the accuracy and effectiveness of model training. Among them, outlier processing can avoid the impact of extreme values ​​on model training and improve the robustness of the model; category information conversion enables string category information to be correctly processed by the machine learning model; data standardization helps to eliminate the dimensional differences between different feature data and improve the convergence speed and performance of the model; correlation analysis helps to identify key feature data, simplify the model structure, and improve the model's interpretability; data set splitting is the basis of model evaluation. By dividing the training set and the test set, the generalization ability of the model can be objectively evaluated.

[0047] S3. Build a prediction model The process of building a predictive model includes selecting a machine learning method, establishing a predictive model, model evaluation and selection, and optimizing the model by combining community structure data.

[0048] Specifically, based on the operating data and operating parameters in the training set divided as above, the prediction models of total nitrogen removal rate were established respectively using the program package Sklearn according to various machine learning methods. The prediction performance of each prediction model on the test set was compared and evaluated using the five-fold cross validation method to select the optimal prediction model.

[0049] (1) Select the machine learning method: Based on the operating data and operating parameters in the training set divided as above, a variety of machine learning methods are selected to establish a prediction model.

[0050] In this embodiment, 9 machine learning methods are used, including linear regression, K nearest neighbor, random forest, gradient boosting, XGBoost, support vector machine, AdaBoost, LightBoost and artificial neural network.

[0051] (2) Establish a prediction model: Using the program package Sklearn, prediction models for total nitrogen removal rate were established based on various machine learning methods.

[0052] Sklearn is an open source machine learning library based on Python. Sklearn supports a variety of machine learning algorithms, including linear regression, logistic regression, decision tree, random forest, support vector machine and neural network, and provides a variety of evaluation indicators and cross-validation methods to measure the performance of the model. In this embodiment, data partitioning, model training and evaluation can be achieved through Sklearn.

[0053] (3) Model evaluation and selection: The five-fold cross-validation method was used to compare and evaluate the prediction performance of each prediction model on the test set and select the optimal prediction model.

[0054] Specifically, the coefficient of determination , mean square error and mean absolute error Three indicators are used to compare the prediction performance of the prediction models.

[0055] Coefficient of determination Measures the degree of fit of the model to the data. The closer the value is to 1, the better the model performance is. The mean square error is used Measures the deviation between the predicted value and the actual value. The smaller the value, the more accurate the model prediction. The mean absolute error is used Measures the average value of the prediction error. The smaller the value, the smaller the model prediction error. The specific calculation process is as follows: ; ; ; in, The sample index in the test set is The actual total nitrogen removal rate value, The sample index in the test set is The total nitrogen removal rate value predicted by the prediction model is is the average of the actual total nitrogen removal rates of all samples in the test set, is the sample size.

[0056] Specifically, the optimal prediction model is selected based on the results of the three evaluation indicators. As shown in Table 1, the prediction performance of each prediction model on the test set is shown.

[0057] Table 1 Prediction performance of each prediction model on the test set

[0058] In this embodiment, according to the results of the three evaluation indicators, it can be found that in each model, gradient boosting and XGBoost have the best prediction performance. Therefore, gradient boosting and XGBoost are selected to further construct a total nitrogen removal rate prediction model based on operation data, operating parameters and community structure data.

[0059] (4) Optimizing the model by combining community structure data: We further considered incorporating microbial community structure data into the prediction model to evaluate its impact on model performance. We compared the performance of the model using only operating data and operating parameters with that using operating data, operating parameters, and microbial community structure data. Based on the evaluation results, we selected the model with the best performance as the final prediction model.

[0060] As shown in Table 2, the prediction performance of the two selected prediction models on the test set is shown.

[0061] Table 2 Prediction performance of the two prediction models on the test set

[0062] According to the results of the three evaluation indicators, it can be seen that after combining the microbial community structure data, gradient boosting has the best prediction performance for the total nitrogen removal rate of the short-range denitrification-anaerobic ammonium oxidation system. Therefore, gradient boosting was selected as the optimal prediction model.

[0063] By constructing and evaluating multiple prediction models, this step identified gradient boosting as the optimal prediction model for total nitrogen removal efficiency in the short-range denitrification-anaerobic ammonium oxidation system, which not only took into account the operating data and operation parameters, but also combined the microbial community structure data, thereby improving the accuracy and reliability of the prediction.

