Leachate treatment method and device, storage medium and computer device

Abstract

The application discloses a leachate treatment method and device, a storage medium and a computer device. The method comprises the following steps: collecting input working condition data of target treatment leachate entering each treatment link in sequence according to the processing sequence of each treatment link in the leachate treatment process; predicting control parameter data of a treatment device corresponding to the input working condition data of the treatment link based on a treatment device control parameter prediction model corresponding to the treatment link; based on the control parameter data, taking the water quality of treated leachate discharged after secondary biochemical treatment as a constraint condition, taking the minimum ton treatment energy consumption and the highest water efficiency in the leachate treatment process as targets, and optimizing to obtain target control parameter data of the treatment device of each treatment link, and processing the target treatment leachate. Based on the working condition perception-intelligent control-autonomous optimization operation big data, a machine learning method is adopted to intelligently control the treatment system, and cost reduction and benefit increase are finally realized.

Description

Technical Field

[0001] This application relates to the field of wastewater treatment technology for high concentrations of organic matter and high ammonia nitrogen, and in particular to a leachate treatment method and apparatus, storage medium, and computer equipment. Background Technology

[0002] Leachate from municipal solid waste is a high-concentration organic wastewater with complex pollutant composition, containing various toxic and harmful substances, including dissolved organic matter, inorganic salts, and heavy metals. Its quality and quantity vary significantly. Leachate treatment processes, based on environmental discharge requirements, generally employ a "biological + physical" treatment approach, namely "pretreatment + anaerobic + aerobic + MBR (Membrane Bioreactor) + nanofiltration + reverse osmosis," which can meet the requirements for compliant leachate discharge.

[0003] Leachate treatment employs both biochemical and physical methods. It is a multivariate, highly correlated, unsteady, nonlinear system incorporating uncertainties related to microbial reactions, water quality, quantity, and the environment, and exhibits significant time delays due to inertia. While advanced treatment systems (membrane systems) offer high automation, stable performance, and controllable energy consumption, biochemical treatment processes are difficult to model mathematically, lack rigorous mathematical methods for quantitative description, have low automation levels, are challenging to control, and suffer from poor stability in treatment effectiveness.

[0004] Currently, in domestic leachate treatment systems, the operational data between and within subsystems exhibit strong correlations and non-linear effects. Leachate contains high concentrations of pollutants and has a complex composition. Water quality monitoring instruments are expensive and require extensive maintenance, necessitating substantial manual testing of water quality indicators. Most operations are conducted manually, and the treatment effectiveness largely depends on the experience and skill level of the operators. High energy consumption, high costs, unstable treatment results, and high labor intensity are common pain points in the leachate treatment system industry. Summary of the Invention

[0005] In view of this, this application provides a leachate treatment method and apparatus, storage medium, and computer equipment, which are based on big data of working condition perception, intelligent control, and autonomous optimization operation, and adopt machine learning methods to intelligently control the treatment system, ultimately achieving cost reduction and efficiency improvement.

[0006] According to one aspect of this application, a leachate treatment method is provided, the method comprising:

[0007] To determine the treatment sequence of each treatment stage in the leachate treatment process, input operating condition data are collected sequentially when the target leachate enters each treatment stage. The leachate treatment process includes the equalization tank treatment stage, the anaerobic system treatment stage, the primary biological treatment stage, and the secondary biological treatment stage, which are carried out in the treatment sequence.

[0008] For any stage in the leachate treatment process, based on the control parameter prediction model of the treatment equipment corresponding to the treatment stage, the control parameter data for the treatment equipment corresponding to the input operating condition data of the treatment stage is predicted.

[0009] Based on the predicted control parameter data for each treatment stage, and with the constraint that the treated leachate discharged after secondary biological treatment meets the water quality standards, and with the objectives of minimizing energy consumption per ton of leachate treatment and maximizing effluent efficiency, the target control parameter data for each treatment stage for each treatment stage is optimized. Based on the optimized target control parameter data, the treatment equipment is controlled to treat the target leachate.

[0010] According to another aspect of this application, a leachate treatment apparatus is provided, the apparatus comprising:

[0011] The operating condition data acquisition module is used to collect the input operating condition data of the target leachate as it enters each treatment stage according to the treatment sequence of each treatment stage in the leachate treatment process. The leachate treatment process includes the equalization tank treatment stage, the anaerobic system treatment stage, the primary biological treatment stage, and the secondary biological treatment stage, which are carried out in the treatment sequence.

[0012] The control parameter prediction module is used to predict the control parameter data for the treatment equipment corresponding to the input operating condition data of any treatment stage in the leachate treatment process, based on the control parameter prediction model of the treatment equipment corresponding to the treatment stage.

[0013] The leachate optimization treatment module is used to optimize the target control parameter data for each treatment equipment based on the predicted control parameter data for each treatment stage, with the constraint that the water quality of the treated leachate discharged after secondary biological treatment meets the standards, and with the objectives of minimizing the energy consumption per ton of treatment and maximizing the effluent efficiency in the leachate treatment process. Based on the optimized target control parameter data, the module controls the treatment equipment to treat the target leachate.

[0014] According to another aspect of this application, a storage medium is provided that stores a computer program thereon, which, when executed by a processor, implements the above-described leachate treatment method.

[0015] According to another aspect of this application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the program to implement the above-described leachate treatment method.

[0016] By employing the above technical solution, this application provides a leachate treatment method and apparatus, storage medium, and computer equipment. The method sequentially collects input operating condition data as the target leachate enters each treatment stage, based on the treatment sequence of each stage. It then predicts the control parameter data corresponding to the treatment equipment based on the control parameter prediction model for each treatment stage's input operating condition data. Based on this control parameter data, and with the constraint that the treated leachate discharged after secondary biological treatment meets standards, and with the objectives of minimizing energy consumption per ton of treatment and maximizing effluent efficiency, the method optimizes the target control parameter data for each treatment stage's treatment equipment, and then treats the target leachate. Based on operating condition perception, intelligent control, and autonomous optimization operation big data, machine learning methods are used to intelligently control the treatment system, ultimately achieving cost reduction and efficiency improvement.

