Intelligent aeration control system and method for sewage treatment plant

Abstract

The invention discloses an intelligent aeration control system and method for a sewage treatment plant, and relates to the technical field of sewage treatment control. Comprising a data acquisition module, an aeration test module, a demand prediction module, a normal state analysis module and an aeration control module, wherein the data acquisition module is used for acquiring real-time working data of a primary sedimentation tank, test data of an aeration tank, historical working data and real-time working data of the aeration tank and preprocessing the data; the technical key points are as follows: an aeration tank is scientifically divided into multiple sections, professional monitoring equipment is deployed in each section, multi-dimensional data is acquired, the data of each section is independently acquired and tested, the operation condition and the processing effect of the aeration equipment in each section can be accurately mastered, and on the basis of the accurate data and in combination with an aeration efficiency evaluation model and a regulation and control strategy, the aeration efficiency of the aeration tank is evaluated. And fine adjustment can be performed according to actual requirements of each section, so that resource waste or poor treatment effect caused by one-step regulation and control is avoided, efficient and accurate operation of the aeration equipment is realized, and the aeration equipment has a good use prospect.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment control, and in particular to an intelligent aeration control system and method for a sewage treatment plant. Background Art

[0002] Faced with the dual challenges of water scarcity and increasing water pollution, sewage treatment plants have emerged as critical infrastructure for protecting urban water environments. Like the "kidneys" of the city, they purify domestic and industrial wastewater through physical treatment methods like screen interception and grit sedimentation, biodegradation technologies like activated sludge and biofilm processes, and advanced treatment methods like chemical coagulation and disinfection. These plants not only effectively reduce pollutants but also enable the recycling of water resources, becoming a core force in maintaining ecological balance and promoting sustainable development.

[0003] In the complex process of sewage treatment, the biological treatment stage is the core link for removing pollutants, and the efficient metabolism of microorganisms cannot be separated from sufficient oxygen. The aeration system is the key equipment for supplying oxygen to the reaction tank, and its control technology directly affects the efficiency and energy consumption of sewage treatment. Aeration control can accurately meet the microorganisms' demand for dissolved oxygen and ensure that organic matter in sewage is fully degraded by intelligently adjusting the aeration volume, while avoiding energy waste caused by excessive aeration. It has become an important technical breakthrough for improving the operating efficiency of sewage treatment plants and achieving green and low-carbon treatment.

[0004] The existing patent authorization announcement number is CN105152308B, and the patent name is a method and control system for controlling aeration of an MBR aerobic tank. The invention patent records the following steps: collecting the ammonia nitrogen concentration signal of the membrane tank; obtaining a first residual value between the ammonia nitrogen concentration signal and a preset ammonia nitrogen concentration value; obtaining a preset dissolved oxygen concentration value of the aerobic tank by a first-order PI algorithm; collecting the dissolved oxygen concentration signal of the aerobic tank; obtaining a second residual value between the dissolved oxygen concentration signal and the preset dissolved oxygen concentration value; obtaining an aeration value of the aerobic tank by a second-order PI algorithm; and controlling multiple blowers according to the aeration value of the aerobic tank and the fan performance curve. The control method of the embodiment of the present invention further takes into account the biochemical action of the membrane tank, improves the control accuracy, better realizes the automatic control of the aeration process of the MBR biochemical treatment, stabilizes the effluent water quality, reduces the energy consumption of sewage treatment, and is simple and easy to implement. The central idea of ​​the solution described in the above patent is to collect the ammonia nitrogen concentration signal of the membrane pool and the dissolved oxygen concentration signal of the aerobic pool, calculate the preset dissolved oxygen concentration value and the aeration value through a two-order PI algorithm, and control the blower in combination with the fan performance curve. It also includes signal validity verification, water volume compensation mechanism, and switching control strategy according to the working status of the water inlet flow meter, online ammonia nitrogen meter, and online dissolved oxygen meter to achieve precise aeration control, stabilize water quality and reduce energy consumption. However, the solution described in the above patent has the following drawbacks when used: During the aeration control process, the system adopted a centralized data collection and maintenance approach, without considering the possibility of local blockage of the aeration equipment. In actual use, due to the influence of sludge, some areas of the aeration equipment were seriously blocked, which greatly reduced the aeration effect of that part. This method could not achieve stable oxygen supply and would greatly increase aeration energy consumption. In addition, existing aeration control usually adopts a real-time and accurate prediction method. When in use, it is affected by the environment or other factors, and the water flow will change. At this time, the amount of data it needs to process is large. At this time, equipment parameters are usually adjusted frequently and significantly, which not only affects the life of the equipment, but also causes energy waste and unstable treatment effects, resulting in abnormally high costs and failing to meet energy-saving requirements. For this reason, we have developed an intelligent aeration control system and method for sewage treatment plants. Summary of the Invention

[0005] (1) Technical problems solved In response to the shortcomings of the existing technology, the present invention provides an intelligent aeration control system and method for sewage treatment plants. The aeration tank is scientifically divided into multiple functional sections, and a variety of professional monitoring equipment are deployed in each section to comprehensively collect multi-dimensional data such as flow, water quality, and dissolved oxygen. Through independent collection and testing of data from each section, the operating status and treatment effect of each aeration equipment can be accurately grasped. Based on these precise data, combined with the aeration efficiency evaluation model and control strategy, fine-tuning can be performed according to the actual needs of each section, avoiding resource waste or poor treatment effect caused by one-size-fits-all control, and realizing efficient and accurate operation of the aeration equipment. It has good application prospects and effectively solves the problems raised in the background technology.

[0006] (2) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: The intelligent aeration control system for sewage treatment plants includes a data acquisition module, an aeration test module, a demand forecast module, a normal analysis module, and an aeration control module: Data acquisition module: collects real-time working data of primary sedimentation tank, test data of aeration tank, historical working data of aeration tank and real-time working data, and performs pre-processing; Aeration test module: extracts pre-processed aeration tank test data according to the aeration tank segmentation standard, analyzes the segmented aeration data, generates evaluation values, and compares the evaluation values ​​with the preset maintenance values; If the evaluation value is less than the maintenance value, no action will be taken; Otherwise, delete the evaluation value, maintain the aeration equipment, and then re-test the aeration tank to obtain the evaluation value; Demand forecasting module: inputs the real-time working data of the primary sedimentation tank and the aeration tank into the trained forecasting model to predict the aeration demand data; Normal analysis module: Analyze the historical working data of the aeration tank, formulate aeration level indicators and corresponding control strategies, and use the evaluation values ​​to correct the aeration demand data; Aeration control module: takes the above set of corrected aeration demand data as the benchmark value, calculates the change value of the corrected aeration demand data, and compares the change value with the set standard range; If the change value is within the standard range, the control strategy of correcting the aeration demand data corresponding to the aeration demand level is executed; If the change value is higher than the upper limit of the standard range, the control strategy corresponding to the aeration demand level one level higher is executed to correct the aeration demand data; If the change value is lower than the lower limit of the standard range, maintain the current state and execute the abnormal supervision strategy.

