AI-based tobacco storage optimization system

Abstract

The present invention relates to the field of adaptive control technology, specifically to an AI-based tobacco storage optimization system, the system comprising: an environmental data acquisition module that captures temperature, humidity, and CO2 concentration data in a tobacco storage environment, and monitors the physiological response of tobacco to real-time environmental changes through time series analysis. In the present invention, by real-time capture and analysis of comprehensive environmental data, the growth prediction of tobacco under different environmental conditions is effectively simulated, thereby allowing real-time and precise adjustment of storage conditions. The dynamic adjustment is based on direct feedback from physiological state monitoring and environmental changes, ensuring that tobacco is always in the optimal environment during storage. This precise control method greatly reduces quality fluctuations caused by environmental errors, and the deep interactive simulation of environmental factors and tobacco physiological activity provides a method for predicting and responding to future changes, making the tobacco storage process more controllable and predictable, and significantly improving the stability and efficiency of the operation.

Description

Technical Field

[0001] The present invention relates to the field of adaptive control technology, and in particular to an AI-based tobacco storage optimization system. Background Art

[0002] Adaptive control is a control strategy that can automatically adjust its control parameters during system operation to adapt to changes in the environment or the system's own state. This technology is widely used in automation, aerospace, biotechnology, energy systems, and industrial process control. Its core advantage is that it can improve the stability, efficiency, and response speed of the system. Adaptive control systems usually rely on real-time data monitoring and dynamic model updates to achieve optimal control effects through continuous learning and adaptation to environmental changes. This technology is particularly important for dealing with dynamic systems with complex, nonlinear or unknown parameters. It can effectively respond to internal and external disturbances and maintain continuous optimization of system performance.

[0003] Among them, the tobacco storage optimization system refers to the use of adaptive control technology to manage and optimize the storage conditions of tobacco leaves, such as temperature, humidity and other environmental factors that may affect the quality of tobacco leaves. The purpose of this system is mainly to ensure that tobacco leaves maintain the best freshness and quality during storage and reduce quality losses due to environmental inadaptability. By real-time monitoring of environmental parameters and tobacco leaf status and automatically adjusting control measures, the system can effectively extend the shelf life of tobacco leaves and increase their market value. The application of this technology not only improves the automation level of tobacco leaf processing technology, but also brings significant economic benefits to the tobacco industry.

[0004] Although adaptive control technology has found applications in multiple industries, it is still insufficient when dealing with systems with highly nonlinear and variable factors, especially in the storage of sensitive crops such as tobacco leaves. Existing technologies usually cannot fully capture the real-time impact of rapidly changing environmental factors on tobacco quality, which may lead to delayed or inaccurate control measures, thus affecting the quality and freshness of tobacco leaves. In addition, adaptive systems that rely on fixed models often have difficulty in responding flexibly to unknown or emerging changes, which limits the adaptability and response speed of the system in actual operation. These deficiencies may lead to inefficiency, increased costs and reduced market competitiveness in the storage process, especially in market conditions with changing demands and complex environments. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an AI-based tobacco storage optimization system.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: The tobacco storage optimization system based on AI comprises:

[0007] The environmental data acquisition module captures the temperature, humidity, and CO2 concentration data in the tobacco storage environment, monitors the physiological response of tobacco leaves to real-time environmental changes through time series analysis, records the correlation data between environmental parameters and the physiological state of tobacco leaves, and generates environmental parameter records;

[0008] The feature analysis module identifies the direct impact of changes in key environmental factors including temperature and humidity on tobacco leaves based on the environmental parameter records, analyzes the correlation between multiple key environmental factors and tobacco leaf growth status, establishes a dynamic feature mapping of tobacco leaf adaptability, and obtains tobacco leaf adaptability analysis results;

[0009] The environmental matching model modeling module extracts the interaction model between tobacco leaf physiological activity and environmental factors from the tobacco leaf adaptability analysis results, simulates tobacco leaf growth prediction under differentiated environmental settings, simulates tobacco leaf growth behavior, and establishes a tobacco leaf state prediction model;

[0010] The parameter adjustment and optimization module adjusts the setting parameters of the tobacco storage control system, including humidity, temperature and CO2 concentration, according to the prediction data output by the tobacco state prediction model, monitors the environmental control parameters in real time, and establishes an environmental control plan.