[0017] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 A schematic flowchart of a leachate treatment method provided in an embodiment of this application is shown;

[0020] Figure 2 A schematic flowchart of another leachate treatment method provided in an embodiment of this application is shown;

[0021] Figure 3 A schematic flowchart of another leachate treatment method provided in an embodiment of this application is shown;

[0022] Figure 4 A schematic flowchart of another leachate treatment method provided in an embodiment of this application is shown;

[0023] Figure 5 A schematic flowchart of another leachate treatment method provided in an embodiment of this application is shown;

[0024] Figure 6 This paper shows a schematic diagram of the structure of a leachate treatment device provided in an embodiment of this application;

[0025] Figure 7 A schematic diagram of another leachate treatment device provided in an embodiment of this application is shown. Detailed Implementation

[0026] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0027] This embodiment provides a leachate treatment method, such as... Figure 1 As shown, the method includes:

[0028] Step 101: Based on the treatment sequence of each treatment stage in the leachate treatment process, the input operating condition data of the target leachate entering each treatment stage are collected sequentially. The leachate treatment process includes the equalization tank treatment stage, the anaerobic system treatment stage, the primary biological treatment stage, and the secondary biological treatment stage, which are carried out in the treatment sequence.

[0029] In the above embodiments of this application, data-driven, multi-dimensional intelligent control is used to treat leachate, achieving cost reduction and efficiency improvement while intelligently controlling the treatment system. Specifically, the leachate treatment process includes, in sequence, an equalization tank treatment stage, an anaerobic system treatment stage, a primary biological treatment stage, and a secondary biological treatment stage. During actual control, input operating condition data of the target leachate entering each treatment stage is collected sequentially according to the treatment order, preparing for subsequent intelligent control treatment of the leachate.

[0030] Step 102: For any treatment stage in the leachate treatment process, based on the control parameter prediction model of the treatment equipment corresponding to the treatment stage, predict the control parameter data of the treatment equipment corresponding to the input operating condition data of the treatment stage.

[0031] Next, for any treatment stage in the leachate treatment process, based on the control parameter prediction model of the corresponding treatment equipment, the control parameter data for the treatment equipment corresponding to the input operating data of the treatment stage are predicted. Specifically, a data model can be constructed that includes water quantity, water quality, online monitoring data, and environmental factors. The data model specifically includes an intelligent control master model and a water quality prediction sub-model. The aforementioned intelligent control master model and water quality prediction sub-model are the treatment equipment control parameter prediction models. The intelligent control master model includes a control model for the equalization tank, an anaerobic system, a primary biological system, and a secondary biological MBR (Membrane Bio-Reactor) system. The water quality prediction sub-model includes a prediction model for the outlet water quality of the secondary biological system, the primary biological system, the anaerobic system, and the equalization tank.

[0032] When using the control parameter prediction model of the treatment equipment for prediction, the output water quality predicted by the water quality prediction sub-model can be used as the input operating condition data of the intelligent control main model. Finally, the load control, aerobic aeration control, carbon source addition control and drainage index control of the overall treatment system are realized through the prediction models of various treatment links.

[0033] Optionally, in step 102, for any treatment stage in the leachate treatment process, based on the control parameter prediction model of the treatment equipment corresponding to the treatment stage, the control parameter data for the treatment equipment corresponding to the input operating condition data of the treatment stage is predicted. For different treatment stages, the control parameter data is predicted by referring to... Figure 3 As shown, it specifically includes:

[0034] Step 1021: When the treatment stage is the equalization tank treatment stage, the input operating condition data includes the ambient temperature of the equalization tank, the biochemical index value and water volume of the target leachate entering the equalization tank treatment stage, and the control parameter data includes the anaerobic pump outlet water volume.

[0035] Step 1022: When the treatment stage is the anaerobic system treatment stage, the input operating condition data includes the anaerobic influent flow rate to the anoxic stage, the anaerobic tank pressure, the outdoor temperature of the anaerobic system treatment stage, the anaerobic tank temperature, the anaerobic influent flow rate to the secondary denitrification stage, the biochemical index values ​​of the target treated leachate entering the anaerobic system treatment stage, and the biochemical index values ​​of the target treated leachate discharged after being treated by the anaerobic system treatment stage. The control parameter data includes the flow rate from the anaerobic circulation pump outlet to the anaerobic tank and the anaerobic influent pump outlet flow rate.

[0036] Step 1023: When the treatment stage is the primary biological treatment stage, the input operating condition data includes the biochemical index values ​​of the target leachate discharged after treatment by the anaerobic system treatment stage, the biochemical index values ​​of the target leachate discharged after treatment by the primary biological treatment stage, the oxidation-reduction potential of the primary denitrification tank, the outdoor temperature of the primary biological treatment stage, the temperature of the primary nitrification tank, the dissolved oxygen content of the primary nitrification tank, the biochemical index values ​​of the target leachate entering the equalization tank treatment stage, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index values ​​of the ultrafiltration outlet. The control parameter data includes the flow rate of the anaerobic influent from the superposition to the anoxic stage and the flow rate of the Roots blower outlet.

[0037] Step 1024: When the treatment stage is a secondary biological treatment stage, the input operating condition data includes the biochemical index values ​​of the target treated leachate discharged after treatment by the primary biological treatment stage, the biochemical index values ​​of the target treated leachate discharged after treatment by the secondary biological treatment stage, the outdoor temperature of the secondary biological treatment stage, the dissolved oxygen content of the secondary nitrification tank, the biochemical index values ​​of the target treated leachate in the equalization tank treatment stage, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index values ​​at the ultrafiltration outlet. The control parameter data includes the flow rate of anaerobic influent to the secondary denitrification stage and the flow rate of the secondary nitrification Roots blower outlet. The biochemical index values ​​include at least one of biochemical oxygen demand, chemical oxygen demand, dissolved oxygen, and total organic carbon.