[0064] This scheme makes full use of a large amount of multi-dimensional data such as the operating parameters of the short-range denitrification-anaerobic ammonium oxidation system and the structure of the microbial community, and uses machine learning methods to build and optimize the system denitrification performance prediction model, identify the key factors affecting the system performance, and fully reflect the operating characteristics of the system. This scheme can simultaneously consider the key factors identified based on machine learning and the unique operating scenarios of different systems, and design a unique optimal control strategy for each scenario, thereby improving the high adaptability of the strategy.

[0065] S4. Importance analysis of feature data The purpose of this step is to perform characteristic data importance analysis and identify key parameters that affect the total nitrogen removal rate of the system.

[0066] Based on the gradient boosting prediction model constructed in step S3 above, the Shapley additive interpretation method is used to perform feature data importance analysis. The SHAP value of each feature data is calculated using the SHAP package in Python to represent the average contribution of each feature data to the prediction value of the prediction model. The SHAP value of the feature data is analyzed, and the features with high SHAP values ​​are used as key parameters.

[0067] Among them, Shapley Additive Explanations (SHAP) is a feature data importance interpretation method based on game theory. It reveals the average contribution of each feature data to the model prediction results by interpreting the prediction results of the machine learning model as the weighted sum of the contributions of each feature. The SHAP value measures the contribution of each feature data in the model prediction, considering the average contribution of all possible feature data combinations, thereby providing an importance evaluation standard from a global perspective. The SHAP package in Python is an implementation tool of the SHAP method, which provides a series of functions and classes for calculating SHAP values, visualizing feature data importance, and explaining the prediction results of machine learning models.

[0068] By analyzing the SHAP value of each feature data, the feature data with high SHAP value are determined as key parameters. The SHAP values ​​of these feature data as key parameters are higher than the SHAP values ​​of other feature data, indicating that they have a significant impact on the prediction results of the prediction model and are factors that need to be focused on when regulating system performance.

[0069] like Figure 3 As shown in the figure, these key parameters include temperature, inlet pH, inlet total nitrogen load, inlet nitrate-ammonia ratio, and inlet carbon-nitrogen ratio. The results of the characteristic data importance analysis provide an important basis for intelligent regulation. In actual operation, the operating conditions of the system can be adjusted according to the high SHAP values ​​of these key parameters to optimize the total nitrogen removal rate.

[0070] For example, if temperature is a key factor affecting system performance, the system temperature can be adjusted to optimize denitrification. Similarly, if influent pH has a significant impact on system performance, denitrification efficiency can be improved by adjusting the influent pH.

[0071] S5. Use particle swarm optimization algorithm to construct the optimal control strategy The process of building an optimal control strategy includes collecting and processing data, selecting control parameters, applying the particle swarm optimization algorithm, and building the optimal control strategy.

[0072] (1) Data collection and processing: For the short-cut denitrification-anaerobic ammonium oxidation system in operation, the system inlet and outlet water are collected, and the inlet and outlet water quality is tested using national standard methods to form specific operating data and detailed operating parameters of the short-cut denitrification-anaerobic ammonium oxidation system.

[0073] Sludge samples in the system were collected and subjected to 16S rRNA high-throughput sequencing. QIIME2 software was used to analyze the genus-level community structure matrix data.

[0074] (2) Select control parameters: According to the optimization and control requirements of the short-range denitrification-anaerobic ammonium oxidation system in a specific scenario, one or more of the key parameters are selected as the control parameters. In this method, the key parameters include temperature, influent pH, influent total nitrogen load, influent nitrate-ammonia nitrogen ratio, influent carbon-nitrogen ratio, etc. These key parameters have been identified as important factors affecting the efficient denitrification of the system in step S4.

[0075] The other operating data, detailed operating parameters and microbial community structure data obtained above were used as input data for subsequent optimization calculations.

[0076] (3) Application of particle swarm optimization algorithm: Based on the above control parameters and input data, the Scikit-opt package in Python is used to perform calculations based on the particle swarm optimization algorithm (PSO) to find the optimal values ​​of the above control parameters as the optimization parameters of the optimal control strategy in a specific scenario.

