Leachate treatment method and device, storage medium and computer equipment

Abstract

The invention discloses a leachate treatment method and device, a storage medium and computer equipment, and the method comprises the steps: sequentially collecting input working condition data when target treatment leachate enters each treatment link according to the treatment sequence of each treatment link in the leachate treatment process; on the basis of a processing equipment control parameter prediction model corresponding to the processing link, predicting control parameter data, corresponding to the input working condition data of the processing link, for the processing equipment; on the basis of the control parameter data, target control parameter data, aiming at treatment equipment, of all treatment links are obtained through optimization by taking the condition that the water quality of treated leachate discharged after treatment in the secondary biochemical treatment link reaches the standard as a constraint condition and taking the minimum energy consumption per ton treatment and the highest water outlet efficiency in the leachate treatment process as targets; and treating the target treatment leachate. Based on working condition sensing-intelligent control-autonomous optimization operation big data, a machine learning method is adopted to perform intelligent control on a processing system, and finally cost reduction and efficiency improvement are realized.

Description

Technical Field

[0001] The present application relates to the technical field of high-concentration organic matter and high-ammonia nitrogen wastewater treatment, and in particular to a leachate treatment method and device, storage medium, and computer equipment. Background Art

[0002] Leachate generated from domestic waste is a high-concentration organic wastewater with complex pollutant composition, containing a variety of toxic and harmful substances, including dissolved organic matter, inorganic salt components, heavy metals, etc., and the water quality and quantity vary greatly. According to the environmental discharge requirements, the leachate treatment process generally adopts the "biochemical + physical" treatment process, that is, the "pretreatment + anaerobic + aerobic + MBR (Membrane Bio-Reactor, membrane bioreactor) + nanofiltration + reverse osmosis" process route, which can meet the requirements for leachate effluent to meet discharge standards.

[0003] The leachate treatment process uses biochemical and physical treatment methods. It is a multivariable, highly correlated, non-steady-state nonlinear system that integrates uncertain factors such as microbial reactions, water quality, water quantity and environment, and has large inertial time lags. Although the deep treatment system (membrane system) has a high degree of automation, stable effects and controllable energy consumption. However, the biochemical treatment process is difficult to mathematically model and difficult to quantitatively describe using strict mathematical methods. It has a low degree of automation, high control difficulty and poor stability of the treatment effect.

[0004] At present, in the domestic leachate treatment system, the operating data between and within the subsystems are strongly correlated and nonlinear. The pollutant concentration in the leachate is high and the composition is complex. The water quality testing instrument is expensive and the maintenance workload is large, and a large amount of manual testing of water quality indicators is required. Most operations are manual, and the treatment effect depends largely on the experience and technical level of the operators. High energy consumption, high cost, unstable treatment effect, and high labor intensity are the common pain points of the leachate treatment system in the industry. Summary of the invention

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

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

[0007] According to the processing sequence of each treatment link in the leachate treatment process, the input operating condition data of the target leachate when entering each treatment link is collected in sequence, wherein the leachate treatment process includes a regulating tank treatment link, an anaerobic system treatment link, a primary biochemical treatment link and a secondary biochemical treatment link which are performed in sequence;

[0008] For any treatment link in the leachate treatment process, based on the treatment equipment control parameter prediction model corresponding to the treatment link, predict the control parameter data for the treatment equipment corresponding to the input working condition data of the treatment link;

[0009] Based on the control parameter data for the treatment equipment predicted by each treatment link, with the water quality compliance of the treated leachate discharged after the secondary biochemical treatment link as the constraint condition, and with the minimum energy consumption per ton of treatment and the maximum water output efficiency in the leachate treatment process as the goal, the target control parameter data for the treatment equipment in each treatment link is obtained by optimization, and the treatment equipment is controlled to treat the target treatment leachate based on the target control parameter data obtained by optimization.

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

[0011] The working condition data acquisition module is used to collect the input working condition data of the target leachate when it enters each treatment link according to the treatment order of each treatment link in the leachate treatment process, wherein the leachate treatment process includes the regulating tank treatment link, the anaerobic system treatment link, the primary biochemical treatment link and the secondary biochemical treatment link which are carried out in sequence according to the treatment order;

[0012] A control parameter prediction module is used to predict the control parameter data for the processing equipment corresponding to the input working condition data of any processing link in the leachate treatment process based on the control parameter prediction model of the processing equipment corresponding to the processing link;

[0013] The leachate optimization treatment module is used to optimize the target control parameter data for the treatment equipment in each treatment link based on the control parameter data for the treatment equipment predicted by each treatment link, with the water quality of the treated leachate discharged after the secondary biochemical treatment link meeting the standard as a constraint condition, and with the minimum energy consumption per ton of treatment and the maximum water output efficiency in the leachate treatment process as the goal, and control the treatment equipment to treat the target treatment leachate based on the target control parameter data obtained by optimization.

[0014] According to another aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned leachate treatment method is implemented.

[0015] According to another aspect of the present 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 implements the above-mentioned leachate treatment method when executing the program.

[0016] By means of the above technical scheme, the present application provides a leachate treatment method and device, storage medium, and computer equipment. According to the processing order of each treatment link in the leachate treatment process, the input working condition data of the target treatment leachate when entering each treatment link is collected in sequence; based on the treatment equipment control parameter prediction model corresponding to the treatment link, the control parameter data for the treatment equipment corresponding to the input working condition data of the treatment link is predicted; based on the control parameter data, with the water quality of the treated leachate discharged after the secondary biochemical treatment link meeting the standard as the constraint condition, with the minimum ton treatment energy consumption and the highest water output efficiency in the leachate treatment process as the goal, the target control parameter data for the treatment equipment of each treatment link is obtained by optimization, and the target treatment leachate is treated. Based on working condition perception - intelligent control - autonomous optimization operation big data, machine learning methods are used to intelligently control the treatment system, and ultimately achieve cost reduction and efficiency improvement.