[0038] Specifically, for each processing stage, the input data (input operating condition data) and output data (control parameter data) of the control parameter prediction model for the processing equipment are as follows:

[0039] For the equalization tank treatment stage, the input operating data includes: various influent biochemical indicators (the biochemical values ​​of the target leachate entering the equalization tank treatment stage), such as COD (Chemical Oxygen Demand), ammonia nitrogen, water volume, and ambient temperature; the output data is the anaerobic pump effluent flow rate. Influent biochemical indicators mainly refer to water quality parameters related to biochemical processes. These parameters are typically used to assess the content of organic pollutants in water bodies and the self-purification capacity of the water body. Common influent biochemical indicators include: Biochemical Oxygen Demand (BOD): This refers to the amount of dissolved oxygen consumed by microorganisms to decompose certain oxidizable substances (especially organic matter) in a given volume of water under specified conditions. It is commonly expressed as five-day biochemical oxygen demand (BOD5), which is the amount of dissolved oxygen consumed by microorganisms to decompose organic matter in water over 5 days at 20℃. The BOD value is an important indicator for measuring the content of organic pollutants in water bodies, reflecting the degree of organic pollution. Chemical Oxygen Demand (COD): This refers to the amount of reducing substances in a water sample that need to be oxidized, measured chemically. It reflects the degree of pollution in water by reducing substances (including organic matter and some inorganic matter). The higher the COD value, the more reducing substances in the water need to be oxidized, and the more serious the pollution. Dissolved Oxygen (DO): This refers to molecular oxygen dissolved in water. It is an important indicator of a water body's self-purification capacity. In clean water bodies, dissolved oxygen is usually close to saturation; while in water bodies polluted by organic matter, the dissolved oxygen content will decrease. Total Organic Carbon (TOC): This refers to the total amount of carbon contained in dissolved and suspended organic matter in a water body. The TOC value reflects the total amount of organic matter in the water body and is an important parameter for assessing organic pollution. These biochemical indicators are of great significance for understanding the pollution status of water bodies, developing water treatment plans, and evaluating the effectiveness of water treatment. In practical applications, it is necessary to select appropriate indicators for detection and analysis based on the specific water quality conditions and treatment requirements.

[0040] For the anaerobic system treatment stage, the input operating data are: anaerobic influent flow rate to anoxic zone, anaerobic tank pressure, outdoor temperature, anaerobic tank temperature, anaerobic influent flow rate to secondary denitrification zone, biochemical indicators (COD, ammonia nitrogen, etc.) of the equalization tank influent, and biochemical indicators (COD, ammonia nitrogen, etc.) of the anaerobic outlet; the output data are: anaerobic circulation pump outlet flow rate to anaerobic tank and anaerobic influent pump outlet flow rate.

[0041] For the biochemical treatment process, the input operating data includes: anaerobic outlet biochemical indicators, primary biochemical system outlet biochemical indicators, primary denitrification tank ORP, outdoor temperature, primary nitrification tank temperature, primary nitrification tank dissolved oxygen (DO), equalization tank biochemical indicators, tubular membrane circulation pump flow rate / frequency, and ultrafiltration outlet biochemical indicators; the output data includes: anaerobic influent flow rate from overflow to anoxic conditions, and Roots blower outlet flow rate.

[0042] For the secondary biological treatment stage, the input operating data includes: biochemical indicators at the outlet of the primary biological system, biochemical indicators at the outlet of the secondary biological system, outdoor temperature, dissolved oxygen (DO) in the secondary nitrification tank, biochemical indicators in the equalization tank, flow rate / frequency of the tubular membrane circulation pump, and biochemical indicators at the outlet of the ultrafiltration system. Output data includes: anaerobic influent flow rate to the secondary denitrification system and the flow rate at the outlet of the secondary nitrification Roots blower.

[0043] Ultimately, the system is further subdivided into a main intelligent control model and a secondary water quality prediction model. The main intelligent control model encompasses the overall system operation control and is divided into sub-process control models (treatment equipment control parameter prediction models), namely, the equalization tank control model, the anaerobic control model, the primary biological system control model, and the secondary biological MBR system control model. Nanofiltration and reverse osmosis control are implemented by an automatic control system. Each sub-process control model, based on highly correlated online detection data, manual detection data, and manually set data inputs, employs machine learning methods to output the load control actuator actions (pumps, fans, valves) of each sub-process for leachate treatment.

[0044] Step 103: Based on the control parameter data predicted for each treatment stage and the water quality of the treated leachate discharged after secondary biological treatment meeting the standards, and with the goal of minimizing energy consumption per ton of leachate treatment and maximizing effluent efficiency, the target control parameter data for each treatment stage and the treatment equipment are optimized. Based on the optimized target control parameter data, the treatment equipment is controlled to treat the target leachate.

[0045] Next, based on the predicted control parameter data for each treatment stage and the constraint that the treated leachate discharged after secondary biological treatment meets the standards, and with the goals of minimizing energy consumption per ton of treatment and maximizing effluent efficiency, the target control parameter data for each treatment stage and its corresponding equipment are optimized. The treatment equipment is then controlled to treat the target leachate based on these optimized target control parameter data. Specifically, the required water quality indicators for the treated leachate can be determined according to relevant environmental regulations and emission standards (e.g., BOD5 ≤ 30 mg / L, COD ≤ 100 mg / L, SS ≤ 30 mg / L, TN ≤ 15 mg / L, TP ≤ 3 mg / L, etc.). Next, the energy consumption sources in each treatment stage of the leachate treatment process are analyzed, such as aeration, pumping, and membrane separation. Finally, considering factors such as treatment time and treatment volume, the effluent efficiency is evaluated. Next, based on the characteristics of the treatment equipment and past operating experience, reasonable ranges (i.e., preset normal control parameter data ranges) for the control parameters (such as aeration rate, reflux ratio, membrane flux, etc.) of the treatment equipment in each treatment stage are set. Under the premise of meeting water quality standards, the goal is to minimize energy consumption per ton of treatment and maximize effluent efficiency. Finally, optimization algorithms are used for optimization: intelligent optimization algorithms such as genetic algorithms and particle swarm optimization can be used to search for the optimal solution within the given parameter range. By simulating the treatment effect, energy consumption, and effluent efficiency under different parameter combinations, the parameter combination that satisfies the constraints and has the optimal objective function is found. Specifically, the optimization results can be verified and optimized by adjusting the parameter combinations obtained through optimization and monitoring the treatment effect, energy consumption, and effluent efficiency. Based on the monitoring results, the model is fine-tuned to ensure the accuracy and reliability of the optimization results. Finally, based on the target control parameter data obtained through optimization, a control strategy for the leachate treatment equipment is formulated. Through an automated control system, precise control of the treatment equipment is achieved, ensuring stable and efficient treatment results.