[0007] Furthermore, the real-time working data of the primary sedimentation tank include effluent indicators, instantaneous effluent flow and sludge ratio. The historical working data and real-time working data of the aeration tank include dissolved oxygen, ammonia nitrogen concentration, sludge concentration, redox potential, effluent indicators, instantaneous effluent flow and sludge ratio. The historical working data of the aeration tank also includes actual oxygen demand data.

[0008] Furthermore, the collected data is preprocessed, including cleaning and conversion, as follows: Outlier processing: The Laida criterion is used to detect outliers, identifying and eliminating data points that exceed the normal fluctuation range; Missing value processing: Use the data trend of adjacent time points to estimate missing values, and use linear interpolation based on time series to fill in missing values: Normalization processing: Normalize all data after outlier processing and missing value processing.

[0009] Furthermore, the aeration tank test is to operate each aeration tank according to the pre-set standard aeration parameters under stable working conditions. The test duration is T, and the test data is collected. The evaluation value is calculated based on the test data. The formula for calculating the evaluation value is: , where Epg is the evaluation value, Ps is the power of the aeration equipment, and B is the pressure loss coefficient. is the pressure loss data of the current aeration equipment, is the baseline pressure loss in the initial state, V is the water volume of each part of the aeration tank after segmentation, is the increment of dissolved oxygen concentration in water body within time T, is the saturated dissolved oxygen concentration at the current sewage temperature, and A is the water quality correction coefficient.

[0010] Furthermore, the prediction model adopts the autoregressive integrated moving average model. The training steps of the prediction model are as follows: Data division: The historical working data of each aeration tank is divided into training set and test set in a ratio of 7:3; Stationarity processing: The unit root test is used to perform stationarity analysis on the original oxygen demand time series. If the original oxygen demand time series does not meet the stationarity conditions, it is converted into a stationary series through difference operation, and the difference order is determined; Model order determination: Plot the processed autocorrelation function and partial autocorrelation function graphs, combine the Akaike Information Criterion and the Bayesian Information Criterion, use the particle swarm optimization algorithm to determine the autoregressive order and moving average order, and build a preliminary model; Parameter estimation: Use the training set data to estimate the parameters of the preliminary model and use the maximum likelihood estimation method to solve the model parameters; Model testing: The test set data is input into the trained model for prediction, and the root mean square error and mean absolute error are used to evaluate the model prediction accuracy.

[0011] Furthermore, the steps for analyzing the historical working data of the aeration tank and formulating the aeration level index are as follows: Data preparation: retrieve the latest N historical actual oxygen demand data of each aeration tank from the database; Statistical data: Calculate the mean and standard deviation of N historical actual oxygen demand data; Grade classification: Based on statistical principles and the calculated mean and standard deviation, the actual oxygen demand of each aeration tank is divided into H grades; Strategy formulation: Obtain the upper limit of the actual oxygen demand data in H levels, preset the parameters of the aeration equipment according to the upper limit, and summarize and generate a control strategy, resulting in a total of H control strategies.

[0012] Furthermore, the steps for correcting the aeration demand data using the estimated value are as follows: The oxygen supply efficiency reduction ratio is calculated based on the evaluation value. The specific formula is: , where G is the reduction ratio of oxygen supply efficiency, En is the energy consumption per unit oxygen supply under normal conditions, and Css is the pressure loss correction coefficient, 0<Css<1; The aeration demand data is adjusted based on the reduction ratio of oxygen supply efficiency. The specific formula is: , where is the adjusted aeration demand data, is the predicted aeration demand data.

[0013] Furthermore, the formula for calculating the change in aeration demand is: , where is the change in aeration demand, is the corrected real-time predicted aeration demand data, This is the revised aeration demand data of the previous set.

[0014] Furthermore, the abnormal supervision strategy is implemented to keep the baseline value unchanged and calculate the next set of change values. If the change value is lower than the lower limit of the standard range for three consecutive times, a detection warning is issued and feedback is waited for. If the feedback is abnormal, maintenance is carried out; If the feedback signal is correct, the real-time corrected aeration demand data is calculated, and a control strategy corresponding to the aeration demand level of the real-time corrected aeration demand data is executed.

[0015] Furthermore, the intelligent aeration control method for a sewage treatment plant includes the following steps: Collect the real-time working data of the primary sedimentation tank, the test data of the aeration tank, the historical working data of the aeration tank and the real-time working data, and perform pre-processing; Extract pre-treated aeration tank test data according to the aeration tank segmentation standard, analyze the segmented aeration data, generate evaluation values, and compare the evaluation values ​​with the preset maintenance values; If the evaluation value is less than the maintenance value, no action will be taken; Otherwise, delete the evaluation value, maintain the aeration equipment, and then re-test the aeration tank to obtain the evaluation value; Input the real-time working data of the primary sedimentation tank and the aeration tank into the trained prediction model to predict the aeration demand data; Analyze the historical working data of the aeration tank, formulate aeration level indicators and corresponding control strategies, and use the evaluation values ​​to revise the aeration demand data; The above set of corrected aeration demand data is used as the baseline value, and the change value of the corrected aeration demand data is calculated and compared with the set standard range; If the change value is within the standard range, the control strategy of correcting the aeration demand data corresponding to the aeration demand level is executed; If the change value is higher than the upper limit of the standard range, the control strategy corresponding to the aeration demand level one level higher is executed to correct the aeration demand data; If the change value is lower than the lower limit of the standard range, maintain the current state and execute the abnormal supervision strategy.

[0016] (3) Beneficial effects The present invention provides an intelligent aeration control system and method for a sewage treatment plant, which has the following beneficial effects: 1. This invention describes an intelligent aeration control system and method for sewage treatment plants. This system scientifically divides the aeration tank into multiple functional segments and deploys specialized monitoring equipment in each segment to collect multi-dimensional data such as flow rate, water quality, and dissolved oxygen. By independently collecting and testing data from each segment, the operating status and treatment effectiveness of each aeration system can be accurately monitored. Based on this precise data, combined with an aeration efficiency evaluation model and control strategy, fine-tuned adjustments can be made to meet the actual needs of each segment, avoiding the waste of resources or poor treatment results caused by one-size-fits-all control measures. This approach ensures efficient and precise operation of the aeration system, demonstrating its promising application prospects.