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 A schematic flow chart of a leachate treatment method provided in an embodiment of the present application is shown;

[0020] Figure 2 A schematic flow chart of another leachate treatment method provided in an embodiment of the present application is shown;

[0021] Figure 3 A schematic diagram of a process of another leachate treatment method provided in an embodiment of the present application is shown;

[0022] Figure 4 A schematic diagram of a process of another leachate treatment method provided in an embodiment of the present application is shown;

[0023] Figure 5 A schematic diagram of a process of another leachate treatment method provided in an embodiment of the present application is shown;

[0024] Figure 6 A schematic structural diagram of a leachate treatment device provided in an embodiment of the present application is shown;

[0025] Figure 7 A schematic structural diagram of another leachate treatment device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0027] In this embodiment, a leachate treatment method is provided. Figure 1 As shown, the method includes:

[0028] Step 101, according to the processing sequence of each processing link in the leachate treatment process, the input operating condition data of the target leachate when it enters each processing link is collected in sequence, wherein the leachate treatment process includes a regulating tank treatment link, an anaerobic system treatment link, a primary biochemical treatment link and a secondary biochemical treatment link which are performed in sequence.

[0029] In the above embodiment of the present application, data-driven and multi-dimensional intelligent control are used to treat leachate, which can achieve cost reduction and efficiency improvement while intelligently controlling the treatment system. Specifically, the leachate treatment process includes the regulating tank treatment link, the anaerobic system treatment link, the primary biochemical treatment link and the secondary biochemical treatment link in the treatment order. In the actual control process, according to the treatment order of each treatment link, the input working condition data of the target treatment leachate when entering each treatment link is collected in turn, in preparation for the subsequent intelligent control treatment of the leachate.

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

[0031] Next, for any treatment link in the leachate treatment process, based on the treatment equipment control parameter prediction model corresponding to the treatment link, the control parameter data for the treatment equipment corresponding to the input working condition data of the treatment link is predicted. Specifically, a data model including water quantity, water quality, online detection data and environmental factors can be constructed, and the data model specifically includes an intelligent control main model and a water quality prediction sub-model. The aforementioned intelligent control main model and water quality prediction sub-model are the treatment equipment control parameter prediction model. The intelligent control main model includes a regulating tank control model, an anaerobic system control model, a primary biochemical system control model and a secondary biochemical MBR (Membrane Bio-Reactor) system control model. The water quality prediction sub-model includes a secondary biochemical system outlet water quality prediction model, a primary biochemical system outlet water quality prediction model, an anaerobic system outlet water quality prediction model and a regulating tank outlet water quality prediction model.

[0032] When using the treatment equipment control parameter prediction model 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. Ultimately, the load control, aerobic aeration control, carbon source addition control and drainage index control of the overall treatment system can be achieved through the respective prediction models of various treatment links.

[0033] Optionally, in step 102, for any treatment link in the leachate treatment process, based on the treatment equipment control parameter prediction model corresponding to the treatment link, the control parameter data for the treatment equipment corresponding to the input operating condition data of the treatment link is predicted, and for different treatment links, reference is made to Figure 3 As shown, specifically including:

[0034] Step 1021, when the treatment link is the equalization tank treatment link, the input operating condition data includes the ambient temperature of the equalization tank, the biochemical index values ​​and water volume of the target treatment leachate entering the equalization tank treatment link, and the control parameter data includes the anaerobic pump output.

[0035] Step 1022, when the treatment link is the anaerobic system treatment link, the input operating condition data include the anaerobic water inlet exceeding the anoxic flow, the anaerobic tank pressure, the outdoor temperature of the anaerobic system treatment link, the anaerobic tank temperature, the anaerobic water inlet exceeding the secondary denitrification flow, the biochemical index values ​​of the target treatment leachate entering the anaerobic system treatment link, and the biochemical index values ​​of the target treatment leachate discharged after being treated by the anaerobic system treatment link, and the control parameter data include the flow from the anaerobic circulation pump outlet to the anaerobic tank and the anaerobic water inlet pump outlet flow.

[0036] Step 1023, when the treatment link is a primary biochemical treatment link, the input operating condition data include the biochemical index values ​​of the target treatment leachate discharged after being treated by the anaerobic system treatment link, the biochemical index values ​​of the target treatment leachate discharged after being treated by the primary biochemical treatment link, the redox potential of the primary denitrification tank, the outdoor temperature of the primary biochemical treatment link, the temperature of the primary nitrification tank, the dissolved oxygen content of the primary nitrification tank, the biochemical index values ​​of the target treatment leachate entering the regulating tank treatment link, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index value of the ultrafiltration outlet. The control parameter data include the anaerobic inlet flow rate exceeding the anoxic flow rate and the Roots blower outlet flow rate.