[0077] Scikit-opt is a Python library for solving optimization problems. It integrates many classic intelligent optimization algorithms, such as genetic algorithm, particle swarm optimization (PSO), simulated annealing algorithm, etc. In Scikit-opt, the particle swarm optimization (PSO) algorithm searches for the optimal solution in the solution space by simulating the foraging behavior of bird flocks. Each particle represents a potential solution, and the optimal solution is approached by iteratively updating the position and velocity.

[0078] In this step, the control parameter is used as the position of the particle, the total nitrogen removal rate of the system or other performance indicators are used as the fitness function, and the PSO algorithm is used to find the optimization parameters that maximize the fitness function.

[0079] (4) Constructing the optimal control strategy: According to the optimization parameters calculated by the PSO algorithm, the optimal control strategy for a specific scenario is constructed, thereby realizing intelligent control of efficient denitrification of the system based on the optimal control strategy.

[0080] These optimal control strategies will serve as a guide for system operation and be used to optimize the total nitrogen removal rate of the system or maintain long-term stable operation of the system under fluctuating influent conditions.

[0081] In a specific embodiment, the optimal control strategy is designed for two specific scenarios: one is to improve the total nitrogen removal rate of the short-cut denitrification-anaerobic ammonium oxidation system, and the other is to maintain the long-term stable operation of the short-cut denitrification-anaerobic ammonium oxidation system under the condition of fluctuating influent. The volume of the short-cut denitrification-anaerobic ammonium oxidation system is 1L, the reflow ratio is 2, the total nitrogen concentration of the influent is 60mg / L, and the other parameters are shown in stage I in Table 3.

[0082] Table 3 Test plan for intelligent control

[0083] As shown in Table 3, in scenario 1, pH, temperature, nitrogen source matrix ratio, and carbon-nitrogen ratio characteristics were selected as control parameters. The optimal values ​​of the above four control parameters were calculated by the particle swarm optimization algorithm as the optimization parameters of the optimal control strategy (Phase II in Table 3), and the remaining parameters were consistent with Phase I. According to the obtained optimal control strategy, the short-range denitrification-anaerobic ammonium oxidation system was optimized and regulated in Phase II, and the average total nitrogen removal rate of the short-range denitrification-anaerobic ammonium oxidation system was increased from 80.7% in Phase I to 92.7% in Phase II.

[0084] As shown in Table 3, in scenario 2, the influent fluctuation conditions (total nitrogen concentration increased from 60 mg / L to 90 mg / L) were simulated, and pH, temperature, nitrogen source matrix ratio, carbon-nitrogen ratio and hydraulic retention time were selected as control parameters. The particle swarm optimization algorithm was used to obtain the optimal values ​​of the above five control parameters, and used as the optimization parameters of the optimal control strategy (Phase III in Table 3). The remaining parameters remained the same as Phase II. According to the optimal control strategy obtained, the short-range denitrification-anaerobic ammonium oxidation system was optimized and regulated in Phase III, and the average total nitrogen removal rate of the short-range denitrification-anaerobic ammonium oxidation system was increased from 92.7% in Phase II to 93.5% in Phase III.

[0085] By adjusting control parameters such as pH, temperature, nitrogen source matrix ratio, carbon-nitrogen ratio and hydraulic retention time, the total nitrogen removal rate of the system was significantly improved.

[0086] like Figure 4 As shown, the total nitrogen removal rate and its predicted value before and after the system intelligent regulation are displayed. Figure 4 In the figure: (a) is the total nitrogen removal rate of the system before intelligent regulation and its predicted value; (b) is the total nitrogen removal rate of the system after intelligent regulation for scenario one and its predicted value; (c) is the total nitrogen removal rate of the system after intelligent regulation for scenario two and its predicted value; (d) is the average of the total nitrogen removal rate and its predicted value before and after intelligent regulation.