[0017] 2. This invention describes an intelligent aeration control system and method for a sewage treatment plant. Based on statistical principles, the actual historical oxygen demand data for each aeration tank is analyzed, and after calculating the mean and standard deviation, the data is divided into multiple clear demand levels. The corresponding levels are matched according to the predicted aeration demand, and adjustments are made according to preset rules. Compared with complex real-time calculations, this level-based adjustment method significantly reduces the amount of data calculation and improves the system response speed. At the same time, through comprehensive consideration of historical data, it can effectively filter out short-term fluctuations and rapid changes in the data, making the aeration strategy adjustment more stable and reliable, ensuring the smooth operation of the aeration system, and has good application prospects.

[0018] 3. The present invention describes an intelligent aeration control system and method for sewage treatment plants. From data collection, testing of each section of aeration tanks, demand forecasting, normal analysis to aeration control, a complete and systematic aeration tank segmented operation management system is formed. Through multi-dimensional data collection and scientific analysis and processing, combined with precise demand forecasting and reasonable control strategies, comprehensive perception, accurate assessment, and timely adjustment of the aeration tank operating status are achieved, ensuring the efficient and stable operation of the aeration link in the sewage treatment process. This not only improves the sewage treatment effect, but also reduces operating costs and optimizes resource allocation, providing strong support for the stable operation and sustainable development of sewage treatment plants. The system has good use effects and a bright prospect.

[0019] 4. The present invention describes an intelligent aeration control system and method for sewage treatment plants, and constructs a systematic architecture that includes data acquisition and processing, model prediction, hierarchical management, and intelligent regulation. It breaks through the defects of traditional aeration control such as single data, insufficient prediction, and extensive regulation. It accurately predicts aeration demand and divides aeration demand levels to achieve refined management, and flexibly regulates according to the degree of demand change. It significantly improves the intelligence level and adaptability of the aeration system, lays the foundation for the intelligent and digital development of the sewage treatment field, and has good application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of the intelligent aeration control system for a sewage treatment plant according to the present invention.

[0021] Figure 2 This is a flow chart of the intelligent aeration control method for a sewage treatment plant according to the present invention. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0023] The central idea of ​​the solution recorded in the existing patent is to collect the ammonia nitrogen concentration signal of the membrane pool and the dissolved oxygen concentration signal of the aerobic pool, calculate the residuals respectively, and then use the two-order PI algorithm to obtain the preset dissolved oxygen concentration value and the aeration volume value, and then combine the fan performance curve to control multiple blowers. At the same time, it has the functions of instrument signal verification, water volume compensation and automatic switching of control strategies in the event of a fault, which can improve control accuracy, realize automatic control of the aeration process, stabilize the effluent water quality and reduce the energy consumption of sewage treatment.

[0024] However, in actual use, this solution has the following limitations: Centralized equipment management: During aeration control, centralized data collection from aeration tanks is used. This is combined with data collected regularly using existing technologies to analyze the aeration tank conditions and centrally maintain aeration equipment. However, in actual use, the impact of sludge on aeration equipment varies, and this approach fails to consider the possibility of localized blockage of aeration equipment. Consequently, sludge can cause severe blockage in some areas of the aeration equipment, significantly reducing the aeration effect in that area. This approach cannot achieve stable oxygen supply and significantly increases aeration energy consumption. Excessive adjustments: Existing aeration control typically uses real-time, precise prediction, involving real-time data collection, analysis, and processing. However, due to environmental and other factors, water flow can change during use, requiring significant processing of large amounts of data. Consequently, frequent and significant adjustments to equipment parameters are often required, impacting equipment lifespan and leading to energy waste, unstable treatment results, and abnormally high costs. From data collection, testing of each section of the aeration tank, demand forecasting, normal analysis to aeration control, the present invention has formed a complete and systematic aeration tank segmented operation management system, and constructed a new technical framework for slope prestressing monitoring and slope anomaly assessment. Its core does not lie in the improvement of a single technology, but breaks through the defects of single data, insufficient forecasting, and extensive regulation in traditional aeration control. The accurate forecast of aeration demand is combined with the classification of aeration demand levels to achieve refined management, and flexible regulation is carried out according to the degree of demand change, which significantly improves the intelligence level and adaptability of the aeration system, lays the foundation for the intelligent and digital development of the sewage treatment field, and leads the industry's technological upgrading and innovative development.

[0025] Example 1 See also Figure 1 This embodiment provides an intelligent aeration control system for a sewage treatment plant. The specific scheme is as follows: 1. System architecture; The system architecture of the intelligent aeration control system of a sewage treatment plant consists of a data acquisition layer, a data processing layer, an analysis and prediction layer, a strategy decision layer, and an equipment control layer. Each layer operates in coordination to achieve efficient management and precise regulation of the aeration tank.

[0026] 1.1 Data collection layer; The data acquisition layer is responsible for obtaining various key data during the operation of the aeration tank. It divides the aeration tank into multiple functional sections, deploys electromagnetic flowmeters and multi-parameter water quality online analyzers at the water inlet, and collects indicators such as water inlet flow and chemical oxygen demand in real time; installs dissolved oxygen sensors and water quality automatic samplers at the outlet of each section to obtain dissolved oxygen concentration and outlet water quality data; installs ultrasonic sludge concentration meters and other equipment in the middle of the tank body to monitor parameters such as sludge concentration and redox potential; installs gas flowmeters on the air supply pipeline of the aeration equipment, and combines the PLC control system to collect operating parameters such as the air supply volume and working voltage of the aeration equipment to provide original data support for subsequent processing.

[0027] 1.2 Data processing layer; The data processing layer receives the original data transmitted by the data collection layer, processes the noise, missing values ​​and outliers in the data, uses the Laida criterion to identify and eliminate outliers, fills missing values ​​through linear interpolation, and uses the normalization formula to eliminate data dimension differences, improve data quality, and ensure that the data input to subsequent layers is accurate and reliable to meet analysis and modeling needs.

[0028] 1.3 Analysis and prediction layer; Based on pre-processed data, each aeration tank section is tested using standard aeration parameters under stable system conditions. By calculating the aeration equipment's evaluation value and comparing the actual oxygen supply with the standard, the equipment's operating status is assessed, and any blockages or other issues are identified, providing a basis for strategic planning.

