Monitoring device and monitoring method for agricultural product storage

Abstract

The invention discloses a monitoring device and method for agricultural product storage, and the device comprises a collection module which is used for obtaining an environment data flow containing the temperature, humidity, gas components and illumination intensity in real time through a multi-mode sensor network disposed in a storage warehouse; the analysis module is used for determining monitoring parameters needing to be dynamically regulated and controlled in the environment data flow based on a preset agricultural product storage threshold condition and the target agricultural product physiological characteristics; the regulation and control strategy module is used for acquiring a preset storage regulation and control strategy library corresponding to the monitoring parameters; and the intelligent regulation and control module is used for matching a corresponding regulation and control strategy according to a preset storage regulation and control strategy library, and carrying out real-time dynamic regulation on the storage environment based on the regulation and control strategy. Through real-time monitoring and intelligent regulation and control, it can be ensured that the agricultural products are in the most suitable environmental conditions in the whole storage process.

Description

Technical Field

[0001] The present invention relates to the field of monitoring technologies, and particularly to a monitoring device and a monitoring method for agricultural product storage. Background Art

[0002] With the advancement of agricultural modernization, the technology for agricultural product storage has gradually developed to ensure the quality and safety of agricultural products during storage. However, there are still many deficiencies in the existing agricultural product storage technologies in terms of automation and intelligence, resulting in inaccurate and inflexible regulation of the storage environment of agricultural products, and relatively single monitoring means, which cannot effectively cope with the impact of environmental changes on the quality of agricultural products.

[0003] Most current agricultural product storage systems adopt a simple temperature and humidity control system to regulate the storage environment. However, this traditional storage method usually only focuses on temperature and humidity, ignoring the combined effects of various environmental parameters such as gas components and light intensity. For example, gas components such as ethylene concentration and carbon dioxide concentration in the storage environment have important effects on the preservation and spoilage of agricultural products, and the traditional system fails to monitor and regulate these factors in a timely manner. Such a single environmental regulation method often increases the spoilage risk of agricultural products, thereby reducing their quality and safety. Existing agricultural product storage systems often rely on manual intervention or preset fixed regulation strategies and lack the ability of real-time dynamic adjustment. For different types of agricultural products and their different growth stages, the requirements for the storage environment are also different, but the traditional storage system does not perform precise regulation according to the specific needs of agricultural products. For example, during the storage of certain agricultural products, the changes in light intensity and gas components have crucial effects on their quality, but the traditional system often cannot dynamically adjust the storage environment based on real-time monitoring data.

[0004] Therefore, there is an urgent need for a monitoring device and a monitoring method for agricultural product storage. Summary of the Invention

[0005] The present invention provides a monitoring device and a monitoring method for agricultural product storage to solve the above problems existing in the prior art.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A monitoring device for agricultural product storage, comprising:

[0008] An acquisition module, configured to obtain in real time an environmental data stream including temperature, humidity, gas components, and light intensity through a multi-modal sensor network deployed in a storage warehouse;

[0009] An analysis module, configured to determine monitoring parameters that need to be dynamically regulated in the environmental data stream based on preset agricultural product storage threshold conditions and the physiological characteristics of target agricultural products;

[0010] A regulation strategy module, configured to obtain a preset storage regulation strategy library corresponding to the monitoring parameters;

[0011] An intelligent regulation module, configured to match a corresponding regulation strategy according to the preset storage regulation strategy library, and perform real-time dynamic adjustment on the storage environment based on the regulation strategy.

[0012] Among them, the analysis module includes:

[0013] A sub-module for time segment division, configured to perform time segment division processing on the environmental data stream to obtain multiple data time segments;

[0014] A detection sub-module, configured to perform component analysis on multiple data time segments respectively based on gas chromatography analysis technology and spectral analysis algorithm, and obtain the corresponding gas components and the current illumination conditions;

[0015] A determination sub-module, configured to use the gas components and the current illumination conditions together as monitoring parameters.