[0037] Step 1024, when the treatment link is a secondary biochemical treatment link, the input operating condition data includes the biochemical index value of the target treatment leachate discharged after being treated by the primary biochemical treatment link, the biochemical index value of the target treatment leachate discharged after being treated by the secondary biochemical treatment link, the outdoor temperature of the secondary biochemical treatment link, the dissolved oxygen content of the secondary nitrification tank, the biochemical index value of the target treatment leachate in the regulating tank treatment link, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index value of the ultrafiltration outlet. The control parameter data includes the anaerobic inlet flow rate exceeding the secondary denitrification flow rate and the secondary nitrification Roots blower outlet flow rate, wherein the biochemical index value includes at least one of biochemical oxygen demand, chemical oxygen demand, dissolved oxygen and total organic carbon.

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

[0039] For the treatment link of the regulating tank, input working condition data: various water quality inlet biochemical indicators (biochemical indicator values ​​of the target treatment leachate entering the regulating tank treatment link), such as COD (Chemical Oxygen Demand), ammonia nitrogen, water volume, ambient temperature; output data: anaerobic pump output. The water quality inlet biochemical indicator values ​​mainly refer to water quality parameters related to biochemical processes. These parameters are usually used to evaluate the content of organic pollutants in water bodies and the self-purification capacity of water bodies. Common inlet biochemical indicators include: Biochemical oxygen demand (BOD): refers to the amount of dissolved oxygen consumed by microorganisms to decompose certain oxidizable substances (especially organic substances) in a certain volume of water under specified conditions. It is often expressed in five-day biochemical oxygen demand (BOD5), that is, the amount of dissolved oxygen consumed by microorganisms to decompose organic matter in water within 5 days at 20°C. BOD value is an important indicator for measuring the content of organic pollutants in water bodies, reflecting the degree of organic pollution in water bodies. Chemical oxygen demand (COD): refers to the amount of reducing substances that need to be oxidized in a water sample measured by chemical methods. It reflects the degree of pollution of water by reducing substances (including organic matter and some inorganic substances). The larger the COD value, the more reducing substances that need to be oxidized in the water body and the more serious the pollution. Dissolved oxygen (DO, DissolvedOxygen): refers to molecular oxygen dissolved in water. It is an important indicator to measure the self-purification capacity of water bodies. In clean water bodies, dissolved oxygen is usually close to the saturation value; while in water bodies polluted by organic matter, the dissolved oxygen content will decrease. Total organic carbon (TOC, OTA l Organic Carbon): refers to the total amount of carbon contained in dissolved and suspended organic matter in water bodies. The TOC value reflects the total amount of organic matter in water bodies and is an important parameter for evaluating organic pollution. These biochemical index values ​​are of great significance for understanding the pollution status of water bodies, formulating water treatment plans, and evaluating water treatment effects. In practical applications, it is necessary to select appropriate indicators for detection and analysis based on specific water quality conditions and treatment requirements.

[0040] For the anaerobic system treatment link, input operating data: anaerobic water inlet exceeding to anoxic flow, anaerobic tank pressure, outdoor temperature, anaerobic tank temperature, anaerobic water inlet exceeding to secondary denitrification flow, equalization tank inlet biochemical indicators (COD, ammonia nitrogen, etc.), anaerobic outlet biochemical indicators (COD, ammonia nitrogen, etc.); output data: anaerobic circulation pump outlet to anaerobic tank flow, anaerobic water inlet pump outlet flow.

[0041] For the biochemical treatment link, input operating data: 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, regulating tank biochemical indicators, tubular membrane circulation pump flow / frequency, ultrafiltration outlet biochemical indicators; output data: anaerobic inlet excess to anoxic flow, Roots blower outlet flow.

[0042] For the secondary biochemical treatment link, input working condition data: biochemical index of the primary biochemical system outlet, biochemical index of the secondary biochemical system outlet, outdoor temperature, dissolved oxygen DO of the secondary nitrification tank, biochemical index of the regulating tank, flow rate / frequency of the tubular membrane circulation pump, and biochemical index of the ultrafiltration outlet. Output data: anaerobic inlet flow rate exceeding the secondary denitrification flow rate, and secondary nitrification Roots blower outlet flow rate.

[0043] Finally, it is subdivided into an intelligent control main model and a water quality prediction sub-model. The intelligent control main model includes the whole system operation control, which is divided into each sub-process control model (treatment equipment control parameter prediction model), namely, the regulating tank control model, the anaerobic control model, the primary biochemical system control model, and the secondary biochemical MBR system control model. Nanofiltration and reverse osmosis control are realized by an automatic control system. Each sub-process system control model uses machine learning methods to output the load control actuator actions (pumps and fans, valves) of each sub-process system based on the strongly correlated online detection data, manual detection data, and manual setting data input for leachate treatment.

[0044] Step 103, based on the control parameter data for the treatment equipment predicted by each treatment link, with the water quality of the treated leachate discharged after the secondary biochemical treatment link meeting the standard as a constraint condition, with the minimum energy consumption per ton of treatment and the maximum water output efficiency in the leachate treatment process as the goal, optimize the target control parameter data for the treatment equipment in each treatment link, and control the treatment equipment to treat the target treatment leachate based on the target control parameter data obtained by optimization.