[0046] By applying the technical solution of this embodiment, the target control parameter data for each treatment stage of the treatment equipment can be optimized, and the treatment equipment can be controlled to treat the target leachate based on these data, thereby achieving the goals of minimizing energy consumption and maximizing effluent efficiency, while ensuring that the treated water quality meets the standards. In the field of leachate treatment from domestic waste, data-driven multi-dimensional intelligent control, combined with meteorological information, process mechanism and expert experience, can be used to treat leachate, thereby achieving cost reduction and efficiency improvement.

[0047] Furthermore, as a refinement and extension of the specific implementation methods of the above embodiments, and to fully illustrate the specific implementation process of this embodiment, another leachate treatment method is provided, such as... Figure 3 As shown, the method includes:

[0048] Step 201: Based on the treatment sequence of each treatment stage in the leachate treatment process, the input operating condition data of the target leachate entering each treatment stage are collected sequentially. The leachate treatment process includes the equalization tank treatment stage, the anaerobic system treatment stage, the primary biological treatment stage, and the secondary biological treatment stage, which are carried out in the treatment sequence.

[0049] In the above embodiments of this application, the input operating condition data of the target leachate entering each treatment stage is collected sequentially according to the processing order of each treatment stage in the leachate treatment process, in order to prepare for subsequent intelligent control treatment of leachate.

[0050] Step 202: For any processing stage in the leachate treatment process, acquire the historical input operating condition data of the processing stage, and the historical control parameter data of the treatment equipment corresponding to the historical input operating condition data.

[0051] Step 203: Based on the historical input operating condition data and the historical control parameter data, construct a control model training dataset.

[0052] Step 204: Train multiple target training models based on the control model training dataset. For any target training model, calculate the mean absolute error index, mean square error index, and F1 score index. The target training models include random forest models and decision tree models.

[0053] Step 205: Based on the mean absolute error index value, the mean square error index value, the F1 score index value, and the preset evaluation weights of each performance evaluation index, obtain the comprehensive performance evaluation value of the target training model, and determine the target training model corresponding to the maximum comprehensive performance evaluation value as the control parameter prediction model for the processing equipment. The performance evaluation index includes the mean absolute error index, the mean square error index, and the F1 score index.

[0054] Next, the model is trained based on historical data. Simultaneously, manual intervention is possible, involving the re-collection of real-time data into the operational knowledge base and learning rule base, and real-time updates to the intelligent control main model and the water quality prediction sub-model. Specifically, for any treatment stage in the leachate treatment process, historical input condition data for that stage and corresponding historical control parameter data for the treatment equipment are acquired. Based on these historical input condition and control parameter data, a control model training dataset is constructed. Multiple target training models are trained using this dataset. For each target training model, the mean absolute error, mean squared error, and F1 score are calculated. These target training models include random forest and decision tree models. Based on the mean absolute error, mean squared error, F1 score, and their respective preset evaluation weights (e.g., 0.4, 0.3, and 0.3 respectively), the comprehensive performance evaluation value of the target training model is obtained. The target training model corresponding to the highest comprehensive performance evaluation value is determined as the control parameter prediction model for the treatment equipment.

[0055] For example, the training process for the anaerobic control model is as follows: First, correlation analysis is performed on the detection data (input operating condition data). Combined with the process mechanism, strongly correlated data (meteorological data, anaerobic overflow flow rate, anaerobic tank pressure, anaerobic influent water quality indicators, anaerobic outlet water quality indicators, anaerobic tank temperature, ambient temperature and pressure, anaerobic circulating pump flow rate, and anaerobic influent pump flow rate) are identified. Data preprocessing is then performed, and the data is input into a machine learning model (e.g., a random forest model) for training. The effectiveness of the model is verified using the root mean square error (RMSE) and coefficient of determination (R²). The machine learning models of each sub-process system constitute the main intelligent control model for leachate treatment, outputting control commands to the system's anaerobic pumps, anaerobic circulating pumps, Roots blowers, and overflow electric valves, ultimately ensuring that the leachate treatment system meets discharge standards. During operation, the outlet water quality indicators of the sub-process systems should be manually set.

[0056] Specifically, an intake condition database can be established based on historical data, including but not limited to water quality, water quantity, and meteorological factors. Based on the data in the intake condition database, various operating condition types can be categorized, along with multiple sets of intake condition data or ranges corresponding to each type. Furthermore, based on expert experience, weighted attributes are initially assigned to data of the same type. Each type of operating condition data also corresponds to one or more sets of control parameters for the treatment equipment. This allows for the matching of input operating condition data with pre-defined operating condition type data when predicting the control parameters for the treatment equipment based on the control parameter prediction model for the corresponding treatment stage.

[0057] Step 206: Based on the control parameter prediction model of the processing equipment corresponding to the processing stage, predict the control parameter data for the processing equipment corresponding to the input operating condition data of the processing stage.

[0058] Next, after the control parameter prediction model for the processing equipment is trained, the control parameter data for the processing equipment corresponding to the input operating condition data of the processing stage is predicted based on the control parameter prediction model for the processing equipment corresponding to the processing stage.

[0059] Optionally, in step 206, based on the control parameter prediction model of the processing equipment corresponding to the processing stage, the control parameter data for the processing equipment corresponding to the input operating condition data of the processing stage is predicted. For any processing stage, such as... Figure 4 As shown, it specifically includes:

[0060] Step 2061: The biochemical index values ​​in the input operating condition data corresponding to the treatment stage are obtained by periodically integrating the water quality of the target leachate entering the treatment stage.

[0061] Step 2062, or predicting the output water quality corresponding to the input operating condition data through a water quality prediction model, to obtain the output water quality of the target leachate after treatment through the treatment process, wherein the water quality prediction model is based on a random forest model, the random forest model is trained on a water quality model training dataset, the water quality model training dataset includes historical input operating condition data and the output water quality corresponding to the historical input operating condition data, and the output water quality includes biochemical index values.

[0062] Specifically, water quality index data considers the cycle integral of water treatment, and online detection data of dissolved oxygen and ORP (oxidation-reduction potential) consider the changes and rates of change in water treatment.

