Nitrogen charging maintenance method, nitrogen charging maintenance device and nitrogen charging maintenance equipment

Abstract

The invention relates to a nitrogen charging maintenance method, a nitrogen charging maintenance device and nitrogen charging maintenance equipment. The method comprises the following steps: acquiring working condition data of a maintenance object associated with a nitrogen charging system; according to the working condition data and the gas diffusion characteristics, predicting a concentration curve of gas concentration changing along with time in the maintenance object when the nitrogen charging system operates based on the initial control parameters; quantifying a preset evaluation index according to the concentration curve and / or the initial control parameters, and constructing a target evaluation function corresponding to each control parameter according to a quantification result; in the search space of the initial control parameters, determining target control parameters when the nitrogen charging system meets the target maintenance efficiency of the maintenance object; wherein the target maintenance efficiency is quantified according to the target evaluation function; and regulating and controlling the operation state of the nitrogen charging system according to the target control parameter. By adopting the method, the applicability of the nitrogen-filling maintenance method can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of tobacco curing, in particular to a nitrogen filling curing method, a nitrogen filling curing device and a nitrogen filling curing equipment. BACKGROUND

[0002] Tobacco products are particularly sensitive to oxygen during their storage and logistics cycle. If the oxygen concentration inside the tobacco package is not effectively controlled during this process, not only will it accelerate the oxidative decomposition of key aromatic substances in tobacco, leading to significant deterioration of aroma and taste, but excessive oxygen will also provide a breeding ground for the reproduction of microorganisms such as mold and bacteria, thereby causing mold growth, producing odors and even toxins, seriously damaging the commercial value and product safety of tobacco, and directly increasing the loss rate and economic cost. Therefore, by means of nitrogen filling and other gas conditioning methods, ensuring that the oxygen concentration inside the tobacco package is maintained at a pre-set low level has become a crucial task in modern tobacco storage management.

[0003] In the process of nitrogen filling curing, the traditional technology generally adopts a control strategy based on fixed parameters, i.e. periodic operation according to pre-set and unchangeable nitrogen filling time and standing time. However, this rigid control method ignores the significant differences in physical characteristics such as stacking density, initial state and packaging tightness of different tobacco stacks, which makes it difficult for fixed control parameters to achieve optimal results for all curing objects, often resulting in low overall oxygen reduction efficiency, unnecessary nitrogen consumption and energy waste.

[0004] In view of the poor applicability of the nitrogen filling curing method in the related art, no effective solution has been proposed so far. SUMMARY

[0005] Therefore, it is necessary to provide a nitrogen filling curing method, a nitrogen filling curing device and a nitrogen filling curing equipment capable of solving the problem of poor applicability of the nitrogen filling curing method.

[0006] In a first aspect, a nitrogen filling curing method is provided in the present embodiment, the method comprising:

[0007] obtaining working condition data of a curing object associated with a nitrogen filling system;

[0008] predicting, according to the working condition data and gas diffusion characteristics, a concentration curve of a gas concentration inside the curing object over time when the nitrogen filling system is running based on initial control parameters;

[0009] quantifying a pre-set evaluation index according to the concentration curve and / or the initial control parameters, and constructing a target evaluation function corresponding to each of the control parameters according to the quantification results;

[0010] determine a target control parameter of the nitrogen charging system satisfying a target curing efficiency of the curing object in a search space of the initial control parameter, wherein the target curing efficiency is quantified according to the target evaluation function;

[0011] control the operation state of the nitrogen charging system according to the target control parameter.

[0012] In some embodiments, according to the working condition data and the gas diffusion characteristics, a concentration curve of the gas concentration inside the curing object changing over time when the nitrogen charging system operates based on the initial control parameter is predicted, including:

[0013] obtain a gas diffusion model pre-constructed according to the gas diffusion characteristics;

[0014] combine the working condition data and the gas diffusion model to generate a physical prediction model for predicting the trend of the gas concentration inside the curing object changing over time;

[0015] obtain the concentration curve output by the physical prediction model when the physical prediction model satisfies the boundary condition with the initial control parameter as the boundary condition.

[0016] In some embodiments, combining the working condition data and the gas diffusion model to generate a physical prediction model for predicting the trend of the gas concentration inside the curing object changing over time includes:

[0017] obtain state data of the nitrogen charging system when the nitrogen charging system operates;

[0018] take the gas concentration data in the working condition data as a known condition and take the state data as a boundary condition to calculate a diffusion coefficient of the gas diffusion model;

[0019] configure the gas diffusion model based on the diffusion coefficient to obtain the physical prediction model.

[0020] In some embodiments, the preset evaluation index includes an oxygen reduction efficiency index, and quantifying the preset evaluation index according to the concentration curve includes:

[0021] According to the concentration curve, the time for the oxygen concentration to drop from the initial concentration to a preset target concentration threshold is calculated to obtain the oxygen reduction efficiency index corresponding to the control parameter, wherein the time is negatively correlated with the oxygen reduction efficiency inside the curing object.

[0022] In some embodiments, the preset evaluation index includes an airtightness index, and quantifying the preset evaluation index according to the concentration curve includes:

[0023] According to the concentration curve, a rate of the oxygen concentration rebounding with time after the oxygen concentration reaches the target concentration threshold and enters the low-oxygen maintenance stage is calculated to obtain the air tightness index corresponding to the control parameter, wherein the rate is negatively correlated with the air tightness of the space where the curing object is located.

[0024] In some embodiments, the preset evaluation index includes an energy consumption efficiency index, and the preset evaluation index is quantified according to the control parameter, including:

[0025] The energy consumption efficiency index is obtained according to the time length sum of all nitrogen charging stages in the control parameter, and the time length sum is negatively correlated with the energy consumption efficiency of the curing object.

