Intelligent aeration optimization control method and system for sewage plant

Abstract

The invention provides an intelligent aeration optimization control method and system for a sewage plant, and relates to the technical field of sewage treatment.The method comprises the steps that water quality, water quantity and aeration quantity data are collected in real time; analyzing and processing the data of the water quality, the water quantity and the aeration quantity to form a sewage treatment process data set which comprises the change rate of a water quality index, the fluctuation condition of the water quantity and aeration efficiency information; and according to the sewage treatment process data set, establishing and training a dynamic mathematical model in the sewage treatment process to reflect the relationship among the water quality, the water quantity and the aeration quantity. Real-time monitoring, model prediction and intelligent adjustment technologies are integrated, the aeration control strategy is effectively optimized, the sewage treatment efficiency is improved, the stability of water quality is ensured, and energy conservation and environmental protection are promoted.

Description

Technical Field

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

[0002] Traditional aeration control technology often relies on manual experience for adjustment and lacks precise control methods, which makes it difficult to accurately match the aeration volume with actual needs, and is prone to insufficient or excessive aeration.

[0003] In the manual control of blower start and stop and valve adjustment to adjust air volume, operators often adjust aeration volume based on experience or fixed schedules. However, the actual water quality and treatment load are dynamically changing, and fixed aeration strategies are difficult to meet actual needs.

[0004] For example, when the sewage load suddenly increases, if the aeration volume is not adjusted in time, the dissolved oxygen concentration may decrease, affecting the activity of microorganisms and thus reducing the treatment efficiency.

[0005] In addition, traditional aeration control technology often leads to high energy consumption due to the lack of intelligent adjustment means. Aeration equipment such as blowers consume a lot of electricity during operation, and traditional control methods are difficult to optimize energy consumption.

[0006] For example, a blower may run at a constant speed, regardless of actual demand. This "one-size-fits-all" approach results in the blower running at high speeds when wastewater loads are low, wasting energy. For example, at night or during holidays, when wastewater loads are typically lower, the blower is still running at peak daytime loads, resulting in unnecessary energy consumption. Summary of the invention

[0007] The technical problem to be solved by the present invention is to provide a sewage treatment plant intelligent aeration optimization control method and system, which realizes the automation, intelligence and efficiency of the sewage treatment process.

[0008] In order to solve the above technical problems, the technical solution of the present invention is as follows: In a first aspect, a method for intelligent aeration optimization control of a sewage treatment plant is provided, the method comprising: Collect water quality, water quantity and aeration volume data in real time; Analyze and process water quality, water volume, and aeration volume data to form a sewage treatment process data set, including the rate of change of water quality indicators, fluctuations in water volume, and aeration efficiency information; Based on the sewage treatment process data set, a dynamic mathematical model of the sewage treatment process is established and trained to reflect the relationship between water quality, water quantity and aeration volume; Use dynamic mathematical models to predict water quality trends over a period of time in the future, so as to obtain the predicted values ​​of future water quality indicators, the estimated changes in water volume, and the suggestions for adjusting aeration demand; According to the dynamic mathematical model and real-time water quality and water quantity data, the fuzzy control algorithm is used to automatically adjust the aeration volume and aeration time parameters to obtain the final aeration control strategy; The adjusted sewage treatment process is monitored in real time through the real-time monitoring device, and the butterfly optimization algorithm is used to intelligently compare and analyze the monitoring data with the predicted values ​​of the dynamic mathematical model and the final aeration control strategy; when an abnormal situation occurs, an alarm is immediately issued and corresponding measures are taken to form a feedback closed loop.

[0009] Furthermore, the water quality, water quantity and aeration volume data are analyzed and processed to obtain processed data, including the change rate of water quality indicators, the fluctuation of water volume and aeration efficiency information, including: At preset time intervals, sensors are used to collect raw data on water quality, water quantity, and aeration volume in real time; Based on the original water quality data, the change rate of each water quality index is calculated through the difference algorithm to reflect the change trend of water quality over time; the fluctuation of water inlet and outlet is analyzed, and the standard deviation and variance statistics are calculated to measure the stability of water volume; based on the operating parameters of the aerator, including operating power, aeration time and sewage treatment effect, the aeration efficiency index is calculated to evaluate the aeration efficiency; The water quality index change rate, water volume fluctuation and aeration efficiency information are integrated to form a sewage treatment process data set.

[0010] Furthermore, based on the sewage treatment process data set, a dynamic mathematical model of the sewage treatment process is established and trained to reflect the relationship between water quality, water quantity and aeration volume, including: Extract characteristic variables reflecting the relationship between water quality, water quantity and aeration volume from the original data, including the change rate of water quality indicators, fluctuation of water quantity and aeration efficiency; Take the time series model as a dynamic mathematical model, and determine the input variables and output variables, parameters and structure of the dynamic mathematical model; The characteristic variables are divided into a training set and a validation set, and the training set is used to train the dynamic mathematical model. By adjusting the parameters and structure of the dynamic mathematical model, the dynamic mathematical model can reflect the relationship between water quality, water quantity and aeration amount.

[0011] Furthermore, the dynamic mathematical model is used to predict the trend of water quality changes in the future to obtain the predicted values ​​of future water quality indicators, the estimated changes in water volume and the suggestions for adjusting aeration demand, including: Collect current water quality and water quantity data, and input the current data into a dynamic mathematical model to predict the water quality trend in the future, and obtain the predicted value of water quality indicators in the future; The dynamic mathematical model analyzes the time series characteristics of water volume data based on historical water volume data and current water volume change trends, estimates water volume changes in the future, and obtains the estimated results of future water volume; Based on the predicted values ​​of water quality indicators and the estimated results of water volume changes, the needs of the sewage treatment process are analyzed and suggestions for adjusting the aeration demand are obtained.

[0012] Furthermore, according to the dynamic mathematical model and real-time water quality and water quantity data, the fuzzy control algorithm is used to automatically adjust the aeration volume and aeration time parameters to achieve control and optimization of the aeration process, including: The real-time water quality and water quantity data collected in real time and the future water quality index prediction value and future water quantity estimation result output by the dynamic mathematical model are input into the fuzzy control algorithm, and the real-time water quality, water quantity data and prediction value are converted into fuzzy language variables through the membership function to form fuzzy input data; According to the preset fuzzy rules, the fuzzy control algorithm infers the fuzzy input data and obtains the fuzzy output data, i.e., the adjustment suggestions for aeration volume and aeration time; The fuzzy output data is converted into numerical values, namely the actual adjustment values ​​of aeration volume and aeration time, and the aeration equipment in the sewage treatment plant is automatically adjusted according to the actual adjustment values ​​of aeration volume and aeration time to obtain the final aeration control strategy.

