An aeration intelligent control method, device, equipment and medium for reconstituted tobacco leaf

Abstract

The application discloses an aeration intelligent control method, device, equipment and medium for reconstituted tobacco, and relates to the technical field of computers, which comprises the following steps: acquiring index parameters of an aeration system, analyzing the index parameters, and obtaining operation parameters; identifying, optimizing and verifying the analysis of a benchmark simulation model based on aeration characteristics and the operation parameters, obtaining a target benchmark simulation model, and constructing a benchmark simulation platform; defining state space parameters, action space parameters and reward functions of a sewage treatment system, and simulating actual operation conditions by using the benchmark simulation platform to obtain simulated operation conditions; verifying the simulated operation conditions and real-time optimizing strategies to obtain optimal control strategies, which are combined with a hardware platform of the aeration system to realize intelligent control of the aeration system according to the optimal control strategies. The application can improve the energy utilization rate of the aeration system, realize intelligent control of the aeration of reconstituted tobacco, reduce the complexity of aeration control, and improve the stability and reliability of the biological pool aeration system.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to an intelligent control method, device, equipment and medium for aeration of reconstituted tobacco leaves. Background Technology

[0002] Currently, wastewater treatment plants generally suffer from drawbacks such as high aeration energy consumption, large fluctuations in effluent quality, and extensive control methods. To meet increasingly stringent water quality standards, wastewater treatment plants often maintain a high aeration rate. The dissolved oxygen produced by excessive aeration is not utilized by microorganisms but is converted into oxygen and escapes into the atmosphere, resulting in significant energy waste. Furthermore, dissolved oxygen concentration is affected by many factors such as influent flow rate, influent composition, and concentration fluctuations. Using a single aeration rate not only wastes energy but also easily leads to substandard effluent quality when the influent pollutant concentration is high.

[0003] As can be seen from the above, how to improve the energy utilization rate of the aeration system, realize intelligent control of aeration in reconstituted tobacco leaves, reduce the complexity of aeration control, and improve the stability and reliability of the biological tank aeration system are problems to be solved in this field. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide an intelligent aeration control method, device, equipment, and medium for reconstituted tobacco, which can improve the energy utilization rate of the aeration system, realize intelligent aeration control for reconstituted tobacco, reduce the complexity of aeration control, and improve the stability and reliability of the biological tank aeration system. The specific solution is as follows:

[0005] In a first aspect, this application discloses an intelligent aeration control method for reconstituted tobacco leaves, applied to an intelligent operation and maintenance system software platform for aeration systems, comprising:

[0006] Obtain the index parameters of the aeration system and analyze the index parameters to obtain the operating parameters;

[0007] Based on the aeration characteristics of the aeration system and the operating parameters, the preset benchmark simulation model is identified, optimized and verified to obtain the target benchmark simulation model, and the benchmark simulation platform is constructed using the target benchmark simulation model.

[0008] Define the state space parameters, action space parameters, and reward function of the wastewater treatment system for recycled tobacco. Based on the state space parameters, action space parameters, and reward function, and using the benchmark simulation platform, simulate the actual operation to obtain the simulated operation.

[0009] The simulated operation is verified and the strategy is optimized in real time to obtain the optimal control strategy. This strategy is then combined with the hardware platform of the aeration system, and intelligent control of the aeration system is achieved according to the optimal control strategy.

[0010] Optionally, the step of acquiring the index parameters of the aeration system and analyzing the index parameters to obtain operating parameters includes:

[0011] The index parameters of the aeration system are obtained from on-site measurements and collections. Computational fluid dynamics analysis is performed on the dissolved oxygen, water temperature, mixed liquor suspended solids concentration, chemical oxygen demand, and ammonia nitrogen content among the index parameters to obtain the operating parameters.

[0012] Optionally, after obtaining the operating parameters, the process further includes:

[0013] The actual oxygen supply and theoretical oxygen demand of the aeration system are calculated based on the operating parameters, and the supply and demand balance of the aeration system is evaluated based on the actual oxygen supply and theoretical oxygen demand.

[0014] The energy-saving potential of the aeration system is analyzed based on the preset supply and demand balance principle.

[0015] Optionally, the step of identifying, optimizing, and verifying the preset benchmark simulation model based on the aeration characteristics of the aeration system and the operating parameters to obtain the target benchmark simulation model includes:

[0016] The initial baseline simulation model is simplified and modified to obtain the simplified and modified initial baseline simulation model;

[0017] Based on the aeration characteristics and operating parameters of the aeration system, the simplified and modified initial benchmark simulation model is identified, optimized, and verified using the least squares method, genetic algorithm, particle swarm optimization algorithm, and Q-learning algorithm to obtain the target benchmark simulation model.

[0018] Optionally, the state-space parameters, action-space parameters, and reward function of the wastewater treatment system for reconstituted tobacco include:

[0019] Define the state-space parameters of the wastewater treatment system for recycled tobacco leaves; the state-space parameters include output variables, input variables, and environmental variables;

[0020] Define the action space parameters of the wastewater treatment system; the action space parameters include various control strategies and decision variables.

[0021] Based on the treatment efficiency, energy consumption, and wastewater discharge quality of the wastewater treatment system, and with the objectives of minimizing energy consumption, maximizing treatment efficiency, and reducing wastewater discharge quality, a reward function for the wastewater treatment system is defined.