[0029] ARIMA models are used to predict aeration demand and equipment oxygen supply. The differencing order is determined through data segmentation and stationarity testing. The autoregressive order and moving average order are determined by combining the autocorrelation function and partial autocorrelation function plots with the AIC and BIC criteria. After training the model, future oxygen demand and supply are predicted, allowing for early understanding of demand trends.

[0030] 1.4 Strategic decision-making layer; The strategic decision-making layer calculates the mean and standard deviation based on historical aeration demand and equipment oxygen supply data, classifies aeration demand levels, and dynamically updates the levels based on the evaluation values ​​of the aeration equipment, providing a hierarchical strategy foundation for aeration control. The degree of change in aeration demand is calculated in real time and compared with the preset standard value. Based on different situations, such as small demand change, increase or decrease in demand with small change, etc., combined with the aeration demand level, the corresponding aeration equipment operating parameter adjustment strategy is generated.

[0031] 1.5 device control layer; The control strategy generated by the receiving strategy decision layer is used to accurately adjust the operating parameters of the aeration equipment, such as the blower air volume and sludge return ratio, through actuators such as frequency converters and PLC control systems, to achieve optimized control of the aeration process and ensure efficient and stable operation of the aeration tank. At the same time, based on the equipment blockage judgment results, the equipment inspection and maintenance process is triggered.

[0032] 2. Hardware foundation; 2.1 Data acquisition hardware; Electromagnetic flowmeter: Choose an electromagnetic flowmeter such as the E+H Promag series, installed at the aeration tank inlet and firmly connected to the pipeline via a flange connection. This flowmeter is used to monitor the inlet flow in real time and provide basic flow data for the system.

[0033] Multi-parameter water quality online analyzer: Hach Amtax NA8000 model is selected, installed near the water inlet, fixed with a special bracket, and connected to the data processing equipment using an RS485 communication line. It can simultaneously collect water quality indicators such as chemical oxygen demand, five-day biochemical oxygen demand, suspended solids and total phosphorus, providing data support for analyzing the water quality of the inlet.

[0034] Dissolved oxygen sensor: The InPro 6050i model is selected and immersed in water at the outlet of each aeration tank through a dedicated mounting bracket to ensure full contact between the probe and the water body, realizing real-time collection and transmission of dissolved oxygen concentration data.

[0035] Automatic water sampler: HACH 3540 model is selected and installed near the sampling point of each water outlet. It is connected to the sampling location through a pipeline and connected to the data processing equipment using RS232 or RS485 communication line to realize remote control sampling and data transmission. Water samples are collected regularly for laboratory testing of water quality indicators.

[0036] Ultrasonic sludge concentration meter: E+H FMX167 model is selected and installed on the pipeline in the middle of the tank body through a pipe clamp. Ensure that the measuring probe is aligned with the center of the fluid. The signal is connected to the data processing equipment through a dedicated cable to obtain real-time sludge concentration data to reflect the sludge status in the middle of the tank body.

[0037] Oxidation-reduction potential (ORP) meter: The model used is PHS-3E, which is wall-mounted and installed at a suitable position in the middle of the tank body. The electrodes are immersed in water, and the electrode signal transmission line is connected to the data processing equipment using a dedicated signal line to monitor the oxidation-reduction potential and assist in judging the reaction status in the aeration tank.

[0038] Sludge concentration monitor: WTW Oxi3310 model is selected. The installation method is similar to that of the ultrasonic sludge concentration meter. After being fixed in the middle of the tank body, it is connected to the data processing equipment through the matching cable to measure the sludge concentration and provide multi-dimensional sludge concentration data for process control.

[0039] Gas flow meter: Use the AXF series gas flow meter, installed on the aeration equipment's air supply line with a flange connection. This meter collects air supply data in real time and calculates actual oxygen supply based on the equipment's performance curve.

[0040] PLC control system: S7-300 series PLC is selected and installed in the control cabinet in the control room. Various input and output modules are used, such as analog input modules that receive analog signals from sensors, and digital input and output modules that control the switching of aeration equipment, the start and stop of frequency converters and other equipment.

[0041] Frequency converter: Installed in the electrical control cabinet near the aeration equipment, connected to the aeration equipment motor, it adjusts the operating speed of the aeration equipment by changing the motor power frequency, thereby controlling the aeration volume. At the same time, it is connected to the PLC control system through a communication line to receive control instructions from the PLC.

[0042] 2.2 Control hardware; Industrial control computers, located in the control room, serve as the data processing and management core for the entire system. Connected via Ethernet to PLC control systems and data acquisition equipment (devices supporting network communications), they enable centralized data storage, analysis, and processing, as well as the issuance of control commands. Equipped with high-performance processors, large-capacity memory, and storage hard drives, they meet the demands of large-scale data processing and system operation.

[0043] Data acquisition card: installed in the industrial control computer, used to collect analog and digital signals from various sensors and convert them into digital quantities that the computer can recognize. According to the type and number of sensors, select a data acquisition card with appropriate number of channels and accuracy to ensure the accuracy and stability of data acquisition.

[0044] 2.3 Software: Data acquisition and transmission software: runs on industrial control computers and is responsible for communicating with various data acquisition hardware devices, collecting data at set time intervals, and transmitting the data to the database for storage. It supports multiple communication protocols such as RS232, RS485, Ethernet, etc., and is compatible with different types of equipment to ensure the timeliness and accuracy of data acquisition.

[0045] Database management software: MySQL database management system is selected to store massive amounts of data such as water quality, flow, equipment operating parameters, etc., establish a reasonable data table structure, classify and store data to facilitate subsequent data query, analysis and mining, and have data backup and recovery functions to ensure data security and integrity.

[0046] Data analysis and modeling software: These software programs analyze historical data stored in databases to build aeration demand forecasting models (ARIMA models) and aeration equipment effectiveness evaluation models. Through data mining and machine learning algorithms, patterns and trends in the data are discovered, providing data support and model basis for strategic decision-making.

[0047] Control Strategy Execution Software: This software works in conjunction with the PLC control system. Based on data analysis results and pre-set control strategies, it generates control instructions and sends them to the PLC. The PLC then controls the aeration equipment, such as adjusting blower air volume and controlling the sludge return ratio, to achieve automated control of the aeration process. It also monitors the equipment's operating status in real time and issues alarms for equipment failures.

[0048] 3. System solution; like Figure 1 As shown, the intelligent aeration control system for a sewage treatment plant of the present invention includes a data acquisition module, an aeration test module, a demand forecast module, a normal analysis module and an aeration control module: 3.1 Data collection; Data acquisition is to obtain the relevant data required for analyzing aeration control, which relies on the data acquisition module to realize data collection and preprocessing.