[0011] As a further solution of the present invention, the step of obtaining the environmental parameter record is specifically as follows:

[0012] The temperature, humidity and CO2 concentration in the tobacco storage environment are monitored using the improved formula:

[0013] ,

[0014] and

[0015] ,

[0016] and

[0017] ,

[0018] Calculate the average temperature, humidity, and CO2 concentration at each time point to generate basic environmental data;

[0019] in, represents the average temperature at a time point, Represents the average humidity at a time point, represents the average CO2 concentration at time point i, , , Respectively represent the temperature, humidity and CO2 concentration monitored at the jth time point, , , are the adjustment coefficients of temperature, humidity and CO2 concentration, respectively, and n represents the number of monitoring times at each time point;

[0020] Analyze the basic environmental data and calculate the change rate of temperature, humidity and CO2 concentration using the formula:

[0021] ,

[0022] and

[0023] ,

[0024] and

[0025] ,

[0026] Get the change rate of temperature, humidity and CO2 concentration to generate environmental change data;

[0027] in, represents the rate of change of temperature, represents the rate of change of humidity, represents the rate of change of CO2 concentration, , , are the square roots of temperature, humidity and CO2 concentration, respectively, to balance the impact of extreme values ​​on the results;

[0028] The environmental change data were used to evaluate the impact of environmental changes on the physiological state of tobacco leaves using the formula:

[0029] ,

[0030] Obtain the correlation between environmental parameters and the physiological state of tobacco leaves, and generate environmental parameter records;

[0031] in, Represents the correlation between environmental parameters and the physiological state of tobacco leaves, , , are the weight coefficients of temperature, humidity and CO2 concentration changes respectively.

[0032] As a further solution of the present invention, the steps for obtaining the tobacco leaf adaptability analysis results are specifically as follows:

[0033] From the environmental parameter records, the key variables of temperature and humidity that affect the physiological state of tobacco leaves are identified using the formula:

[0034] ,

[0035] Calculate the impact index of key environmental factors at each time point and generate the impact data of key environmental factors;

[0036] in, Represents the impact index of key environmental factors, Represents the temperature data in the environmental parameter record, Represents the humidity data in the environmental parameter record, , Represent the average values ​​of temperature and humidity, , is the weight coefficient of temperature and humidity, is the square root of the sum of the squares of the temperature and humidity combination;

[0037] The correlation between the key environmental factors and the growth status of tobacco leaves was analyzed using the formula:

[0038] ,

[0039] Calculate the correlation coefficient between environmental factors and tobacco leaf growth status at each time point to generate data on the correlation between environmental factors and growth status;

[0040] in, Represents the correlation between environmental factors and tobacco leaf growth status, Represents the impact index of key environmental factors, is the maximum value of the key environmental factor impact index. is the tobacco leaf growth status index, and n is the number of reference growth status indicators;

[0041] The data on correlation between environmental factors and growth status are used to establish a dynamic characteristic map of tobacco leaf adaptability using the formula:

[0042] ,

[0043] Generate tobacco leaf adaptability analysis results;

[0044] in, Represents the adaptability of tobacco leaves. is the standard deviation of the correlation index between environmental factors and tobacco leaf growth status, and exp is the natural index.

[0045] As a further solution of the present invention, the steps of acquiring the tobacco leaf state prediction model are specifically as follows:

[0046] The key parameters were extracted from the tobacco leaf adaptability analysis results using the formula:

[0047] ,

[0048] Calculate the standardized physiological activity of tobacco leaves and generate an interaction model between the physiological activity of tobacco leaves and environmental factors;

[0049] in, Represents the interaction model between tobacco leaf physiological activity and environmental factors. represents the adjustment factor, represent The mean of represent square root of variance;

[0050] Based on the interaction model between tobacco leaf physiological activity and environmental factors, tobacco leaf growth behavior simulation was performed using the formula:

[0051] ,

[0052] Calculate the impact of multiple environmental factors and generate tobacco leaf growth prediction data;

[0053] in, Represents tobacco leaf growth forecast data, represents the influence coefficient, exp represents the natural index, represents the normalization factor;

[0054] Using the tobacco leaf growth prediction data, the formula is adopted:

[0055] ,

[0056] The contribution of multiple predictors is calculated through linear combination to generate a tobacco leaf state prediction model;

[0057] in, represents the tobacco leaf status prediction model, represents the model intercept, Representative predictors The coefficient of .