[0026] In some embodiments, the target control parameter when the nitrogen charging system meets the target curing efficiency of the curing object in the search space of the initial control parameter is determined, including:

[0027] The parameter value in the control parameter is taken as a position variable of each particle in the particle swarm;

[0028] According to the historical optimal position of the particle and the global optimal position of the particle swarm, the position and the speed of the particle are iteratively updated in the search space of the initial control parameter;

[0029] When the number of iterations reaches a preset number, or when the change amount of the target evaluation function value corresponding to the global optimal position of the particle swarm is less than a preset threshold, the target control parameter is obtained according to the position component corresponding to the global optimal position.

[0030] In some embodiments, the working condition data of the curing object associated with the nitrogen charging system is obtained, including:

[0031] The working condition data is obtained according to the data collected by the plurality of sensors deployed inside and outside the curing object.

[0032] In a second aspect, a nitrogen charging curing device is provided in the embodiments, and the device includes:

[0033] The acquisition module is configured to obtain the working condition data of the curing object associated with the nitrogen charging system;

[0034] The processing module is configured to predict, according to the working condition data and the gas diffusion characteristics, a concentration curve of the gas concentration inside the curing object changing with time when the nitrogen charging system operates based on the initial control parameter;

[0035] The construction module is configured to quantify a preset evaluation index according to the concentration curve and / or the initial control parameter, and to construct a target evaluation function corresponding to each control parameter according to the quantification result.

[0036] a parameter optimization module, configured to determine a target control parameter when the nitrogen charging system satisfies a target curing efficiency of the curing object, in a search space of the initial control parameter, wherein the target curing efficiency is quantified according to the target evaluation function;

[0037] a regulation module, configured to regulate a running state of the nitrogen charging system according to the target control parameter.

[0038] In a third aspect, the embodiment provides a nitrogen charging and curing device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the nitrogen charging and curing method of the first aspect when executing the computer program.

[0039] The nitrogen charging and curing method, the nitrogen charging and curing device and the nitrogen charging and curing equipment can predict the future gas concentration change according to the actual working condition data and the gas diffusion characteristics of the curing object, quantify the preset evaluation index based on the predicted concentration curve, and find the target control parameter when the target curing efficiency of the curing object is satisfied based on the target evaluation function constructed based on the quantified structure, so as to dynamically find the optimal control strategy for the physical characteristics of the curing object, and achieve the effect of improving the pertinence and accuracy of the nitrogen charging and curing method. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 It is an application environment diagram of the nitrogen charging and curing method in an embodiment;

[0041] Figure 2 It is a flowchart of the nitrogen charging and curing method in an embodiment;

[0042] Figure 3 It is a result thermal diagram of the particle swarm optimization algorithm for optimizing the control parameter in an embodiment;

[0043] Figure 4 It is a schematic diagram of the arrangement of the oxygen concentration sensor in an embodiment;

[0044] Figure 5 It is a curve diagram of the change of the oxygen concentration with time in an embodiment;

[0045] Figure 6 It is a flowchart of the slice nitrogen charging and curing multi-objective optimization method based on the FICK model and the PSO in an embodiment;

[0046] Figure 7 It is a structural block diagram of the slice nitrogen charging and curing multi-objective optimization system based on the FICK model and the PSO in an embodiment;

[0047] Figure 8A structural block diagram of the nitrogen filling maintenance device in one embodiment;

[0048] Figure 9 An internal structural diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0049] For the purpose, technical solutions and advantages of the present application to be more clearly understood, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0050] For the purpose, technical solutions and advantages of the present application to be more clearly understood, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0051] The nitrogen filling maintenance method provided by the embodiments of the present application can be applied to the application environment as shown in Figure 1 . The terminal 102 communicates with the server 104 through a network. The data storage system can store data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on a cloud or other network server. The target control parameter is generated based on the control parameter, the working condition data and the gas diffusion characteristics, and the operation of the nitrogen filling system is automatically regulated based on the target control parameter, so as to realize the nitrogen filling maintenance of the maintenance object. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, tablet computers, Internet of Things devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0052] In one embodiment, as shown in Figure 2 , a nitrogen filling maintenance method is provided. Taking the terminal 102 in Figure 1 as an example, the method includes the following steps:

[0053] Step 202, obtaining working condition data of a maintenance object in a nitrogen filling system associated with the nitrogen filling system.

[0054] The nitrogen filling system is used to input nitrogen to the maintenance object. The maintenance object includes cut tobacco, and the number, volume, stacking mode, packaging sealing performance and other storage states of the cut tobacco are not limited. The working condition data of the maintenance object includes the nitrogen concentration inside and / or outside the maintenance object, and the working condition data can also include humidity, temperature and other data inside and / or outside the maintenance object.

[0055] Optionally, the tobacco stacks composed of tobacco strips are wrapped by plastic film, and a plurality of oxygen concentration sensors are arranged inside and outside the tobacco stacks wrapped by the plastic film to collect oxygen concentration data of the tobacco stacks at different time and space points to obtain the working condition data. Further, temperature sensors and humidity sensors can also be arranged to collect humidity data and temperature data as the working condition data.

[0056] In step 204, according to the working condition data and the gas diffusion characteristics, a concentration curve of the gas concentration inside the curing object over time is predicted when the nitrogen charging system operates based on the initial control parameters.

[0057] The gas diffusion characteristics are the relationship between the gas concentration and the time and space in the non-steady-state diffusion process. Based on different calculation requirements, the nitrogen concentration curve or the oxygen concentration curve inside the curing object at a future time can be predicted according to the working condition data and the gas diffusion characteristics. The initial control parameters are the operation sequence for regulating the operation state of the nitrogen charging system; optionally, the initial control parameters are generated according to a set of preset nitrogen charging time and standing time of the nitrogen charging system.

[0058] Optionally, a physical prediction model for predicting the oxygen concentration change of the curing object is constructed according to the working condition data and the preset FICK gas diffusion model, the physical prediction model takes the initial control parameters as the boundary conditions, and outputs the prediction results, i.e., obtains the concentration curve.

[0059] In step 206, the preset evaluation indexes are quantified according to the concentration curve and / or the initial control parameters, and a target evaluation function corresponding to each control parameter is constructed according to the quantification results.