[0022] Optionally, the hardware platform of the aeration system includes a blower, air duct, aerator, reaction tank, communication interface, sensors, actuators, and communication module components; the sensors include dissolved oxygen sensor, temperature sensor, and pH sensor.

[0023] Optionally, the step of verifying the simulated operation and optimizing the strategy in real time to obtain the optimal control strategy, combining it with the hardware platform of the aeration system, and realizing intelligent control of the aeration system according to the optimal control strategy includes:

[0024] Deep reinforcement learning algorithms are used to verify the simulated operation and optimize the strategy in real time to obtain the optimal control strategy;

[0025] By combining with the hardware platform of the aeration system and adjusting the operating parameters of the aeration system in real time according to the optimal control strategy, intelligent control of the aeration system can be achieved.

[0026] Secondly, this application discloses an intelligent aeration control device for reconstituted tobacco leaves, applied to an intelligent operation and maintenance system software platform for aeration systems, comprising:

[0027] The parameter analysis module is used to acquire the index parameters of the aeration system and analyze the index parameters to obtain the operating parameters.

[0028] The model and platform construction module is used to identify, optimize and verify the preset benchmark simulation model based on the aeration characteristics and operating parameters of the aeration system to obtain the target benchmark simulation model, and to construct the benchmark simulation platform using the target benchmark simulation model.

[0029] The simulation module is used to define the state space parameters, action space parameters, and reward function of the wastewater treatment system for reconstituted tobacco leaves. Based on the state space parameters, action space parameters, and reward function, the module uses the benchmark simulation platform to simulate the actual operation to obtain the simulated operation.

[0030] The intelligent control module is used to verify the simulated operation and optimize the strategy in real time to obtain the optimal control strategy. It is combined with the hardware platform of the aeration system and realizes intelligent control of the aeration system according to the optimal control strategy.

[0031] Thirdly, this application discloses an electronic device, including:

[0032] Memory, used to store computer programs;

[0033] A processor is used to execute the computer program to implement the aforementioned intelligent aeration control method for reconstituted tobacco leaves.

[0034] Fourthly, this application discloses a computer storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned disclosed intelligent aeration control method for reconstituted tobacco leaves.

[0035] As can be seen, this application provides an intelligent control method for aeration of reconstituted tobacco leaves, including acquiring index parameters of the aeration system and analyzing the index parameters to obtain operating parameters; identifying, optimizing, and verifying a preset benchmark simulation model based on the aeration characteristics of the aeration system and the operating parameters to obtain a target benchmark simulation model, and constructing a benchmark simulation platform using the target benchmark simulation model; defining state space parameters, action space parameters, and reward function of the wastewater treatment system for reconstituted tobacco leaves, simulating the actual operating conditions based on the state space parameters, action space parameters, and reward function, and using the benchmark simulation platform to obtain simulated operating conditions; verifying the simulated operating conditions and optimizing the strategy in real time to obtain the optimal control strategy, combining it with the hardware platform of the aeration system, and realizing intelligent control of the aeration system according to the optimal control strategy. This application applies to an intelligent operation and maintenance system software platform for aeration systems. It utilizes aeration characteristics and operating parameters to identify, optimize, and verify a benchmark simulation model, thereby constructing a target benchmark simulation model and a benchmark simulation platform. This reduces the need for manual intervention and lowers operational difficulty. Considering the influence of multiple factors, it defines the state-space parameters, action-space parameters, and reward function of the wastewater treatment system for recycled tobacco. Then, it simulates the actual operation to obtain the simulated operating conditions. The simulated operating conditions are verified, and the strategy is optimized in real time to obtain the optimal control strategy, reducing energy waste. Combined with the hardware platform of the aeration system, the operating parameters of the aeration system are adjusted in real time according to the optimal control strategy, improving wastewater treatment efficiency, reducing the need for manual intervention, lowering operational difficulty, and improving the stability and reliability of the biological tank aeration system, achieving efficient and energy-saving intelligent aeration control. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0037] Figure 1 This is a flowchart of an intelligent aeration control method for reconstituted tobacco leaves disclosed in this application;

[0038] Figure 2 This is a diagram of the visualization module interface of an intelligent operation and maintenance system disclosed in this application;

[0039] Figure 3 This is a structural diagram of an intelligent aeration control system disclosed in this application;

[0040] Figure 4 This is a schematic diagram of a gas volume calculation module disclosed in this application;

[0041] Figure 5 This application discloses a visual diagram of the status of a blower.

[0042] Figure 6 This is a schematic diagram of the aeration intelligent control device for reconstituted tobacco disclosed in this application;

[0043] Figure 7 This application provides a structural diagram of an electronic device. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Currently, wastewater treatment plants generally suffer from drawbacks such as high aeration energy consumption, large fluctuations in effluent quality, and extensive control methods. To meet increasingly stringent water quality standards, wastewater treatment plants often maintain a high aeration rate. The dissolved oxygen produced by excessive aeration is not utilized by microorganisms but is converted into oxygen and escapes into the atmosphere, resulting in significant energy waste. Furthermore, dissolved oxygen concentration is affected by many factors such as influent flow rate, influent composition, and concentration fluctuations. Using a single aeration rate not only wastes energy but also easily leads to substandard effluent quality when the influent pollutant concentration is high. Therefore, improving the energy utilization rate of aeration systems, achieving intelligent control of aeration in reconstituted tobacco, reducing the complexity of aeration control, and improving the stability and reliability of biological tank aeration systems are problems that need to be solved in this field.