[0058] As a further solution of the present invention, the step of obtaining the environmental control solution is specifically as follows:

[0059] Based on the data output by the tobacco leaf state prediction model, the humidity control parameters are adjusted using the formula:

[0060] ,

[0061] Update humidity settings and generate humidity adjustment plans;

[0062] in, Represents the new humidity setting, Represents the current humidity. represents the humidity adjustment factor, Represents the target humidity value, represents the standard deviation of humidity;

[0063] Using the tobacco leaf state prediction model, the temperature parameter is adjusted, and the formula is adopted:

[0064] ,

[0065] Update temperature settings and generate temperature adjustment plans;

[0066] in, Represents the new temperature setting, Represents the current temperature, represents the temperature adjustment factor, Represents the target temperature value, represents the standard deviation of temperature;

[0067] According to the output of the tobacco leaf state prediction model, the CO2 concentration parameter is adjusted using the formula:

[0068] ,

[0069] Update CO2 settings and establish CO2 adjustment plan;

[0070] in, represents the new CO2 setting, Represents the current CO2 concentration, represents the CO2 adjustment factor, Represents the target CO2 concentration value, represents the standard deviation of CO2;

[0071] The humidity adjustment scheme, the temperature adjustment scheme and the CO2 adjustment scheme are combined to monitor and optimize environmental parameters in real time, using the formula:

[0072] ,

[0073] Determine environmental control plan .

[0074] Compared with the prior art, the advantages and positive effects of the present invention are:

[0075] In the present invention, by real-time capture and analysis of comprehensive environmental data, the growth prediction of tobacco leaves under different environmental conditions is effectively simulated, thereby allowing real-time and precise adjustment of storage conditions. This dynamic adjustment is based on direct feedback from physiological state monitoring and environmental changes, ensuring that tobacco leaves are always in the optimal environment during storage. This precise control method greatly reduces quality fluctuations caused by environmental errors and optimizes the market performance and economic value of tobacco leaves. In addition, the deep interactive simulation of environmental factors and the physiological activity of tobacco leaves provides a method for predicting and responding to future changes, making the tobacco storage process more controllable and predictable, and significantly improving the stability and efficiency of operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 is a system flow chart of the present invention;

[0077] Figure 2 A flowchart of the steps for obtaining the environmental parameter record of the present invention;

[0078] Figure 3 A flowchart of steps for obtaining tobacco leaf adaptability analysis results of the present invention;

[0079] Figure 4 A flowchart of the steps for obtaining the tobacco leaf state prediction model of the present invention;

[0080] Figure 5 The figure is a flow chart of the steps for obtaining the environmental control scheme of the present invention. DETAILED DESCRIPTION

[0081] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0082] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0083] Example:

[0084] See also Figure 1 , the AI-based tobacco storage optimization system includes:

[0085] The environmental data acquisition module captures the temperature, humidity, and CO2 concentration data in the tobacco storage environment, monitors the physiological response of tobacco leaves to real-time environmental changes through time series analysis, records the correlation data between environmental parameters and the physiological state of tobacco leaves, and generates environmental parameter records;

[0086] The feature analysis module identifies the direct impact of changes in key environmental factors including temperature and humidity on tobacco leaves based on environmental parameter records, analyzes the correlation between multiple key environmental factors and tobacco leaf growth status, establishes a dynamic feature mapping of tobacco leaf adaptability, and obtains tobacco leaf adaptability analysis results;

[0087] The environmental matching model modeling module extracts the interaction model between tobacco leaf physiological activity and environmental factors from the tobacco leaf adaptability analysis results, simulates tobacco leaf growth prediction under differentiated environmental settings, simulates tobacco leaf growth behavior, and establishes a tobacco leaf state prediction model;

[0088] The parameter adjustment and optimization module adjusts the setting parameters of the tobacco storage control system, including humidity, temperature and CO2 concentration, according to the prediction data output by the tobacco state prediction model, monitors the environmental control parameters in real time, and establishes an environmental control plan.