[0060] The preset evaluation indexes include one or more of the oxygen reduction efficiency index, the air tightness index, and the energy consumption efficiency index. The oxygen reduction efficiency index and the air tightness index can be calculated based on the concentration curve, and the energy consumption efficiency index can be calculated based on the initial control parameters.

[0061] Optionally, in the case of obtaining a plurality of preset evaluation indexes, corresponding weights can be configured for different preset evaluation indexes, and the target evaluation function is obtained by weighted summation.

[0062] In step 208, the target control parameters of the nitrogen charging system that meet the target curing efficiency of the curing object are determined in the preset search space; wherein the target curing efficiency is quantified according to the target evaluation function.

[0063] The search space of the initial control parameters can be obtained based on the physical performance of the nitrogen charging system, or can be set according to application requirements.

[0064] Optionally, the target maintenance efficiency is quantified by the value of the target evaluation function. Taking the target maintenance efficiency of the maintenance object as the objective, the global optimal solution in the search space is obtained based on optimization methods such as particle swarm optimization, genetic algorithm, and gradient descent. The global optimal solution obtained by the search is used as the target control parameter.

[0065] Step 210: Adjust the operation of the nitrogen filling system according to the target control parameters.

[0066] Optionally, the target control parameters can be set to the actual operating parameters of the nitrogen purging system associated with the object being maintained. This allows the nitrogen purging system to operate periodically according to the target control parameters. For example, nitrogen purging can be performed for 8 hours according to the target control parameters, followed by stopping nitrogen purging and allowing the system to stand for 13 hours. This constitutes one complete operating cycle, which will be repeated until the entire maintenance process is completed.

[0067] In the aforementioned nitrogen-filling curing method, actual operating data is acquired, and a physical prediction model capable of predicting future changes in oxygen concentration is constructed based on the characteristics of the FICK gas diffusion model. This achieves precise quantification of the gas diffusion characteristics of different curing objects. Pre-defined evaluation indicators are quantified based on the predicted concentration curves, and target control parameters that meet the target curing efficiency of the curing objects are found based on the target evaluation function constructed from the quantified structure. This allows subsequent optimization and control to be based on the physical characteristics of the curing objects corresponding to the pre-defined evaluation indicators. This overcomes the shortcomings of traditional fixed nitrogen-filling strategies that cannot adapt to the differences in physical characteristics of curing objects in different batches and stacking states, significantly improving the targeting and accuracy of control and enhancing the applicability of the nitrogen-filling curing method.

[0068] In one embodiment, predicting the gas concentration curve inside the object under maintenance as a function of the nitrogen filling system based on control parameters, based on operating condition data and gas diffusion characteristics, includes: acquiring a gas diffusion model pre-constructed based on gas diffusion characteristics; combining operating condition data and the gas diffusion model to generate a physical prediction model for predicting the trend of gas concentration change inside the object under maintenance as a function of time; and using initial control parameters as boundary conditions to acquire the concentration curve output by the physical prediction model when the boundary conditions are met.

[0069] Optionally, a FICK gas diffusion model is pre-constructed based on gas diffusion characteristics; wherein, the FICK gas diffusion model conforms to FICK's second law, which describes the relationship between concentration and time and space during unsteady diffusion. Its mathematical expression can be simplified to the following partial differential equation:

[0070] ;

[0071] In the formula, This represents the oxygen concentration at spatial location x and time t; is a physical parameter representing the gas diffusion capability of a specific medium, which in this embodiment is the curing object. According to the change of the gas concentration in the working condition data over time, and combined with the mathematical expression of the FICK gas diffusion model, the diffusion coefficient representing the gas diffusion characteristics of the curing object is calculated. Optionally, in order to improve the accuracy of the gas diffusion model, after the gas diffusion model is constructed according to the FICK second law, the mapping relationship between temperature, humidity and gas concentration change is calibrated using the historical humidity data and historical temperature data in the working condition data, and the mapping relationship is embedded in the original gas diffusion model, so that the gas diffusion model has the ability to adapt to environmental changes.

[0072] The physical prediction model takes the calculated diffusion coefficient as the core physical parameter, and can make deterministic prediction of the future oxygen concentration change under the given initial control parameters. Optionally, obtaining the initial control parameters includes: obtaining a set of future operation sequences of the nitrogen charging system defined by the nitrogen charging time and the standing time. The physical prediction model takes the future operation sequence as the boundary condition, solves the partial differential equation, and outputs a predicted concentration change curve of a specific position inside the curing object in a future period of time, i.e. the concentration curve.

[0073] In this embodiment, the gas diffusion model is pre-constructed based on the gas diffusion characteristics, and the universal physical law contained in the gas diffusion model is combined with the measured working condition data of the specific curing object to establish a targeted physical prediction model that can be used for forward deduction. Through the mathematical model of the physical prediction model, the current curing object is adapted to realize accurate prediction of the concentration curve.

[0074] Further, in order to improve the accuracy of the constructed physical prediction model, the working condition data, the state data and the gas diffusion model can be combined during model construction. In one embodiment, the working condition data and the gas diffusion model are combined to generate a physical prediction model for predicting the trend of the gas concentration inside the curing object over time, including: obtaining the state data of the nitrogen charging system during operation, taking the gas concentration data in the working condition data as the known condition, and taking the state data as the boundary condition to calculate the diffusion coefficient of the gas diffusion model; and configuring the gas diffusion model based on the diffusion coefficient to obtain the physical prediction model.

[0075] The state data of the nitrogen charging system during operation includes: the opening and closing time of the nitrogen charging electromagnetic valve in the nitrogen charging system, the cumulative running time of the nitrogen charging pump, etc. The diffusion coefficient is used to represent the gas diffusion characteristics of the curing object. The number, arrangement and type of the curing objects may be different, and the diffusion coefficient may be different.