[0046] See Figure 1 As shown, this invention discloses an intelligent aeration control method for reconstituted tobacco leaves, applied to an intelligent operation and maintenance system software platform for aeration systems, specifically including:

[0047] Step S11: Obtain the index parameters of the aeration system and analyze the index parameters to obtain the operating parameters.

[0048] In this embodiment, the index parameters of the aeration system are obtained from on-site measurements and collections, and computational fluid dynamics analysis is performed on the dissolved oxygen, water temperature, mixed liquor suspended solids concentration, chemical oxygen demand, and ammonia nitrogen content among the index parameters to obtain the operating parameters.

[0049] In addition, after obtaining the operating parameters, the process also includes: calculating the actual oxygen supply and theoretical oxygen demand of the aeration system based on the operating parameters; evaluating the supply-demand balance of the aeration system based on the actual oxygen supply and theoretical oxygen demand; and analyzing the energy-saving potential of the aeration system based on a preset supply-demand balance principle.

[0050] This application applies to an intelligent operation and maintenance system software platform for aeration systems. The aeration system of the wastewater treatment plant for recycled tobacco mainly consists of blowers, air ducts, and aerators, employing an A / O (Anaerobic / Oxic) process for biological treatment. Currently, the aerobic tank of the company's wastewater treatment plant uses three sets of Gordon jet aerators and three jet circulation pumps for aeration. Through on-site measurement and sampling, index parameters were obtained. The dissolved oxygen, water temperature, MLSS (Mixed Liquor Suspended Solids), COD (Chemical Oxygen Demand), and NH3-N (ammonia nitrogen content) parameters in the aeration system were analyzed to explore the influencing factors of the aeration system on the wastewater treatment effect. Preliminary CFD (Computational Fluid Dynamics) analysis of the aeration system was conducted to understand the spatial distribution of the aeration system's influence area and obtain operating parameters.

[0051] After obtaining the operating parameters, the supply and demand balance and energy-saving potential of the aeration system are analyzed: Based on the above analysis of the process flow and operating parameters of the aeration system, the actual oxygen supply and theoretical oxygen demand of the aeration system are calculated, the degree of supply and demand balance of the aeration system is evaluated, the phenomenon of excessive oxygen supply or hypoxia in the aeration system is identified, and its impact on sewage treatment effect and energy consumption is analyzed; based on the principle of supply and demand balance, the energy-saving potential of the aeration system is analyzed, providing basic data for subsequent research.

[0052] Step S12: Based on the aeration characteristics of the aeration system and the operating parameters, identify, optimize and verify the preset benchmark simulation model to obtain the target benchmark simulation model, and use the target benchmark simulation model to build a benchmark simulation platform.

[0053] In this embodiment, the initial benchmark simulation model is simplified and modified to obtain the simplified and modified initial benchmark simulation model; based on the aeration characteristics of the aeration system and the operating parameters, the simplified and modified initial benchmark simulation model is identified, optimized and verified using the least squares method, genetic algorithm, particle swarm optimization algorithm and Q-learning algorithm to obtain the target benchmark simulation model, and the benchmark simulation platform is constructed using the target benchmark simulation model.

[0054] The establishment process of the target benchmark simulation model is as follows: Based on the above aeration characteristics and operating parameters, the International Water Association's BSM1 (Benchmark Simulation Model NO.1) model is adopted as the mathematical model for the aerobic treatment system. This initial benchmark simulation model classifies pollutants and bacteria involved in the reaction in wastewater and uses differential equations to describe the process of microorganisms consuming pollutants, establishing a series of wastewater treatment benchmark models, mainly including three parts: hydraulic model, bioreaction model, and sludge settling model. First, the BSM1 model is appropriately simplified and modified according to the actual situation of the reconstituted tobacco wastewater treatment plant. Then, based on the aeration characteristics and on-site detection parameters, the parameters in the BSM1 model are identified and optimized using the least squares method, genetic algorithm, particle swarm optimization algorithm, and Q-learning90 algorithm, so that the model can better reflect the actual operation of the aerobic treatment system of the reconstituted tobacco wastewater treatment plant, thus obtaining the target benchmark simulation model. Finally, the established target benchmark simulation model is verified and sensitivity analyzed to evaluate the accuracy and applicability of the model.

[0055] The process of building a benchmark simulation platform is as follows: Based on the established and validated BSM1 model, we study the construction technology of BSM1 simulation platform for aerobic treatment system, develop BSM1 models based on MATLAB / Simulink platform, LabVIEW platform, and ASPEN Plus platform, compare the advantages and disadvantages of different simulation platforms in terms of interface design, function implementation, data interaction and result display, and develop the most suitable BSM1 simulation platform for tobacco wastewater treatment plant.

[0056] Step S13: Define the state space parameters, action space parameters, and reward function of the wastewater treatment system for reconstituted tobacco leaves. Based on the state space parameters, action space parameters, and reward function, simulate the actual operation using the benchmark simulation platform to obtain the simulated operation.