[0016] Among them, the intelligent regulation module includes:

[0017] An initial data acquisition sub-module, configured to obtain a first data time segment that first triggers the monitoring condition based on the environmental data stream, and simultaneously obtain the data type of the first monitoring parameter;

[0018] A gas matching sub-module, configured to identify the first gas concentration feature in the first data time segment if the data type is gas components;

[0019] A first strategy matching sub-module, configured to match the first gas concentration feature with the standard gas threshold in the corresponding storage regulation strategy library to obtain a first gas matching strategy;

[0020] A ventilation regulation sub-module, configured to start a hierarchical ventilation program if the first gas matching strategy is that the concentration exceeds the standard, preferentially enable the low-speed circulation mode, and output a first gas regulation instruction;

[0021] A continuous monitoring sub-module, configured to continuously obtain a second data time segment after the first data time segment if the first matching strategy is within the safe range, where the first matching strategy includes a first gas matching strategy and a first illumination matching strategy;

[0022] A data sequence construction sub-module, configured to integrate the first data time segment and the second data time segment into an environmental change trend stream according to the time sequence;

[0023] A quality prediction sub-module, configured to determine a first regulation strategy according to the environmental change trend stream, and the first gas regulation strategy is an environmental parameter adjustment plan based on the prediction of the maturity of agricultural products.

[0024] Among them, the intelligent regulation module further includes:

[0025] A light analysis sub-module, configured to identify the first light distribution feature in the first data period if the data type is light conditions;

[0026] A second policy matching sub-module, configured to match the first light distribution feature with the standard light atlas in the corresponding stored regulation policy library to obtain the first light matching policy;

[0027] A supplementary light control sub-module, configured to automatically adjust the LED lighting system and output a first light regulation instruction if the first light matching policy is spectral deficiency.

[0028] Among them, the quality prediction sub-module includes:

[0029] A trend analysis unit, configured to analyze each data period in the environmental change trend stream in chronological order;

[0030] A metabolic feature extraction unit, configured to extract the gas exchange features of the current data period based on the agricultural product respiration metabolism model during each analysis and integrate them into a metabolic feature sequence;

[0031] A correlation evaluation unit, configured to analyze the parameter correlation degree between the currently analyzed data period and the previous data period. When the ethylene concentration change rate and the carbon dioxide accumulation amount are positively correlated within a preset time window, it is determined as the associated storage state;

[0032] A prediction model input unit, configured to input the real-time obtained metabolic feature sequence into a preset quality prediction model after each analysis to obtain a quality prediction result;

[0033] An emergency regulation determination unit, configured to immediately trigger a temperature and humidity regulation instruction to adjust the temperature and humidity if the correlation degree exceeds a preset correlation threshold and the prediction result is a quality deterioration risk;

[0034] A progressive regulation determination unit, configured to output a progressive regulation strategy if the correlation degree is lower than the preset threshold and the prediction result continues to be normal maturation.

[0035] Among them, the correlation evaluation unit includes:

[0036] A gas phase identification sub-unit, configured to identify the ethylene release phase of the current data period and the carbon dioxide absorption phase of the previous period;

[0037] A metabolic balance calculation sub-unit, configured to calculate the metabolic balance coefficient of the two gas phases, and determine metabolic imbalance when the coefficient is lower than the preset balance threshold;

[0038] A light influence factor acquisition sub-unit, configured to acquire the influence factor of the current light intensity on the photosynthesis of agricultural products;

[0039] The comprehensive correlation generation subunit is used to perform weighted fusion on the metabolic balance coefficient and the light influence factor to generate an environmental correlation index;

[0040] The storage state classification subunit is used to re-divide the storage stage and update the regulation strategy library when the environmental correlation index breaks through the dynamic adjustment boundary.

[0041] Among them, the metabolic feature extraction unit includes:

[0042] The metabolic parameter calibration subunit is used to obtain the standard respiratory metabolic curves of different agricultural products and establish a metabolic parameter calibration template;

[0043] The real-time metabolism tracking subunit is used to identify the deviation between the actual metabolic rate and the theoretical value in the current data period according to the calibration template;

[0044] The feature vector construction subunit is used to encode the ethylene concentration change gradient, the carbon dioxide accumulation slope, and the light response delay time into a multi-dimensional feature vector;

[0045] The metabolic map update subunit is used to construct a dynamic metabolic map based on the feature vectors of three consecutive data periods, and perform a difference comparison with the reference map in the regulation strategy library, and the comparison result is fed back to the relevance evaluation unit in real time.

[0046] Among them, the storage regulation strategy library includes:

[0047] The gas component safety threshold matrix of different agricultural product types, where each matrix element corresponds to the extreme values of ethylene / carbon dioxide concentration under specific temperature and humidity conditions;

[0048] The dynamic light regulation strategy tree, and the strategy tree nodes include the matching relationship between the light intensity - wavelength - irradiation period combination parameters and the photosynthesis requirements at different maturity stages;

[0049] The environmental parameter coupling rule library stores the influence function of temperature fluctuation on the gas diffusion coefficient and the humidity and light synergy model.