[0063] The water quality prediction sub-model includes predictions for water quality indicators of each sub-process system, namely, the equalization tank water quality prediction model, the anaerobic system water quality prediction model, the primary biological treatment system water quality prediction model, and the secondary biological MBR system water quality prediction model. Each sub-process system water quality prediction model uses machine learning methods to output the effluent water quality indicators of each sub-process system based on strongly correlated online and manual detection data as input. The effectiveness of the models is verified using root mean square error and coefficient of determination. During runtime, the water quality prediction modules of each sub-process system output the inlet water quality indicators for the next-level sub-process system.

[0064] Step 2063: When the processing stage is the regulating pool processing stage, if the control parameter data for the processing equipment corresponding to the input operating condition data of the processing stage is predicted based on the control parameter prediction model of the processing equipment corresponding to the processing stage, and the control parameter prediction model of the processing equipment fails to predict the control parameter data corresponding to the input operating condition data, the unpredicted sudden input operating condition data and the new control parameter data for the processing equipment in response to the sudden input operating condition data are obtained.

[0065] Step 2064: Add the sudden input condition data and the newly added control parameter data to the control model training dataset of the control parameter prediction model of the processing equipment corresponding to the regulating pool processing stage, and retrain the control parameter prediction model of the processing equipment based on the added control model training dataset.

[0066] Therefore, when the influent conditions of the equalization tank undergo a sudden change, and such conditions are not found in the original database, the database needs to be updated, and the model needs to be relearned and optimized. This could be due to changes in biochemical indicators exceeding ranges or water volume exceeding ranges, in order to improve the model's subsequent prediction accuracy.

[0067] Step 207: Based on the control parameter data predicted for each treatment stage and the water quality of the treated leachate discharged after secondary biological treatment meeting the standards, and with the goal of minimizing energy consumption per ton of leachate treatment and maximizing effluent efficiency, the target control parameter data for each treatment stage and the treatment equipment are optimized. Based on the optimized target control parameter data, the treatment equipment is controlled to treat the target leachate.

[0068] Step 208: If the predicted control parameter data exceeds the preset normal control parameter data range of the processing device, then an alarm message for the processing device is generated based on the error control parameter data that exceeds the preset normal control parameter data range, the type of the processing device, and the preset normal control parameter data range.

[0069] Step 209: Send the alarm information of the processing device to the preset receiving terminal.

[0070] Next, based on the big data of working condition perception, intelligent control, and autonomous optimization operation, machine learning methods are used to intelligently control the processing system.

[0071] Specifically, an alarm mechanism can be set up, for example, for the bioreactor in a leachate treatment plant. This reactor maintains suitable microbial activity by controlling the aeration rate, thereby effectively degrading organic matter. The bioreactor has a set of preset normal control parameter data ranges, such as an aeration rate of 100-200 cubic meters per hour. Through monitoring systems and data analysis tools, it can be predicted that in the future, in order to achieve specific effluent quality standards, the aeration rate of the bioreactor needs to be adjusted to 250 cubic meters per hour. At this time, when the predicted aeration rate of 250 cubic meters per hour exceeds the preset normal control parameter data range (100-200 cubic meters per hour) of the bioreactor, the system will identify a potential anomaly. Based on this exceeded error control parameter data (aeration rate of 250 cubic meters per hour), the type of treatment equipment (bioreactor), and the preset normal control parameter data range (100-200 cubic meters per hour), the system will automatically generate an alarm message for the treatment equipment. This message might include: "Abnormal aeration rate in the biological reactor; the predicted value of 250 cubic meters per hour exceeds the normal range by 100-200 cubic meters per hour. Please check and take immediate action." The system will then send this alarm message to pre-set receiving terminals, such as the treatment plant's monitoring center, maintenance personnel's mobile phones, or email addresses. This allows relevant personnel to receive the alert immediately and take appropriate measures, such as adjusting process parameters, checking equipment status, or activating emergency plans. Therefore, it helps maintenance personnel to promptly identify and handle potential anomalies, preventing problems such as substandard effluent quality or increased energy consumption caused by equipment failure or improper parameter settings. Simultaneously, real-time monitoring and early warning can improve the treatment plant's operational efficiency and stability, reducing maintenance costs and environmental risks.

[0072] By applying the technical solution of this embodiment, for example Figure 5 As shown, the system makes decisions through a comprehensive model using machine learning algorithms, thereby controlling the flow of pumps and fans, and the operation of electric valves to ensure that leachate is discharged in compliance with standards. The system then processes the detection data to update and optimize the model in real time. It focuses on intelligent control of leachate treatment across multiple dimensions of the entire system, consisting of a main intelligent control model and a secondary water quality prediction model. By combining an expert knowledge base and a machine learning model, it can effectively solve the problems in the industry where the leachate treatment effect is unstable depending on the experience and technical level of the operators, and the workload of manual testing is large.

[0073] Furthermore, as Figure 1 To specifically implement the method, this application provides a leachate treatment device, such as... Figure 6 As shown, the device includes:

[0074] The operating condition data acquisition module 301 is used to collect the input operating condition data of the target leachate entering each treatment stage in sequence according to the treatment order of each treatment stage in the leachate treatment process. The leachate treatment process includes the equalization tank treatment stage, the anaerobic system treatment stage, the primary biological treatment stage and the secondary biological treatment stage performed in sequence according to the treatment order.

[0075] The control parameter prediction module 302 is used to predict the control parameter data for the treatment equipment corresponding to the input operating condition data of the treatment stage for any treatment stage in the leachate treatment process, based on the control parameter prediction model of the treatment equipment corresponding to the treatment stage.

[0076] The leachate optimization treatment module 303 is used to optimize the target control parameter data for each treatment equipment based on the predicted control parameter data for each treatment stage, with the constraint that the water quality of the treated leachate discharged after secondary biological treatment meets the standards, and with the goal of minimizing the energy consumption per ton of treatment and maximizing the effluent efficiency in the leachate treatment process. Based on the optimized target control parameter data, the module controls the treatment equipment to treat the target leachate.