[0057] In this embodiment, state-space parameters of the wastewater treatment system for recycled tobacco are defined; the state-space parameters include output variables, input variables, and environmental variables; action-space parameters of the wastewater treatment system are defined; the action-space parameters include various control strategies and decision variables; based on the treatment efficiency, energy consumption, and wastewater discharge quality of the wastewater treatment system, with the objectives of minimizing energy consumption, maximizing treatment efficiency, and reducing wastewater discharge quality, a reward function of the wastewater treatment system is defined; based on the state-space parameters, the action-space parameters, and the reward function, the actual operating conditions are simulated using the benchmark simulation platform to obtain the simulated operating conditions.

[0058] Specifically, using the BSM1 simulation environment and reinforcement learning methods, the actual operation of a wastewater treatment system is simulated. The wastewater treatment process in the simulation environment is rigorously tested and verified to ensure the reliability and applicability of the equipment in actual operation. By monitoring parameters such as oxygen concentration and flow rate, the rate and amount of oxygen supply are intelligently controlled to ensure that the oxygen concentration remains within a suitable range, thereby improving the treatment efficiency and water quality of the wastewater treatment system. Simultaneously, the Q-learning algorithm is used to identify the wastewater state in the simulation environment. The state space, action space, and reward function of the wastewater treatment environment are defined, and an O matrix is ​​constructed. The optimal action is selected in each state to maximize the reward function, and iterative updates are performed using the following formula:

[0059] ;

[0060] Where s represents the current state and a represents the current action. For the next state, R represents the current reward for the next action. For learning rate, This represents the discount factor. In the BSM1 simulation platform, Q-learning reinforcement learning can be specifically applied to the following aspects:

[0061] (1) Define the state space of the wastewater treatment system, including output variables, input variables, and environmental variables: By adjusting operating parameters such as influent flow rate, aeration rate, and mixed liquor return flow rate, the treatment efficiency can be maximized and energy consumption reduced. In addition, intelligent control and optimization can be achieved through reinforcement learning algorithms, such as adjusting the aeration cycle and oxygen supply according to different situations, in order to maximize treatment efficiency and reduce energy consumption;

[0062] (2) Define the action space of the sewage treatment system, including various control strategies and decision variables: In the BSM1 simulation environment, the inlet pipe, primary sedimentation tank, aeration tank, secondary sedimentation tank, and related sensors, actuators and control systems are simulated to monitor and control the sewage treatment process and to verify and optimize the intelligent control method.

[0063] (3) Define the reward function of the sewage treatment system to measure the quality of the control strategy. It usually includes indicators such as treatment efficiency, energy consumption and sewage discharge quality. The reward function is defined based on the indicators such as treatment efficiency, energy consumption and sewage discharge quality of the sewage treatment system. The goal is to minimize energy consumption, maximize treatment efficiency and reduce the quality of sewage discharge. The specific reward function can be defined according to the actual operation.

[0064] In the BSM1 simulation environment, the state space includes variables such as COD concentration, pH value, ammonia nitrogen concentration, and total phosphorus concentration in wastewater, as well as COD concentration, ammonia nitrogen concentration, and total phosphorus concentration in sludge. The action space includes operational parameters such as adjusting influent flow rate, aeration rate, and mixed liquor return flow rate. The reward function is defined based on indicators such as the wastewater treatment system's treatment efficiency, energy consumption, and wastewater discharge quality, with the goal of minimizing energy consumption, maximizing treatment efficiency, and reducing wastewater discharge quality.

[0065] Step S14: Verify the simulated operation and optimize the strategy in real time to obtain the optimal control strategy, combine it with the hardware platform of the aeration system, and realize intelligent control of the aeration system according to the optimal control strategy.

[0066] In this embodiment, a deep reinforcement learning algorithm is used to verify the simulated operation and optimize the strategy in real time to obtain the optimal control strategy. This strategy is then combined with the hardware platform of the aeration system, and the operating parameters of the aeration system are adjusted in real time according to the optimal control strategy to achieve intelligent control of the aeration system. The hardware platform of the aeration system includes a blower, air ducts, aerators, a reaction tank, a communication interface, sensors, actuators, and a communication module component. The sensors include a dissolved oxygen sensor, a temperature sensor, and a pH sensor.

[0067] This application enables the integrated research of an intelligent operation and maintenance system for a biological treatment pond for regenerated tobacco wastewater. This includes the development and research of both the hardware and software platforms for the intelligent operation and maintenance system: based on reinforcement learning particle swarm optimization, a hardware platform for a precision aeration system and a software platform for the intelligent operation and maintenance system are developed. On the hardware platform side, equipment such as blowers, air ducts, aerators, and reaction tanks are optimized, communication interfaces are added, and corresponding sensors, actuators, and communication module components are configured to construct the hardware platform for the precision aeration system. On the software platform side, based on the characteristics and requirements of the hardware platform, a suitable programming language and development environment are selected, and the reinforcement learning machine learning algorithm is written into an executable program and embedded into the hardware platform to realize the software functions of the precision aeration system. Simultaneously, the visualization module in the software platform is a key development focus. This module can display the real-time operating status, parameter changes, data analysis, and other information of relevant equipment, and provides an intelligent human-machine interface to facilitate monitoring, adjustment, and optimization by operation and maintenance personnel. The interface of the intelligent operation and maintenance system visualization module is as follows: Figure 2 As shown.