[0089] Environmental parameter records specifically include temperature records, humidity records, and CO2 concentration records. The tobacco leaf adaptability analysis results include changes in key environmental factors such as temperature and humidity, and dynamic feature mapping of tobacco leaf adaptability. The tobacco leaf state prediction model includes the interaction between physiological activity and environmental factors, growth prediction, and growth behavior simulation. The environmental control scheme includes humidity adjustment, temperature adjustment, and CO2 concentration adjustment.

[0090] See also Figure 2 , the specific steps for obtaining environmental parameter records are:

[0091] The temperature, humidity and CO2 concentration in the tobacco storage environment are monitored using the improved formula:

[0092] ,

[0093] and

[0094] ,

[0095] and

[0096] ,

[0097] Calculate the average temperature, humidity, and CO2 concentration at each time point to generate basic environmental data;

[0098] in, represents the average temperature at a time point, Represents the average humidity at a time point, represents the average CO2 concentration at time point i, , , Respectively represent the temperature, humidity and CO2 concentration monitored at the jth time point, , , are the adjustment coefficients of temperature, humidity and CO2 concentration, respectively, and n represents the number of monitoring times at each time point;

[0099] Analyze the basic environmental data and calculate the change rate of temperature, humidity and CO2 concentration using the formula:

[0100] ,

[0101] and

[0102] ,

[0103] and

[0104] ,

[0105] Get the change rate of temperature, humidity and CO2 concentration to generate environmental change data;

[0106] in, represents the rate of change of temperature, represents the rate of change of humidity, represents the rate of change of CO2 concentration, , , are the square roots of temperature, humidity and CO2 concentration, respectively, to balance the impact of extreme values ​​on the results;

[0107] Using environmental change data, the impact of environmental changes on the physiological state of tobacco leaves was evaluated using the formula:

[0108] ,

[0109] Obtain the correlation between environmental parameters and the physiological state of tobacco leaves, and generate environmental parameter records;

[0110] in, Represents the correlation between environmental parameters and the physiological state of tobacco leaves, , , are the weight coefficients of temperature, humidity and CO2 concentration changes respectively.

[0111] The actual data set:

[0112] Temperature data : (Unit: Celsius);

[0113] Humidity data : (unit:%);

[0114] CO2 concentration data : (Unit: ppm);

[0115] Adjustment coefficient =1.1, =1.05, =1.02; monitoring times n=5;

[0116] formula: ,

[0117] and

[0118] ,

[0119] and

[0120] ,

[0121] calculate:

[0122] temperature Calculation:

[0123] ,

[0124] humidity Calculation:

[0125] ,

[0126] CO2 concentration Calculation:

[0127] ,

[0128] formula: ,

[0129] and

[0130] ,

[0131] and

[0132] ,

[0133] Set the average temperature at the next time point to 27.5°C, the humidity to 60.25%, and the CO2 concentration to 455ppm.

[0134] calculate:

[0135] Temperature change rate :

[0136] ,

[0137] Humidity change rate :

[0138] ,

[0139] CO2 concentration change rate :

[0140] ,

[0141] formula: ,

[0142] Set weight coefficient =0.5, =0.3, =0.2.

[0143] calculate: ,

[0144] Analysis: It means that at time point i, the comprehensive impact index of environmental changes on the physiological state of tobacco leaves is 0.265, and lower values ​​indicate slight environmental impact.