[0049] Data acquisition module: collects real-time working data of primary sedimentation tank, test data of aeration tank, historical working data of aeration tank and real-time working data, and performs pre-processing; The real-time working data of the primary sedimentation tank include effluent indicators, instantaneous effluent flow and sludge ratio. The historical working data and real-time working data of the aeration tank include dissolved oxygen, ammonia nitrogen concentration, sludge concentration, redox potential, effluent indicators, instantaneous effluent flow and sludge ratio. The historical working data of the aeration tank also includes actual oxygen demand data (real oxygen demand data).

[0050] The aeration equipment in each section of the aeration tank is set up or aerated independently without interfering with each other.

[0051] Aeration tank test data includes the power of the aeration equipment, the pressure loss data of the aeration equipment, the water volume and dissolved oxygen concentration of each part after the aeration tank is segmented.

[0052] Preprocessing of the collected data includes cleaning and conversion, as follows: Outlier processing: Use the Laida criterion to detect outliers, calculate the mean and standard deviation of the data, and identify and eliminate data points that exceed the normal fluctuation range; For example: the aeration tank is divided into 5 sections. The chemical oxygen demand of the first section of the aeration tank is 80, 85, 200, 90 and 95 during a certain period of time. The calculated mean is 110 and the standard deviation is 49.5. The data are all within the range and there are no outliers.

[0053] Missing value processing: Use the data trend of adjacent time points to estimate missing values, and use linear interpolation based on time series to fill in missing values: For example, the data sequence of dissolved oxygen content in one section of the aeration tank is 2.2, 2.4, blank, 2.8, 3, and 0. The missing value calculated by linear interpolation is (2.4+2.8) / 2=2.6 mg / L.

[0054] Normalization processing: All data after outlier processing and missing value processing are normalized. Normalization processing is a commonly used technology in existing data processing and is common knowledge, so it will not be described in detail.

[0055] The present invention describes an intelligent aeration control system and method for a sewage treatment plant. The control system scientifically divides the aeration tank into multiple functional sections, deploys a variety of professional monitoring equipment in each section, and comprehensively collects multi-dimensional data such as flow rate, water quality, and dissolved oxygen. By independently collecting and testing data from each section, the operating status and treatment effect of each aeration device can be accurately grasped. Based on this precise data, combined with an aeration efficiency evaluation model and control strategy, fine-tuning can be performed according to the actual needs of each section, avoiding resource waste or poor treatment effects caused by one-size-fits-all control, and achieving efficient and accurate operation of the aeration equipment. The system has good prospects for use.

[0056] 3.2, aeration analysis; To achieve precise control of aeration, it is necessary to understand the condition of the aeration equipment, so it is necessary to analyze the aeration equipment accordingly, and this step is based on the aeration test module; The aeration test module extracts pre-processed aeration tank test data according to the aeration tank segmentation standard, analyzes the segmented aeration data, generates an evaluation value, and compares the evaluation value with the preset maintenance value; If the evaluation value is less than the maintenance value, no action will be taken; Otherwise, delete the evaluation value, maintain the aeration equipment, and then re-test the aeration tank to obtain the evaluation value; The aeration tank test is to operate each aeration tank according to the pre-set standard aeration parameters under stable working conditions. The test duration is T, and the test data is collected. The evaluation value is calculated based on the test data. The formula for calculating the evaluation value is: , where Epg is the evaluation value, Ps is the power of the aeration equipment, and B is the pressure loss coefficient. is the pressure loss data of the current aeration equipment, is the baseline pressure loss in the initial state, V is the water volume of each part of the aeration tank after segmentation, is the increment of dissolved oxygen concentration in water body within time T, is the saturated dissolved oxygen concentration at the current sewage temperature, A is the water quality correction coefficient, A<1, normally taken as 0.7-0.9.

[0057] For example, the aeration equipment uses a fan. Under normal circumstances, the data voltage is 380V and the current is 25A. The calculated input power is 13.9. The actual oxygen supply increases from 2mg / L to 8mg / L in 15 minutes. The volume of each section of the aeration tank is 500m 3 , the pressure loss is 4.2KPa, and the evaluation value under normal circumstances is 2.5kW·h After a period of use, the current status monitoring shows that the voltage remains unchanged and the power meter shows a power of 15.6. The actual oxygen supply increases from 2mg / L to 6mg / L in 15 minutes, with a pressure loss of 6.5KPa. The calculated evaluation value is 2.78kW·h.

[0058] At this time, if the set maintenance value is 2.75kW·h, it does not meet the requirements. If the set maintenance value is 2.85kW·h, it meets the requirements. The maintenance value is set based on the energy consumption requirements of the sewage treatment plant.

[0059] 3.3, demand forecast; Demand forecasting is to process and analyze existing data and historical data to predict the current aeration demand data. This step is based on the demand forecasting module.

[0060] Demand forecasting module: inputs the real-time working data of the primary sedimentation tank and the aeration tank into the trained forecasting model to predict the aeration demand data; The forecasting model uses the Autoregressive Integrated Moving Average (ARIMA) model. The training steps of the forecasting model are as follows: Data division: The historical working data of each aeration tank is divided into training set and test set in a ratio of 7:3; For example, a certain aeration tank has 100 historical oxygen demand data, the first 70 of which are used as training sets, and the last 30 as test sets.

[0061] Historical data is the most recent data, and the recent data environment is the same, so it is for reference. In addition, data for the same sewage treatment is needed. For new sewage treatment, this solution is not applicable if there is not enough data.

[0062] Stationarity processing: The unit root test (ADF test) is used to analyze the stationarity of the original oxygen demand time series. If the original oxygen demand time series does not meet the stationarity conditions, it is converted into a stationary series through difference operation, and the difference order is determined; For example: the original sequence of oxygen demand in the aeration tank, by drawing a sequence diagram and calculating statistics, it was found that the data had an obvious upward trend, and it was preliminarily judged to be a non-stationary sequence. An ADF test was performed, and the test statistic was -1.5. Compared with the critical values ​​at different significance levels (such as the critical value at the 1% significance level is -3.5), it was found to be greater than the critical value, so the original hypothesis could not be rejected, that is, the sequence was non-stationary. After taking the first-order difference, the ADF test was performed again, and the test statistic became -3.8, which was less than the critical value at the 1% significance level. At this time, it can be considered that the sequence has been converted into a stationary sequence, and thus d=1 is determined.