[0068] The structure of the intelligent aeration control system is as follows: Figure 3 As shown, a multi-level control method is adopted, combining an intelligent central control room and a PLC (Programmable Logic Controller) control station. An intelligent aeration control system module is added to the intelligent central control room. The computer in the intelligent central control room can view dissolved oxygen meter readings, query historical data, and display historical curves of data parameters. The main data monitored includes DO (Data Object), airflow, and blower pressure values. This data is collected by the PLC station, and real-time data parameters are transmitted to the intelligent aeration system for calculating the oxygen demand (OD) of each aeration tank.

[0069] The core of the intelligent aeration control system is the intelligent control module. This module employs a multi-parameter control approach combining feedforward, feedback, and model-based control to effectively address the large time delays and nonlinear characteristics of reconstituted tobacco wastewater. It enables on-demand aeration and incorporates an air volume calculation module. Figure 4 As shown, an air flow calculation module is added between the dissolved oxygen meter and the gas flow regulating valve with a stroke control mechanism. The output of the air flow calculation module is connected to the stroke control mechanism of the gas flow regulating valve and the blower, so that the air flow calculated by the air flow calculation module can be used to control the opening of the gas flow regulating blower valve, and the blower pressure can be controlled by the blower pressure value calculated by the air flow calculation module. A parameter setting module is also added to set the parameters required by the aeration tank treatment process calculation module, including: the size of the aeration tank, wastewater flow rate, influent COD (chemical oxygen demand), BOD (biochemical oxygen demand), pH value, average sludge return ratio, disturbance range, and normal aeration pressure limit.

[0070] The intelligent aeration control module adds optimized control of the blower unit, distributing air according to the calculated optimal aeration results. Blower status is visualized as follows: Figure 5 As shown.

[0071] Based on the hardware and software platforms of the aerobic treatment system, simulation operation and optimization evaluation were conducted. Simulation operation and field verification tests were carried out on the aerobic treatment system under different seasons, time periods, and wastewater qualities. The microbial treatment process was monitored and controlled, and relevant data and information were collected. Finally, based on the experimental data and information, the system's effect on dissolved oxygen control, wastewater treatment effect, and energy consumption in actual operation were analyzed. A comparison was made with the original aeration system to evaluate the advantages and potential limitations of the aerobic treatment system.

[0072] Intelligent equipment operation and maintenance (O&M) is based on intelligent decision-making according to the changing trends of equipment status. The difference between O&M and traditional O&M lies in the utilization of modern Industrial Internet and Internet of Things (IoT) technologies, shifting from experience-based to knowledge-based decision-making. This application focuses on the intelligentization of aerobic treatment systems, using this as a starting point to explore a comprehensive digital solution for the entire process of tobacco wastewater treatment plants. By optimizing and improving existing wastewater treatment processes, it aims to achieve functions such as source control, process monitoring, and end-of-pipe treatment of wastewater. Furthermore, by combining Industrial Internet and IoT technologies, it proposes an intelligent equipment O&M solution.

[0073] The innovations of this application are as follows: (1) Sensor selection and arrangement: Select water quality sensors with high precision and stability, such as dissolved oxygen sensors, temperature sensors, pH sensors, etc., and arrange the sensors in different positions in the biological tank to comprehensively monitor the water quality parameters of the wastewater; (2) State space modeling: Convert the data collected by the sensors into a state space, for example, use parameters such as dissolved oxygen concentration, temperature, and pH value as state variables to construct a state model of the biological tank aeration system; (3) Action space definition: Determine the control parameters of the aeration system, such as the operating frequency of the aerator and the working time of the aerator, and construct the action space; (4) Design of reward function: Give rewards or penalties to different control actions according to the changes in water quality parameters in the biological tank to guide the reinforcement learning algorithm to learn a suitable control strategy; (5) Reinforcement learning algorithm optimization control: Select deep reinforcement learning algorithm as the optimization control algorithm, and learn the optimal control strategy through the model based on real-time monitoring; (6) Real-time control strategy execution: Adjust the working parameters of the aeration system in real time according to the optimal control strategy obtained by the reinforcement learning algorithm to maintain the stability of water quality in the biological tank.

[0074] The technical effects of this application are as follows: (1) Improved wastewater treatment efficiency: After adopting the intelligent control method, the biological tank aeration system can intelligently adjust according to the real-time changes in wastewater quality, optimize oxygen transfer efficiency, and improve the degradation rate of organic matter, thereby improving wastewater treatment efficiency; (2) Reduced energy consumption: The intelligent control method can adjust the working state of the aeration system according to the real-time monitored water quality parameters, avoiding energy waste under the traditional fixed control strategy and achieving energy reduction; (3) Simple operation: The intelligent control method reduces the need for manual intervention through self-learning and optimization, reduces the difficulty of operation, and improves the stability and reliability of the biological tank aeration system. In summary, this invention can effectively improve the treatment efficiency of the tobacco wastewater biological tank aeration system, reduce energy consumption, simplify operation, and has good practical application value.