[0045] Next, based on the control parameter data predicted for the treatment equipment in each treatment link, the water quality of the treated leachate discharged after the secondary biochemical treatment link is up to standard as a constraint condition, and the target is to minimize the ton treatment energy consumption and maximize the water effluent efficiency in the leachate treatment process, and optimize the target control parameter data for the treatment equipment in each treatment link, and control the treatment equipment to treat the target treated leachate based on the target control parameter data obtained by optimization. Specifically, the water quality indicators that the treated leachate needs to achieve can be clarified according to relevant environmental protection regulations and emission standards (such as BOD5≤30mg / L, COD≤100mg / L, SS≤30mg / L, TN≤15mg / L, TP≤3mg / L, etc.). Next, analyze the energy consumption sources of each treatment link in the leachate treatment process, such as aeration, pumping, membrane separation, etc. Next, consider factors such as treatment time and treatment volume to evaluate the water effluent efficiency. Next, according to the characteristics of the treatment equipment and previous operating experience, the reasonable range (that is, the preset normal control parameter data range) of the control parameters (such as aeration volume, recirculation ratio, membrane flux, etc.) of the treatment equipment in each treatment link is set. Under the premise of meeting the water quality standards, determine the minimum treatment energy consumption per ton and maximize the water outlet efficiency. Finally, the optimization algorithm is used for optimization: intelligent optimization algorithms such as genetic algorithms and particle swarm algorithms can be used to search for the optimal solution within a given parameter range. By simulating the treatment effect, energy consumption and water outlet efficiency under different parameter combinations, find the parameter combination that meets the constraints and has the optimal objective function. In particular, the verification and optimization results can also be carried out, that is, adjustments are made according to the parameter combination obtained by optimization, and the treatment effect, energy consumption and water outlet efficiency are monitored. According to 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 by optimization, the control strategy of the leachate treatment equipment is formulated. Through the automated control system, precise control of the treatment equipment is achieved to ensure stable and efficient treatment effects.

[0046] By applying the technical solution of this embodiment, it is possible to optimize the target control parameter data for the treatment equipment in each treatment link, and control the treatment equipment based on these data to treat the target leachate, thereby achieving the goals of minimizing energy consumption and maximizing water output efficiency, while ensuring that the treated water quality meets the standards. In the field of leachate treatment generated by domestic waste, data-driven, multi-dimensional intelligent control combined with meteorological information, process mechanism and expert experience is used to treat the leachate, which can achieve cost reduction and efficiency improvement.

[0047] Further, as a refinement and expansion of the specific implementation of the above embodiment, in order 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, according to the processing sequence of each processing link in the leachate treatment process, the input operating condition data of the target leachate when it enters each processing link is collected in sequence, wherein the leachate treatment process includes a regulating tank treatment link, an anaerobic system treatment link, a primary biochemical treatment link and a secondary biochemical treatment link which are performed in sequence.

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

[0050] Step 202, for any processing link in the leachate treatment process, obtain the historical input operating condition data of the processing link, and the historical control parameter data of the processing equipment corresponding to the historical input operating condition data.

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

[0052] Step 204: train multiple target training models based on the control model training data set, and calculate the mean absolute error index value, mean square error index value and F1 score index value of any target training model, wherein the target training model includes a random forest model and a decision tree model.

[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 various performance evaluation indicators, 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 processing equipment control parameter prediction model, wherein the performance evaluation indicators include the mean absolute error index, the mean square error index and the F1 score index.

[0054] Then, the model is trained based on historical data. At the same time, manual operation can also be performed, that is, real-time data is collected again into the operation knowledge base and the learning rule base, and the intelligent control main model and the water quality prediction sub-model are updated in real time. Specifically, for any processing link in the leachate treatment process, the historical input working condition data of the processing link and the historical control parameter data of the processing equipment corresponding to the historical input working condition data are obtained, and the control model training data set is constructed based on the historical input working condition data and the historical control parameter data. Based on the control model training data set, multiple target training models are trained respectively, and for any target training model, the mean absolute error index value, mean square error index value and F1 score index value of the target training model are calculated, wherein the target training model includes a random forest model and a decision tree model. Based on the mean absolute error index value, mean square error index value, F1 score index value and the preset evaluation weights of various performance evaluation indicators (for example, 0.4, 0.3, and 0.3 respectively), the comprehensive performance evaluation value of the target training model is obtained, and the target training model corresponding to the maximum comprehensive performance evaluation value is determined as the processing equipment control parameter prediction model.

[0055] For example, the training process of the anaerobic control model is as follows: first, conduct a correlation analysis on the detection data (input operating condition data), combine the process mechanism, determine the strongly correlated data (meteorological data, anaerobic exceedance flow, anaerobic tank pressure, anaerobic inlet water quality index, anaerobic outlet water quality index, anaerobic tank temperature, ambient temperature and pressure, anaerobic circulation pump flow, anaerobic inlet pump flow), perform data preprocessing, input the machine learning model (such as random forest model) for training, and verify the model effectiveness based on the root mean square error RMSE and the determination coefficient R2. The machine learning models of each sub-process system constitute the main intelligent control model for leachate treatment, and output control instructions for the system anaerobic pump, anaerobic circulation pump, Roots blower and exceedance electric valve, etc., to ultimately ensure that the leachate treatment system meets the emission standards. Among them, during operation, the outlet water quality index of the sub-process system should be manually set input.

[0056] In particular, a water inlet condition library can also be established based on historical data, including but not limited to water quality, water quantity, and meteorological factors. According to the data in the water inlet condition library, it can be divided into multiple types of conditions, and multiple groups of water inlet condition data corresponding to each type of condition, or water inlet condition data range. At the same time, weight attributes are preliminarily assigned to the same type of condition data according to expert experience. Each type of condition data also corresponds to one or more groups of control parameters of the treatment equipment, so that when the control parameter data for the treatment equipment corresponding to the input condition data of the treatment link is predicted based on the treatment equipment control parameter prediction model corresponding to the treatment link, the input condition data can be matched with the pre-set condition type data to obtain the control parameter data.