[0013] Furthermore, the adjusted sewage treatment process is monitored in real time through the real-time monitoring device, and the butterfly optimization algorithm is used to intelligently compare and analyze the monitoring data with the predicted values ​​of the dynamic mathematical model and the final aeration control strategy; when abnormal conditions occur, including water quality exceeding the standard and equipment failure, an alarm is immediately issued and corresponding measures are taken to form a feedback closed loop, including: Compare the real-time monitoring data with the predicted values ​​of the dynamic mathematical model and analyze the differences, including comparing the actual water quality with the predicted water quality and the actual water volume with the predicted water volume; The butterfly optimization algorithm is used to intelligently analyze the differences between monitoring data and predicted values ​​and control strategies, and the final solution is determined by simulating the foraging behavior of butterflies; According to the final solution, the parameters of the dynamic mathematical model are automatically adjusted, and the abnormal conditions in the sewage treatment process are continuously monitored through real-time monitoring devices, including water quality exceeding the standard and equipment failure. When an abnormal situation is detected, an alarm is issued, and according to the type and severity of the abnormal situation, corresponding measures are automatically taken, including adjusting the aeration volume, shutting down faulty equipment, and starting backup equipment, so as to form a feedback closed loop.

[0014] Furthermore, the butterfly optimization algorithm is used to intelligently analyze the differences between the monitoring data and the predicted values ​​and control strategies, and the final solution is determined by simulating the foraging behavior of butterflies, including: Initialize the butterfly population, each butterfly represents a control strategy adjustment plan, and calculate the fitness score of each butterfly based on the difference between the monitoring data and the predicted value and the control strategy; Simulate the foraging behavior of butterflies, including local search and global search, and continuously update the location and fitness score of the butterfly population through iteration; When the iteration reaches the preset number of iterations, the final solution is determined from the butterfly population based on the fitness scores of the individuals.

[0015] Furthermore, the calculation formula for the fitness score of each butterfly is: ; in, represents the fitness score of each butterfly; Indicates the total number of monitoring points; Indicates the index of the monitoring point; Indicates The actual value of each monitoring point; Indicates The predicted value of each monitoring point; represents the difference weight; represents the cost required to implement the control strategy adjustment; represents the total cost; represents the cost weight; Indicates the total number of status indicators; The index representing the status indicator; Indicates The actual value of the status indicator; Indicates The baseline value of each status indicator; Represents the state deviation weight.

[0016] In the second aspect, an intelligent aeration optimization control system for a sewage treatment plant includes: Data acquisition module, used to collect water quality, water quantity and aeration volume data in real time through sensors at the sewage treatment site; The data analysis module is used to analyze and process the collected water quality, water quantity and aeration volume data to form a sewage treatment process data set; Model building module, used to build and train the dynamic mathematical model of the sewage treatment process based on the sewage treatment process data set to reflect the relationship between water quality, water quantity and aeration volume; The prediction and optimization module is used to use dynamic mathematical models to predict the trend of water quality changes in the future, obtain the predicted values ​​of future water quality indicators, the estimated changes in water volume, and the suggestions for adjusting aeration demand; The control strategy generation module is used to automatically adjust the aeration volume and aeration time parameters according to the dynamic mathematical model and real-time water quality and water quantity data, and generate the final aeration control strategy by using the fuzzy control algorithm; The real-time monitoring and feedback module is used to monitor the adjusted sewage treatment process in real time through the real-time monitoring device, and use the butterfly optimization algorithm to intelligently compare and analyze the monitoring data with the predicted values ​​of the dynamic mathematical model and the final aeration control strategy; when abnormal conditions occur, including water quality exceeding the standard and equipment failure, an alarm is issued and corresponding measures are taken to form a feedback closed loop.

[0017] In a third aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described above is implemented.

[0018] The above solution of the present invention includes at least the following beneficial effects: By collecting and analyzing water quality, water volume, and aeration volume data in real time, the real-time status of the sewage treatment process can be more accurately understood. The dynamic mathematical model is used to predict future water quality trends, making aeration control more forward-looking and scientific, effectively improving sewage treatment efficiency and water quality compliance rates. The fuzzy control algorithm is used to automatically adjust the aeration volume and aeration time parameters, and the aeration process can be accurately controlled according to actual needs to avoid over-aeration or under-aeration, thereby saving energy and reducing operating costs.

[0019] The establishment and training of dynamic mathematical models can reflect the complex relationship between water quality, water volume and aeration volume, and enhance the adaptability and stability of the control system. The application of real-time monitoring devices and butterfly optimization algorithms can timely detect and handle abnormal situations, such as water quality exceeding the standard and equipment failure, to ensure the continuity and reliability of the sewage treatment process. This method integrates multiple technologies such as data acquisition, analysis and processing, model prediction, and intelligent control to achieve intelligent management of the sewage treatment process.

[0020] By intelligently comparing and analyzing monitoring data, model prediction values, and control strategies, we can continuously optimize aeration control strategies and improve the intelligence level of sewage treatment. Optimizing aeration control strategies can reduce energy consumption and pollutant emissions, which is beneficial to environmental protection and sustainable development. Improving sewage treatment efficiency and water quality compliance rate will help meet increasingly stringent environmental regulations. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flow chart of a sewage treatment plant intelligent aeration optimization control method provided by an embodiment of the present invention.

[0022] Figure 2 It is a schematic diagram of an intelligent aeration optimization control system for a sewage treatment plant provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0024] like Figure 1 As shown, an embodiment of the present invention provides a method for intelligent aeration optimization control of a sewage treatment plant, the method comprising the following steps: Step 1, real-time collection of water quality, water quantity, and aeration volume data; Step 2: Analyze and process the water quality, water volume, and aeration volume data to form a sewage treatment process data set, including the change rate of water quality indicators, water volume fluctuations, and aeration efficiency information; Step 3, based on the sewage treatment process data set, establish and train a dynamic mathematical model in the sewage treatment process to reflect the relationship between water quality, water quantity and aeration amount; Step 4: Use a dynamic mathematical model to predict the water quality change trend in the future to obtain the predicted values ​​of future water quality indicators, the estimated changes in water volume, and the aeration demand adjustment suggestions; Step 5: According to the dynamic mathematical model and the real-time water quality and water quantity data, the fuzzy control algorithm is used to automatically adjust the aeration volume and aeration time parameters to obtain the final aeration control strategy; Step 6: Monitor the adjusted sewage treatment process in real time through the real-time monitoring device, and use the butterfly optimization algorithm to intelligently compare and analyze the monitoring data with the predicted values ​​of the dynamic mathematical model and the final aeration control strategy; when an abnormal situation occurs, an alarm is immediately issued and corresponding measures are taken to form a feedback loop.

[0025] In the embodiment of the present invention, real-time data collection through sensors at the sewage treatment site ensures that the system can accurately and timely obtain key information in the sewage treatment process. Through in-depth analysis and processing of raw data, more valuable information can be extracted, such as the changing trend of water quality indicators, the fluctuation law of water volume and the level of aeration efficiency, providing rich data support for the establishment and optimization of the model.