[0087] The present invention constructs a multidimensional data set that integrates operating parameters, operation parameters and microbial community structure, uses a gradient boosting algorithm to establish a high-precision prediction model (the test set R² reaches 0.958), combines SHAP feature importance analysis to accurately identify key regulatory factors such as temperature, pH, and carbon-nitrogen ratio, and generates a scenario-adaptive control strategy based on a particle swarm optimization algorithm to achieve a total nitrogen removal rate of a short-range denitrification-anaerobic ammonia oxidation system from 80.7% to 93.5%, and reduces the removal rate fluctuation range under the condition of a total nitrogen concentration fluctuation of ±50% in the influent. At the same time, the operating cost is reduced by optimizing the carbon source dosage, effectively solving the problem of system instability caused by ignoring the dynamic changes of microbial communities in traditional methods. The present invention has the technical advantages of high multi-source data fusion, strong model generalization ability and excellent adaptability of regulatory strategies.

[0088] This step optimizes the performance of the short-range denitrification-anaerobic ammonium oxidation system by collecting system data, selecting key control parameters, applying the particle swarm optimization algorithm to construct the optimal control strategy, and implementing and verifying it in the actual system. This step provides a specific implementation path and method for intelligent control, which helps to improve the total nitrogen removal rate and operational stability of the system.

[0089] In a specific embodiment, a short-range denitrification-anaerobic ammonium oxidation system includes a data module, a processing module, a model module, an analysis module, and a construction module.

[0090] Specifically, the data module is used to obtain the sample point data of the short-range denitrification-anaerobic ammonium oxidation system, including operation data, operating parameters, and microbial community structure data, and to construct a data set for machine learning; The processing module is used to process outliers, convert category information, standardize data, perform correlation analysis, and split the data set to obtain training sets and test sets; The model module is used to establish a prediction model based on the training set through machine learning methods, and evaluate the prediction performance of each prediction model on the test set to select the optimal prediction model; The analysis module is used to use the data in the data set as feature data, perform feature data importance analysis, and identify key parameters that affect the total nitrogen removal rate of the system; The construction module is used to use key parameters as the optimization and regulation parameters of the short-range denitrification-anaerobic ammonium oxidation system, and to construct the optimal control strategy through the particle swarm optimization algorithm.

[0091] The technical solution of the present invention reveals the microbial community structure in sludge samples by comprehensively using 16S rRNA high-throughput sequencing technology, uses QIIME2 software for in-depth analysis to obtain genus-level community structure matrix data, combines the gradient boosting prediction model and the SHAP method to perform feature importance analysis and optimize the prediction performance, and uses the particle swarm optimization algorithm (PSO) in the Scikit-opt package for calculation, which effectively improves the accuracy and efficiency of wastewater treatment process parameter optimization, provides a scientific basis and intelligent means for understanding the function of microbial communities and optimizing wastewater treatment processes, and realizes full-chain technology integration and innovation from data collection and analysis to model optimization and application.

[0092] The above schematically describes the invention and its implementation methods, which is not restrictive. Without departing from the spirit or basic features of the invention, the invention can be implemented in other specific forms. What is shown in the accompanying drawings is only one of the implementation methods of the invention. The actual structure is not limited to this, and any figure mark in the claims should not limit the claims involved. Therefore, if a person of ordinary skill in the art is inspired by it, without departing from the purpose of the invention, a structural method and an embodiment similar to the technical solution are designed without creativity, which should all fall within the scope of protection of this patent. In addition, the word "including" does not exclude other elements or steps, and the word "one" before the element does not exclude the inclusion of "multiple" elements. The multiple elements stated in the product claim can also be implemented by one element through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any specific order.

Claims

1. A smart control method for a short-range denitrification-anaerobic ammonium oxidation system, characterized in that: The following steps are involved: Obtain sample point data of the short-range denitrification-anaerobic ammonium oxidation system, including operation data, operating parameters, and microbial community structure data, and construct a data set for machine learning; Perform outlier processing, category information conversion, data standardization, correlation analysis, and data set splitting on the data set to obtain training sets and test sets; Based on the training set, a prediction model is established through machine learning methods, and the prediction performance of each prediction model on the test set is evaluated to select the optimal prediction model; The data in the dataset are used as characteristic data, and the importance analysis of characteristic data is performed to identify the key parameters that affect the total nitrogen removal rate of the system; The key parameters are used as the optimization and regulation parameters of the short-range denitrification-anaerobic ammonium oxidation system, and the optimal control strategy is constructed through the particle swarm optimization algorithm.