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

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

[0059] Optionally, in step 206, based on the control parameter prediction model of the processing equipment corresponding to the processing link, the control parameter data for the processing equipment corresponding to the input working condition data of the processing link is predicted, for any processing link, such as Figure 4 As shown, specifically including:

[0060] Step 2061, the biochemical index value in the input working condition data corresponding to the treatment link is obtained by periodically integrating the water quality of the target treatment leachate entering the treatment link.

[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 treated leachate after being treated by the treatment link, wherein the water quality prediction model is established based on a random forest model, and the random forest model is trained based on a water quality model training data set, and the water quality model training data set 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 indicator values.

[0062] Specifically, the water quality index data considers the periodic integration of water treatment, and the dissolved oxygen and Oxide-Reduction Potential (ORP) online detection data considers the changes and change rates of water treatment.

[0063] The water quality prediction sub-model includes the prediction of water quality indicators of each sub-process system, namely, the water quality prediction model of the regulating tank, the water quality prediction model of the anaerobic system, the water quality prediction model of the primary biochemical system, and the water quality prediction model of the secondary biochemical MBR system. Each sub-process system water quality prediction model uses machine learning methods to output the drainage water quality indicators of each sub-process system based on the input of strongly correlated online detection data and manual detection data. The model validity is verified by the root mean square error and the coefficient of determination. Among them, during operation, the water quality prediction module of each sub-process system outputs the inlet water quality indicator of the next-level sub-process system.

[0064] Step 2063, when the processing link is the regulating tank processing link, if the control parameter data for the processing equipment corresponding to the input operating condition data of the processing link is predicted based on the processing equipment control parameter prediction model corresponding to the processing link, the processing equipment control parameter prediction model fails to predict the control parameter data corresponding to the input operating condition data, obtains the unpredicted sudden input operating condition data, and the newly added control parameter data for the processing equipment to deal with the sudden input operating condition data.

[0065] Step 2064, adding the sudden input operating condition data and the newly added control parameter data to the control model training data set of the processing equipment control parameter prediction model corresponding to the regulation pool processing link, and retraining the processing equipment control parameter prediction model based on the added control model training data set.

[0066] Therefore, when the water inflow conditions of the regulating pool change suddenly, and there is no such condition in the original database, it is necessary to update the database and relearn the optimization model. For example, the biochemical index changes beyond the range, the water volume exceeds the range, etc., in order to improve the subsequent prediction accuracy of the model.

[0067] Step 207, based on the control parameter data for the treatment equipment predicted by each treatment link, with the water quality of the treated leachate discharged after the secondary biochemical treatment link meeting the standard as a constraint condition, with the minimum energy consumption per ton of treatment and the maximum water output efficiency in the leachate treatment process as the goal, optimize the target control parameter data for the treatment equipment in each treatment link, and control the treatment equipment to treat the target treatment leachate based on the target control parameter data obtained by optimization.

[0068] Step 208, if the predicted control parameter data exceeds the preset normal control parameter data range of the processing device, a processing device alarm message is generated based on the error control parameter data exceeding 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 processing device alarm information to a preset receiving terminal.

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

[0071] In particular, an alarm mechanism can also be set up, for example, for a bioreactor in a leachate treatment plant, which controls the aeration volume to maintain appropriate microbial activity, thereby effectively degrading organic matter. The bioreactor has a set of preset normal control parameter data ranges, such as the aeration volume should be between 100-200 cubic meters per hour. Through the monitoring system and data analysis tools, it can be predicted that in the future, in order to achieve a specific effluent water quality standard, the aeration volume of the bioreactor needs to be adjusted to 250 cubic meters per hour. At this time, when the predicted aeration volume of 250 cubic meters per hour exceeds the preset normal control parameter data range of the bioreactor (100-200 cubic meters per hour), the system will identify a potential anomaly. Based on the exceeded error control parameter data (aeration volume 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 a treatment equipment alarm message. This message may include: The aeration volume of the biological reactor is abnormal, and the predicted value of 250 cubic meters per hour exceeds the normal range by 100-200 cubic meters per hour. Please check and take measures immediately. Then, the system will send this alarm message to the preset receiving terminal, such as the monitoring center of the treatment plant, the mobile phone or email of the operation and maintenance personnel. In this way, relevant personnel can receive the alarm immediately and take corresponding countermeasures, such as adjusting process parameters, checking equipment status or launching emergency plans. To this end, it can help operation and maintenance personnel to promptly discover and deal with potential abnormal situations, and prevent problems such as substandard effluent water quality or increased energy consumption caused by equipment failure or improper parameter settings. At the same time, through real-time monitoring and early warning, the operating efficiency and stability of the treatment plant can be improved, and the operation and maintenance costs and environmental risks can be reduced.

[0072] By applying the technical solution of this embodiment, for example Figure 5 As shown, decisions are made through a comprehensive model of machine learning algorithms to control the flow of pumps and fans, and the action of electric valves to control the leachate discharge to meet the discharge standards. The detection data is processed in real time to update the optimization model. This focuses on the multi-dimensional leachate treatment intelligent control of the entire system, and is divided into an intelligent control main model and a water quality prediction sub-model. Combined with the expert knowledge base and machine learning model, it can effectively solve the problems in the industry that the leachate treatment effect is unstable depending on the experience and technical level of the operators, and the workload of manual inspection is large.