[0063] Model order determination: Plot the processed autocorrelation function and partial autocorrelation function graphs, combine the Akaike Information Criterion and the Bayesian Information Criterion, use the particle swarm optimization algorithm to determine the autoregressive order and moving average order, and build a preliminary model; The autocorrelation function (ACF) and partial autocorrelation function (PACF) show the degree of autocorrelation of the sequence at different lag orders. The autocorrelation function diagram shows the degree of partial autocorrelation of the sequence at different lag orders after eliminating the influence of the intermediate lag terms. By observing the truncation and tailing characteristics of these two diagrams, the value range of p and q can be preliminarily determined.

[0064] Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) are indicators used to evaluate model goodness of fit and complexity. Smaller values ​​indicate better model fit and lower model complexity. When determining p and q, try different value combinations, calculate the corresponding AIC and BIC values, and select the combination that minimizes the AIC and BIC values ​​as the final p and q values.

[0065] For example, after plotting the ACF and PACF graphs for the oxygen supply data of a certain aeration tank, it was found that the ACF graph rapidly approaches 0 after a lag of 2, showing a truncation characteristic; the PACF graph approaches 0 after a lag of 3, also showing a truncation characteristic. Then, starting from p=0, q=0, we gradually tried different combinations of p and q and calculated the AIC and BIC values. When p=3, q=2, the AIC and BIC values ​​both reached their minimum, so we finally determined p=3, q=2.

[0066] Parameter estimation: Use the training set data to estimate the parameters of the preliminary model and use the maximum likelihood estimation method to solve the model parameters; The basic idea of ​​the maximum likelihood estimation method is to find a set of parameter values ​​so that the probability of the training data occurring is maximized under this set of parameters, so that the model can best fit the characteristics and rules of the training data.

[0067] For example, using 70 training set data of the second section of aeration tank oxygen demand, the maximum likelihood estimation method is used to estimate the parameters. After iterative calculation, the autoregressive coefficient and moving average coefficient are finally obtained, thereby determining the ARIMA model for predicting the oxygen demand of the aeration tank in this section.

[0068] The calculation formula of the ARIMA model is as follows:

[0069] Where: is the symbol for performing d-order difference operation on the sequence, is the oxygen demand time series or oxygen supply time series of the i-th aeration tank at time t, Is the autoregressive coefficient, which is used to measure the weight of the impact of the sequence's own historical value on the current value. is the oxygen demand time series or oxygen supply time series of the i-th aeration tank at time tj, p is the autoregressive order, q is the moving average order, is the moving average coefficient, is the white noise sequence of the i-th aeration tank at time t, is the white noise sequence of the i-th aeration tank at time to.

[0070] Model testing: The test set data is input into the trained model for prediction, and the root mean square error and mean absolute error are used to evaluate the model prediction accuracy.

[0071] For example, for a certain aeration tank oxygen demand prediction model, the test set contains 30 data points. The 30 actual oxygen demand data points in the test set and the oxygen demand data predicted by the model are substituted into the root mean square error and mean absolute error formulas for calculation. First, the error at each moment is calculated, and then the root mean square error and mean absolute error formulas are used for calculation. The calculated root mean square error and mean absolute error are 4 and 2.5, respectively. If they are pre-set to 5 and 3, the model meets the threshold requirements.

[0072] The present invention records an intelligent aeration control system and method for a sewage treatment plant. Based on statistical principles, the historical actual oxygen demand data of each aeration tank is analyzed, and the data is divided into multiple clear demand levels after calculating the mean and standard deviation. The corresponding levels are matched according to the predicted aeration demand, and adjustments are made according to preset rules. Compared with complex real-time calculations, this level-based adjustment method greatly reduces the amount of data calculation and improves the system response speed. At the same time, through comprehensive consideration of historical data, it can effectively filter out short-term fluctuations and rapid changes in the data, making the aeration strategy adjustment more stable and reliable, ensuring the smooth operation of the aeration system, and has good application prospects.

[0073] 3.4、Specific analysis; Analyze historical data, summarize the historical data, and formulate appropriate control strategies based on the historical data. This step is based on the normal analysis module.

[0074] Normal analysis module: Analyze the historical working data of the aeration tank, formulate aeration level indicators and corresponding control strategies, and use the evaluation values ​​to correct the aeration demand data; The steps to analyze the historical working data of the aeration tank and formulate the aeration level index are as follows: Data preparation: retrieve the latest N historical actual oxygen demand data of each aeration tank from the database; The most recent N historical actual oxygen demand data must be reviewed and evaluated to ensure they are correct.

[0075] Statistical data: Calculate the mean and standard deviation of N historical actual oxygen demand data; The calculation formulas for the mean and standard deviation are commonly used techniques, so they will not be described in detail.

[0076] Grade classification: Based on statistical principles and calculated mean and standard deviation, the actual oxygen demand of each aeration tank is divided into H grades to clarify the current operating status of the aeration tank and provide a reference for subsequent regulation; For example, 2 times the standard deviation can be used as the grade difference, that is, the difference between the grade upper limit and the grade lower limit is 2 times the standard deviation, and the mean data can be combined to realize H grades corresponding to the historical actual oxygen demand data.

[0077] Strategy formulation: Obtain the upper limit of the actual oxygen demand data in H levels, preset the parameters of the aeration equipment according to the upper limit, and summarize and generate a control strategy, resulting in a total of H control strategies.

[0078] For example: the upper limit of the second level is Bmax, and the lowest is Bmin. The parameters of the aeration equipment are preset based on the actual oxygen demand data Bmax. The corresponding settings of the historical plan can be directly searched, including setting the aeration volume, aeration time, blower speed, etc.

[0079] According to the upper limit setting, the aeration effect can be stably guaranteed.

[0080] The steps to use the estimated value to correct the aeration demand data are as follows: The oxygen supply efficiency reduction ratio is calculated based on the evaluation value. The specific formula is: , where G is the reduction ratio of oxygen supply efficiency, En is the energy consumption per unit oxygen supply under normal conditions, and Css is the pressure loss correction coefficient, 0<Css<1; For example, under normal circumstances, the energy consumption per unit of oxygen supply is 2.5kW·h, while under current circumstances, the energy consumption per unit of oxygen supply is 3kW·h. The calculated reduction in oxygen supply efficiency is 16.7%.

[0081] The aeration demand data is adjusted based on the reduction ratio of oxygen supply efficiency. The specific formula is: , where is the adjusted aeration demand data, is the predicted aeration demand data.

[0082] For example, the calculated aeration demand data here is 116.7% of the predicted aeration demand data.