[0145] See also Figure 3 , the steps for obtaining the tobacco leaf adaptability analysis results are as follows:

[0146] From the environmental parameter records, the key variables of temperature and humidity that affect the physiological state of tobacco leaves are identified using the formula:

[0147] ,

[0148] Calculate the impact index of key environmental factors at each time point and generate the impact data of key environmental factors;

[0149] in, Represents the impact index of key environmental factors, Represents the temperature data in the environmental parameter record, Represents the humidity data in the environmental parameter record, , Represent the average values ​​of temperature and humidity, , is the weight coefficient of temperature and humidity, is the square root of the sum of the squares of the temperature and humidity combination;

[0150] The correlation between the key environmental factors and the growth status of tobacco leaves was analyzed using the formula:

[0151] ,

[0152] Calculate the correlation coefficient between environmental factors and tobacco leaf growth status at each time point to generate data on the correlation between environmental factors and growth status;

[0153] in, Represents the correlation between environmental factors and tobacco leaf growth status, Represents the impact index of key environmental factors, is the maximum value of the key environmental factor impact index. is the tobacco leaf growth status index, and n is the number of reference growth status indicators;

[0154] The correlation data between environmental factors and growth status are used to establish the dynamic characteristic mapping of tobacco leaf adaptability using the formula:

[0155] ,

[0156] Generate tobacco leaf adaptability analysis results;

[0157] in, Represents the adaptability of tobacco leaves. is the standard deviation of the correlation index between environmental factors and tobacco leaf growth status, and exp is the natural index.

[0158] formula: ,

[0159] Parameter explanation and source:

[0160] , : represents the measured values ​​of temperature and humidity at a certain time point i. For example, the temperature and humidity at 12 noon on a certain day are measured as 25℃ and 40% humidity respectively;

[0161] , : Indicates the average value of temperature and humidity over a period of time. In the data of one month, the average temperature is 22℃ and the average humidity is 50%;

[0162] , : Weight coefficient, used to adjust the importance of the impact of temperature and humidity changes on the physiological state of tobacco leaves; the coefficient is set based on previous research or experimental data. =0.6 and =0.4.

[0163] Calculation process:

[0164] Calculate the deviation of temperature and humidity:

[0165] Temperature deviation: ,

[0166] Humidity deviation: ,

[0167] Calculate the numerator:

[0168] ,

[0169] Calculate the denominator:

[0170] ,

[0171] calculate : ,

[0172] Result analysis: =0.123 means that at the target time point, the impact index of environmental factors on tobacco leaves is 0.123, which is a standardized value and is low, indicating that environmental changes have less impact on tobacco leaves.

[0173] formula: ,

[0174] Parameter explanation and source:

[0175] : Key environmental factors impact index; :all The maximum value in the measurement period is set to 0.2; : Tobacco leaf growth status indicators, such as leaf length and chlorophyll content, are set to 1.0, indicating a healthy state; n: The number of growth status indicators involved in the calculation, set to 1.

[0176] Calculation process:

[0177] standardization : ,

[0178] calculate : ,

[0179] Result analysis: =0.165 indicates that the correlation between environmental factors and tobacco leaf growth status is moderate. This is a standardized correlation index, indicating that the impact of environmental changes on tobacco leaf growth is significant but not extreme.

[0180] formula: ,

[0181] Parameter explanation and source:

[0182] : The standard deviation of the growth rate is set to 0.1 in a typical growth cycle.

[0183] Calculation process:

[0184] Calculate the exp parameter: ,

[0185] Compute the exponential function: ,

[0186] calculate : ,

[0187] Result analysis: =0.998 indicates that tobacco leaves have extremely high adaptability and can match the current environmental conditions well.

[0188] See also Figure 4 , the steps for obtaining the tobacco leaf state prediction model are as follows:

[0189] The key parameters were extracted from the tobacco leaf adaptability analysis results using the formula:

[0190] ,

[0191] Calculate the standardized physiological activity of tobacco leaves and generate an interaction model between the physiological activity of tobacco leaves and environmental factors;

[0192] in, Represents the interaction model between tobacco leaf physiological activity and environmental factors. represents the adjustment factor, represent The mean of represent square root of variance;

[0193] Based on the interaction model between tobacco leaf physiological activity and environmental factors, tobacco leaf growth behavior simulation was performed using the formula:

[0194] ,

[0195] Calculate the impact of multiple environmental factors and generate tobacco leaf growth prediction data;

[0196] in, Represents tobacco leaf growth forecast data, represents the influence coefficient, exp represents the natural index, represents the normalization factor;

[0197] Using tobacco leaf growth forecast data, the formula is:

[0198] ,

[0199] The contribution of multiple predictors is calculated through linear combination to generate a tobacco leaf state prediction model;

[0200] in, represents the tobacco leaf status prediction model, represents the model intercept, Representative predictors The coefficient of .