[0073] Further, as Figure 1 The specific implementation of the method, the embodiment of the present application provides a leachate treatment device, such as Figure 6 As shown, the device comprises:

[0074] The working condition data acquisition module 301 is used to collect the input working condition data of the target leachate when it enters each treatment link according to the treatment sequence of each treatment link in the leachate treatment process, wherein the leachate treatment process includes the regulating tank treatment link, the anaerobic system treatment link, the primary biochemical treatment link and the secondary biochemical treatment link which are carried out in sequence according to the treatment sequence;

[0075] The control parameter prediction module 302 is used to predict the control parameter data for the processing equipment corresponding to the input working condition data of any processing link in the leachate treatment process based on the control parameter prediction model of the processing equipment corresponding to the processing link;

[0076] The leachate optimization treatment module 303 is used to optimize the target control parameter data for the treatment equipment in each treatment link based on the control parameter data for the treatment equipment predicted by each treatment link, with the water quality of the treated leachate discharged after the secondary biochemical treatment link meeting the standard as a constraint condition, and with the minimum energy consumption per ton of treatment and the maximum water output efficiency in the leachate treatment process as the goal, and control the treatment equipment to treat the target treatment leachate based on the target control parameter data obtained by optimization.

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

[0078] When the treatment link is the regulating tank treatment link, the input working condition data includes the ambient temperature of the regulating tank, the biochemical index value and water volume of the target treatment leachate entering the regulating tank treatment link, and the control parameter data includes the anaerobic pump water output;

[0079] When the treatment link is an anaerobic system treatment link, the input operating condition data include the anaerobic inlet flow rate exceeding to anoxic flow rate, the anaerobic tank pressure, the outdoor temperature of the anaerobic system treatment link, the anaerobic tank temperature, the anaerobic inlet flow rate exceeding to secondary denitrification flow rate, the biochemical index value of the target treatment leachate entering the anaerobic system treatment link, and the biochemical index value of the target treatment leachate discharged after being treated by the anaerobic system treatment link, and the control parameter data include the flow rate from the anaerobic circulation pump outlet to the anaerobic tank and the anaerobic inlet pump outlet flow rate;

[0080] When the treatment link is a primary biochemical treatment link, the input operating condition data include the biochemical index value of the target treatment leachate discharged after being treated by the anaerobic system treatment link, the biochemical index value of the target treatment leachate discharged after being treated by the primary biochemical treatment link, the redox potential of the primary denitrification tank, the outdoor temperature of the primary biochemical treatment link, the temperature of the primary nitrification tank, the dissolved oxygen content of the primary nitrification tank, the biochemical index value of the target treatment leachate entering the regulating tank treatment link, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index value of the ultrafiltration outlet. The control parameter data include the anaerobic inlet flow rate exceeding the anoxic flow rate and the Roots blower outlet flow rate;

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

[0082] The biochemical index value includes 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 further used to:

[0084] For any treatment link, the biochemical indicator value in the input operating condition data corresponding to the treatment link is obtained by periodically integrating the water quality of the target treated leachate entering the treatment link, 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 treated leachate after being treated by the treatment link, wherein the water quality prediction model is established based on a random forest model, and the random forest model is trained based on a water quality model training data set, and the water quality model training data set 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 the biochemical indicator value.

[0085] Furthermore, the present application provides another leachate treatment device, such as Figure 7 As shown, the device comprises:

[0086] The working condition data acquisition module 401 is used to collect the input working condition data of the target leachate when it enters each treatment link according to the treatment sequence of each treatment link in the leachate treatment process, wherein the leachate treatment process includes the regulating tank treatment link, the anaerobic system treatment link, the primary biochemical treatment link and the secondary biochemical treatment link which are performed in sequence according to the treatment sequence;

[0087] A control parameter prediction module 402 is used to predict control parameter data for a processing device corresponding to the input operating condition data of any processing link in the leachate treatment process based on a control parameter prediction model of the processing device corresponding to the processing link;

[0088] The leachate optimization treatment module 403 is used to optimize the target control parameter data for the treatment equipment in each treatment link based on the control parameter data for the treatment equipment predicted by each treatment link, with the water quality of the treated leachate discharged after the secondary biochemical treatment link reaching the standard as a constraint condition, with the minimum per-ton treatment energy consumption and the maximum water output efficiency in the leachate treatment process as the goal, and control the treatment equipment to treat the target treatment leachate based on the target control parameter data obtained by optimization;

[0089] The device execution alarm module 404 is used for generating a processing device alarm message based on the error control parameter data exceeding 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 sending the processing device alarm message to a preset receiving terminal;

[0090] The control model training module 405 is used to obtain the historical input operating condition data of the processing link, and the historical control parameter data of the processing equipment corresponding to the historical input operating condition data; construct a control model training data set based on the historical input operating condition data and the historical control parameter data; train multiple target training models based on the control model training data set, wherein the target training models include a random forest model and a decision tree model; 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 processing equipment control parameter prediction model, wherein the performance evaluation indicators include a mean absolute error indicator, a mean square error indicator and an F1 score indicator.