[0083] The present invention describes an intelligent aeration control system and method for a sewage treatment plant. From data collection, testing of each section of the aeration tank, demand forecasting, normal analysis to aeration control, a complete and systematic aeration tank segmented operation management system is formed. Through multi-dimensional data collection and scientific analysis and processing, combined with precise demand forecasting and reasonable control strategies, comprehensive perception, accurate assessment and timely adjustment of the aeration tank operating status are achieved, ensuring the efficient and stable operation of the aeration link in the sewage treatment process. This not only improves the sewage treatment effect, but also reduces operating costs, optimizes resource allocation, and provides strong support for the stable operation and sustainable development of the sewage treatment plant. The system has good use effect and a bright prospect.

[0084] 3.5. Aeration control; When in use, real-time data collection, real-time comparison, and real-time adjustment are required to achieve precise aeration control, and this process is based on the aeration control module.

[0085] Aeration control module: takes the above set of corrected aeration demand data as the benchmark value, calculates the change value of the corrected aeration demand data, and compares the change value with the set standard range; The formula for calculating the change in aeration demand is: , where is the change in aeration demand, is the corrected real-time predicted aeration demand data, This is the revised aeration demand data of the previous set.

[0086] If the change value is within the standard range, the control strategy of correcting the aeration demand data corresponding to the aeration demand level is executed; For example, the corrected aeration demand data of the previous set is 25kg, and the corrected real-time predicted aeration demand data is 30kg, corresponding to the aeration demand level 3. The calculated aeration demand change value is 0.2. If the standard interval is (-0.1, 0.1), the level 4 control strategy is executed.

[0087] If the change value is higher than the upper limit of the standard range, the control strategy corresponding to the aeration demand level one level higher is executed to correct the aeration demand data; For example, the corrected aeration demand data of the previous set is 25kg, and the corrected real-time predicted aeration demand data is 27kg, corresponding to the aeration demand level 3. The calculated aeration demand change value is 0.08. If the standard interval is (-0.1, 0.1), the level 3 control strategy is executed.

[0088] If the change value is lower than the lower limit of the standard range, maintain the current state and execute the abnormal supervision strategy.

[0089] For example, the previous set of corrected aeration demand data is 25 kg, and the corrected real-time predicted aeration demand data is 20 kg, corresponding to aeration demand level 3. The calculated aeration demand change value is -0.2. If the standard interval is (-0.1, 0.1), the abnormal supervision strategy is to maintain the baseline value of 25 kg unchanged, calculate the next set of change values, and if the change value is lower than the lower limit of the standard interval for three consecutive times (three collections and three tests, that is, after three test cycles), a detection warning is issued (usually an abnormality, a decrease in sewage volume or damage to the detection instrument), and feedback is waited for (manual rapid detection and analysis to determine whether the sewage volume has decreased). If the feedback is abnormal, maintenance is carried out (if the sewage volume has decreased, the parameters need to be adjusted, and if the detection instrument is damaged, it needs to be inspected and maintained). If the feedback signal is correct, the real-time corrected aeration demand data is calculated, and a control strategy corresponding to the aeration demand level of the real-time corrected aeration demand data is executed.

[0090] This method mainly provides a range and does not make adjustments within the range to avoid frequent adjustments of the equipment. In addition, when the aeration demand data increases sharply, adjustments are made in advance to ensure the aeration effect. When the aeration demand data decreases sharply, timely feedback is given to ensure that the aeration equipment can provide stable aeration.

[0091] The present invention describes an intelligent aeration control system and method for sewage treatment plants, and constructs a systematic architecture including data collection and processing, model prediction, hierarchical management, and intelligent regulation. It breaks through the defects of single data, insufficient prediction, and extensive regulation in traditional aeration control. It accurately predicts aeration demand and divides aeration adjustment levels to achieve refined management. It can flexibly regulate according to the degree of demand change, significantly improving the intelligence level and adaptive ability of the aeration system, laying the foundation for the intelligent and digital development of sewage treatment field, and has good application prospects. Example 2 On the basis of Example 1, Figure 2 As shown, the intelligent aeration control method for a sewage treatment plant includes the following steps: Collect the real-time working data of the primary sedimentation tank, the test data of the aeration tank, the historical working data of the aeration tank and the real-time working data, and perform pre-processing; Extract pre-treated aeration tank test data according to the aeration tank segmentation standard, analyze the segmented aeration data, generate evaluation values, and compare the evaluation values ​​with the preset maintenance values; If the evaluation value is less than the maintenance value, no action will be taken; Otherwise, delete the evaluation value, maintain the aeration equipment, and then re-test the aeration tank to obtain the evaluation value; Input the real-time working data of the primary sedimentation tank and the aeration tank into the trained prediction model to predict the aeration demand data; Analyze the historical working data of the aeration tank, formulate aeration level indicators and corresponding control strategies, and use the evaluation values ​​to revise the aeration demand data; The above set of corrected aeration demand data is used as the baseline value, and the change value of the corrected aeration demand data is calculated and compared with the set standard range; If the change value is within the standard range, the control strategy of correcting the aeration demand data corresponding to the aeration demand level is executed; If the change value is higher than the upper limit of the standard range, the control strategy corresponding to the aeration demand level one level higher is executed to correct the aeration demand data; If the change value is lower than the lower limit of the standard range, maintain the current state and execute the abnormal supervision strategy.

[0092] In this application, the several formulas involved are all calculated by taking their numerical values ​​after removing the dimensions, and the formulas are established by collecting a large amount of data and performing software simulation to obtain a formula for the most recent real situation. Some coefficients or weights in the formulas are set by technical personnel in this field according to actual conditions, so they are not elaborated here.

[0093] 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 the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0094] 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.

[0095] 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. Intelligent aeration control system for sewage treatment plants, characterized by: include: Data acquisition module: collects real-time working data of primary sedimentation tank, test data of aeration tank, historical working data of aeration tank and real-time working data, and performs pre-processing; Aeration test module: extracts pre-processed aeration tank test data according to the aeration tank segmentation standard, analyzes the segmented aeration data, generates evaluation values, and compares the evaluation values ​​with the preset maintenance values; If the evaluation value is less than the maintenance value, no action will be taken; Otherwise, delete the evaluation value, maintain the aeration equipment, and then re-test the aeration tank to obtain the evaluation value; Demand forecasting module: inputs the real-time working data of the primary sedimentation tank and the aeration tank into the trained forecasting model to predict the aeration demand data; Normal analysis module: Analyze the historical working data of the aeration tank, formulate aeration level indicators and corresponding control strategies, and use the evaluation values ​​to correct the aeration demand data; Aeration control module: takes the above set of corrected aeration demand data as the benchmark value, calculates the change value of the corrected aeration demand data, and compares the change value with the set standard range; If the change value is within the standard range, the control strategy of correcting the aeration demand data corresponding to the aeration demand level is executed; If the change value is higher than the upper limit of the standard range, the control strategy corresponding to the aeration demand level one level higher is executed to correct the aeration demand data; If the change value is lower than the lower limit of the standard range, maintain the current state and execute the abnormal supervision strategy.