[0201] formula: ,

[0202] in: : Output of the interactive model between tobacco leaf physiological activity and environmental factors; :Analysis results of tobacco leaf adaptability; : Adjustment coefficient, set as a constant, assumed to be 1.0 to simplify the model; : The variance of .

[0203] Set up the data:

[0204] Set a group The data is ;

[0205] calculate ;

[0206] variance Calculated as ,but .

[0207] Calculation example:

[0208] choose =0.9,

[0209] ,

[0210] Result analysis:

[0211] =0.447 means that under given environmental factors, the interactive model output of tobacco leaf physiological activity is 0.447, reflecting the response intensity of tobacco leaves to the target environment.

[0212] formula:

[0213] ,

[0214] in:

[0215] :Tobacco leaf growth prediction data; : Interaction model output; : influence coefficient, set to 1.0; m: the number of environmental factors, assumed to be 4.

[0216] Set up the data:

[0217] Set the M value to ;

[0218] ,

[0219] Calculation example:

[0220] ;

[0221] Result analysis: =0.243 indicates the contribution of environmental factors to tobacco leaf growth.

[0222] formula:

[0223] ,

[0224] in:

[0225] : Output of tobacco leaf status prediction model; : Model intercept, set to 0.1; : Predictors The coefficient of is set to 1.0.

[0226] Calculation example:

[0227] ,

[0228] Result analysis: =0.343 represents the predicted value of tobacco leaf growth status under given environmental factors.

[0229] See also Figure 5 , the specific steps for obtaining the environmental control plan are:

[0230] Based on the data output by the tobacco leaf state prediction model, the humidity control parameters are adjusted using the formula:

[0231] ,

[0232] Update humidity settings and generate humidity adjustment plans;

[0233] in, Represents the new humidity setting, Represents the current humidity. represents the humidity adjustment factor, Represents the target humidity value, represents the standard deviation of humidity;

[0234] Use the tobacco leaf state prediction model to adjust the temperature parameters and use the formula:

[0235] ,

[0236] Update temperature settings and generate temperature adjustment plans;

[0237] in, Represents the new temperature setting, Represents the current temperature, represents the temperature adjustment factor, Represents the target temperature value, represents the standard deviation of temperature;

[0238] According to the output of the tobacco leaf state prediction model, the CO2 concentration parameter is adjusted using the formula:

[0239] ,

[0240] Update CO2 settings and establish CO2 adjustment plan;

[0241] in, represents the new CO2 setting, Represents the current CO2 concentration, represents the CO2 adjustment factor, Represents the target CO2 concentration value, represents the standard deviation of CO2;

[0242] Comprehensive humidity adjustment plan, temperature adjustment plan and CO2 adjustment plan, real-time monitoring and optimization of environmental parameters, using the formula:

[0243] ,

[0244] Determine environmental control plan .

[0245] formula: ,

[0246] Parameter definition and actual data application:

[0247] : Current humidity, assumed to be 50% as measured by the environmental monitoring system; : The humidity requirement output by the tobacco leaf state prediction model is calculated by the data analysis model and is assumed to be 55%; : Target humidity, set to the optimal humidity determined based on long-term data analysis, which is 53%; : The standard deviation of humidity data, assumed to be 3%; : Humidity adjustment coefficient, determined based on system debugging and feedback adjustment, with a value of 0.1.

[0248] Calculation process:

[0249] Calculate the difference ratio: ,

[0250] Calculate the adjustment factor: ,

[0251] Update humidity settings: ,

[0252] Result interpretation: The results show that based on the model's recommendations and current environmental data, humidity should be adjusted from 50% to 53.5% to meet the optimal storage conditions for tobacco leaves.