[0076] In the physical prediction model construction process, the diffusion coefficient D is a key parameter to be solved. Optionally, the state data of the nitrogen charging system during operation is obtained while collecting the working condition data. The measured value of the oxygen concentration in the working condition data is taken as a known condition, and the recorded state data of the nitrogen charging system executor is taken as a boundary condition. Through numerical fitting or parameter identification algorithm, the diffusion coefficient D value that can minimize the error between the solution of the above partial differential equation and the measured data is calculated. After the specific diffusion coefficient D value is calculated and determined, the FICK gas diffusion model is configured as a physical prediction model for the current curing object.

[0077] In this embodiment, on the basis of the pre-constructed gas diffusion model, the accurate diffusion coefficient is solved by combining the working condition data and the state data, thereby improving the accuracy of the predicted concentration curve.

[0078] In one embodiment, the preset evaluation index includes an oxygen reduction efficiency index, and the preset evaluation index is quantified according to the concentration curve, including: according to the concentration curve, the time for the oxygen concentration to drop from the initial concentration to the preset target concentration threshold is calculated to obtain the oxygen reduction efficiency index corresponding to the control parameter, wherein the time is negatively correlated with the oxygen reduction efficiency in the curing object.

[0079] The shorter the time for the oxygen concentration to drop from the initial concentration to the preset target concentration threshold, the higher the oxygen reduction efficiency; otherwise, the longer the time, the lower the oxygen reduction efficiency.

[0080] Taking the oxygen curve as an example, optionally, in the case of forward deduction based on any given initial control parameter combination to obtain a predicted oxygen concentration curve with time, the time required for the oxygen concentration to drop to the preset target threshold from the predicted initial time is calculated. The target threshold is set to 2%. It can be understood that the target threshold can also be set to other values. When the concentration curve is a nitrogen curve, the oxygen concentration corresponding to the nitrogen concentration can be calculated according to the relationship between the nitrogen and oxygen concentrations in the air, and the oxygen reduction efficiency index can be calculated based on this, which is not described here.

[0081] In this embodiment, the oxygen reduction efficiency index is set so that the searched target control parameter meets the oxygen reduction efficiency requirement of the curing object, and the nitrogen charging system under the control of the target control parameter can achieve the effect of improving the nitrogen charging curing efficiency.

[0082] In one embodiment, the preset evaluation index includes an air tightness index, and the preset evaluation index is quantified according to the concentration curve, including: according to the concentration curve, the rate of the oxygen concentration rising with time after the oxygen concentration reaches the target concentration threshold and enters the low-oxygen maintenance stage is calculated to obtain the air tightness index corresponding to the control parameter, wherein the rate is negatively correlated with the air tightness of the space where the curing object is located.

[0083] The slower the back-up rate is, the better the overall sealing performance of the maintenance object is, that is, the better the air tightness index is; otherwise, the air tightness index is worse.

[0084] Optionally, the oxygen concentration is obtained according to the predicted concentration curve; after the predicted oxygen concentration reaches a target threshold, it is determined whether the change rate of the oxygen concentration is continuously less than the rate within a preset time window, and if so, it is determined that the oxygen concentration tends to be stable, that is, enters a low-oxygen maintenance stage; then, the rate at which the concentration rebounds over time is calculated.

[0085] In this embodiment, by setting the air tightness index, the air tightness of the nitrogen filling system under the control of the target control parameter is improved, so that the effect of improving the nitrogen filling maintenance efficiency can be achieved.

[0086] In one embodiment, the preset evaluation index includes an energy consumption efficiency index, and the preset evaluation index is quantified according to the control parameter, including: obtaining the energy consumption efficiency index according to the time length sum of all nitrogen filling stages in the control parameter; wherein the time length sum is negatively correlated with the energy consumption efficiency of the maintenance object.

[0087] The shorter the time length sum is, the less nitrogen is consumed to complete the maintenance task, that is, the higher the energy consumption efficiency is; otherwise, the longer the time length sum is, the lower the energy consumption efficiency is. Optionally, the initial control parameter is obtained, the sum of all nitrogen filling durations in the extreme initial control parameter is obtained, and the time length sum of the nitrogen filling stage is obtained.

[0088] In this embodiment, by setting the energy consumption efficiency index, the energy consumption required for the nitrogen filling system under the control of the target control parameter to achieve the target maintenance efficiency is reduced, so that the effect of reducing the energy consumption and cost of nitrogen filling maintenance can be achieved.

[0089] In one embodiment, the preset evaluation index can include at least one of the air tightness index, the energy consumption efficiency index, and the energy consumption efficiency index. The target evaluation function corresponding to each control parameter is constructed according to the quantification result, including: different preset evaluation indexes are assigned corresponding weights, and they are combined into a single composite evaluation index, that is, the target evaluation function, by weighted summation.

[0090] Taking the preset evaluation index including the air tightness index, the energy consumption efficiency index, and the energy consumption efficiency index as an example, after the three indexes are quantified, the specific mathematical expression of the target evaluation function is:

[0091] ;

[0092] In the formula, is the evaluation value of the target evaluation function, which is used to comprehensively evaluate the overall performance of a group of control parameters; is the quantification value of the oxygen reduction efficiency index; a quantitative value of the air tightness index; a quantitative value of the energy consumption efficiency index; , and are preset weight factors corresponding to the oxygen reduction efficiency index, the air tightness index and the energy consumption efficiency index respectively. , and The values of the above can be set according to requirements.

[0093] In this embodiment, a target evaluation function for evaluating the performance of different control parameter combinations is established according to a plurality of preset evaluation indexes, and a plurality of mutually restrictive engineering targets in the nitrogen charging maintenance process are converted into a unified and quantifiable mathematical evaluation index, thereby providing a clear optimization direction for subsequent optimization algorithms.

[0094] In one embodiment, the target control parameter at which the nitrogen charging system satisfies the target maintenance performance of the maintenance object is determined within the search space of initial control parameters, including: taking the parameter values in the control parameters as the position variables of each particle in the particle swarm; based on the historical optimal position of the particle and the global optimal position of the particle swarm, iteratively updating the position and velocity of the particle within the search space of the initial control parameters; in the case where the number of iterations reaches a preset number, or in the case where the change amount of the target evaluation function value corresponding to the global optimal position of the particle swarm is less than a preset threshold, obtaining the target control parameter according to the position components corresponding to the global optimal position.