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

[0092] When the treatment link is the regulating tank treatment link, the input working condition data includes the ambient temperature of the regulating tank, the biochemical index value and water volume of the target treatment leachate entering the regulating tank treatment link, and the control parameter data includes the anaerobic pump water output;

[0093] When the treatment link is an anaerobic system treatment link, the input operating condition data include the anaerobic inlet flow rate exceeding to anoxic flow rate, the anaerobic tank pressure, the outdoor temperature of the anaerobic system treatment link, the anaerobic tank temperature, the anaerobic inlet flow rate exceeding to secondary denitrification flow rate, the biochemical index value of the target treatment leachate entering the anaerobic system treatment link, and the biochemical index value of the target treatment leachate discharged after being treated by the anaerobic system treatment link, and the control parameter data include the flow rate from the anaerobic circulation pump outlet to the anaerobic tank and the anaerobic inlet pump outlet flow rate;

[0094] When the treatment link is a primary biochemical treatment link, the input operating condition data include the biochemical index value of the target treatment leachate discharged after being treated by the anaerobic system treatment link, the biochemical index value of the target treatment leachate discharged after being treated by the primary biochemical treatment link, the redox potential of the primary denitrification tank, the outdoor temperature of the primary biochemical treatment link, the temperature of the primary nitrification tank, the dissolved oxygen content of the primary nitrification tank, the biochemical index value of the target treatment leachate entering the regulating tank treatment link, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index value of the ultrafiltration outlet. The control parameter data include the anaerobic inlet flow rate exceeding the anoxic flow rate and the Roots blower outlet flow rate;

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

[0096] The biochemical index value includes 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 further used to:

[0098] For any treatment link, the biochemical indicator value in the input operating condition data corresponding to the treatment link is obtained by periodically integrating the water quality of the target treated leachate entering the treatment link, 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 treated leachate after being treated by the treatment link, wherein the water quality prediction model is established based on a random forest model, and the random forest model is trained based on a water quality model training data set, and the water quality model training data set 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 the biochemical indicator value.

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

[0100] For any target training model, calculate the mean absolute error index value, mean square error index value and F1 score index value of the target training model;

[0101] 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 various performance evaluation indicators, a comprehensive performance evaluation value of the target training model is obtained.

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

[0103] When the processing link is a regulating tank processing link, if the control parameter data for the processing equipment corresponding to the input operating condition data of the processing link is predicted based on the processing equipment control parameter prediction model corresponding to the processing link, and the processing equipment control parameter prediction model fails to predict the control parameter data corresponding to the input operating condition data, the unpredicted sudden input operating condition data and the newly added 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 data set of the processing equipment control parameter prediction model corresponding to the regulation pool processing link, and the processing equipment control parameter prediction model is retrained based on the added control model training data set.

[0105] It should be noted that for other corresponding descriptions of the functional units involved in the leachate treatment device provided in the embodiment of the present application, reference can be made to Figures 1 to 4 The corresponding description in the method will not be repeated here.

[0106] Based on the above Figures 1 to 4 The method shown in the embodiment of the present application is accordingly provided with a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned Figures 1 to 4 The leachate treatment method shown.

[0107] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0108] Based on the above Figures 1 to 4 The method shown, and Figure 6 , Figure 7 In order to achieve the above-mentioned purpose, the embodiment of the present application further provides a computer device, which can be a personal computer, a server, a network device, etc. The computer device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figures 1 to 4 The leachate treatment method shown.

[0109] Optionally, the computer device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display screen (Displ ay), an input unit such as a keyboard (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, a WI-FI interface), etc.

[0110] Those skilled in the art will appreciate that the computer device structure provided in this embodiment does not limit the computer device, and may include more or fewer components, or a combination of certain components, or 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 saves the hardware and software resources of the computer device, and supports the operation of information processing programs and other software and / or programs. The network communication module is used to realize communication between the components inside the storage medium, and communication with other hardware and software in the physical device.

[0112] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware platforms, or by hardware: according to the processing order of each processing link in the leachate treatment process, the input operating condition data of the target leachate when entering each processing link is collected in sequence; based on the processing equipment control parameter prediction model corresponding to the processing link, the control parameter data for the processing equipment corresponding to the input operating condition data of the processing link is predicted; based on the control parameter data, with the water quality of the treated leachate discharged after the secondary biochemical treatment link meeting the standard as the constraint condition, with the minimum energy consumption per ton of treatment and the highest water output efficiency in the leachate treatment process as the goal, the target control parameter data for the processing equipment of each processing link is obtained by optimization, and the target leachate is processed. Based on the operating condition perception - intelligent control - autonomous optimization operation big data, machine learning methods are used to intelligently control the processing system, and ultimately achieve cost reduction and efficiency improvement.

[0113] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the description of the implementation scenario, or can be changed accordingly and located in one or more devices different from the present implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple submodules.

[0114] The above serial numbers of this application are only for description and do not represent the advantages and disadvantages of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of this application, but this application is not limited to them, and any changes that can be thought of by technicians in this field should fall within the scope of protection of this application.

Claims

1. A leachate treatment method, characterized in that: The method comprises: According to the processing sequence of each treatment link in the leachate treatment process, the input operating condition data of the target leachate when entering each treatment link is collected in sequence, wherein the leachate treatment process includes a regulating tank treatment link, an anaerobic system treatment link, a primary biochemical treatment link and a secondary biochemical treatment link which are performed in sequence; For any treatment link in the leachate treatment process, based on the treatment equipment control parameter prediction model corresponding to the treatment link, predict the control parameter data for the treatment equipment corresponding to the input working condition data of the treatment link; Based on the control parameter data for the treatment equipment predicted by each treatment link, with the water quality compliance of the treated leachate discharged after the secondary biochemical treatment link as the constraint condition, and with the minimum energy consumption per ton of treatment and the maximum water output efficiency in the leachate treatment process as the goal, the target control parameter data for the treatment equipment in each treatment link is obtained by optimization, and the treatment equipment is controlled to treat the target treatment leachate based on the target control parameter data obtained by optimization.