2. The intelligent aeration control system for a sewage treatment plant according to claim 1, characterized in that: The real-time working data of the primary sedimentation tank include effluent indicators, instantaneous effluent flow and sludge ratio. The historical working data and real-time working data of the aeration tank include dissolved oxygen, ammonia nitrogen concentration, sludge concentration, redox potential, effluent indicators, instantaneous effluent flow and sludge ratio. The historical working data of the aeration tank also includes actual oxygen demand data.

3. The intelligent aeration control system for a sewage treatment plant according to claim 2, characterized in that: Preprocessing of the collected data includes cleaning and conversion, as follows: Outlier processing: Use the Laida criterion to detect outliers, identify and eliminate data points that exceed the normal fluctuation range; Missing value processing: Use the data trend of adjacent time points to estimate missing values, and use linear interpolation based on time series to fill in missing values: Normalization processing: Normalize all data after outlier processing and missing value processing.

4. The intelligent aeration control system for a sewage treatment plant according to claim 3, characterized in that: The aeration tank test is to operate each aeration tank according to the pre-set standard aeration parameters under stable working conditions. The test duration is T, and the test data is collected. The evaluation value is calculated based on the test data. The formula for calculating the evaluation value is: , where Epg is the evaluation value, Ps is the power of the aeration equipment, and B is the pressure loss coefficient. is the pressure loss data of the current aeration equipment, is the baseline pressure loss in the initial state, V is the water volume of each part of the aeration tank after segmentation, is the increment of dissolved oxygen concentration in water body within time T, is the saturated dissolved oxygen concentration at the current sewage temperature, and A is the water quality correction coefficient.

5. The intelligent aeration control system for a sewage treatment plant according to claim 4, characterized in that: The prediction model uses the autoregressive integrated moving average model. The training steps of the prediction model are as follows: Data division: The historical working data of each aeration tank is divided into training set and test set in a ratio of 7:3; Stationarity processing: The unit root test is used to perform stationarity analysis on the original oxygen demand time series. If the original oxygen demand time series does not meet the stationarity conditions, it is converted into a stationary series through difference operation and the difference order is determined; Model order determination: Plot the processed autocorrelation function and partial autocorrelation function graphs, combine the Akaike Information Criterion and the Bayesian Information Criterion, use the particle swarm optimization algorithm to determine the autoregressive order and moving average order, and build a preliminary model; Parameter estimation: Use the training set data to estimate the parameters of the preliminary model and use the maximum likelihood estimation method to solve the model parameters; Model testing: The test set data is input into the trained model for prediction, and the root mean square error and mean absolute error are used to evaluate the model prediction accuracy.

6. The intelligent aeration control system for a sewage treatment plant according to claim 5, characterized in that: The steps to analyze the historical working data of the aeration tank and formulate the aeration level index are as follows: Data preparation: retrieve the latest N historical actual oxygen demand data of each aeration tank from the database; Statistical data: Calculate the mean and standard deviation of N historical actual oxygen demand data; Grade classification: Based on statistical principles and the calculated mean and standard deviation, the actual oxygen demand of each aeration tank is divided into H grades; Strategy formulation: Obtain the upper limit of the actual oxygen demand data in H levels, preset the parameters of the aeration equipment according to the upper limit, and summarize and generate a control strategy, resulting in a total of H control strategies.

7. The intelligent aeration control system for a sewage treatment plant according to claim 6, characterized in that: The steps to use the estimated value to correct the aeration demand data are as follows: The oxygen supply efficiency reduction ratio is calculated based on the evaluation value. The specific formula is: , where G is the reduction ratio of oxygen supply efficiency, En is the energy consumption per unit oxygen supply under normal conditions, and Css is the pressure loss correction coefficient, 0<Css<1; The aeration demand data is adjusted based on the reduction ratio of oxygen supply efficiency. The specific formula is: , where is the adjusted aeration demand data, is the predicted aeration demand data.

8. The intelligent aeration control system for a sewage treatment plant according to claim 7, characterized in that: The formula for calculating the change in aeration demand is: , where is the change in aeration demand, is the corrected real-time predicted aeration demand data, This is the revised aeration demand data of the previous set.

9. The intelligent aeration control system for a sewage treatment plant according to claim 8, characterized in that: The abnormal supervision strategy is to maintain the baseline value unchanged and calculate the next set of change values. If the change value is lower than the lower limit of the standard range for three consecutive times, a detection warning will be issued and feedback will be waited for. If the feedback is abnormal, maintenance will be carried out; If the feedback signal is correct, the real-time corrected aeration demand data is calculated, and a control strategy corresponding to the aeration demand level of the real-time corrected aeration demand data is executed.

10. An intelligent aeration control method for a sewage treatment plant, using the system according to any one of claims 1 to 9, characterized in that: The steps include: Collect the real-time working data of the primary sedimentation tank, the test data of the aeration tank, the historical working data of the aeration tank and the real-time working data, and perform pre-processing; Extract pre-treated aeration tank test data according to the aeration tank segmentation standard, analyze the segmented aeration data, generate evaluation values, and compare the evaluation values ​​with the preset maintenance values; If the evaluation value is less than the maintenance value, no action will be taken; Otherwise, delete the evaluation value, maintain the aeration equipment, and then re-test the aeration tank to obtain the evaluation value; Input the real-time working data of the primary sedimentation tank and the aeration tank into the trained prediction model to predict the aeration demand data; Analyze the historical working data of the aeration tank, formulate aeration level indicators and corresponding control strategies, and use the evaluation values ​​to revise the aeration demand data; The above set of corrected aeration demand data is used as the baseline value, and the change value of the corrected aeration demand data is calculated and compared with the set standard range; If the change value is within the standard range, the control strategy of correcting the aeration demand data corresponding to the aeration demand level is executed; If the change value is higher than the upper limit of the standard range, the control strategy corresponding to the aeration demand level one level higher is executed to correct the aeration demand data; If the change value is lower than the lower limit of the standard range, maintain the current state and execute the abnormal supervision strategy.

Images