[0077] Optionally, the control parameter prediction module 302 is further configured to:

[0078] When the treatment stage is the equalization tank treatment stage, the input operating condition data includes the ambient temperature of the equalization tank, the biochemical index value and water volume of the target leachate entering the equalization tank treatment stage, and the control parameter data includes the anaerobic pump effluent volume.

[0079] When the treatment stage is an anaerobic system treatment stage, the input operating condition data includes the anaerobic influent flow rate from the anoxic stage, the anaerobic tank pressure, the outdoor temperature of the anaerobic system treatment stage, the anaerobic tank temperature, the anaerobic influent flow rate from the secondary denitrification stage, the biochemical index values ​​of the target treated leachate entering the anaerobic system treatment stage, and the biochemical index values ​​of the target treated leachate discharged after being treated by the anaerobic system treatment stage. The control parameter data includes the flow rate from the anaerobic circulation pump outlet to the anaerobic tank and the anaerobic influent pump outlet flow rate.

[0080] When the treatment stage is a primary biological treatment stage, the input operating condition data includes the biochemical index values ​​of the target leachate discharged after treatment by the anaerobic system treatment stage, the biochemical index values ​​of the target leachate discharged after treatment by the primary biological treatment stage, the oxidation-reduction potential of the primary denitrification tank, the outdoor temperature of the primary biological treatment stage, the temperature of the primary nitrification tank, the dissolved oxygen content of the primary nitrification tank, the biochemical index values ​​of the target leachate entering the equalization tank treatment stage, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index values ​​of the ultrafiltration outlet. The control parameter data includes the flow rate of the anaerobic influent from the superposition to the anoxic stage and the flow rate of the Roots blower outlet.

[0081] When the treatment stage is a secondary biological treatment stage, the input operating condition data includes the biochemical index values ​​of the target treated leachate discharged after treatment by the primary biological treatment stage, the biochemical index values ​​of the target treated leachate discharged after treatment by the secondary biological treatment stage, the outdoor temperature of the secondary biological treatment stage, the dissolved oxygen content of the secondary nitrification tank, the biochemical index values ​​of the target treated leachate in the equalization tank treatment stage, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index values ​​at the ultrafiltration outlet. The control parameter data includes the flow rate of anaerobic influent exceeding the secondary denitrification flow rate and the outlet flow rate of the secondary nitrification Roots blower.

[0082] The biochemical index values ​​include at least one of biochemical oxygen demand, chemical oxygen demand, dissolved oxygen, and total organic carbon.

[0083] Optionally, the control parameter prediction module 302 is also used for:

[0084] For any processing stage, the biochemical index values ​​in the input operating condition data corresponding to the processing stage are obtained by periodically integrating the water quality of the target leachate entering the processing stage, or by predicting the output water quality corresponding to the input operating condition data through a water quality prediction model, thereby obtaining the output water quality of the target leachate after processing through the processing stage. The water quality prediction model is based on a random forest model, which is trained on a water quality model training dataset. The water quality model training dataset includes historical input operating condition data and the output water quality corresponding to the historical input operating condition data, and the output water quality includes biochemical index values.

[0085] Furthermore, embodiments of this application provide another leachate treatment device, such as... Figure 7 As shown, the device includes:

[0086] The operating condition data acquisition module 401 is used to collect the input operating condition data of the target leachate entering each treatment stage in sequence according to the treatment order of each treatment stage in the leachate treatment process. The leachate treatment process includes the equalization tank treatment stage, the anaerobic system treatment stage, the primary biological treatment stage and the secondary biological treatment stage performed in sequence according to the treatment order.

[0087] The control parameter prediction module 402 is used to predict the control parameter data for the treatment equipment corresponding to the input operating condition data of the treatment stage for any treatment stage in the leachate treatment process, based on the control parameter prediction model of the treatment equipment corresponding to the treatment stage.

[0088] The leachate optimization treatment module 403 is used to optimize the target control parameter data for each treatment equipment based on the control parameter data predicted for each treatment stage, with the constraint that the water quality of the treated leachate discharged after secondary biological treatment meets the standards, and with the goal of minimizing the energy consumption per ton of treatment and maximizing the effluent efficiency in the leachate treatment process. Based on the optimized target control parameter data, the module controls the treatment equipment to treat the target leachate.

[0089] The device executes an alarm module 404, which is used to generate alarm information for the processing device based on the error control parameter data that exceeds the preset normal control parameter data range, the type of the processing device, and the preset normal control parameter data range if the predicted control parameter data exceeds the preset normal control parameter data range of the processing device, and then send the alarm information to a preset receiving terminal.

[0090] The control model training module 405 is used to acquire historical input condition data of the processing stage and historical control parameter data of the processing equipment corresponding to the historical input condition data; construct a control model training dataset based on the historical input condition data and the historical control parameter data; train multiple target training models based on the control model training dataset, wherein the target training models include random forest models and decision tree models; calculate the comprehensive performance evaluation value of each target training model under multiple performance evaluation indicators, and determine the target training model corresponding to the maximum comprehensive performance evaluation value as the control parameter prediction model of the processing equipment, wherein the performance evaluation indicators include mean absolute error, mean square error, and F1 score.

[0091] Optionally, the control parameter prediction module 402 is further configured to:

[0092] When the treatment stage is the equalization tank treatment stage, the input operating condition data includes the ambient temperature of the equalization tank, the biochemical index value and water volume of the target leachate entering the equalization tank treatment stage, and the control parameter data includes the anaerobic pump effluent volume.

[0093] When the treatment stage is an anaerobic system treatment stage, the input operating condition data includes the anaerobic influent flow rate from the anoxic stage, the anaerobic tank pressure, the outdoor temperature of the anaerobic system treatment stage, the anaerobic tank temperature, the anaerobic influent flow rate from the secondary denitrification stage, the biochemical index values ​​of the target treated leachate entering the anaerobic system treatment stage, and the biochemical index values ​​of the target treated leachate discharged after being treated by the anaerobic system treatment stage. The control parameter data includes the flow rate from the anaerobic circulation pump outlet to the anaerobic tank and the anaerobic influent pump outlet flow rate.