[0095] In the process of iteratively updating the position and velocity of the particle, the initial control parameter obtained by each iteration is different.

[0096] Optionally, the nitrogen charging time t1 and the standing time t2 in the initial control parameters are taken as a group of control parameters, and the control parameter combination to be optimized is defined as the position of a particle in a two-dimensional search space. Each particle represents a group of candidate control parameter solutions. The target evaluation function value δ is taken as the fitness function value of the particle swarm optimization algorithm, that is, for the position of any particle, the fitness function value thereof is obtained by calculating the evaluation value δ corresponding to the position. The goal of algorithm iteration is to find the particle position that minimizes the fitness function value (target evaluation function value). The particle swarm optimization algorithm is used to optimize the target evaluation function to obtain a group of control parameters, i.e., the target control parameter, Figure 3 is the result heat map of the particle swarm optimization algorithm in this embodiment for optimizing the control parameters, and the color is used to represent the delta value (function value δ). Figure 3 The distribution of the fitness function value in the entire parameter search space is intuitively displayed, and the darker area in the figure represents the parameter combination area with a smaller evaluation value δ, i.e., a better comprehensive performance. With Figure 3The region indicated by the arrow is an example. The minimum value of the optimization function (Min Delta) is 0.400, the nitrogen filling duration t1 is 8.0 hours, the standing duration t2 is 13.0 hours, the cumulative nitrogen filling duration TN2 is 694.1 hours, the length of time during which the oxygen content is accumulated to 2% or more (T≥2%) is 456.0 hours, and the length of time during which the oxygen content is accumulated to less than 2% (T<2%) is 113.0 hours.

[0097] For example, at the beginning of the optimization process, a preset parameter range is determined according to the search space of the initial control parameters. For example, the value range of t1 is [0, 24] hours, and the value range of t2 is [0, 48] hours. A group of particles is randomly initialized in the preset parameter range, and each particle has an initial position and velocity. Subsequently, the algorithm enters an iterative optimization phase. In each iteration, the following operations are performed for each particle:

[0098] According to its current position, i.e., the current t1 and t2 values, its objective evaluation function is calculated, and the corresponding fitness function value is determined based on the objective evaluation function . The current fitness function value is compared with its own historical optimal fitness function value. If the current value is better (i.e., smaller), the historical optimal position is updated. The current fitness function value is compared with the global optimal fitness function value of the entire particle group. If the current value is better, the global optimal position is updated. After the fitness evaluation of all particles is completed, the velocity and position of each particle are updated according to the particle's own historical optimal position and the global optimal position of the entire particle group. The update process of the particle velocity and position can follow the following formulas:

[0099] Velocity update formula:

[0100] ;

[0101] Position update formula:

[0102] ;

[0103] where t is the current iteration number; is the velocity of particle i at the tth iteration; is the position of particle i at the tth iteration; is the inertia factor; and are learning factors; is a function that generates a random number between 0 and 1; is the optimal position experienced by particle i up to the tth iteration; is the optimal position experienced by the entire particle group up to the tth iteration.

[0104] The iteration process continues until a preset termination condition is met. According to actual needs, the termination condition can be set to reach a maximum number of iterations, or the termination condition can be set to a variation of the global optimal fitness function value being less than a preset threshold. When the algorithm terminates, the output global optimal position is the optimal control parameter combination found.

[0105] Table 1 lists some candidate parameter combinations and their corresponding evaluation values . In combination Figure 3 with Table 1, when the nitrogen filling time t1 is 8 hours and the standing time t2 is 13 hours, the minimum evaluation value 0.400014 is obtained. Therefore, this parameter combination is the optimal control parameter obtained by the optimization in this step.

[0106] Table 1: Example table of key optimization parameters

[0107]

[0108] In one embodiment, the working condition data of the maintenance object associated with the nitrogen filling system is obtained by collecting data from a plurality of sensors deployed inside and outside the maintenance object.

[0109] The sensors can include oxygen sensors, nitrogen sensors, temperature sensors, humidity sensors, etc. Optionally, a plurality of data acquisition sensors, such as oxygen concentration sensors, temperature sensors, and humidity sensors, are uniformly arranged at different spatial positions inside and outside the smoke stack.

[0110] Figure 4 FIG. 1 is a schematic diagram of the arrangement of one oxygen concentration sensor in this embodiment, wherein Figure 4 The horizontal and vertical numbers in the table represent the positions of the sensors, and the "outside" in each table represents that the sensor is arranged outside the smoke stack. The data "1,3" and "2,4" in the table represent the layers of the sensor arranged inside the smoke stack, for example, "1,3" represents the first layer and the third layer inside the smoke stack. Optionally, in order to ensure that the gas environment state inside and outside the smoke stack can be comprehensively monitored, the data acquisition device records the measurement values of all sensors at a preset time frequency, for example, every 2 hours, within a set maintenance period, for example, 90 days. In this way, a series of discrete working condition data corresponding to a specific space-time point can be obtained. Based on the data collected by the oxygen sensor during the entire maintenance period, a curve of oxygen concentration change over time can be drawn. Figure 5 FIG. 2 is a schematic diagram of a curve of oxygen concentration change over time in this embodiment, wherein different concentration curves correspond to different positions of the sensors, for example, the indices from left to right in "[9,6,3]" correspond to the horizontal coordinate, the vertical coordinate, and the layer number of the position of the sensor.

[0111] Further, during the data collection process, the state data of the nitrogen filling system actuators when working also needs to be recorded, such as the opening and closing time of the nitrogen filling electromagnetic valve, the cumulative running time of the nitrogen filling pump, etc. These actuator state data will be aligned in time with the environmental data collected by the sensors. The collected raw data may contain abnormal values or missing values due to temporary sensor failure or signal transmission interference. Therefore, before the data is used for subsequent steps, it needs to be preprocessed. The preprocessing step can include rejecting abnormal data points that are obviously beyond the physically possible range, and using interpolation methods to complete the missing data points to form a complete and reliable time series working condition data set. This data set will be used as the input of the subsequent steps.