[0050] Among them, a monitoring method for agricultural product storage includes:

[0051] S101: Through the multi-modal sensor network deployed in the storage warehouse, real-time obtain the environmental data stream including temperature, humidity, gas components, and light intensity;

[0052] S102: Based on the preset agricultural product storage threshold conditions and the physiological characteristics of the target agricultural product, determine the monitoring parameters that need to be dynamically regulated in the environmental data stream;

[0053] S103: Obtain the preset storage regulation strategy library corresponding to the monitoring parameters;

[0054] S104: Match the corresponding regulation strategy according to the preset storage regulation strategy library, and perform real-time dynamic adjustment on the storage environment based on the regulation strategy.

[0055] Among them, step S102 includes:

[0056] S1021: Perform time period segmentation processing on the environmental data stream to obtain multiple data time periods;

[0057] S1022: Based on gas chromatography analysis technology and spectral analysis algorithm, perform component analysis on multiple data time periods respectively to obtain the corresponding gas components and current light conditions;

[0058] S1023: Use the gas components and the current light conditions together as monitoring parameters.

[0059] Compared with the prior art, the present invention has the following advantages:

[0060] A monitoring device for agricultural product storage includes: a collection module for real-time obtaining an environmental data stream including temperature, humidity, gas components, and light intensity through a multi-modal sensor network deployed in a storage warehouse; an analysis module for determining monitoring parameters that need to be dynamically regulated in the environmental data stream based on preset agricultural product storage threshold conditions and the physiological characteristics of target agricultural products; a regulation strategy module for obtaining a preset storage regulation strategy library corresponding to the monitoring parameters; and an intelligent regulation module for matching the corresponding regulation strategy according to the preset storage regulation strategy library and performing real-time dynamic adjustment on the storage environment based on the regulation strategy. Through real-time monitoring and intelligent regulation, it can ensure that agricultural products are in the most suitable environmental conditions throughout the storage process.

[0061] Other features and advantages of the present invention will be described in the following specification, and part of them will be obvious from the specification, or will be understood by implementing the present invention.

[0062] The technical solutions of the present invention will be further described in detail below through the accompanying drawings and embodiments. Description of the Drawings

[0063] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0064] Figure 1 is a structural diagram of a monitoring device for agricultural product storage in an embodiment of the present invention;

[0065] Figure 2 is a structural diagram of the analysis module in an embodiment of the present invention;

[0066] Figure 3It is a flowchart of a monitoring method for agricultural product storage in an embodiment of the present invention. Detailed implementation manners

[0067] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for the purpose of illustrating and explaining the present invention, and are not intended to limit the present invention.

[0068] An embodiment of the present invention provides as Figure 1 shown, a monitoring device for agricultural product storage, including:

[0069] An acquisition module, configured to obtain in real time an environmental data stream including temperature, humidity, gas components, and light intensity through a multi-modal sensor network deployed in a storage warehouse;

[0070] An analysis module, configured to determine monitoring parameters that need to be dynamically regulated in the environmental data stream based on preset agricultural product storage threshold conditions and physiological characteristics of target agricultural products;

[0071] A regulation strategy module, configured to obtain a preset storage regulation strategy library corresponding to the monitoring parameters;

[0072] An intelligent regulation module, configured to match corresponding regulation strategies according to the preset storage regulation strategy library, and perform real-time dynamic adjustment on the storage environment based on the regulation strategies.

[0073] The working principle of the above technical solution is as follows: The device deploys a multi-modal sensor network inside the storage warehouse to monitor and collect various environmental data in real time, such as temperature, humidity, gas components (such as oxygen, carbon dioxide, etc.), light intensity, etc. These information constitute a data stream, and these data are continuously collected and transmitted to the analysis module of the system. Temperature and humidity are key factors affecting the quality of agricultural products. For example, too high a temperature may cause rotting, while too low humidity will cause the agricultural products to lose water, affecting taste and nutritional components. Monitoring of gas components helps to understand whether the storage environment is suitable for the respiration of agricultural products. Too high a carbon dioxide concentration will accelerate the senescence of some agricultural products. Light intensity also affects certain agricultural products, especially those fruits and vegetables that are easily affected by light.