[0075] In this embodiment, the index parameters of the aeration system are acquired and analyzed to obtain operating parameters. Based on the aeration characteristics of the aeration system and the operating parameters, a preset benchmark simulation model is identified, optimized, and verified to obtain a target benchmark simulation model. A benchmark simulation platform is constructed using the target benchmark simulation model. The state space parameters, action space parameters, and reward function of the wastewater treatment system for reconstituted tobacco are defined. Based on the state space parameters, action space parameters, and reward function, the actual operating conditions are simulated using the benchmark simulation platform to obtain simulated operating conditions. The simulated operating conditions are verified and the strategy is optimized in real time to obtain the optimal control strategy. This strategy is then combined with the hardware platform of the aeration system, and intelligent control of the aeration system is achieved according to the optimal control strategy. This application applies to an intelligent operation and maintenance system software platform for aeration systems. It utilizes aeration characteristics and operating parameters to identify, optimize, and verify a benchmark simulation model, thereby constructing a target benchmark simulation model and a benchmark simulation platform. This reduces the need for manual intervention and lowers operational difficulty. Considering the influence of multiple factors, it defines the state-space parameters, action-space parameters, and reward function of the wastewater treatment system for recycled tobacco. Then, it simulates the actual operation to obtain the simulated operating conditions. The simulated operating conditions are verified, and the strategy is optimized in real time to obtain the optimal control strategy, reducing energy waste. Combined with the hardware platform of the aeration system, the operating parameters of the aeration system are adjusted in real time according to the optimal control strategy, improving wastewater treatment efficiency, reducing the need for manual intervention, lowering operational difficulty, and improving the stability and reliability of the biological tank aeration system, achieving efficient and energy-saving intelligent aeration control.

[0076] See Figure 6 As shown, this invention discloses an intelligent aeration control device for reconstituted tobacco leaves, applied to an intelligent operation and maintenance system software platform for aeration systems, specifically including:

[0077] The parameter analysis module 11 is used to acquire the index parameters of the aeration system and analyze the index parameters to obtain the operating parameters.

[0078] The model and platform construction module 12 is used to identify, optimize and verify the preset benchmark simulation model based on the aeration characteristics of the aeration system and the operating parameters to obtain the target benchmark simulation model, and to construct the benchmark simulation platform using the target benchmark simulation model.

[0079] The simulation module 13 is used to define the state space parameters, action space parameters, and reward function of the wastewater treatment system for reconstituted tobacco leaves. Based on the state space parameters, action space parameters, and reward function, the actual operation is simulated using the benchmark simulation platform to obtain the simulated operation.

[0080] The intelligent control module 14 is used to verify the simulated operation and optimize the strategy in real time to obtain the optimal control strategy. It is combined with the hardware platform of the aeration system and realizes intelligent control of the aeration system according to the optimal control strategy.

[0081] In this embodiment, the index parameters of the aeration system are acquired and analyzed to obtain operating parameters. Based on the aeration characteristics of the aeration system and the operating parameters, a preset benchmark simulation model is identified, optimized, and verified to obtain a target benchmark simulation model. A benchmark simulation platform is constructed using the target benchmark simulation model. The state space parameters, action space parameters, and reward function of the wastewater treatment system for reconstituted tobacco are defined. Based on the state space parameters, action space parameters, and reward function, the actual operating conditions are simulated using the benchmark simulation platform to obtain simulated operating conditions. The simulated operating conditions are verified and the strategy is optimized in real time to obtain the optimal control strategy. This strategy is then combined with the hardware platform of the aeration system, and intelligent control of the aeration system is achieved according to the optimal control strategy. This application applies to an intelligent operation and maintenance system software platform for aeration systems. It utilizes aeration characteristics and operating parameters to identify, optimize, and verify a benchmark simulation model, thereby constructing a target benchmark simulation model and a benchmark simulation platform. This reduces the need for manual intervention and lowers operational difficulty. Considering the influence of multiple factors, it defines the state-space parameters, action-space parameters, and reward function of the wastewater treatment system for recycled tobacco. Then, it simulates the actual operation to obtain the simulated operating conditions. The simulated operating conditions are verified, and the strategy is optimized in real time to obtain the optimal control strategy, reducing energy waste. Combined with the hardware platform of the aeration system, the operating parameters of the aeration system are adjusted in real time according to the optimal control strategy, improving wastewater treatment efficiency, reducing the need for manual intervention, lowering operational difficulty, and improving the stability and reliability of the biological tank aeration system, achieving efficient and energy-saving intelligent aeration control.

[0082] In some specific embodiments, the parameter analysis module 11 may specifically include:

[0083] The computational fluid dynamics analysis module is used to acquire the index parameters of the aeration system measured and collected from the field, and to perform computational fluid dynamics analysis on the index parameters such as dissolved oxygen, water temperature, mixed liquor suspended solids concentration, chemical oxygen demand, and ammonia nitrogen content to obtain the operating parameters.

[0084] In some specific embodiments, the parameter analysis module 11 may specifically include:

[0085] The calculation module is used to calculate the actual oxygen supply and theoretical oxygen demand of the aeration system based on the operating parameters, and to evaluate the supply and demand balance of the aeration system based on the actual oxygen supply and theoretical oxygen demand.