[0026] The establishment of a dynamic mathematical model enables the system to more accurately describe the complex relationships in the sewage treatment process, providing a powerful tool for prediction and optimization. Through training, the model can continuously learn and adapt to changes in the sewage treatment process, improving the accuracy of prediction and the adaptability of the control strategy. The realization of the prediction function enables the system to perceive changes in the sewage treatment process in advance and provide decision support for operators. Through prediction, the system can adjust the aeration control strategy in time to cope with future changes in water quality and water volume fluctuations, ensuring the stable operation of the sewage treatment process.

[0027] The application of fuzzy control algorithm enables the system to dynamically adjust the aeration volume and aeration time according to real-time data and water quality changes, and realize the optimal control of the sewage treatment process. This adaptive control method improves the control accuracy and response speed of the system, and reduces energy consumption and treatment costs. Through the real-time monitoring device, the adjusted sewage treatment process is monitored in real time, and the butterfly optimization algorithm is used to intelligently compare and analyze the monitoring data with the predicted value of the dynamic mathematical model and the final aeration control strategy; when abnormal conditions occur, including water quality exceeding the standard and equipment failure, an alarm is immediately issued and corresponding measures are taken to form a feedback closed loop.

[0028] The realization of real-time monitoring and intelligent comparison and analysis functions can timely detect and handle abnormal situations in the sewage treatment process. Through the butterfly optimization algorithm, the system can conduct in-depth analysis of monitoring data, find deviations from predicted values ​​and control strategies, and provide adjustment suggestions for operators. At the same time, the establishment of alarm and emergency response mechanisms ensures that the system can respond quickly when abnormal situations occur, ensuring the stable operation of the sewage treatment process.

[0029] In a preferred embodiment of the present invention, the above step 1, real-time collection of water quality, water quantity, and aeration volume data, may include: In an embodiment of the present invention, water quality, water quantity, and aeration volume data are collected in real time through sensors at the sewage treatment site. Specifically, according to the characteristics and requirements of the sewage treatment process, select appropriate water quality sensors (such as dissolved oxygen sensors, pH sensors, turbidity sensors, etc.), water volume sensors (such as flow meters), and aeration volume sensors (such as gas flow meters), and ensure that the selected sensors have the characteristics of high precision, good stability, and strong anti-interference ability to meet the requirements of real-time data collection. Determine the installation location of the sensor at the sewage treatment site to ensure that the sensor can accurately measure the relevant data of water quality, water quantity, and aeration volume, and install and debug the sensor according to the sensor installation instructions and the requirements of the sewage treatment process.

[0030] Build a data acquisition system, including a data collector, data transmission lines, and data processing software, to ensure that the data acquisition system can communicate with the sensor stably and reliably to achieve real-time data transmission and processing. The sensor collects data on water quality, water volume, and aeration volume in real time according to the preset sampling frequency. The collected data includes real-time values ​​of water quality indicators (such as dissolved oxygen concentration, pH value, turbidity, etc.), real-time flow of water volume, and real-time value of aeration volume. The collected data is transmitted to the data collector through data transmission lines (such as cables, optical fibers, etc.).

[0031] In a preferred embodiment of the present invention, the above step 2 analyzes and processes the water quality, water quantity, and aeration volume data to obtain processed data, including the change rate of water quality indicators, the fluctuation of water volume, and aeration efficiency information, which may include: Step 221, using sensors to collect raw data of water quality, water quantity and aeration volume in real time at preset time intervals; Step 222, based on the original water quality data, calculate the change rate of each water quality index through a differential algorithm to reflect the change trend of water quality over time; analyze the fluctuation of water inlet and outlet, calculate the standard deviation and variance statistics to measure the stability of water volume; calculate the aeration efficiency index based on the operating parameters of the aerator, including operating power, aeration time and sewage treatment effect, to evaluate the aeration efficiency; Step 223, integrating the water quality index change rate, water volume fluctuation and aeration efficiency information to form a sewage treatment process data set.

[0032] In an embodiment of the present invention, a fixed time interval is set in the data acquisition system, such as every minute, every five minutes or every ten minutes, as the frequency of sensor data collection. The sensor automatically triggers the data acquisition instruction according to the preset time interval, and obtains the original data of water quality (such as dissolved oxygen, pH value, turbidity, etc.), water volume (such as inlet flow, outlet flow) and aeration volume (such as aerator operating power, aeration time) in real time. The collected original data is transmitted to the data collector through the data transmission line and stored in the specified database or file.

[0033] Step 222, extract the original water quality data from the database, arrange them in chronological order, and use the difference algorithm to calculate the difference between two adjacent time points, i.e. the rate of change, for each water quality indicator (such as dissolved oxygen, pH value, turbidity, etc.). ;in, It's in time The rate of change when It's in time The calculated change rate is stored in a new database field, the original data of water inflow and water outflow are extracted from the database, and the standard deviation and variance of water inflow and water outflow are calculated using statistical software to measure the stability of water volume, and the calculation results are stored in the specified database field.

[0034] Extract the original data of aerator operating parameters (such as operating power, aeration time) and sewage treatment effect (such as BOD / COD removal rate) from the database. According to the definition and calculation formula of aeration efficiency (such as ), calculate the aeration efficiency index; where, is the aeration efficiency; is the sewage removal rate; is the operating power of the aerator; is the aeration time, and the calculated result is stored in the specified database field.

[0035] Step 223, extract the calculation results of the water quality index change rate, water volume fluctuation and aeration efficiency index from the database, integrate these data in chronological order to form a sewage treatment process data set containing multiple time points, and store the integrated data set in a specified database table.

[0036] Suppose a wastewater treatment plant decides to implement a data analysis system to optimize its treatment process. The system can collect and analyze data on water quality, water quantity and aeration in real time to provide key treatment efficiency indicators: The time interval in the data acquisition system is set to every 5 minutes. The sensor is automatically triggered according to this time interval to collect real-time raw data on water quality indicators (such as dissolved oxygen, pH value, turbidity), water volume (inlet flow, outlet flow) and aeration volume (aerator operating power, aeration time). The collected data is transmitted to the data collector through the data transmission line and stored in the designated database.

[0037] Extract the original water quality data from the database and arrange them in chronological order. For each water quality index (such as dissolved oxygen), use the difference algorithm to calculate the difference between two adjacent time points (such as 10:00 and 10:05), that is, the rate of change. For example, the rate of change of dissolved oxygen at 10:05 = dissolved oxygen (10:05) - dissolved oxygen (10:00), and store the calculated rate of change in a new database field. Extract the original data of water inflow and water outflow from the database. Use statistical software to calculate the standard deviation and variance of water inflow and water outflow to measure the stability of water volume. For example, calculate the standard deviation and variance of water inflow flow to understand the fluctuation of water inflow. Store the calculation results in the specified database field, and extract the operating parameters of the aerator (such as operating power of 10kW, aeration time of 2 hours) and sewage treatment effect (such as BOD removal rate of 80%) from the database. Calculate the aeration efficiency index according to the definition and calculation formula of aeration efficiency. For example, aeration efficiency = = 0.04 (or 4%, depending on the units), and stores the result in the specified database field.