[0074] The collected environmental data stream will be transmitted to the analysis module. This module analyzes based on preset agricultural product storage threshold conditions and the physiological characteristics of each agricultural product. Each agricultural product has different requirements for the environment. For example, apples and watermelons have different temperature requirements. The analysis module will identify which environmental parameters (such as temperature, humidity) need to be adjusted to maintain the optimal storage conditions. For example, a certain agricultural product requires the temperature to be maintained at 10°C and the humidity to be controlled at about 80%. If the real-time data exceeds this range, the analysis module will respond in a timely manner, informing the system that adjustment is needed.

[0075] The analysis module will select a suitable regulation strategy according to the detected parameter changes. The regulation strategy module contains a stored regulation strategy library, which stores a variety of preset regulation strategies, such as temperature control, humidity control, gas composition regulation and other strategies. These strategies are optimized for different types of agricultural products, different storage environments and different requirements. For example: if the humidity is too low, the system will select a "humidity increase" strategy from the strategy library and increase the humidity in the warehouse through a humidifying device.

[0076] The intelligent regulation module will automatically execute the dynamic adjustment of the storage environment according to the strategy selected from the regulation strategy library. For example, when the temperature exceeds the predetermined range, the intelligent regulation module will start the air conditioning system to lower the temperature; if the humidity is too low, the humidifying equipment may be started. This intelligent regulation system can respond to environmental changes in real time, ensure that agricultural products are always in the best storage conditions, reduce manual intervention and improve storage efficiency.

[0077] The beneficial effects of the above technical solution are: through real-time monitoring and intelligent regulation, it can ensure that agricultural products are in the most suitable environmental conditions during the whole storage process. This will significantly reduce problems such as decay, deterioration, and nutrient loss of agricultural products, extend the preservation period, and maintain their taste and nutritional value. Since the system can automatically adjust the storage environment according to real-time data, it avoids over-regulation and energy waste, and provides an energy-saving storage solution. In traditional storage, the control of the storage environment of agricultural products often relies on manual inspection and adjustment, which may be untimely or inaccurate. This system reduces human intervention through automatic adjustment, ensuring the accuracy and timeliness of environmental control.

[0078] In another embodiment, as Figure 2 shown, the analysis module includes:

[0079] A time-division sub-module for performing time-division segmentation processing on the environmental data stream to obtain multiple data time periods;

[0080] A detection sub-module for performing component analysis on multiple data time periods respectively based on gas chromatography analysis technology and spectral analysis algorithms to obtain the corresponding gas components and current light conditions;

[0081] A determination sub-module for using the gas components and the current light conditions together as monitoring parameters.

[0082] The working principle of the above technical solution is as follows: In order to more accurately capture the changes in the environment, the environmental data stream is first segmented by the time division sub-module. This module divides the real-time collected environmental data according to a certain time period to obtain multiple data time periods. Such time period division can help the system identify the environmental characteristics at different time points and ensure reasonable analysis of the environment in different time periods. For example, the temperature, humidity, gas composition, etc. in the agricultural product storage environment change over time. By segmenting the data by time period, the dynamic changes in the environment within a certain time period can be more accurately reflected, helping the system to take appropriate control measures at the appropriate time period.

[0083] The detection sub-module is responsible for in-depth analysis of the data within each time period. This module uses gas chromatography analysis technology and spectral analysis algorithms to analyze the gas composition and light conditions in each time period to obtain the specific gas composition and light intensity. Gas chromatography analysis technology: This is a method for separating and quantitatively measuring gas components. By injecting a gas sample into a chromatographic column and using the separation characteristics of different gases in the column, the proportion of gas components is analyzed one by one. Gas components such as oxygen and carbon dioxide in the storage environment can be accurately detected by this technology, helping to judge whether it meets the respiratory needs of agricultural products. Spectral analysis algorithm: This algorithm determines the characteristics of light such as intensity and wavelength by analyzing light data, and then evaluates the impact of light conditions on agricultural products. For example, some agricultural products are prone to yellowing or spoilage when the light is too strong, while insufficient light affects their maturity. Through this algorithm, the system can accurately understand the current light situation.

[0084] After completing the analysis of the gas composition and light conditions, the determination sub-module will jointly evaluate the gas composition and the current light conditions as monitoring parameters. This module combines these two factors to more comprehensively reflect the impact of the current environment on agricultural products and provide data support for subsequent control. For example, some agricultural products (such as apples) require a low carbon dioxide concentration and a specific light intensity during storage. By comprehensively evaluating these two parameters, the system can more accurately judge whether the current storage environment meets the storage requirements of agricultural products.