2. The intelligent control method of the short-range denitrification-anaerobic ammonium oxidation system according to claim 1, characterized in that: Outlier processing includes calculating the mean and standard deviation of the feature data of all sample points and making a judgment on each feature data. The judgment process is as follows: Take the data in the data set as feature data and calculate the mean and standard deviation of each feature data of all sample points; The current range is defined by taking the mean value of the feature data of the current sample point minus the standard deviation as the minimum value and taking the mean value of the feature data of the current sample point plus the standard deviation as the maximum value; Determine whether the feature data of the current sample point is within the current range. If not, it is considered an outlier and replaced with the average value of the feature data of the current sample point.

3. The intelligent control method of the short-range denitrification-anaerobic ammonium oxidation system according to claim 1, characterized in that: Data standardization includes using the Standardscaler standard method to normalize the sample point data. The process is expressed as: ； Represents sample feature data, is the average value of each feature data, is the standard deviation of each feature data.

4. The intelligent control method of the short-range denitrification-anaerobic ammonium oxidation system according to claim 1, characterized in that: The process of splitting the data set is as follows: according to the five-fold cross-validation method in the machine learning model evaluation method, the data set is randomly split into two mutually exclusive data sets in a ratio of 8:2, of which 80% of the data is used as the training set for model training; and 20% of the data is used as the test set for model testing.

5. The intelligent control method of the short-range denitrification-anaerobic ammonium oxidation system according to claim 1, characterized in that: Operational data include ammonia nitrogen concentration, nitrate nitrogen concentration, nitrite concentration, COD concentration, pH, carbon-nitrogen ratio and nitrate-ammonia nitrogen ratio; Operational parameters include system type, system volume, recirculation ratio, hydraulic retention time, temperature, inoculum sludge type, and carbon source type; The microbial community structure data are presented in matrix form, with each column representing a species, each row representing a sample, and the element value being the relative abundance of the corresponding species.

6. The intelligent control method of the short-range denitrification-anaerobic ammonium oxidation system according to claim 1, characterized in that: Based on the operating data and operating parameters in the training set, a machine learning method is selected to establish a prediction model; Coefficient of determination , mean square error and mean absolute error The indicators are used to compare the prediction performance of the prediction models and select the optimal prediction model.

7. The intelligent control method of the short-range denitrification-anaerobic ammonium oxidation system according to claim 6, characterized in that: The process of comparing the predictive performance of the prediction models is expressed as: ； ； ； The sample index in the test set is The actual total nitrogen removal rate value, The sample index in the test set is The total nitrogen removal rate value predicted by the prediction model is is the average of the actual total nitrogen removal rates of all samples in the test set, is the sample size.

8. The intelligent control method of the short-range denitrification-anaerobic ammonium oxidation system according to claim 1, characterized in that: The process of feature data importance analysis includes using Python's SHAP package to calculate the SHAP value of each feature data; analyzing the SHAP value of the feature data, and taking features with high SHAP values ​​as key parameters.

9. The intelligent control method of the short-range denitrification-anaerobic ammonium oxidation system according to claim 1, characterized in that: The process of constructing the optimal control strategy includes: selecting one or more key parameters as control parameters, using the particle swarm optimization algorithm to find the optimization parameters, and constructing the optimal control strategy for a specific scenario.

10. A short-cut denitrification-anaerobic ammonium oxidation system, characterized in that: Including data module: obtain sample point data of short-range denitrification-anaerobic ammonium oxidation system, including operation data, operating parameters and microbial community structure data, and construct a data set for machine learning; Processing module: performs outlier processing, category information conversion, data standardization, correlation analysis, and data set splitting on the data set to obtain training sets and test sets; Model module: Based on the training set, a prediction model is established through machine learning methods, and the prediction performance of each prediction model on the test set is evaluated to select the optimal prediction model; Analysis module: Take the data in the data set as feature data, perform feature data importance analysis, and identify key parameters that affect the total nitrogen removal rate of the system; Building module: Using key parameters as the optimization and regulation parameters of the short-range denitrification-anaerobic ammonium oxidation system, the optimal control strategy is constructed through the particle swarm optimization algorithm.

Images