Microenvironment oxygen concentration rapid regulation and control method, system, equipment and medium

Abstract

The invention discloses a microenvironment oxygen concentration rapid regulation and control method, system, equipment and medium, and relates to the technical field of tobacco mellowing maintenance, and the method comprises the following steps: obtaining historical data of a nitrogen charging and oxygen reduction process in a previous microenvironment; constructing a training sample through the current oxygen concentration and the real oxygen concentration of each time of air exhaust and nitrogen charging; training a preset initial model through each training set, and determining the preset initial model reaching a training ending condition as a concentration prediction model; the initial oxygen concentration and the final oxygen concentration of the current microenvironment are obtained, and the total duration of nitrogen charging and oxygen reduction is determined according to the number of processing times of the concentration prediction model; if the total time length exceeds the preset time length, the operation power of the regulation and control equipment is improved, and reprocessing is carried out through the concentration prediction model until the total time length does not exceed the preset time length; the descending speed of the oxygen concentration is controlled based on the control of the nitrogen charging and oxygen reducing process, the time needed by the process is shortened, the efficiency is improved, and rapid oxygen reducing and insect killing are achieved.

Description

Technical Field

[0001] This invention relates to the field of tobacco leaf aging and maintenance technology, and more specifically, to a method, system, device, and medium for rapid regulation of microenvironment oxygen concentration. Background Technology

[0002] Before being used in cigarette production, re-dried tobacco leaves typically undergo a 2-3 year aging process to harmonize chemical components, remove impurities, and reduce irritation. Freedom from mold, carbonization, and pests is the most basic requirement during aging. In the field of tobacco leaf maintenance, the focus is on maintaining quality and ensuring safety during storage and maintenance. Currently, the primary method for controlling pests is nitrogen-filled modified atmosphere packaging, which effectively inhibits pests and mold growth by reducing oxygen content. Through continuous nitrogen supply and dynamic control of oxygen content, automated management of the tobacco storage environment is achieved, providing technical support for pest and mold control, moisture retention, and quality maintenance.

[0003] During the process of nitrogen filling and oxygen reduction, since there is some oxygen in the smoke box, this process needs to be repeated multiple times to reduce the oxygen concentration to a qualified range and achieve the purpose of pest control. In order to clearly understand the process of nitrogen filling and oxygen reduction and to reduce the oxygen concentration in the maintenance environment more quickly, a method, system, equipment and medium for rapid regulation of microenvironment oxygen concentration is proposed. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, device, and medium for rapid regulation of oxygen concentration in a microenvironment. This method can clearly identify the number of times air is pumped out and nitrogen is pumped in during the process of nitrogen filling and oxygen reduction, as well as the total time required for the entire process, so that staff can easily control the process. Furthermore, based on the control of this process, the rate of oxygen concentration reduction can be increased, the time required for the process can be reduced, efficiency can be improved, and rapid oxygen reduction and pest control can be achieved.

[0005] The above-mentioned technical objective of the present invention is achieved through the following technical solution: Firstly, this application provides a method for rapid regulation of oxygen concentration in a microenvironment, comprising the following specific steps: Obtain historical data on previous nitrogen filling and oxygen deoxygenation processes in the microenvironment. The historical data includes the current oxygen concentration, actual oxygen concentration, ambient temperature, and operating power of the control equipment during each nitrogen filling and oxygen deoxygenation process. Under the same ambient temperature and / or controlled equipment operating power, training samples are constructed by the current oxygen concentration and the actual oxygen concentration during each air extraction and nitrogen filling. The training samples include multiple training sets. The pre-set initial model is trained on each training set until the loss function of the pre-set initial model reaches the training termination condition. The pre-set initial model that reaches the training termination condition is determined as the concentration prediction model. Obtain the initial oxygen concentration and the final oxygen concentration of the current microenvironment, and input the initial oxygen concentration and / or the predicted oxygen concentration output by the concentration prediction model into the concentration prediction model for processing until the predicted oxygen concentration does not exceed the final oxygen concentration. Under the premise that the gas pressure in the current microenvironment remains consistent after each gas extraction and nitrogen filling, the oxygen reduction time for each gas extraction and nitrogen filling is determined, and the total oxygen reduction time for nitrogen filling is determined by the number of treatments of the concentration prediction model. If the total duration exceeds the preset duration, the operating power of the control equipment will be increased and the concentration prediction model will be used for reprocessing until the total duration does not exceed the preset duration.