[0112] In this embodiment, the control parameters are automatically optimized based on the target evaluation function, replacing the experience-dependent manual trial process in an algorithm-driven manner, which can efficiently search and determine the optimal target control parameters in a complex parameter search space; not only reduces the dependence on the experience of the operator, but also enables the optimization process to be no longer limited to a single target, but can comprehensively and balancedly weigh between the oxygen reduction speed, the low oxygen maintenance ability and the operating cost, so as to obtain the maintenance scheme with the optimal comprehensive benefit and ensure the optimization effect.

[0113] In one embodiment, Figure 6 A flowchart of a tobacco bale nitrogen filling maintenance multi-objective optimization method based on the FICK model and PSO is provided. As shown in Figure 6 the steps include:

[0114] Step 601, obtaining the working condition data of the maintenance object.

[0115] Optionally, the oxygen concentration, temperature and humidity data at different space-time points are collected through oxygen concentration sensors, temperature sensors and humidity sensors deployed inside and outside the maintenance object; the state of the nitrogen filling system actuators is recorded to obtain state data; and the collected data is preprocessed to obtain a time series working condition data set. The data preprocessing includes denoising, interpolation and other preprocessing methods.

[0116] Step 602, constructing a physical prediction model.

[0117] The physical prediction model for predicting the oxygen concentration change of the maintenance object can be constructed based on the working condition data and the preset FICK gas diffusion model. Optionally, the time series working condition data set is input, the FICK gas diffusion model is set, and the diffusion coefficient is calculated by numerical fitting method according to the oxygen concentration change in the working condition data and the FICK gas diffusion model, and the physical prediction model is obtained with the diffusion coefficient as the core physical parameter.

[0118] Step 603, predict the working condition of the maintenance object.

[0119] Wherein, the future working condition data of the maintenance object is predicted based on the physical prediction model. A multi-objective evaluation function for evaluating the effectiveness of different control parameter combinations is established, which integrates the oxygen reduction efficiency index, the air tightness index and the energy consumption efficiency index, and quantifies the multi-objective evaluation function based on the predicted working condition data (concentration curve).

[0120] Optionally, a set of control parameters (t1, t2) is input, i.e. the initial control parameters in the above embodiment, and the physical prediction model derives the predicted oxygen concentration curve with the given control parameters as the boundary conditions; the quantified values of the oxygen reduction efficiency index, the air tightness index and the energy consumption efficiency index are obtained based on the oxygen concentration curve; and the evaluation value of the multi-objective evaluation function is calculated and output based on the obtained quantified values of each index. The multi-objective evaluation function is the objective evaluation function in the above embodiment.

[0121] Step 604, adopt PSO (Particle Swarm Optimization) optimization.

[0122] Wherein, the particle swarm optimization algorithm is used to optimize the multi-objective evaluation function to obtain a set of target control parameters. Optionally, the multi-objective evaluation function is defined as the fitness function, a group of particles is initialized, each particle represents a set of candidate control parameters, the control parameters include: nitrogen filling time parameter and standing time parameter; the particle swarm optimization algorithm is used to optimize the multi-objective evaluation function, and the fitness of all particles is evaluated, in the case that the number of iterations reaches a preset number, or in the case that the change amount of the multi-objective evaluation function value corresponding to the global optimal position of the particle swarm is less than a preset threshold, it is judged that the termination condition is met, and the evaluation value is output to obtain a set of optimal control parameters. The iteration steps are as follows: the speed and position of each particle in the particle swarm are iteratively updated, and the update process is based on the historical optimal position of the particle itself and the global optimal position of the entire particle swarm; wherein, the historical optimal position and the global optimal position are determined by evaluating the multi-objective evaluation function.

[0123] Step 605, control the maintenance object.

[0124] Optionally, the optimal control parameters, i.e. the target control parameters, are input, and the nitrogen filling time parameter and the standing time parameter in the optimal control parameters are configured to the execution device for controlling the nitrogen filling system, so that the nitrogen filling system periodically performs the steps of nitrogen filling or standing according to the optimal control parameters.

[0125] Optionally, the target control parameters obtained by optimization can be displayed on a man-machine interaction interface and confirmed by system operators before application, or automatically configured to the lower control execution device by the system.

[0126] Figure 7 A structural diagram of a system for implementing multi-objective optimization of nitrogen-filled tobacco bale curing based on FICK model and PSO is provided. The system can be used to execute the method shown and includes a data acquisition device 110, a processing device 120, and a control execution device 130. Figure 6

[0127] The data acquisition device 110 is used to obtain the working condition data of the curing object through a sensor interface. Optionally, the data acquisition device 110 includes a sensor array deployed inside and outside the tobacco bale. The sensor array includes at least a plurality of oxygen concentration sensors for collecting oxygen concentration data at different space-time points. The device can also include temperature sensors and humidity sensors for recording temperature data and humidity data, and a state monitor for recording state data of the nitrogen filling system actuator.

[0128] The processing device 120 is used to receive the working condition data collected by the data acquisition device 110 and process it to generate optimal control parameters. The processing device 120 includes a physical modeling module 121, an evaluation function construction module 122, and a parameter optimization module 123.

[0129] The physical modeling module 121 is used to receive the working condition data and obtain a diffusion coefficient representing the gas diffusion characteristics of the curing object based on a pre-set FICK gas diffusion model through calculation, and then construct a physical prediction model capable of predicting oxygen concentration changes.

[0130] The evaluation function construction module 122 is used to establish a multi-objective evaluation function for evaluating the effectiveness of different control parameter combinations based on the physical prediction model constructed by the physical modeling module 121. The function performs weighted summation of the oxygen reduction efficiency, air tightness, and energy consumption efficiency to obtain a multi-objective evaluation function.

[0131] The parameter optimization module 123 is used to use the multi-objective evaluation function established by the evaluation function construction module 122 as the optimization target and use the particle swarm optimization algorithm to iteratively optimize the initial control parameters. The parameter optimization module 123 outputs a set of optimal control parameters that minimize the evaluation value.