[0253] formula: ,

[0254] Parameter definition and actual data application:

[0255] : The current temperature, the monitored data is 22℃; : The temperature requirement output by the model is assumed to be 23°C; : Target temperature, the optimal temperature determined based on data analysis, is 21°C; : standard deviation of temperature, assumed to be 2°C; : Temperature adjustment coefficient, set according to the equipment response speed and safety standards, with a value of 0.1.

[0256] Calculation process:

[0257] Calculate the difference ratio: ,

[0258] Calculate the adjustment factor: ,

[0259] Update temperature settings: ;

[0260] Result interpretation: The results show that the temperature should be adjusted from 22℃ to 24.31℃ to meet the recommendations of the prediction model based on current data and optimize the storage environment of tobacco leaves.

[0261] formula: ,

[0262] Parameter definition and actual data application:

[0263] : Current CO2 concentration, obtained in real time through environmental monitoring instruments, assumed to be 400ppm; : The CO2 demand output by the forecast model is assumed to be 450ppm based on data analysis; : The target CO2 concentration is set at 420ppm based on the analysis of the optimal conditions for tobacco leaf storage; : The standard deviation of CO2 data is calculated from long-term monitoring data and is set to 30ppm; : CO2 adjustment coefficient, set to 0.05.

[0264] Calculation process:

[0265] Calculate the difference ratio: ,

[0266] Calculate the adjustment factor: ,

[0267] Update CO2 settings: ;

[0268] Result analysis:

[0269] The results indicate that the CO2 concentration should be adjusted from 400 ppm to 420.4 ppm to approach the optimal concentration recommended by the model. Such an adjustment will help optimize the storage environment of tobacco leaves and maintain their physiological activity.

[0270] formula: ,

[0271] Parameter definition and actual data application: , , Adjusted settings for humidity, temperature and CO2 respectively.

[0272] Calculation process:

[0273] Already obtained , , .

[0274] Result analysis:

[0275] A comprehensive environmental control program is established to ensure that each parameter of humidity, temperature and CO2 is in the optimal state after adjustment.

[0276] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. AI-based tobacco storage optimization system, characterized in that: The system comprises: The environmental data acquisition module captures the temperature, humidity, and CO2 concentration data in the tobacco storage environment, monitors the physiological response of tobacco leaves to real-time environmental changes through time series analysis, records the correlation data between environmental parameters and the physiological state of tobacco leaves, and generates environmental parameter records; The feature analysis module identifies the direct impact of changes in key environmental factors including temperature and humidity on tobacco leaves based on the environmental parameter records, analyzes the correlation between multiple key environmental factors and tobacco leaf growth status, establishes a dynamic feature mapping of tobacco leaf adaptability, and obtains tobacco leaf adaptability analysis results; The steps for obtaining the tobacco leaf adaptability analysis results are specifically as follows: From the environmental parameter records, the key variables of temperature and humidity that affect the physiological state of tobacco leaves are identified using the formula: ， Calculate the impact index of key environmental factors at each time point and generate the impact data of key environmental factors; in, Represents the impact index of key environmental factors, Represents the temperature data in the environmental parameter record, Represents the humidity data in the environmental parameter record, , Represent the average values ​​of temperature and humidity, , is the weight coefficient of temperature and humidity, is the square root of the sum of the squares of the temperature and humidity combination; The correlation between the key environmental factors and the growth status of tobacco leaves was analyzed using the formula: ， Calculate the correlation coefficient between environmental factors and tobacco leaf growth status at each time point to generate data on the correlation between environmental factors and growth status; in, Represents the correlation between environmental factors and tobacco leaf growth status, Represents the impact index of key environmental factors, is the maximum value of the key environmental factor impact index. is the tobacco leaf growth status index, and n is the number of reference growth status indicators; The data on correlation between environmental factors and growth status are used to establish a dynamic characteristic map of tobacco leaf adaptability using the formula: ， Generate tobacco leaf adaptability analysis results; in, Represents the adaptability of tobacco leaves. is the standard deviation of the correlation index between environmental factors and tobacco leaf growth status, and exp is the natural index; The environmental matching model modeling module extracts the interaction model between tobacco leaf physiological activity and environmental factors from the tobacco leaf adaptability analysis results, simulates tobacco leaf growth prediction under differentiated environmental settings, simulates tobacco leaf growth behavior, and establishes a tobacco leaf state prediction model; The steps for obtaining the tobacco leaf state prediction model are specifically as follows: The key parameters were extracted from the tobacco leaf adaptability analysis results using the formula: ， Calculate the standardized physiological activity of tobacco leaves and generate an interaction model between the physiological activity of tobacco leaves and environmental factors; in, Represents the interaction model between tobacco leaf physiological activity and environmental factors. represents the adjustment factor, represent The mean of represent square root of variance; Based on the interaction model between tobacco leaf physiological activity and environmental factors, tobacco leaf growth behavior simulation was performed using the formula: ， Calculate the impact of multiple environmental factors and generate tobacco leaf growth prediction data; in, Represents tobacco leaf growth forecast data, represents the influence coefficient, exp represents the natural index, represents the normalization factor; Using the tobacco leaf growth prediction data, the formula is adopted: ， The contribution of multiple predictors is calculated through linear combination to generate a tobacco leaf state prediction model; in, represents the tobacco leaf status prediction model, represents the model intercept, Representative predictors The coefficient of The parameter adjustment and optimization module adjusts the setting parameters of the tobacco storage control system, including humidity, temperature and CO2 concentration, according to the prediction data output by the tobacco state prediction model, monitors the environmental control parameters in real time, and establishes an environmental control plan.