[0006] Based on the above technical solution, the present invention can be further improved as follows.

[0007] Furthermore, the aforementioned current oxygen concentration and / or actual oxygen concentration include oxygen concentrations at multiple locations within the microenvironment.

[0008] Furthermore, the loss function described above is as follows:

[0009] In the formula, N is the size of the training set, and n represents the number of locations in the microenvironment where oxygen concentration values ​​are collected. Indicates the first i The training set of the nth training set j The actual oxygen concentration at each location Indicates the first i The training set of the nth training set j The current oxygen concentration at each location, Indicates the first i The training set of the nth training set j Predicted oxygen concentration at each location.

[0010] Furthermore, the above methods also include: Based on a total duration not exceeding a preset duration, establish a duration model, energy consumption model, and cost model for the nitrogen filling and oxygen reduction process; Construct a total objective function based on the objective functions of the duration model, energy consumption model, and cost model; A genetic algorithm is used to perform multi-objective optimization of the overall objective function, and nitrogen replenishment and oxygen reduction of the current microenvironment are carried out based on the results of the multi-objective optimization.

[0011] Furthermore, the above duration model is specifically as follows:

[0012] In the formula, Total duration Represents the volume of the microenvironment. To regulate the flow rate of a single pump in the equipment during the air extraction process. To control the number of pumps used in the air extraction process of the equipment. This indicates the total number of pumping operations. This is the sequence number of the number of times the air was pumped out; To regulate the flow rate of individual pumps used in the nitrogen purging process within the equipment, To control the number of pumps used in the nitrogen charging process of the equipment, This indicates the total number of nitrogen filling cycles. This is the sequence number of the nitrogen filling cycle.

[0013] Furthermore, the objective function of the above energy consumption model is as follows:

[0014] The objective function of the energy consumption model is as follows:

[0015] In the above formula, Total energy consumption, To regulate the power of individual pumps used in the air extraction process within the equipment. Represents the volume of the microenvironment. To regulate the flow rate of a single pump in the equipment during the air extraction process. To control the number of pumps used in the air extraction process of the equipment. This indicates the total number of pumping operations. This is the sequence number of the number of times the air was pumped out; To regulate the power of individual pumps used in the nitrogen purging process within the equipment, To regulate the flow rate of individual pumps used in the nitrogen purging process within the equipment, To control the number of pumps used in the nitrogen charging process of the equipment, This indicates the total number of nitrogen filling cycles. This is the sequence number of the nitrogen filling cycle; Indicates the total cost. The unit price of energy consumption. The unit price of the pump used in the air extraction process of the control equipment. This indicates the unit price of the pump used in the nitrogen charging process within the control equipment. This indicates the cost of other equipment in the control system. For equipment maintenance costs.

[0016] Furthermore, the above overall objective function is as follows:

[0017] In the formula, Describe the overall objective function. This represents the total duration after normalization. This represents the total energy consumption after normalization. This represents the total cost after normalization. These are their respective weights, and .