[0086] The energy-saving potential analysis module is used to analyze the energy-saving potential of the aeration system based on a preset supply and demand balance principle.

[0087] In some specific embodiments, the model and platform construction module 12 may specifically include:

[0088] The model simplification and modification module is used to simplify and modify the initial benchmark simulation model to obtain the simplified and modified initial benchmark simulation model;

[0089] The identification, optimization, and verification analysis module is used to identify, optimize, and verify the simplified and modified initial benchmark simulation model based on the aeration characteristics of the aeration system and the operating parameters, and using the least squares method, genetic algorithm, particle swarm optimization algorithm, and Q-learning algorithm to obtain the target benchmark simulation model.

[0090] In some specific embodiments, the simulation module 13 may specifically include:

[0091] The state-space parameter definition module is used to define the state-space parameters of the wastewater treatment system for regenerated tobacco leaves; the state-space parameters include output variables, input variables, and environmental variables;

[0092] The action space parameter definition module is used to define the action space parameters of the wastewater treatment system; the action space parameters include various control strategies and decision variables.

[0093] The reward function definition module is used to define the reward function of the wastewater treatment system based on the treatment efficiency, energy consumption, and wastewater discharge quality of the wastewater treatment system, with the objectives of minimizing energy consumption, maximizing treatment efficiency, and reducing wastewater discharge quality.

[0094] In some specific embodiments, the hardware platform of the aeration system includes a blower, air duct, aerator, reaction tank, communication interface, sensors, actuators, and communication module components; the sensors include dissolved oxygen sensor, temperature sensor, and pH sensor.

[0095] In some specific embodiments, the intelligent control module 14 may specifically include:

[0096] The optimal control strategy determination module is used to verify the simulated operation and optimize the strategy in real time using a deep reinforcement learning algorithm to obtain the optimal control strategy.

[0097] The intelligent control module is used to integrate with the hardware platform of the aeration system and adjust the operating parameters of the aeration system in real time according to the optimal control strategy to achieve intelligent control of the aeration system.

[0098] Figure 7 This is a schematic diagram of an electronic device provided in an embodiment of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the intelligent aeration control method for reconstituted tobacco leaves executed by the electronic device disclosed in any of the foregoing embodiments.

[0099] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0100] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored on it include operating system 221, computer program 222 and data 223, etc., and the storage method can be temporary storage or permanent storage.

[0101] The operating system 221 manages and controls the various hardware devices on the electronic device 20 and the computer program 222 to enable the processor 21 to perform calculations and processing on the data 223 in the memory 22. It can be Windows, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the intelligent aeration control method for reconstituted tobacco leaves executed by the electronic device 20 as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the intelligent aeration control device for reconstituted tobacco leaves from external devices, as well as data collected by its own input / output interface 25.

[0102] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0103] Furthermore, this application also discloses a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, it implements the steps of the intelligent aeration control method for reconstituted tobacco leaves disclosed in any of the foregoing embodiments.

[0104] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0105] The above provides a detailed description of the intelligent aeration control method, device, equipment, and storage medium for reconstituted tobacco provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for intelligent control of aeration in reconstituted tobacco leaves, characterized in that, The intelligent operation and maintenance system software platform applied to aeration systems includes: Obtain the index parameters of the aeration system and analyze the index parameters to obtain the operating parameters; Based on the aeration characteristics of the aeration system and the operating parameters, the preset benchmark simulation model is identified, optimized and verified to obtain the target benchmark simulation model, and the benchmark simulation platform is constructed using the target benchmark simulation model. Define the state space parameters, action space parameters, and reward function of the wastewater treatment system for recycled tobacco. Based on the state space parameters, action space parameters, and reward function, and using the benchmark simulation platform, simulate the actual operation to obtain the simulated operation. The simulated operation is verified and the strategy is optimized in real time to obtain the optimal control strategy, which is then combined with the hardware platform of the aeration system to realize intelligent control of the aeration system according to the optimal control strategy. The process of obtaining the operating parameters further includes: calculating the actual oxygen supply and theoretical oxygen demand of the aeration system based on the operating parameters; evaluating the supply-demand balance of the aeration system based on the actual oxygen supply and theoretical oxygen demand; and analyzing the energy-saving potential of the aeration system based on the preset supply-demand balance principle. The benchmark simulation model is the BSM1 model; The simulated operation is verified and the strategy is optimized in real time to obtain the optimal control strategy. This strategy is then combined with the hardware platform of the aeration system, and intelligent control of the aeration system is achieved according to the optimal control strategy. This includes: using a deep reinforcement learning algorithm to verify the simulated operation and optimize the strategy in real time to obtain the optimal control strategy; and combining this strategy with the hardware platform of the aeration system to adjust the operating parameters of the aeration system in real time according to the optimal control strategy to achieve intelligent control of the aeration system. The intelligent control of the aeration system is a control method that combines an intelligent central control room and a programmable logic controller control station. The data detected by the intelligent central control room includes DO, air flow rate, and blower pressure value. Define the state-space parameters, action-space parameters, and reward function of a wastewater treatment system for recycled tobacco, including: defining the state-space parameters of the wastewater treatment system for recycled tobacco; the state-space parameters include output variables, input variables, and environmental variables; defining the action-space parameters of the wastewater treatment system; the action-space parameters include various control strategies and decision variables; and defining the reward function of the wastewater treatment system based on its treatment efficiency, energy consumption, and wastewater discharge quality, with the objective of minimizing energy consumption, maximizing treatment efficiency, and improving wastewater discharge quality. In the BSM1 simulation environment, the state space includes the COD concentration, pH value, ammonia nitrogen concentration, and total phosphorus concentration of wastewater, as well as the COD concentration, ammonia nitrogen concentration, and total phosphorus concentration of sludge; the action space includes adjusting the influent flow rate, aeration rate, and mixed liquor return flow rate.