[0085] The beneficial effects of the above technical solution are as follows: By dividing environmental data into time periods and analyzing it in combination with gas components and light conditions, the system can monitor environmental changes more precisely and achieve more accurate regulation. This time-period-based data processing method can help the system detect environmental fluctuations in a timely manner, avoid delayed responses, and improve the safety of agricultural product storage. The combination of gas chromatography analysis technology and spectral analysis algorithms provides in-depth analysis of gas components and light conditions in the environment, enabling more accurate capture of the impact of environmental changes on agricultural products. Through automated time-period data analysis and environmental monitoring, the system can not only adjust the storage environment in real time but also make comprehensive judgments based on multiple parameters, improving the intelligent level of management. Managers do not need to intervene too much, and the system will automatically identify and adjust environmental conditions, saving labor costs and improving efficiency.

[0086] In another embodiment, the intelligent regulation module includes:

[0087] An initial data acquisition sub-module, which is used to obtain the first data period when the monitoring condition is first triggered based on the environmental data stream, and at the same time obtain the data type of the first monitoring parameter;

[0088] A gas matching sub-module, which is used to identify the first gas concentration characteristic in the first data period if the data type is gas component;

[0089] A first strategy matching sub-module, which is used to match the first gas concentration characteristic with the standard gas threshold in the corresponding storage regulation strategy library to obtain the first gas matching strategy;

[0090] A ventilation regulation sub-module, which is used to start a hierarchical ventilation program, preferentially enable the low-speed circulation mode, and output the first gas regulation instruction if the first gas matching strategy is that the concentration exceeds the standard;

[0091] A continuous monitoring sub-module, which is used to continuously obtain the second data period after the first data period if the first matching strategy is within the safe range, where the first matching strategy includes the first gas matching strategy and the first light matching strategy;

[0092] A data sequence construction sub-module, which is used to integrate the first data period and the second data period into an environmental change trend stream according to the time sequence;

[0093] A quality prediction sub-module, which is used to determine the first regulation strategy according to the environmental change trend stream, and the first gas regulation strategy is an environmental parameter adjustment plan based on the prediction of the maturity of agricultural products.

[0094] The working principle of the above technical solution is as follows: The initial data acquisition sub-module accesses the environmental data stream, real-time obtains and records the data period when the monitoring condition is first triggered, and extracts the data type of the first monitoring parameter. For example, in an agricultural product storage environment, when the temperature, humidity, or gas concentration reaches the set monitoring condition, the environmental data stream will trigger the first record. Assuming that during the storage of apples, the monitoring condition is that the CO2 concentration exceeds the set threshold, then the first record in the environmental data stream is the first data period, and the first monitoring parameter can be "gas concentration".

[0095] When the data type is gas component, the gas matching sub-module will identify the first gas concentration feature in the first data period and process it. Assuming that in the gas concentration monitoring data stream of the apple storage environment, the first triggered gas is CO2, and the CO2 concentration is 10% at this time, the system will identify this data as the first gas concentration feature, and this gas concentration feature is crucial for the storage of agricultural products.

[0096] The first strategy matching sub-module matches the first gas concentration feature with the standard gas threshold stored in the regulation strategy library to determine what gas regulation strategy to adopt. Assuming in the case of apple storage, the standard gas threshold library stipulates that when the CO2 concentration exceeds 8%, the ripening speed of apples accelerates, so ventilation measures need to be taken. If the first obtained CO2 concentration is 10%, the system will match this data with the standard gas threshold and obtain the first gas matching strategy as "concentration exceeding the standard".

[0097] When the first gas matching strategy indicates that the gas concentration exceeds the standard, the ventilation regulation sub-module starts the hierarchical ventilation program, preferentially enables the low-speed circulation mode as needed, and outputs relevant gas regulation instructions. If the CO2 concentration in the apple storage warehouse reaches 10%, exceeding the standard threshold, the system will start the ventilation program, and the system will enable the low-speed circulation mode to gradually reduce the CO2 concentration in the warehouse to maintain a suitable storage environment.

[0098] If the first matching strategy considers that the current environment is within the safe range, the system will continuously obtain and record subsequent data periods. The first matching strategy includes gas concentration matching strategies and other possible monitoring parameters, such as light. Assuming that during the storage of apples, the CO2 concentration is below 10% and within the safe range, the system will continuously monitor other environmental data, such as light, humidity, etc., and adjust the control strategy in a timely manner according to the changes.

[0099] The data sequence construction sub-module integrates the first data period and the second data period in chronological order to form an environmental change trend stream for subsequent analysis and decision-making. For example, the system records that the CO2 concentration in the first data period is 10%, and after a period of time, the CO2 concentration in the second data period drops to 8%. At this time, the system integrates the data of these two periods in time series to obtain the change trend of the CO2 concentration in the apple storage environment.