[0094] When the treatment stage is a primary biological treatment stage, the input operating condition data includes the biochemical index values ​​of the target leachate discharged after treatment by the anaerobic system treatment stage, the biochemical index values ​​of the target leachate discharged after treatment by the primary biological treatment stage, the oxidation-reduction potential of the primary denitrification tank, the outdoor temperature of the primary biological treatment stage, the temperature of the primary nitrification tank, the dissolved oxygen content of the primary nitrification tank, the biochemical index values ​​of the target leachate entering the equalization tank treatment stage, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index values ​​of the ultrafiltration outlet. The control parameter data includes the flow rate of the anaerobic influent from the superposition to the anoxic stage and the flow rate of the Roots blower outlet.

[0095] When the treatment stage is a secondary biological treatment stage, the input operating condition data includes the biochemical index values ​​of the target treated leachate discharged after treatment by the primary biological treatment stage, the biochemical index values ​​of the target treated leachate discharged after treatment by the secondary biological treatment stage, the outdoor temperature of the secondary biological treatment stage, the dissolved oxygen content of the secondary nitrification tank, the biochemical index values ​​of the target treated leachate in the equalization tank treatment stage, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index values ​​at the ultrafiltration outlet. The control parameter data includes the flow rate of anaerobic influent exceeding the secondary denitrification flow rate and the outlet flow rate of the secondary nitrification Roots blower.

[0096] The biochemical index values ​​include at least one of biochemical oxygen demand, chemical oxygen demand, dissolved oxygen, and total organic carbon.

[0097] Optionally, the control parameter prediction module 402 is also used for:

[0098] For any processing stage, the biochemical index values ​​in the input operating condition data corresponding to the processing stage are obtained by periodically integrating the water quality of the target leachate entering the processing stage, or by predicting the output water quality corresponding to the input operating condition data through a water quality prediction model, thereby obtaining the output water quality of the target leachate after processing through the processing stage. The water quality prediction model is based on a random forest model, which is trained on a water quality model training dataset. The water quality model training dataset includes historical input operating condition data and the output water quality corresponding to the historical input operating condition data, and the output water quality includes biochemical index values.

[0099] Optionally, the control model training module 405 is further configured to:

[0100] For any target training model, calculate the mean absolute error, mean squared error, and F1 score of the target training model.

[0101] Based on the mean absolute error index, the mean square error index, the F1 score index, and the preset evaluation weights of various performance evaluation indicators, the comprehensive performance evaluation value of the target training model is obtained.

[0102] Optionally, the control model training module 405 is further configured to:

[0103] When the processing stage is the regulating tank processing stage, if the control parameter data for the processing equipment corresponding to the input operating condition data of the processing stage is predicted based on the control parameter prediction model of the processing equipment corresponding to the processing stage, and the control parameter prediction model of the processing equipment fails to predict the control parameter data corresponding to the input operating condition data, the unpredicted sudden input operating condition data and the new control parameter data for the processing equipment in response to the sudden input operating condition data are obtained.

[0104] The sudden input operating condition data and the newly added control parameter data are added to the control model training dataset of the control parameter prediction model of the corresponding processing equipment in the regulating pool processing stage, and the control parameter prediction model of the processing equipment is retrained based on the added control model training dataset.

[0105] It should be noted that other corresponding descriptions of the functional units involved in the leachate treatment device provided in this application embodiment can be found by referring to... Figures 1 to 4 The corresponding descriptions in the method will not be repeated here.

[0106] Based on the above, Figures 1 to 4 Accordingly, this application also provides a storage medium storing a computer program, which, when executed by a processor, implements the above-described method. Figures 1 to 4 The leachate treatment method shown is illustrated.

[0107] Based on this understanding, the technical solution of this application can be embodied in the form of a software product. This software product can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or portable hard drive), and includes several instructions to cause a computer device (such as a personal computer, server, or network device) to execute the methods described in the various implementation scenarios of this application.

[0108] Based on the above, Figures 1 to 4 The method shown, and Figure 6 , Figure 7 To achieve the above objectives, the present application also provides a computer device, specifically a personal computer, server, network device, etc., as shown in the virtual device embodiment. This computer device includes a storage medium and a processor; the storage medium stores a computer program; the processor executes the computer program to achieve the above-described objectives. Figures 1 to 4 The leachate treatment method shown is illustrated.

[0109] Optionally, the computer device may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Bluetooth interfaces, Wi-Fi interfaces), etc.

[0110] Those skilled in the art will understand that the computer device structure provided in this embodiment does not constitute a limitation on the computer device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0111] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages and stores the hardware and software resources of a computer device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software within the physical device.

[0112] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented using software plus necessary general-purpose hardware platforms, or it can be implemented using hardware: For the processing sequence of each treatment stage in the leachate treatment process, input condition data of the target leachate entering each treatment stage is collected sequentially; based on the control parameter prediction model of the treatment equipment corresponding to each treatment stage, the control parameter data of the treatment equipment corresponding to the input condition data of the treatment stage is predicted; based on the control parameter data, with the constraint that the water quality of the treated leachate discharged after secondary biological treatment meets the standards, and with the objectives of minimizing the energy consumption per ton of treatment and maximizing the effluent efficiency in the leachate treatment process, the target control parameter data of each treatment stage for the treatment equipment is optimized, and the target leachate is treated. Based on the big data of operating condition perception, intelligent control, and autonomous optimization, machine learning methods are used to intelligently control the treatment system, ultimately achieving cost reduction and efficiency improvement.

[0113] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing this application. Those skilled in the art will understand that the modules in the apparatus of the embodiment can be distributed within the apparatus of the embodiment as described, or can be modified to be located in one or more apparatuses different from this embodiment. The modules of the above-described embodiment can be combined into one module, or further divided into multiple sub-modules.

[0114] The serial numbers in this application are for descriptive purposes only and do not represent the superiority or inferiority of any particular implementation scenario. The above disclosures are merely a few specific implementation scenarios of this application; however, this application is not limited thereto, and any variations conceived by those skilled in the art should fall within the protection scope of this application.