2. The intelligent aeration control method for reconstituted tobacco leaves according to claim 1, characterized in that, The process of acquiring the index parameters of the aeration system and analyzing these index parameters to obtain operating parameters includes: The index parameters of the aeration system are obtained from on-site measurements and collections. Computational fluid dynamics analysis is performed on the dissolved oxygen, water temperature, mixed liquor suspended solids concentration, chemical oxygen demand, and ammonia nitrogen content among the index parameters to obtain the operating parameters.

3. The intelligent aeration control method for reconstituted tobacco leaves according to claim 1, characterized in that, The process of identifying, optimizing, and verifying a preset benchmark simulation model based on the aeration characteristics of the aeration system and the operating parameters to obtain a target benchmark simulation model includes: The initial baseline simulation model is simplified and modified to obtain the simplified and modified initial baseline simulation model; Based on the aeration characteristics and operating parameters of the aeration system, the simplified and modified initial benchmark simulation model is identified, optimized, and verified using the least squares method, genetic algorithm, particle swarm optimization algorithm, and Q-learning algorithm to obtain the target benchmark simulation model.

4. The intelligent aeration control method for reconstituted tobacco leaves according to claim 1, characterized in that, The hardware platform of the aeration system includes a blower, air duct, aerator, reaction tank, communication interface, sensors, actuators, and communication module components; the sensors include dissolved oxygen sensor, temperature sensor, and pH sensor.

5. An intelligent aeration control device for reconstituted tobacco leaves, characterized in that, The intelligent operation and maintenance system software platform applied to aeration systems includes: The parameter analysis module is used to acquire the index parameters of the aeration system and analyze the index parameters to obtain the operating parameters. The model and platform construction module is used to identify, optimize and verify the preset benchmark simulation model based on the aeration characteristics and operating parameters of the aeration system to obtain the target benchmark simulation model, and to construct the benchmark simulation platform using the target benchmark simulation model. The simulation module is used to define the state space parameters, action space parameters, and reward function of the wastewater treatment system for reconstituted tobacco leaves. Based on the state space parameters, action space parameters, and reward function, the module uses the benchmark simulation platform to simulate the actual operation to obtain the simulated operation. The intelligent control module is used to verify the simulated operation and optimize the strategy in real time to obtain the optimal control strategy. It is combined with the hardware platform of the aeration system and realizes intelligent control of the aeration system according to the optimal control strategy. The process of obtaining the operating parameters further includes: calculating the actual oxygen supply and theoretical oxygen demand of the aeration system based on the operating parameters; evaluating the supply-demand balance of the aeration system based on the actual oxygen supply and theoretical oxygen demand; and analyzing the energy-saving potential of the aeration system based on the preset supply-demand balance principle. The benchmark simulation model is the BSM1 model; The simulated operation is verified and the strategy is optimized in real time to obtain the optimal control strategy. This strategy is then combined with the hardware platform of the aeration system, and intelligent control of the aeration system is achieved according to the optimal control strategy. This includes: using a deep reinforcement learning algorithm to verify the simulated operation and optimize the strategy in real time to obtain the optimal control strategy; and combining this strategy with the hardware platform of the aeration system to adjust the operating parameters of the aeration system in real time according to the optimal control strategy to achieve intelligent control of the aeration system. The intelligent control of the aeration system is a control method that combines an intelligent central control room and a programmable logic controller control station. The data detected by the intelligent central control room includes DO, air flow rate, and blower pressure value. Define the state-space parameters, action-space parameters, and reward function of a wastewater treatment system for recycled tobacco, including: defining the state-space parameters of the wastewater treatment system for recycled tobacco; the state-space parameters include output variables, input variables, and environmental variables; defining the action-space parameters of the wastewater treatment system; the action-space parameters include various control strategies and decision variables; and defining the reward function of the wastewater treatment system based on its treatment efficiency, energy consumption, and wastewater discharge quality, with the objective of minimizing energy consumption, maximizing treatment efficiency, and improving wastewater discharge quality. In the BSM1 simulation environment, the state space includes the COD concentration, pH value, ammonia nitrogen concentration, and total phosphorus concentration of wastewater, as well as the COD concentration, ammonia nitrogen concentration, and total phosphorus concentration of sludge; the action space includes adjusting the influent flow rate, aeration rate, and mixed liquor return flow rate.

6. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor is configured to execute the computer program to implement the intelligent aeration control method for reconstituted tobacco leaves as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, Used to store computer programs; wherein, when the computer programs are executed by a processor, they implement the intelligent aeration control method for reconstituted tobacco leaves as described in any one of claims 1 to 4.

Images