[0132] The control execution device 130 is used to receive the target control parameters output by the parameter optimization module 123 of the processing device 120 through a parameter configuration interface. A control instruction generator generates control instructions based on the parameters and sends the control instructions to the nitrogen filling system to implement the regulation and control of the nitrogen filling system associated with the curing object. For example, the optimal nitrogen filling time and resting time are set as the working parameters of the nitrogen filling machine and related valve groups.

[0133] ​​Optionally, the target control parameter combination (e.g., t1=8 hours, t2=13 hours) found in step 604 is output to the control execution device 130 by the parameter optimization module 123 of the processing device 120. After receiving the target control parameter combination, the control execution device 130 sets the target control parameter combination as the actual working parameters of the nitrogen filling system associated with the curing object. Subsequently, the nitrogen filling system periodically operates according to the new parameters, that is, the nitrogen filling is performed for 8 hours, and then the nitrogen filling is stopped and the curing object is kept still for 13 hours, which is one complete operation cycle. The cycle is repeated until the end of the entire curing process. It can be understood that, according to different application scenarios, the target control parameters calculated by the method can be other values.

[0134] Based on the target control parameters in the embodiment, the nitrogen filling system can be regulated to achieve better technical effects than the existing fixed strategy. For example, in a comparative embodiment, the existing fixed strategy uses a parameter combination of t1=8 hours and t2=16 hours. It takes 750 hours for the oxygen concentration to reach a preset threshold (≤2%). In a 90-day cycle, the cumulative nitrogen filling time is 720 hours. However, using the parameter combination of t1=8 hours and t2=13 hours obtained by the optimization method in the embodiment, it only takes 456 hours for the oxygen concentration to reach the same threshold, which is 294 hours ahead of schedule. In a 90-day cycle, the cumulative nitrogen filling time is 694 hours, which is reduced by 26 hours. The results show that the method of the embodiment can significantly improve the oxygen reduction efficiency and reduce the total energy consumption.

[0135] It should be understood that, although the steps in the flowcharts involved in the above-described embodiments are displayed in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowcharts involved in the above-described embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or stages. For example, the working conditions of the curing object can be obtained synchronously while the PSO optimization is performed.

[0136] Based on the same inventive concept, the embodiments of the present application also provide a nitrogen filling curing device for implementing the above-mentioned nitrogen filling curing method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more nitrogen filling curing device embodiments provided below can refer to the limitations of the nitrogen filling curing method described above, which will not be described again herein.

[0137] In one embodiment, as shown in Figure 8 a nitrogen charging device is provided, comprising:

[0138] a collection module configured to acquire working condition data of a maintenance object associated with the nitrogen charging system;

[0139] a processing module configured to predict, according to the working condition data and the gas diffusion characteristics, a concentration curve of the gas concentration inside the maintenance object over time when the nitrogen charging system operates based on initial control parameters;

[0140] a construction module configured to quantify a preset evaluation index according to the concentration curve and / or the initial control parameters, and to construct a target evaluation function corresponding to each control parameter according to the quantification result;

[0141] a parameter optimization module configured to determine, within a search space of the initial control parameters, a target control parameter at which the nitrogen charging system satisfies a target maintenance effectiveness of the maintenance object; wherein the target maintenance effectiveness is quantified according to the target evaluation function;

[0142] a control module configured to control the operation state of the nitrogen charging system according to the target control parameter.

[0143] In some embodiments, the processing module predicts, according to the working condition data and the gas diffusion characteristics, the concentration curve of the gas concentration inside the maintenance object over time when the nitrogen charging system operates based on the initial control parameters, including: obtaining a gas diffusion model pre-constructed according to the gas diffusion characteristics; generating a physical prediction model for predicting the trend of the gas concentration inside the maintenance object over time by combining the working condition data and the gas diffusion model; and obtaining the concentration curve output by the physical prediction model when the physical prediction model satisfies the boundary conditions with the initial control parameters as the boundary conditions.

[0144] Optionally, the processing module generates the physical prediction model for predicting the trend of the gas concentration inside the maintenance object over time by combining the working condition data and the gas diffusion model, including: obtaining state data when the nitrogen charging system operates; calculating the diffusion coefficient of the gas diffusion model with the gas concentration data in the working condition data as the known conditions and the state data as the boundary conditions; and configuring the gas diffusion model based on the diffusion coefficient to obtain the physical prediction model.

[0145] In some embodiments, the preset evaluation index includes an oxygen reduction efficiency index, and the construction module quantifies the preset evaluation index according to the concentration curve, including: calculating the time for the oxygen concentration to drop from an initial concentration to a preset target concentration threshold according to the concentration curve to obtain the oxygen reduction efficiency index corresponding to the control parameter, wherein the time is negatively correlated with the oxygen reduction efficiency inside the maintenance object.

[0146] Optionally, the preset evaluation index includes an air tightness index, and the constructing module quantifies the preset evaluation index according to the concentration curve, including: according to the concentration curve, a rate of the oxygen concentration rebounding with time after the oxygen concentration reaches the target concentration threshold and enters the low-oxygen maintenance stage is calculated to obtain the air tightness index corresponding to the control parameter, wherein the rate is negatively correlated with the air tightness of the space where the curing object is located.

[0147] Optionally, the preset evaluation index includes an energy consumption efficiency index, and the constructing module quantifies the preset evaluation index according to the control parameter, including: an energy consumption efficiency index is obtained according to the time length sum of all nitrogen charging stages in the control parameter; wherein the time length sum is negatively correlated with the energy consumption efficiency of the curing object.

[0148] In some embodiments, the parameter optimization module determines the target control parameter when the nitrogen charging system meets the target curing efficiency of the curing object in the search space of the initial control parameter, including: taking the parameter value in the control parameter as the position variable of each particle in the particle swarm; based on the historical optimal position of the particle and the global optimal position of the particle swarm, iteratively updating the position and velocity of the particle in the search space of the initial control parameter; in the case where the number of iterations reaches a preset number, or in the case where the change amount of the target evaluation function value corresponding to the global optimal position of the particle swarm is less than a preset threshold, the target control parameter is obtained according to the position component corresponding to the global optimal position.