Claims

1. A method for treating leachate, characterized in that, The method for treating leachate from municipal solid waste includes: To determine the treatment sequence of each treatment stage in the leachate treatment process, input operating condition data are collected sequentially when the target leachate enters each treatment stage. The leachate treatment process includes the equalization tank treatment stage, the anaerobic system treatment stage, the primary biological treatment stage, and the secondary biological treatment stage, which are carried out in the treatment sequence. For any stage in the leachate treatment process, based on the control parameter prediction model of the treatment equipment corresponding to the treatment stage, the control parameter data for the treatment equipment corresponding to the input operating condition data of the treatment stage is predicted. When the treatment stage is the equalization tank treatment stage, the input operating condition data includes the ambient temperature of the equalization tank, the biochemical index value and water volume of the target leachate entering the equalization tank treatment stage, and the control parameter data includes the anaerobic pump effluent volume. When the treatment stage is an anaerobic system treatment stage, the input operating condition data includes the anaerobic influent flow rate from the anoxic stage, the anaerobic tank pressure, the outdoor temperature of the anaerobic system treatment stage, the anaerobic tank temperature, the anaerobic influent flow rate from the secondary denitrification stage, the biochemical index values ​​of the target treated leachate entering the anaerobic system treatment stage, and the biochemical index values ​​of the target treated leachate discharged after being treated by the anaerobic system treatment stage. The control parameter data includes the flow rate from the anaerobic circulation pump outlet to the anaerobic tank and the anaerobic influent pump outlet flow rate. When the treatment stage is a primary biological treatment stage, the input operating condition data includes the biochemical index values ​​of the target leachate discharged after treatment by the anaerobic system treatment stage, the biochemical index values ​​of the target leachate discharged after treatment by the primary biological treatment stage, the oxidation-reduction potential of the primary denitrification tank, the outdoor temperature of the primary biological treatment stage, the temperature of the primary nitrification tank, the dissolved oxygen content of the primary nitrification tank, the biochemical index values ​​of the target leachate entering the equalization tank treatment stage, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index values ​​of the ultrafiltration outlet. The control parameter data includes the flow rate of the anaerobic influent from the superposition to the anoxic stage and the flow rate of the Roots blower outlet. When the treatment stage is a secondary biological treatment stage, the input operating condition data includes the biochemical index values ​​of the target treated leachate discharged after treatment by the primary biological treatment stage, the biochemical index values ​​of the target treated leachate discharged after treatment by the secondary biological treatment stage, the outdoor temperature of the secondary biological treatment stage, the dissolved oxygen content of the secondary nitrification tank, the biochemical index values ​​of the target treated leachate in the equalization tank treatment stage, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index values ​​at the ultrafiltration outlet. The control parameter data includes the flow rate of anaerobic influent exceeding the secondary denitrification flow rate and the outlet flow rate of the secondary nitrification Roots blower. The biochemical index values ​​include at least one of biochemical oxygen demand, chemical oxygen demand, dissolved oxygen, and total organic carbon. For any processing stage, the biochemical index values ​​in the input operating condition data corresponding to the processing stage are obtained by periodically integrating the water quality of the target leachate entering the processing stage, or by predicting the output water quality corresponding to the input operating condition data through a water quality prediction model, thereby obtaining the output water quality of the target leachate after processing through the processing stage. The water quality prediction model is based on a random forest model, which is trained on a water quality model training dataset. The water quality model training dataset includes historical input operating condition data and the output water quality corresponding to the historical input operating condition data, and the output water quality includes biochemical index values. Based on the predicted control parameter data for each treatment stage, and with the constraint that the treated leachate discharged after secondary biological treatment meets the water quality standards, and with the objectives of minimizing energy consumption per ton of leachate treatment and maximizing effluent efficiency, the target control parameter data for each treatment stage for each treatment stage is optimized. Based on the optimized target control parameter data, the treatment equipment is controlled to treat the target leachate.

2. The method according to claim 1, characterized in that, After predicting the control parameter data for the processing equipment corresponding to the input operating condition data of the processing stage based on the control parameter prediction model of the processing equipment corresponding to the processing stage, the method further includes: If the predicted control parameter data exceeds the preset normal control parameter data range of the processing device, then an alarm message for the processing device is generated based on the error control parameter data that exceeds the preset normal control parameter data range, the type of the processing device, and the preset normal control parameter data range. The alarm information from the processing device is sent to a preset receiving terminal.

3. The method according to claim 1, characterized in that, Before predicting the control parameter data for the processing equipment corresponding to the input operating condition data of the processing stage based on the control parameter prediction model of the processing equipment corresponding to the processing stage, the method further includes: Acquire historical input condition data of the processing stage, and historical control parameter data of the processing equipment corresponding to the historical input condition data; Based on the historical input operating condition data and the historical control parameter data, a control model training dataset is constructed. Multiple target training models are trained based on the control model training dataset, wherein the target training models include a random forest model and a decision tree model; The comprehensive performance evaluation value of each target training model under multiple performance evaluation indicators is calculated respectively, and the target training model corresponding to the maximum comprehensive performance evaluation value is determined as the control parameter prediction model of the processing equipment. The performance evaluation indicators include the mean absolute error index, the mean square error index, and the F1 score index.

4. The method according to claim 3, characterized in that, The calculation of the comprehensive performance evaluation value of each target training model under multiple performance evaluation metrics includes: For any target training model, calculate the mean absolute error, mean squared error, and F1 score of the target training model. Based on the mean absolute error index, the mean square error index, the F1 score index, and the preset evaluation weights of various performance evaluation indicators, the comprehensive performance evaluation value of the target training model is obtained.

5. The method according to claim 1, characterized in that, The method further includes: When the processing stage is the regulating pool processing stage, if the control parameter data for the processing equipment corresponding to the input operating condition data of the processing stage is predicted based on the control parameter prediction model of the processing equipment corresponding to the processing stage, and the control parameter prediction model of the processing equipment fails to predict the control parameter data corresponding to the input operating condition data, the unpredicted sudden input operating condition data and the new control parameter data for the processing equipment in response to the sudden input operating condition data are obtained. The sudden input operating condition data and the newly added control parameter data are added to the control model training dataset of the control parameter prediction model of the corresponding processing equipment in the regulating pool processing stage, and the control parameter prediction model of the processing equipment is retrained based on the added control model training dataset.

6. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the leachate treatment method according to any one of claims 1 to 5.

7. A computer device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the leachate treatment method according to any one of claims 1 to 5.

Images