[0038] Extract the calculation results of water quality index change rate, water volume fluctuation and aeration efficiency index from the database. Integrate these data in chronological order to form a sewage treatment process data set containing multiple time points. For example, create a data set for each day, including the water quality change rate, water volume fluctuation and aeration efficiency index every 5 minutes of the day, and store the integrated data set in the specified database table.

[0039] By automatically collecting, processing and analyzing data on water quality, water volume and aeration volume, manual intervention can be reduced and data processing efficiency can be improved. By calculating the rate of change of water quality indicators, water volume fluctuations and aeration efficiency indicators, the machine can accurately reflect the real-time status and historical change trends of the sewage treatment process, and provide decision support for operators. Based on the processed data set, abnormal conditions in the sewage treatment process can be discovered in a timely manner, such as water quality exceeding the standard, excessive water volume fluctuations or low aeration efficiency, and corresponding measures can be taken to adjust and optimize, thereby improving the sewage treatment effect. Through automated data collection and analysis, the frequency and cost of manual inspections can be reduced, and operation and maintenance costs can be reduced. At the same time, the optimized sewage treatment process can also reduce energy consumption and the use of chemicals, further reducing operating costs.

[0040] In a preferred embodiment of the present invention, the above step 3, based on the sewage treatment process data set, establishes and trains a dynamic mathematical model in the sewage treatment process to reflect the relationship between water quality, water quantity and aeration amount, which may include: Step 331, extracting characteristic variables reflecting the relationship between water quality, water quantity and aeration amount from the original data, including the change rate of water quality indicators, fluctuation of water quantity, and aeration efficiency; Step 332, taking the time series model as a dynamic mathematical model, and determining the input variables and output variables of the dynamic mathematical model, and the parameters and structure of the dynamic mathematical model; Step 333, dividing the characteristic variables into a training set and a validation set, and using the training set to train the dynamic mathematical model, by adjusting the parameters and structure of the dynamic mathematical model, so that the dynamic mathematical model reflects the relationship between water quality, water quantity and aeration amount.

[0041] In the embodiment of the present invention, raw data including the change rate of water quality indicators (such as dissolved oxygen, pH value, turbidity, etc.), the fluctuation of water volume (such as standard deviation, variance, etc.) and aeration efficiency are extracted from the sewage treatment process data set. The raw data are cleaned and standardized to remove abnormal values ​​and missing values ​​to ensure the accuracy and consistency of the data. According to the characteristics and requirements of the sewage treatment process, characteristic variables reflecting the relationship between water quality, water volume and aeration volume are extracted from the pre-processed data. These characteristic variables may include the change rate sequence of water quality indicators, the fluctuation statistics of water volume and the index value of aeration efficiency, etc.

[0042] Step 332, according to the dynamic characteristics and data characteristics of the sewage treatment process, a time series model is selected as a dynamic mathematical model, including an ARIMA model. The input variables and output variables of the dynamic mathematical model are determined. The input variables may include the rate of change of water quality indicators, the fluctuation of water volume, etc., and the output variable is the aeration volume. According to the number and characteristics of the input variables, the parameters and structure of the dynamic mathematical model are determined, including the order of the model, the selection of lag terms, the number of layers and nodes of the neural network, etc.

[0043] Step 333, divide the extracted characteristic variables into a training set and a validation set. The training set is used to train the dynamic mathematical model, while the validation set is used to evaluate the performance and generalization ability of the model. The dynamic mathematical model is trained using the training set. During the training process, the parameters and structure of the model are adjusted so that the model can accurately reflect the relationship between water quality, water quantity and aeration volume. During the training process, optimization algorithms such as gradient descent and back propagation can be used to update the parameters of the model to minimize the loss function. The trained dynamic mathematical model is verified using the validation set to evaluate the performance and generalization ability of the model. If the performance of the model does not meet the requirements, the performance of the model can be improved by adjusting the parameters and structure of the model and increasing the amount of training data.

[0044] By building and training a dynamic mathematical model, the machine can predict and adjust the aeration volume in real time, making the sewage treatment process more efficient and stable. The dynamic mathematical model can reduce the frequency and cost of manual intervention and reduce operation and maintenance costs. At the same time, the optimized sewage treatment process can also reduce energy consumption and the use of chemicals, further reducing operating costs. The dynamic mathematical model can accurately reflect the relationship between water quality, water volume and aeration volume, thereby optimizing the sewage treatment process and improving the treatment effect. This helps reduce pollutant emissions and protect water resources.

[0045] In a preferred embodiment of the present invention, the above step 4, using a dynamic mathematical model to predict the water quality change trend in the future period of time, so as to obtain the predicted value of the future water quality index, the estimated situation of water volume change and the aeration demand adjustment suggestion, may include: Step 441, collecting current water quality and water quantity related data, and inputting the current data into a dynamic mathematical model to predict the water quality change trend in the future period of time, and obtaining the predicted value of the water quality index in the future period of time; Step 442, the dynamic mathematical model analyzes the time series characteristics of the water volume data based on the historical water volume data and the current water volume change trend, estimates the water volume change in the future period, and obtains the estimated result of the future water volume; Step 443, based on the predicted values ​​of water quality indicators and the estimated results of water volume changes, the requirements of the sewage treatment process are analyzed to obtain aeration demand adjustment suggestions.

[0046] In an embodiment of the present invention, current water quality data, including key indicators such as dissolved oxygen, pH value, turbidity, etc., are collected from sensors in real time. The collected data is standardized or normalized to better meet the input requirements of the dynamic mathematical model. Time series analysis is performed on the data to extract trends, periodicity and other features. A suitable dynamic mathematical model, such as ARIMA, is selected for predicting water quality change trends. Based on historical water quality data, model parameters are trained to optimize model performance. The pre-processed current water quality data is input into the dynamic mathematical model, and the prediction time range is set, such as the next 24 hours, 48 ​​hours, etc. The model is run to obtain the predicted values ​​of water quality indicators in the future. The prediction results are stored in a database for subsequent analysis and use.

[0047] Step 442, collect historical water volume data and current water volume change trends from sensors. Perform time series analysis on water volume data to identify trends, periodicity, seasonality and other characteristics. Calculate statistics such as mean, standard deviation, autocorrelation coefficient, etc. based on historical water volume data. Select a suitable dynamic mathematical model, such as SARIMA, for estimating water volume changes. Train model parameters and optimize model performance based on historical water volume data and current change trends. Input the current water volume change trend into the dynamic mathematical model, set the estimated time range, such as the next week, month, etc., run the model, and obtain the water volume estimation results for a period of time in the future.