2. The method according to claim 1, characterized in that When the treatment link is the regulating tank treatment link, the input working condition data includes the ambient temperature of the regulating tank, the biochemical index value and water volume of the target treatment leachate entering the regulating tank treatment link, and the control parameter data includes the anaerobic pump water output; When the treatment link is an anaerobic system treatment link, the input operating condition data include the anaerobic inlet flow rate exceeding to anoxic flow rate, the anaerobic tank pressure, the outdoor temperature of the anaerobic system treatment link, the anaerobic tank temperature, the anaerobic inlet flow rate exceeding to secondary denitrification flow rate, the biochemical index value of the target treatment leachate entering the anaerobic system treatment link, and the biochemical index value of the target treatment leachate discharged after being treated by the anaerobic system treatment link, and the control parameter data include the flow rate from the anaerobic circulation pump outlet to the anaerobic tank and the anaerobic inlet pump outlet flow rate; When the treatment link is a primary biochemical treatment link, the input operating condition data include the biochemical index value of the target treatment leachate discharged after being treated by the anaerobic system treatment link, the biochemical index value of the target treatment leachate discharged after being treated by the primary biochemical treatment link, the redox potential of the primary denitrification tank, the outdoor temperature of the primary biochemical treatment link, the temperature of the primary nitrification tank, the dissolved oxygen content of the primary nitrification tank, the biochemical index value of the target treatment leachate entering the regulating tank treatment link, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index value of the ultrafiltration outlet. The control parameter data include the anaerobic inlet flow rate exceeding the anoxic flow rate and the Roots blower outlet flow rate; When the treatment link is a secondary biochemical treatment link, the input operating condition data includes the biochemical index value of the target treatment leachate discharged after being treated by the primary biochemical treatment link, the biochemical index value of the target treatment leachate discharged after being treated by the secondary biochemical treatment link, the outdoor temperature of the secondary biochemical treatment link, the dissolved oxygen content of the secondary nitrification tank, the biochemical index value of the target treatment leachate in the regulating tank treatment link, the flow rate and frequency of the tubular membrane circulation pump, and the biochemical index value of the ultrafiltration outlet. The control parameter data includes the anaerobic inlet flow rate exceeding the secondary denitrification flow rate and the secondary nitrification Roots blower outlet flow rate; The biochemical index value includes at least one of biochemical oxygen demand, chemical oxygen demand, dissolved oxygen and total organic carbon.

3. The method according to claim 2, characterized in that For any treatment link, the biochemical indicator value in the input operating condition data corresponding to the treatment link is obtained by periodically integrating the water quality of the target treated leachate entering the treatment link, 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 treated leachate after being treated by the treatment link, wherein the water quality prediction model is established based on a random forest model, and the random forest model is trained based on a water quality model training data set, and the water quality model training data set 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 the biochemical indicator value.

4. The method according to claim 1, characterized in that: After predicting the control parameter data for the processing equipment corresponding to the input working condition data of the processing link based on the processing equipment control parameter prediction model corresponding to the processing link, the method further includes: If the predicted control parameter data exceeds the preset normal control parameter data range of the processing device, generating processing device alarm information based on the error control parameter data exceeding the preset normal control parameter data range, the type of the processing device, and the preset normal control parameter data range; The processing device alarm information is sent to a preset receiving terminal.

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

6. The method according to claim 5, characterized in that The comprehensive performance evaluation values ​​of each target training model under multiple performance evaluation indicators are calculated respectively, including: For any target training model, calculate the mean absolute error index value, mean square error index value and F1 score index value of the target training model; 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 various performance evaluation indicators, a comprehensive performance evaluation value of the target training model is obtained.

7. The method according to claim 1, characterized in that The method further comprises: When the processing link is a regulating tank processing link, if the control parameter data for the processing equipment corresponding to the input operating condition data of the processing link is predicted based on the processing equipment control parameter prediction model corresponding to the processing link, and the processing equipment control parameter prediction model fails to predict the control parameter data corresponding to the input operating condition data, the unpredicted sudden input operating condition data and the newly added 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 data set of the processing equipment control parameter prediction model corresponding to the regulation pool processing link, and the processing equipment control parameter prediction model is retrained based on the added control model training data set.

8. A leachate treatment device, characterized in that: The device comprises: The working condition data acquisition module is used to collect the input working condition data of the target leachate when it enters each treatment link according to the treatment order of each treatment link in the leachate treatment process, wherein the leachate treatment process includes the regulating tank treatment link, the anaerobic system treatment link, the primary biochemical treatment link and the secondary biochemical treatment link which are carried out in sequence according to the treatment order; A control parameter prediction module is used to predict the control parameter data for the processing equipment corresponding to the input working condition data of any processing link in the leachate treatment process based on the control parameter prediction model of the processing equipment corresponding to the processing link; The leachate optimization treatment module is used to optimize the target control parameter data for the treatment equipment in each treatment link based on the control parameter data for the treatment equipment predicted by each treatment link, with the water quality of the treated leachate discharged after the secondary biochemical treatment link meeting the standard as a constraint condition, and with the minimum energy consumption per ton of treatment and the maximum water output efficiency in the leachate treatment process as the goal, and control the treatment equipment to treat the target treatment leachate based on the target control parameter data obtained by optimization.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for treating leachate according to any one of claims 1 to 7 is implemented.

10. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method for treating leachate according to any one of claims 1 to 7 is implemented.

Images