[0018] Secondly, this application provides a rapid microenvironment oxygen concentration regulation system, applied to any of the rapid microenvironment oxygen concentration regulation methods in the first aspect, comprising: The data acquisition module is used to acquire historical data of previous nitrogen filling and oxygen depletion processes in the microenvironment. The historical data includes the current oxygen concentration, actual oxygen concentration, ambient temperature, and control equipment operating power during each nitrogen filling and oxygen depletion process. The sample construction module is used to construct training samples by using the current oxygen concentration and the actual oxygen concentration during each air extraction and nitrogen filling under the same ambient temperature and / or controlled equipment operating power. The training samples include multiple training sets. The model training module is used to train the preset initial model using various training sets until the loss function of the preset initial model reaches the training termination condition. The preset initial model that reaches the training termination condition is then identified as the concentration prediction model. The model processing module is used to obtain the initial oxygen concentration and the final oxygen concentration of the current microenvironment, and input the initial oxygen concentration and / or the predicted oxygen concentration output by the concentration prediction model into the concentration prediction model for processing until the predicted oxygen concentration does not exceed the final oxygen concentration. The duration determination module is used to determine the oxygen reduction duration of each air extraction and nitrogen filling under the premise that the gas pressure in the current microenvironment is consistent after each air extraction and nitrogen filling, and to determine the total duration of nitrogen filling and oxygen reduction by the number of processing times of the concentration prediction model. The equipment control module is used to increase the operating power of the control equipment and reprocess it through the concentration prediction model if the total duration exceeds the preset duration, until the total duration does not exceed the preset duration.

[0019] Thirdly, this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method of any one of the first aspects.

[0020] Fourthly, this application provides a non-transitory computer-readable storage medium that stores computer instructions that cause a computer to perform any of the methods in the first aspect.

[0021] Compared with the prior art, the present invention has at least the following beneficial effects: In this application, a deep learning-based neural network model is first trained using historical data, i.e., a pre-set initial model. Secondly, the trained prediction model is used to predict the number of times nitrogen pumping and filling are required to reach the final oxygen concentration in the current microenvironment, given the initial oxygen concentration. Finally, the total duration of the entire process is obtained using the predicted number of pumping and filling cycles. Based on this total duration, if it exceeds a preset duration, the operating power and other parameters of the control equipment are adjusted to improve the efficiency of the pumping and filling process, thereby reducing the overall process duration. This allows for clear understanding of the number of pumping and filling cycles and the required duration of the entire process during nitrogen reduction, making it easier for staff to control the process. Furthermore, this process control can increase the rate of oxygen concentration reduction, shorten the required process duration, improve efficiency, and achieve rapid oxygen reduction and pest control.

[0022] In this application, by constructing a duration model, an energy consumption model, and a cost model, as well as a total objective function constructed from the objective functions of these three models, and solving the total objective function through a genetic algorithm, a balance is achieved in terms of cost, energy consumption, and duration. That is, under the condition that the duration is met, the cost and energy consumption involved in the whole process are reduced, thus achieving the purpose of tobacco leaf maintenance at low cost. Attached Figure Description

[0023] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of the control method in an embodiment of the present invention; Figure 2 This is a schematic diagram of the connection of the control system in an embodiment of the present invention; Figure 3 This is a schematic diagram of the connection of an electronic device in an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0025] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0026] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0027] In the description of the embodiments of the present invention, "multiple" means at least two.

[0028] Example 1: To clearly and easily control the repeated process of multiple air extractions and nitrogen fillings, and to reduce the oxygen concentration to a qualified range to achieve pest control, this invention uses deep learning, reinforcement learning, and strategy optimization to perform concentration regulation in the microenvironment; specifically, this example provides a method for rapid regulation of oxygen concentration in the microenvironment, such as... Figure 1 As shown, the specific steps include the following: S1, acquire historical data of previous nitrogen filling and oxygen depletion processes in the microenvironment. The historical data includes the current oxygen concentration, actual oxygen concentration, ambient temperature, and operating power of the control equipment during each nitrogen filling and oxygen depletion process.

[0029] In previous nitrogen filling and oxygen reduction microenvironments, the site and volume of the microenvironment were often fixed. Therefore, the historical data in this embodiment were conducted in the same site, so the volume of the microenvironment was also the same. This data can be obtained by recording the previous process.

[0030] S2, under the same ambient temperature and / or controlled equipment operating power, construct training samples by using the current oxygen concentration and the actual oxygen concentration during each air extraction and nitrogen filling. The training samples include multiple training sets.