[0048] Step 443, combining the predicted value of water quality index and the estimated result of water volume change, analyze the demand of sewage treatment process, and consider the operating parameters, treatment effect, energy consumption and other factors of aerator. According to the changing trend of water quality and water volume, evaluate the demand of sewage treatment process for aeration, set the target value or threshold of aeration efficiency, and judge whether the aeration demand needs to be adjusted. According to the demand assessment result, generate aeration demand adjustment suggestion, which includes adjusting the operating power, aeration time, and operation strategy of the aerator.

[0049] Assume that a wastewater treatment plant is using a dynamic mathematical model to predict water quality trends, estimate water volume changes, and generate aeration demand adjustment recommendations: Assume that the current water quality data shows that the dissolved oxygen concentration is 6 mg / L, the pH value is 7.2, and the turbidity is 10 NTU.

[0050] The dynamic mathematical model predicts that the dissolved oxygen concentration will drop to 5 mg / L, the pH value will remain at around 7.2, and the turbidity will rise to 15 NTU in the next 24 hours based on historical water quality data. Historical water volume data shows that the inflow reaches a peak between 8 and 10 a.m. every day, and there is also a small peak between 4 and 6 p.m.

[0051] The dynamic mathematical model predicts that the water flow rate will increase by 10% in the next week based on the current water volume change trend. Combining the predicted values ​​of water quality indicators and the estimated results of water volume changes, the demand for aeration in the sewage treatment process is analyzed. Considering the decrease in dissolved oxygen concentration and the increase in turbidity, it is recommended to increase the operating power and aeration time of the aerator to improve the treatment effect.

[0052] The specific suggestions are: adjust the operating power of the aerator from 10kW to 12kW and extend the aeration time from 2 hours to 2.5 hours.

[0053] By using dynamic mathematical models to predict water quality and water volume changes, the parameters of the sewage treatment process can be adjusted in time to improve treatment efficiency. By adjusting the operating power and aeration time of the aerator according to actual needs, energy consumption and cost expenditure can be avoided. Generating aeration demand adjustment suggestions can provide support for the decision-making of sewage treatment plants, help optimize the treatment process and improve water quality. By real-time monitoring and predicting changes in water quality, water volume and aeration demand, problems can be discovered and solved in a timely manner, improving the stability and reliability of the system.

[0054] In a preferred embodiment of the present invention, the above step 5, based on the dynamic mathematical model and real-time water quality and water quantity data, adopts a fuzzy control algorithm to automatically adjust the aeration volume and aeration time parameters to achieve control and optimization of the aeration process, which may include: Step 551, input the real-time water quality and water quantity data collected in real time and the future water quality index prediction value and future water quantity estimation result output by the dynamic mathematical model into the fuzzy control algorithm, and convert the real-time water quality, water quantity data and prediction value into fuzzy language variables through the membership function to form fuzzified input data; Step 552, according to the preset fuzzy rules, the fuzzy control algorithm infers the fuzzified input data to obtain fuzzified output data, i.e., adjustment suggestions for aeration volume and aeration time; Step 553, converting the fuzzy output data into numerical values, namely, actual adjustment values ​​of aeration volume and aeration time, and automatically adjusting the aeration equipment in the sewage treatment plant according to the actual adjustment values ​​of aeration volume and aeration time to obtain the final aeration control strategy.

[0055] In an embodiment of the present invention, water quality (such as dissolved oxygen, pH value, turbidity, etc.) and water quantity (such as inlet flow, outlet flow) data are collected in real time. The predicted values ​​of future water quality indicators and the estimated results of future water quantity are obtained from the dynamic mathematical model, and these data are integrated together as the input of the fuzzy control algorithm. According to the characteristics of water quality and water quantity data, appropriate membership functions are defined. For example, for dissolved oxygen concentration, three fuzzy linguistic variables of "low", "medium" and "high" can be defined, and corresponding membership functions can be assigned to them. Similar membership functions can also be defined for predicted values ​​and estimated results to reflect their fuzziness.

[0056] The real-time water quality and quantity data as well as the predicted values ​​and estimated results are converted into fuzzy linguistic variables using the defined membership functions.

[0057] For example, if the real-time dissolved oxygen concentration is 5 mg / L and its membership function is defined as "low" as 0-6 mg / L, "medium" as 6-8 mg / L, and "high" as 8-12 mg / L, then the concentration can be fuzzified to "low" or "medium" (depending on the shape and definition of the membership function).

[0058] Step 552, based on the experience and knowledge of the sewage treatment process, define a set of fuzzy rules. For example, "if the dissolved oxygen concentration is low and the influent flow is high, increase the aeration volume". Fuzzy rules are expressed in the form of "if...then...", where the "if" part is the condition and the "then" part is the conclusion. Fuzzy input data is inferred using fuzzy rules, and for each fuzzy rule, its satisfaction (i.e., the degree of match between the condition part and the input data) is calculated. Based on the satisfaction and the conclusion of the rule, the fuzzy output data (i.e., the adjustment suggestions for aeration volume and aeration time) are obtained.

[0059] Step 553, using a defuzzification method (such as a weighted average method) to convert the fuzzified output data into a numerical value. For example, if the fuzzified output data is "increase aeration volume", a specific increase (such as 10% or 20%) may be obtained after defuzzification. According to the actual adjustment values ​​of aeration volume and aeration time obtained after defuzzification, the aeration equipment in the sewage treatment plant is automatically adjusted. For example, the operating power of the aerator is increased or decreased, the aeration time is extended or shortened, etc. The adjusted aeration volume and aeration time are used as part of the aeration control strategy. Continuously monitor water quality and water quantity data, as well as the prediction results of the dynamic mathematical model, so as to update the aeration control strategy in a timely manner.

[0060] Assume that a wastewater treatment plant is using fuzzy control algorithm to adjust the aeration volume: The real-time dissolved oxygen concentration is 5mg / L, and the inlet flow is 1000m³ / h. The dynamic mathematical model predicts that the dissolved oxygen concentration will drop to 4mg / L and the inlet flow will increase to 1200m³ / h in the future. Use the membership function to fuzzify these data into "low dissolved oxygen concentration" and "high inlet flow". Define the fuzzy rule: "If the dissolved oxygen concentration is low and the inlet flow is high, increase the aeration volume by 20%". Use this rule to reason about the fuzzified input data and get a conclusion with high satisfaction. After defuzzification, the suggestion of increasing the aeration volume by 20% is obtained. According to this suggestion, the operating power of the aerator is automatically adjusted to increase it by 20%, forming a new aeration control strategy.

[0061] Automatically adjusting the aeration volume and aeration time through fuzzy control algorithms can more effectively remove pollutants from sewage and improve treatment efficiency. Adjusting the aeration volume based on real-time water quality and quantity data and prediction results can avoid unnecessary energy consumption and cost expenditures. Fuzzy control algorithms can handle uncertainty and ambiguity, making the system more adaptable to complex and changing sewage treatment environments. Even when water quality and quantity data fluctuate greatly, the stability and robustness of the system can be maintained. Automatically adjusting aeration equipment, reducing manual intervention, and improving the automation level of sewage treatment will help achieve intelligent and refined management of the sewage treatment process.