[0149] In some embodiments, the collecting module obtains the working condition data of the curing object associated with the nitrogen charging system, including: obtaining the working condition data according to the data of the plurality of sensors deployed inside and outside the curing object.

[0150] The above-mentioned various modules in the nitrogen charging curing device can be all or partially realized by software, hardware and combinations thereof. The above-mentioned various modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the above-mentioned various modules.

[0151] In one embodiment, a computer device is provided, which can be a terminal, and its internal structure diagram can be as shown in Figure 9As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with the external terminal in a wired or wireless manner. The wireless manner can be realized by WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to realize a nitrogen charging maintenance method.

[0152] Those skilled in the art can understand that, Figure 9 The skilled in the art can understand that,

[0153] In one embodiment, a computer device is also provided, including a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the steps in the above method embodiments.

[0154] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by the processor to realize the steps in the above method embodiments.

[0155] In one embodiment, a computer program product is provided, which includes a computer program, and the computer program is executed by the processor to realize the steps in the above method embodiments.

[0156] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0157] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0158] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A nitrogen-filled curing method, characterized in that, The method includes: Obtain the operating condition data of the maintenance objects associated with the nitrogen filling system; Based on the operating data and gas diffusion characteristics, predict the gas concentration curve inside the object being maintained as a function of time when the nitrogen filling system is running based on the initial control parameters. Based on the concentration curve and / or initial control parameters, the preset evaluation index is quantified, and based on the quantification results, a target evaluation function corresponding to each of the control parameters is constructed. Within the search space of the initial control parameters, the target control parameters are determined so that the nitrogen filling system satisfies the target maintenance efficiency of the object being maintained; wherein, the target maintenance efficiency is quantified according to the target evaluation function; The operating status of the nitrogen filling system is adjusted according to the target control parameters.

2. The method according to claim 1, characterized in that, Based on the operating data and gas diffusion characteristics, predict the gas concentration curve inside the object being maintained as a function of time when the nitrogen filling system is running based on the initial control parameters, including: Obtain a pre-constructed gas diffusion model based on gas diffusion characteristics; By combining the operating data and the gas diffusion model, a physical prediction model is generated to predict the trend of gas concentration changes over time inside the object being maintained. Using the initial control parameters as boundary conditions, the concentration curve output by the physical prediction model when the boundary conditions are met is obtained.

3. The method according to claim 2, characterized in that, Combining the operating data and the gas diffusion model, a physical prediction model is generated to predict the trend of gas concentration changes over time inside the object being maintained, including: Obtain the status data of the nitrogen filling system during operation; Using the gas concentration data in the operating condition data as known conditions and the state data as boundary conditions, the diffusion coefficient of the gas diffusion model is calculated. The gas diffusion model is configured based on the diffusion coefficient to obtain the physical prediction model.

4. The method according to claim 1, characterized in that, The preset evaluation indicators include an oxygen reduction efficiency indicator. The preset evaluation indicators are quantified based on the concentration curve, including: Based on the concentration curve, the time it takes for the oxygen concentration to decrease from the initial concentration to the preset target concentration threshold is calculated, and the oxygen reduction efficiency index corresponding to the control parameter is obtained, wherein the time is negatively correlated with the oxygen reduction efficiency within the maintained object.

5. The method according to claim 1, characterized in that, The preset evaluation indicators include airtightness indicators, and the preset evaluation indicators are quantified according to the concentration curve, including: Based on the concentration curve, the rate at which the oxygen concentration recovers over time after reaching the target concentration threshold and entering the low-oxygen maintenance phase is calculated, and the airtightness index corresponding to the control parameter is obtained, wherein the rate is negatively correlated with the airtightness of the space where the object being maintained is located.

6. The method according to claim 1, characterized in that, The preset evaluation indicators include energy efficiency indicators. The preset evaluation indicators are quantified according to the control parameters, including: The energy efficiency index is obtained based on the sum of the time lengths of all nitrogen-filling stages in the control parameters; wherein the sum of the time lengths is negatively correlated with the energy efficiency of the object being maintained.

7. The method according to claim 1, characterized in that, Within the search space of the initial control parameters, the target control parameters for the nitrogen-filling system to meet the target maintenance efficiency of the object being maintained are determined, including: The parameter values ​​within the control parameters are used as the position variables for each particle in the particle swarm. Based on the historical best position of the particle and the global best position of the particle swarm, the position and velocity of the particle are iteratively updated within the search space of the initial control parameters. When the number of iterations reaches a preset number, or when the change in the target evaluation function value corresponding to the global optimal position of the particle swarm is less than a preset threshold, the target control parameters are obtained based on the position component corresponding to the global optimal position.

8. The method according to claim 1, characterized in that, Obtain operational data of the maintenance objects associated with the nitrogen filling system, including: The operating condition data is obtained by collecting data from multiple sensors deployed inside and outside the object being maintained.

9. A nitrogen-filled curing device, characterized in that, The device includes: The data acquisition module is used to acquire the operating condition data of the maintenance objects associated with the nitrogen filling system; The processing module is used to predict, based on the operating data and gas diffusion characteristics, the concentration curve of the gas concentration inside the object under maintenance as a function of time when the nitrogen filling system is running based on the initial control parameters. The construction module is used to quantify the preset evaluation index according to the concentration curve and / or the initial control parameters, and to construct the target evaluation function corresponding to each of the control parameters according to the quantification results; The parameter optimization module is used to determine the target control parameters within the search space of the initial control parameters, so that the nitrogen filling system satisfies the target maintenance efficiency of the object being maintained; wherein, the target maintenance efficiency is quantified according to the target evaluation function; The control module is used to control the operating status of the nitrogen filling system according to the target control parameters.

10. A nitrogen-filled curing device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 8.

Images