[0031] The nitrogen filling and oxygen reduction process is often achieved through control equipment, which includes devices for both the extraction and nitrogen filling processes, such as pumps and fans. Furthermore, in this embodiment, the same ambient temperature and the same operating power of the control equipment are used as the classification criteria for training samples. The classification results can be threefold: those with the same ambient temperature form one group; those with the same operating power of the control equipment form another group; and those with both the same ambient temperature and the same operating power of the control equipment form a third group. Through these training samples, the neural network model can learn the influence of temperature and power on concentration control. If the number of training samples is insufficient, the samples can be expanded using interpolation, a relatively mature method that will not be elaborated upon here.

[0032] S3. Train the pre-set initial model using various training sets until the loss function of the pre-set initial model reaches the training termination condition. The pre-set initial model that reaches the training termination condition is then determined as the concentration prediction model.

[0033] Specifically, since the training set includes the current oxygen concentration and the actual oxygen concentration before and after each evacuation and nitrogen filling, the pre-set initial model can learn the oxygen changes during each evacuation and nitrogen filling, thereby enabling prediction of subsequent processes.

[0034] The aforementioned pre-set initial model can be a long short-term memory network, and the model structure can adopt the structure commonly used in this model, which will not be elaborated here.

[0035] Optionally, the current oxygen concentration and / or actual oxygen concentration mentioned above include oxygen concentrations at multiple locations in the microenvironment.

[0036] To obtain the oxygen concentration for each dataset, sensors can be placed at multiple locations within the microenvironment. For example, since the microenvironment is typically a three-dimensional square structure, multiple sensors can be placed on each end face above the ground. Inside the microenvironment, multiple sensors can be placed at intervals in both the horizontal and vertical directions to detect changes in oxygen concentration at each location. Therefore, the loss function of the preset initial model can be set using the oxygen concentration at each location, as follows: The loss function described above is as follows:

[0037] In the formula, N is the size of the training set, and n represents the number of locations in the microenvironment where oxygen concentration values ​​are collected. Indicates the first i The training set of the nth training set j The actual oxygen concentration at each location Indicates the first i The training set of the nth training set j The current oxygen concentration at each location, Indicates the first i The training set of the nth training set j Predicted oxygen concentration at each location.

[0038] S4. Obtain the initial oxygen concentration and the final oxygen concentration of the current microenvironment. Input the initial oxygen concentration and / or the predicted oxygen concentration output by the concentration prediction model into the concentration prediction model for processing until the predicted oxygen concentration does not exceed the final oxygen concentration.

[0039] Once the training process is complete and a prediction model is obtained, it is possible to predict the number of times the oxygen concentration in the current microenvironment will be reduced by nitrogen injection.

[0040] S5. Under the premise that the gas pressure in the current microenvironment is consistent after each gas extraction and nitrogen filling, determine the oxygen reduction time for each gas extraction and nitrogen filling, and determine the total oxygen reduction time for nitrogen filling by the number of treatments of the concentration prediction model.

[0041] It should be noted that the current microenvironment consists of multiple tobacco boxes containing tobacco leaves, which are then sealed with a sealing cover to form the microenvironment. Therefore, with consistent internal air pressure, the volume of air extraction and nitrogen filling can be made consistent, which also ensures the accuracy of the prediction model for concentration changes.

[0042] S6. If the total duration exceeds the preset duration, increase the operating power of the control equipment and reprocess it through the concentration prediction model until the total duration does not exceed the preset duration.

[0043] Among them, for the equipment in the control equipment that realizes the process of air extraction and nitrogen filling, such as multiple air extraction pumps, multiple air extraction ports can be distributed on various end faces of the microenvironment, or one air extraction pump can be set with multiple interconnected air extraction ports and set in different positions of the microenvironment; the same applies to the setup for realizing nitrogen filling.