[0062] In a preferred embodiment of the present invention, in step 6, the adjusted sewage treatment process is monitored in real time by a real-time monitoring device, and the monitoring data is intelligently compared and analyzed with the predicted value of the dynamic mathematical model and the final aeration control strategy by using a butterfly optimization algorithm; when an abnormal situation occurs, including water quality exceeding the standard and equipment failure, an alarm is immediately issued and corresponding measures are taken to form a feedback closed loop, which may include: Step 661, comparing the real-time monitoring data with the predicted value of the dynamic mathematical model, and analyzing the differences, including comparing the actual water quality with the predicted water quality, and the actual water volume with the predicted water volume; Step 662, using the butterfly optimization algorithm to intelligently analyze the differences between the monitoring data and the predicted values ​​and control strategies, and determining the final solution by simulating the foraging behavior of butterflies; Step 663, according to the final solution, automatically adjust the parameters of the dynamic mathematical model, and continuously monitor the abnormal conditions in the sewage treatment process through the real-time monitoring device, including water quality exceeding the standard and equipment failure; when an abnormal condition is detected, an alarm is issued, and according to the type and severity of the abnormal condition, corresponding measures are automatically taken, including adjusting the aeration volume, shutting down the faulty equipment, and starting the backup equipment, so as to form a feedback closed loop.

[0063] In the embodiment of the present invention, the actual water quality (such as dissolved oxygen, pH value, turbidity, etc.) and water quantity data in the sewage treatment process are obtained through a real-time monitoring device, and the predicted water quality and water quantity data are obtained from the dynamic mathematical model to ensure that the real-time monitoring data and the predicted value are aligned in the time dimension for accurate comparison. The difference between the actual water quality and the predicted water quality is calculated, such as the absolute difference, the relative difference, etc., and the difference between the actual water quantity and the predicted water quantity is calculated, and the reasons for the difference are analyzed, such as model error, external interference, etc.

[0064] Step 662, set the parameters of the butterfly optimization algorithm, such as population size, number of iterations, sensing mode, etc., initialize the butterfly population, each butterfly represents a solution, and define the fitness function according to the difference between the monitoring data and the predicted value and control strategy, and calculate the fitness value of each butterfly to reflect the quality of its solution.

[0065] The foraging behavior of butterflies is simulated, including global search and local search. In the global search phase, the butterfly moves to a more optimal direction based on the concentration of the fragrance (i.e., the fitness value). In the local search phase, the butterfly conducts a fine search near its current position. The position of the butterfly is iteratively updated until the preset number of iterations is reached, and the final solution is determined based on the fitness value. The final solution includes the results of intelligent analysis of the differences between the monitoring data and the predicted values ​​and the control strategy.

[0066] Step 663, according to the final solution, automatically adjust the parameters of the dynamic mathematical model to improve the prediction accuracy of the model. Real-time monitoring devices are used to continuously monitor abnormal conditions in the sewage treatment process, such as water quality exceeding the standard, equipment failure, etc., and set abnormal thresholds. When the monitoring data exceeds the threshold, it is determined to be an abnormal situation. When an abnormal situation is detected, an alarm is immediately issued to notify relevant personnel or systems. According to the type and severity of the abnormal situation, corresponding measures are automatically taken. For example, the aeration volume is adjusted to improve water quality; faulty equipment is shut down to prevent the accident from expanding; and backup equipment is started to ensure the continuity of the sewage treatment process.

[0067] Suppose a sewage treatment plant is using the butterfly optimization algorithm to intelligently analyze monitoring data and predicted values ​​and form a feedback loop: The real-time monitoring device shows that the current dissolved oxygen concentration is 4mg / L, while the dynamic mathematical model predicts a value of 5mg / L. The actual water inflow is 900m³ / h and the predicted value is 950m³ / h. The difference is calculated and analyzed, which may be caused by model error or external interference. Initialize the butterfly optimization algorithm, set the population size to 50, and the number of iterations to 100. Define the fitness function, consider the difference between the monitoring data and the predicted value and the control strategy, perform iterative optimization, simulate the foraging behavior of butterflies, and find the final solution. The final solution shows that some parameters of the dynamic mathematical model need to be adjusted to improve the prediction accuracy. According to the final solution, the parameters of the dynamic mathematical model are automatically adjusted. The real-time monitoring device detects that the dissolved oxygen concentration has dropped to 3mg / L, which is lower than the set threshold of 4mg / L, and it is judged that the water quality exceeds the standard. Immediately issue an alarm, and automatically increase the aeration volume to improve the water quality, and record abnormal conditions and treatment measures.

[0068] Through real-time monitoring and intelligent analysis, abnormal situations can be discovered and handled in a timely manner to improve the stability of the sewage treatment process. According to the difference between the monitoring data and the predicted value, the parameters of the dynamic mathematical model are automatically adjusted to improve the prediction accuracy of the model. Intelligent analysis results and abnormal handling measures provide support for the decision-making of the sewage treatment plant, which helps to optimize the treatment process and improve water quality. Automatically adjust the aeration volume, shut down faulty equipment, start backup equipment and other measures to reduce manual intervention, improve the automation level of sewage treatment, and help realize the intelligent and refined management of the sewage treatment process, reduce labor costs and improve work efficiency.

[0069] In another preferred embodiment of the present invention, the above step 662, using the butterfly optimization algorithm to perform intelligent analysis on the differences between the monitoring data and the predicted value and the control strategy, and determining the final solution by simulating the foraging behavior of butterflies, may include: Step 6621, initialize the butterfly population, each butterfly represents a control strategy adjustment scheme, and calculate the fitness score of each butterfly according to the difference between the monitoring data and the predicted value and the control strategy; the calculation formula of the fitness score of each butterfly is: ; in, represents the fitness score of each butterfly; Indicates the total number of monitoring points; Indicates the index of the monitoring point; Indicates The actual value of each monitoring point; Indicates The predicted value of each monitoring point; represents the difference weight; represents the cost required to implement the control strategy adjustment; represents the total cost; represents the cost weight; Indicates the total number of status indicators; The index representing the status indicator; Indicates The actual value of the status indicator; Indicates The baseline value of each status indicator; represents the state deviation weight; Step 6622, simulating the foraging behavior of butterflies, including local search and global search, and continuously updating the location and fitness score of the butterfly population through iteration; Step 6623, when the iteration reaches the preset number of iterations, the final solution is determined from the butterfly population based on the fitness scores of the individuals.

[0070] In the embodiment of the present invention, a population of multiple butterflies is randomly generated, each butterfly represents a control strategy adjustment scheme, and the position of each butterfly (i.e., control strategy parameter) is randomly initialized within the allowed range. For each butterfly, the fitness score is calculated using the formula based on the difference between the monitoring data and the predicted value and the control strategy. .

[0071] Collect actual values ​​from each monitoring point and predicted values , and organize them into a data list to determine the cost required to implement control strategy adjustments and total cost . Collect the actual values ​​of the status indicators and benchmark value (For example, the benchmark value can be a preset standard value or a historical average value) and organized into a data list.