2. The AI-based tobacco storage optimization system according to claim 1, characterized in that: The steps for obtaining the environmental parameter records are specifically as follows: The temperature, humidity and CO2 concentration in the tobacco storage environment are monitored using the improved formula: ， and ， and ， Calculate the average temperature, humidity, and CO2 concentration at each time point to generate basic environmental data; in, represents the average temperature at a time point, Represents the average humidity at a time point, represents the average CO2 concentration at time point i, , , Respectively represent the temperature, humidity and CO2 concentration monitored at the jth time point, , , are the adjustment coefficients of temperature, humidity and CO2 concentration, respectively, and n represents the number of monitoring times at each time point; Analyze the basic environmental data and calculate the change rate of temperature, humidity and CO2 concentration using the formula: ， and ， and ， Get the change rate of temperature, humidity and CO2 concentration to generate environmental change data; in, represents the rate of change of temperature, represents the rate of change of humidity, represents the rate of change of CO2 concentration, , , are the square roots of temperature, humidity and CO2 concentration, respectively, to balance the impact of extreme values ​​on the results; The environmental change data were used to evaluate the impact of environmental changes on the physiological state of tobacco leaves using the formula: ， Obtain the correlation between environmental parameters and the physiological state of tobacco leaves, and generate environmental parameter records; in, Represents the correlation between environmental parameters and the physiological state of tobacco leaves, , , are the weight coefficients of temperature, humidity and CO2 concentration changes respectively.

3. The AI-based tobacco storage optimization system according to claim 1, characterized in that: The steps for obtaining the environmental control scheme are specifically as follows: Based on the data output by the tobacco leaf state prediction model, the humidity control parameters are adjusted using the formula: ， Update humidity settings and generate humidity adjustment plans; in, Represents the new humidity setting, Represents the current humidity. represents the humidity adjustment factor, Represents the target humidity value, represents the standard deviation of humidity; Using the tobacco leaf state prediction model, the temperature parameter is adjusted, and the formula is adopted: ， Update temperature settings and generate temperature adjustment plans; in, Represents the new temperature setting, Represents the current temperature, represents the temperature adjustment factor, Represents the target temperature value, represents the standard deviation of temperature; According to the output of the tobacco leaf state prediction model, the CO2 concentration parameter is adjusted using the formula: ， Update CO2 settings and establish CO2 adjustment plan; in, represents the new CO2 setting, Represents the current CO2 concentration, represents the CO2 adjustment factor, Represents the target CO2 concentration value, represents the standard deviation of CO2; The humidity adjustment scheme, the temperature adjustment scheme and the CO2 adjustment scheme are combined to monitor and optimize environmental parameters in real time, using the formula: ， Determine the environmental control plan .

Images