[0044] Optionally, the above methods also include: S61. Based on a total duration not exceeding a preset duration, establish a duration model, energy consumption model, and cost model for the nitrogen filling and oxygen reduction process.

[0045] The aforementioned duration model is specifically as follows:

[0046] In the formula, Total duration Represents the volume of the microenvironment. To regulate the flow rate of a single pump in the equipment during the air extraction process. To control the number of pumps used in the air extraction process of the equipment. This indicates the total number of pumping operations. This is the sequence number of the number of times the air was pumped out; To regulate the flow rate of individual pumps used in the nitrogen purging process within the equipment, To control the number of pumps used in the nitrogen charging process of the equipment, This indicates the total number of nitrogen filling cycles. This is the sequence number of the nitrogen filling cycle.

[0047] Optionally, the objective function of the above energy consumption model is as follows:

[0048] Optionally, the objective function of the above energy consumption model is as follows:

[0049] In the above formula, Total energy consumption, To regulate the power of individual pumps used in the air extraction process within the equipment. Represents the volume of the microenvironment. To regulate the flow rate of a single pump in the equipment during the air extraction process. To control the number of pumps used in the air extraction process of the equipment. This indicates the total number of pumping operations. This is the sequence number of the number of times the air was pumped out; To regulate the power of individual pumps used in the nitrogen purging process within the equipment, To regulate the flow rate of individual pumps used in the nitrogen purging process within the equipment, To control the number of pumps used in the nitrogen charging process of the equipment, This indicates the total number of nitrogen filling cycles. This is the sequence number of the nitrogen filling cycle; Indicates the total cost. The unit price of energy consumption. The unit price of the pump used in the air extraction process of the control equipment. This indicates the unit price of the pump used in the nitrogen charging process within the control equipment. This indicates the cost of other equipment in the control system. For equipment maintenance costs.

[0050] S62, construct the overall objective function based on the objective functions of the duration model, energy consumption model and cost model respectively.

[0051] The overall objective function mentioned above is as follows:

[0052] In the formula, Describe the overall objective function. This represents the total duration after normalization. This represents the total energy consumption after normalization. This represents the total cost after normalization. These are their respective weights, and .

[0053] The purpose of normalizing the total duration, total cost, and total energy consumption is to transform these three data into the same data range; the weight distribution can be adjusted adaptively according to the actual situation, and can be 0.3, 0.3, and 0.4 respectively.

[0054] S63 uses a genetic algorithm to perform multi-objective optimization of the overall objective function, and then uses the results of the multi-objective optimization to perform nitrogen replenishment and oxygen reduction in the current microenvironment.

[0055] Among them, the genetic algorithm is designed based on the principles of natural selection and genetics. It searches for the optimal solution to the problem through iterative optimization. The steps of its solution process can be described as follows: initializing the population, estimating fitness, performing selection operations based on fitness, crossover operations, mutation updates, and reaching the update condition. This update condition can be reaching the required number of iterations, the optimal fitness of the population not significantly improving for several consecutive generations, or the fitness reaching a preset threshold. Its solution object is to realize the number of devices, their respective power, and their respective flow rates for gas extraction and nitrogen filling in the gas extraction and nitrogen filling processes, so as to achieve nitrogen filling and oxygen reduction within a specified time and minimize the cost of the entire process, greatly improving economic efficiency. The genetic algorithm can also be used to perform multi-objective optimization of the installation positions of various devices in the gas extraction and nitrogen filling processes, which will not be elaborated here.