[0072] Setting Difference Weights = 0.5 (indicates that the difference has a 50% impact on the fitness score), cost weight = 0.3 (indicating that the cost has a 30% impact on the fitness score), and the state deviation weight =0.2 (indicates that the influence of state index deviation on fitness score is 20%). Initialize the butterfly population, each butterfly represents a control strategy adjustment scheme, and its position (i.e., control strategy parameter) is randomly initialized within the allowed range. For each butterfly (i.e., each control strategy adjustment scheme), perform the following operations: Traverse all monitoring points, calculate the absolute difference between the actual value and the predicted value of each monitoring point, and sum them up to get the total difference. Divide the total difference by the sum of the actual values ​​of all monitoring points to get the difference ratio. Multiply the difference ratio by the difference weight = 0.5, and the impact of the difference on the fitness score is obtained. The cost required to implement the control strategy adjustment Divide by total cost , get the cost ratio. Multiply the cost ratio by the cost weight = 0.3, and we get the effect of cost on the fitness score.

[0073] Traverse all status indicators, calculate the absolute difference between the actual value of each status indicator and the benchmark value (for example, the benchmark value is set to 100 or determined based on historical data), and sum them up to get the total deviation. Divide the total deviation by the sum of the actual values ​​of all status indicators to get the deviation ratio. Multiply the deviation ratio by the status deviation weight =0.2, and the effect of state index deviation on fitness score is obtained. Subtract the above three effects from 1 to obtain the fitness score of each butterfly. In this way, the fitness score of each butterfly takes into account the difference between the monitoring data and the predicted value, the cost of implementing the control strategy adjustment, and the degree of deviation of the status indicator.

[0074] In step 6622, each butterfly performs a fine search near its current position to try to find a better solution. The scope and step size of the local search are dynamically adjusted according to the current position, historical position and fitness score.

[0075] The butterflies move towards a better direction based on the concentration of the fragrance (i.e., the fitness score). Areas with higher fragrance concentrations indicate better solution quality, and the butterflies will move towards these areas, continuously iterating and updating the position and fitness score of the butterfly population until the preset number of iterations is reached.

[0076] Step 6623, when the iteration reaches the preset number of iterations, the final butterfly is selected from the butterfly population according to the individual fitness score as the final solution. The final solution includes the intelligent analysis results of the differences between the monitoring data and the predicted values ​​and the control strategy.

[0077] Assume that a sewage treatment plant is using the butterfly optimization algorithm to intelligently analyze the differences between monitoring data and predicted values ​​and control strategies: A population of 50 butterflies is randomly generated, and each butterfly represents an aeration adjustment scheme. The aeration adjustment range is randomly initialized between [0, 100%]. For each butterfly, the fitness score is calculated using the above formula based on the difference between the monitoring data and the predicted value and control strategy. Assume that the difference weight =0.5, cost weight =0.3, state deviation weight =0.2. Perform local search and global search, and continuously iterate and update the position and fitness score of the butterfly population. Assume that the number of iterations is 100. When the iterations reach 100, select the butterfly with the highest fitness score from the butterfly population as the final solution. The final solution shows that when the aeration volume is adjusted to 80%, the difference between the monitoring data and the predicted value and the control strategy is the smallest.

[0078] By intelligently analyzing the differences between monitoring data and predicted values ​​and control strategies, the final control strategy adjustment plan is found to improve the accuracy of the control strategy. The cost required to implement the control strategy adjustment is considered when calculating the fitness score to reduce the implementation cost. The intelligent analysis results and final solution provide support for the decision-making of the sewage treatment plant, which helps to optimize the treatment process and improve water quality. Automatically perform difference analysis, foraging behavior simulation and final solution determination to reduce manual intervention and improve the automation level of sewage treatment.

[0079] like Figure 2 As shown, an embodiment of the present invention further provides an intelligent aeration optimization control system for a sewage treatment plant, comprising: Data acquisition module, used to collect water quality, water quantity and aeration volume data in real time through sensors at the sewage treatment site; The data analysis module is used to analyze and process the collected water quality, water quantity and aeration volume data to form a sewage treatment process data set; Model building module, used to build and train the dynamic mathematical model of the sewage treatment process based on the sewage treatment process data set to reflect the relationship between water quality, water quantity and aeration volume; The prediction and optimization module is used to use dynamic mathematical models to predict the trend of water quality changes in the future, obtain the predicted values ​​of future water quality indicators, the estimated changes in water volume, and the suggestions for adjusting aeration demand; The control strategy generation module is used to automatically adjust the aeration volume and aeration time parameters according to the dynamic mathematical model and real-time water quality and water quantity data, and generate the final aeration control strategy by using the fuzzy control algorithm; The real-time monitoring and feedback module is used to monitor the adjusted sewage treatment process in real time through the real-time monitoring device, and use the butterfly optimization algorithm to intelligently compare and analyze the monitoring data with the predicted values ​​of the dynamic mathematical model and the final aeration control strategy; when abnormal conditions occur, including water quality exceeding the standard and equipment failure, an alarm is issued and corresponding measures are taken to form a feedback closed loop.

[0080] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0081] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0082] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0083] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A sewage treatment plant intelligent aeration optimization control method, characterized in that: The method comprises: Collect water quality, water quantity and aeration volume data in real time; Analyze and process water quality, water volume, and aeration volume data to form a sewage treatment process data set, including the rate of change of water quality indicators, fluctuations in water volume, and aeration efficiency information; Based on the sewage treatment process data set, a dynamic mathematical model of the sewage treatment process is established and trained to reflect the relationship between water quality, water quantity and aeration volume; Use dynamic mathematical models to predict water quality trends over a period of time in the future, so as to obtain the predicted values ​​of future water quality indicators, the estimated changes in water volume, and the suggestions for adjusting aeration demand; According to the dynamic mathematical model and real-time water quality and water quantity data, the fuzzy control algorithm is used to automatically adjust the aeration volume and aeration time parameters to obtain the final aeration control strategy; The adjusted sewage treatment process is monitored in real time through the real-time monitoring device, and the butterfly optimization algorithm is used to intelligently compare and analyze the monitoring data with the predicted values ​​of the dynamic mathematical model and the final aeration control strategy; when an abnormal situation occurs, an alarm is immediately issued and corresponding measures are taken to form a feedback closed loop.

2. The intelligent aeration optimization control method for a sewage treatment plant according to claim 1 is characterized in that: Analyze and process water quality, water quantity, and aeration volume data to obtain processed data, including the rate of change of water quality indicators, fluctuations in water volume, and aeration efficiency information, including: At preset time intervals, sensors are used to collect raw data on water quality, water quantity, and aeration volume in real time; Based on the original water quality data, the change rate of each water quality index is calculated through the difference algorithm to reflect the change trend of water quality over time; the fluctuation of water inlet and outlet is analyzed, and the standard deviation and variance statistics are calculated to measure the stability of water volume; based on the operating parameters of the aerator, including operating power, aeration time and sewage treatment effect, the aeration efficiency index is calculated to evaluate the aeration efficiency; The water quality index change rate, water volume fluctuation and aeration efficiency information are integrated to form a sewage treatment process data set.