[0056] Example 2: This application provides a rapid microenvironment oxygen concentration control system, applied to a rapid microenvironment oxygen concentration control method described in Example 1, such as... Figure 2 As shown, it includes: The data acquisition module is used to acquire historical data of previous nitrogen filling and oxygen depletion processes in the microenvironment. The historical data includes the current oxygen concentration, actual oxygen concentration, ambient temperature, and control equipment operating power during each nitrogen filling and oxygen depletion process. The sample construction module is used to construct training samples by using the current oxygen concentration and the actual oxygen concentration during each air extraction and nitrogen filling under the same ambient temperature and / or controlled equipment operating power. The training samples include multiple training sets. The model training module is used to train the preset initial model using various training sets until the loss function of the preset initial model reaches the training termination condition. The preset initial model that reaches the training termination condition is then identified as the concentration prediction model. The model processing module is used to obtain the initial oxygen concentration and the final oxygen concentration of the current microenvironment, and input the initial oxygen concentration and / or the predicted oxygen concentration output by the concentration prediction model into the concentration prediction model for processing until the predicted oxygen concentration does not exceed the final oxygen concentration. The duration determination module is used to determine the oxygen reduction duration of each air extraction and nitrogen filling under the premise that the gas pressure in the current microenvironment is consistent after each air extraction and nitrogen filling, and to determine the total duration of nitrogen filling and oxygen reduction by the number of processing times of the concentration prediction model. The equipment control module is used to increase the operating power of the control equipment and reprocess it through the concentration prediction model if the total duration exceeds the preset duration, until the total duration does not exceed the preset duration.

[0057] Example 3: This application provides an electronic device, such as... Figure 3As shown, it includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method of Embodiment 1.

[0058] Example 4: This application provides a non-transitory computer-readable storage medium that stores computer instructions that cause a computer to execute the method of Example 1.

[0059] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0060] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0061] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0062] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0063] Those skilled in the art will understand that all or part of the steps in the above facts and methods can be implemented by a program instructing related hardware. The program or the program described therein can be stored in a computer-readable storage medium. When the program is executed, it includes the following steps: at this time, the corresponding method steps are introduced. The storage medium can be ROM / RAM, magnetic disk, optical disk, etc.

[0064] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for rapid regulation of oxygen concentration in a microenvironment, characterized in that, The specific steps include the following: Obtain historical data on previous nitrogen filling and oxygen depletion processes in the microenvironment. The historical data includes the current oxygen concentration, actual oxygen concentration, ambient temperature, and operating power of the control equipment during each nitrogen filling and oxygen depletion process. Under the same ambient temperature and / or controlled equipment operating power, training samples are constructed by the current oxygen concentration and the actual oxygen concentration during each air extraction and nitrogen filling, and the training samples include multiple training sets. The preset initial model is trained using each of the training sets until the loss function of the preset initial model reaches the training termination condition. The preset initial model that reaches the training termination condition is then determined as the concentration prediction model. Obtain the initial oxygen concentration and the final oxygen concentration of the current microenvironment, and input the initial oxygen concentration and / or the predicted oxygen concentration output by the concentration prediction model into the concentration prediction model for processing until the predicted oxygen concentration does not exceed the final oxygen concentration. Under the premise that the air pressure in the current microenvironment remains consistent after each air extraction and nitrogen filling, the oxygen reduction time for each air extraction and nitrogen filling is determined, and the total oxygen reduction time for nitrogen filling is determined by the number of processing steps of the concentration prediction model. If the total duration exceeds the preset duration, the operating power of the control equipment is increased and the concentration prediction model is used for reprocessing until the total duration does not exceed the preset duration.

2. The method for rapid regulation of oxygen concentration in a microenvironment according to claim 1, characterized in that, The current oxygen concentration and / or actual oxygen concentration include the oxygen concentration at multiple locations in the microenvironment.

3. The method for rapid regulation of oxygen concentration in a microenvironment according to claim 2, characterized in that, The loss function is specifically as follows: In the formula, N is the size of the training set, and n represents the number of locations in the microenvironment where oxygen concentration values ​​are collected. Indicates the first i The training set of the nth training set j The actual oxygen concentration at each location Indicates the first i The training set of the nth training set j The current oxygen concentration at each location, Indicates the first i The training set of the nth training set j Predicted oxygen concentration at each location.

4. The method for rapid regulation of oxygen concentration in a microenvironment according to claim 1, characterized in that, The method further includes: Based on the total duration not exceeding the preset duration, establish a duration model, energy consumption model, and cost model for the nitrogen filling and oxygen reduction process; A total objective function is constructed based on the objective functions of the duration model, the energy consumption model, and the cost model, respectively. A genetic algorithm is used to perform multi-objective optimization of the overall objective function, and nitrogen replenishment and oxygen reduction of the current microenvironment are carried out based on the results of the multi-objective optimization.

5. The method for rapid regulation of oxygen concentration in a microenvironment according to claim 4, characterized in that, The duration model is specifically as follows: In the formula, Total duration Represents the volume of the microenvironment. To regulate the flow rate of a single pump in the equipment during the air extraction process. To control the number of pumps used in the air extraction process of the equipment. This indicates the total number of pumping operations. This is the sequence number of the number of times the air was pumped out; To regulate the flow rate of individual pumps used in the nitrogen purging process within the equipment, To control the number of pumps used in the nitrogen charging process of the equipment, This indicates the total number of nitrogen filling cycles. This is the sequence number of the nitrogen filling cycle.

6. The method for rapid regulation of oxygen concentration in a microenvironment according to claim 4, characterized in that, The objective function of the energy consumption model is as follows: The objective function of the energy consumption model is as follows: In the above formula, Total energy consumption, To regulate the power of a single pump used in the air extraction process within the equipment. Represents the volume of the microenvironment. To regulate the flow rate of a single pump in the equipment during the air extraction process. To control the number of pumps used in the air extraction process of the equipment. This indicates the total number of pumping operations. This is the sequence number of the number of times the air was pumped out; To regulate the power of individual pumps used in the nitrogen charging process within the equipment, To regulate the flow rate of individual pumps used in the nitrogen purging process within the equipment, To control the number of pumps used in the nitrogen charging process of the equipment, This indicates the total number of nitrogen filling cycles. This is the sequence number of the nitrogen filling cycle; Represents the total cost. The unit price of energy consumption. The unit price of the pump used in the air extraction process of the control equipment. This indicates the unit price of the pump used in the nitrogen charging process within the control equipment. This indicates the cost of other equipment in the control system. For equipment maintenance costs.

7. The method for rapid regulation of oxygen concentration in a microenvironment according to claim 4, characterized in that, The overall objective function is as follows: In the formula, Describe the overall objective function. This represents the total duration after normalization. This represents the total energy consumption after normalization. This represents the total cost after normalization. These are their respective weights, and .

8. A rapid microenvironment oxygen concentration regulation system, characterized in that, include: The data acquisition module is used to acquire historical data of previous nitrogen filling and oxygen depletion processes in the microenvironment. The historical data includes the current oxygen concentration, actual oxygen concentration, ambient temperature, and operating power of the control equipment during each nitrogen filling and oxygen depletion process. The sample construction module is used to construct training samples by using the current oxygen concentration and the actual oxygen concentration during each air extraction and nitrogen filling under the same ambient temperature and / or controlled equipment operating power. The training samples include multiple training sets. The model training module is used to train the preset initial model using each of the training sets until the loss function of the preset initial model reaches the training termination condition, and the preset initial model that reaches the training termination condition is determined as the concentration prediction model. The model processing module is used to obtain the initial oxygen concentration and the final oxygen concentration of the current microenvironment, and input the initial oxygen concentration and / or the predicted oxygen concentration output by the concentration prediction model into the concentration prediction model for processing until the predicted oxygen concentration does not exceed the final oxygen concentration. The duration determination module is used to determine the oxygen reduction duration of each air extraction and nitrogen filling under the premise that the gas pressure in the current microenvironment is consistent after each air extraction and nitrogen filling, and to determine the total duration of nitrogen filling and oxygen reduction by the number of processing times of the concentration prediction model. The equipment control module is used to increase the operating power of the control equipment and reprocess it through the concentration prediction model if the total duration exceeds the preset duration, until the total duration does not exceed the preset duration.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method of any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the method of any one of claims 1-7.

Images