3. The intelligent aeration optimization control method for a sewage treatment plant according to claim 2 is characterized in that: Based on the sewage treatment process data set, a dynamic mathematical model of the sewage treatment process is established and trained to reflect the relationship between water quality, water quantity and aeration volume, including: Extract characteristic variables reflecting the relationship between water quality, water quantity and aeration volume from the original data, including the change rate of water quality indicators, fluctuation of water quantity and aeration efficiency; Take the time series model as a dynamic mathematical model, and determine the input variables and output variables, parameters and structure of the dynamic mathematical model; The characteristic variables are divided into a training set and a validation set, and the training set is used to train the dynamic mathematical model. By adjusting the parameters and structure of the dynamic mathematical model, the dynamic mathematical model can reflect the relationship between water quality, water quantity and aeration amount.

4. The intelligent aeration optimization control method for a sewage treatment plant according to claim 3 is characterized in that: Use dynamic mathematical models to predict water quality trends over a period of time in the future to obtain the predicted values ​​of future water quality indicators, the estimated changes in water volume, and suggestions for adjusting aeration demand, including: Collect current water quality and water quantity data, and input the current data into a dynamic mathematical model to predict the water quality trend in the future, and obtain the predicted value of water quality indicators in the future; The dynamic mathematical model analyzes the time series characteristics of water volume data based on historical water volume data and current water volume change trends, estimates water volume changes in the future, and obtains the estimated results of future water volume; Based on the predicted values ​​of water quality indicators and the estimated results of water volume changes, the needs of the sewage treatment process are analyzed and suggestions for adjusting the aeration demand are obtained.

5. The intelligent aeration optimization control method for a sewage treatment plant according to claim 4 is characterized in that: According to the dynamic mathematical model and real-time water quality and water quantity data, the fuzzy control algorithm is used to automatically adjust the aeration volume and aeration time parameters to achieve control and optimization of the aeration process, including: The real-time water quality and water quantity data collected in real time and the future water quality index prediction value and future water quantity estimation result output by the dynamic mathematical model are input into the fuzzy control algorithm, and the real-time water quality, water quantity data and prediction value are converted into fuzzy language variables through the membership function to form fuzzy input data; According to the preset fuzzy rules, the fuzzy control algorithm infers the fuzzy input data and obtains the fuzzy output data, i.e., the adjustment suggestions for aeration volume and aeration time; The fuzzy output data is converted into numerical values, namely the actual adjustment values ​​of aeration volume and aeration time, and the aeration equipment in the sewage treatment plant is automatically adjusted according to the actual adjustment values ​​of aeration volume and aeration time to obtain the final aeration control strategy.

6. The intelligent aeration optimization control method for a sewage treatment plant according to claim 5 is characterized in that: The adjusted sewage treatment process is monitored in real time through the real-time monitoring device, and the butterfly optimization algorithm is used to intelligently compare and analyze the monitoring data with the predicted values ​​of the dynamic mathematical model and the final aeration control strategy; When an abnormal situation occurs, including water quality exceeding the standard or equipment failure, an alarm is immediately issued and corresponding measures are taken to form a feedback loop, including: Compare the real-time monitoring data with the predicted values ​​of the dynamic mathematical model and analyze the differences, including comparing the actual water quality with the predicted water quality and the actual water volume with the predicted water volume; The butterfly optimization algorithm is used to intelligently analyze the differences between monitoring data and predicted values ​​and control strategies, and the final solution is determined by simulating the foraging behavior of butterflies; According to the final solution, the parameters of the dynamic mathematical model are automatically adjusted, and the abnormal conditions in the sewage treatment process are continuously monitored through real-time monitoring devices, including water quality exceeding the standard and equipment failure. When an abnormal situation is detected, an alarm is issued, and according to the type and severity of the abnormal situation, corresponding measures are automatically taken, including adjusting the aeration volume, shutting down faulty equipment, and starting backup equipment, so as to form a feedback closed loop.

7. The intelligent aeration optimization control method for a sewage treatment plant according to claim 6 is characterized in that: The butterfly optimization algorithm is used to intelligently analyze the differences between monitoring data and predicted values ​​and control strategies, and the final solution is determined by simulating the foraging behavior of butterflies, including: Initialize the butterfly population, each butterfly represents a control strategy adjustment plan, and calculate the fitness score of each butterfly based on the difference between the monitoring data and the predicted value and the control strategy; Simulate the foraging behavior of butterflies, including local search and global search, and continuously update the location and fitness score of the butterfly population through iteration; When the iteration reaches the preset number of iterations, the final solution is determined from the butterfly population based on the fitness scores of the individuals.

8. The intelligent aeration optimization control method for a sewage treatment plant according to claim 7 is characterized in that: The fitness score of each butterfly is calculated as: ； in, represents the fitness score of each butterfly; Indicates the total number of monitoring points; Indicates the index of the monitoring point; Indicates The actual value of each monitoring point; Indicates The predicted value of each monitoring point; represents the difference weight; represents the cost required to implement the control strategy adjustment; represents the total cost; represents the cost weight; Indicates the total number of status indicators; The index representing the status indicator; Indicates The actual value of the status indicator; Indicates The baseline value of each status indicator; Represents the state deviation weight.

9. An intelligent aeration optimization control system for a sewage treatment plant, the system implementing the method according to any one of claims 1 to 8, characterized in that: include: Data acquisition module, used to collect water quality, water quantity and aeration volume data in real time through sensors at the sewage treatment site; The data analysis module is used to analyze and process the collected water quality, water quantity and aeration volume data to form a sewage treatment process data set; Model building module, used to build and train the dynamic mathematical model of the sewage treatment process based on the sewage treatment process data set to reflect the relationship between water quality, water quantity and aeration volume; The prediction and optimization module is used to use dynamic mathematical models to predict the trend of water quality changes in the future, obtain the predicted values ​​of future water quality indicators, the estimated changes in water volume, and the suggestions for adjusting aeration demand; The control strategy generation module is used to automatically adjust the aeration volume and aeration time parameters according to the dynamic mathematical model and real-time water quality and water quantity data, and generate the final aeration control strategy by using the fuzzy control algorithm; The real-time monitoring and feedback module is used to monitor the adjusted sewage treatment process in real time through the real-time monitoring device, and use the butterfly optimization algorithm to intelligently compare and analyze the monitoring data with the predicted values ​​of the dynamic mathematical model and the final aeration control strategy; when abnormal conditions occur, including water quality exceeding the standard and equipment failure, an alarm is issued and corresponding measures are taken to form a feedback closed loop.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which implements the method according to any one of claims 1 to 8 when executed by a processor.

Images