[0100] Based on the environmental change trend stream, the quality prediction sub-module can adjust environmental parameters to predict the maturity of agricultural products and make corresponding control strategies. For example, after a period of monitoring, the CO2 concentration in the apple storage environment has dropped to a safe range. According to the previous environmental data and the change trend of gas concentration, the system will predict the maturity of the apples and formulate an environmental parameter adjustment plan based on this prediction. For example, if the apples require a lower CO2 concentration to maintain freshness, the system will correspondingly reduce the ventilation volume and adjust the storage environment.

[0101] The first data period: refers to the data of the first time period recorded when the monitoring condition is first triggered. The first monitoring parameter: the first recorded monitoring item, such as gas concentration, temperature, humidity, etc. The first gas concentration feature: refers to the gas concentration feature obtained during the first monitoring. For example, the CO2 concentration in the apple storage environment is 10%. The standard gas threshold: the gas concentration standard preset by the system for judging whether control measures need to be taken. For example, if the CO2 concentration exceeds 8%, ventilation is required. The first gas matching strategy: the control strategy obtained by comparing the standard gas threshold with the actual gas concentration. For example, the concentration over-standard strategy when the CO2 concentration exceeds the threshold.

[0102] The beneficial effects of the above technical solution are as follows: Through precise environmental monitoring and control, the storage period of agricultural products can be effectively extended, losses can be reduced, and the quality of agricultural products can be ensured. The system can automatically adjust environmental parameters according to real-time data without manual intervention, reducing the complexity and errors of manual operations. The system can monitor the environment in real time and respond quickly to environmental changes to ensure that the environment is within the most suitable range. Through data sequence construction and quality prediction, the system can make scientific decisions and optimize the storage environment. Whether it is apples, strawberries or other agricultural products, the system can flexibly adjust environmental parameters according to their different storage requirements to ensure the best preservation effect.

[0103] In another embodiment, the intelligent control module further includes:

[0104] The light analysis sub-module is used to identify the first light distribution feature in the first data period if the data type is light conditions;

[0105] The second strategy matching sub-module is used to match the first light distribution feature with the standard light atlas in the corresponding stored control strategy library to obtain the first light matching strategy;

[0106] The supplementary light control sub-module is used to automatically adjust the LED lighting system and output the first light control instruction if the first light matching strategy is spectral deficiency.

[0107] The working principle of the above technical solution is as follows: The function of the light analysis sub-module is to identify the light conditions in the storage environment. Suppose we want to store tomatoes. This agricultural product has a high demand for light, especially during the fruit growth stage. If the place where tomatoes are stored has insufficient light, they will turn yellow or grow slowly. This sub-module will collect the light data in the first data period and analyze information such as the light intensity, distribution, and frequency of the current environment through sensors. The sensor detects that the current light intensity is 500 lux and the light distribution is relatively uniform. The system will record this light data and analyze the light distribution characteristics to determine whether it meets the growth requirements of tomatoes.

[0108] The second strategy matching sub-module compares the light data with the standard light atlas in the stored control strategy library to obtain the control strategy suitable for the current storage environment. The standard light atlas contains the optimal light distributions of various agricultural products, helping the system understand the effects of different light conditions on various agricultural products. For example: The system queries the standard light atlas and finds that the optimal light distribution for tomatoes should be in the range of 200 lux to 800 lux, and the light is relatively uniform, avoiding strong direct light. Based on the previously collected 500 lux data, the system determines that the current light conditions are relatively appropriate and there is no serious deviation.

[0109] If during the matching process, the system determines that the light conditions do not meet the best requirements for the growth of agricultural products (such as spectral deficiency or too strong light), the supplementary light control sub-module will automatically adjust the LED lighting system. At this time, the system will send a control instruction to the LED lighting device to supplement or adjust the intensity and distribution of the light. If the light intensity in the tomato storage environment is insufficient, the system will automatically activate the LED lighting system to supplement the missing light frequency and intensity to make it reach the standard range. For example, when the detected light intensity is 300 lux, the system increases the light intensity to 600 lux through the LED lighting system to ensure that tomatoes receive sufficient light to promote their ripening.

[0110] The beneficial effects of the above technical solution are as follows: By intelligently controlling the light, it ensures that agricultural products, such as tomatoes and cucumbers, are in the optimal light environment, effectively extending their storage time and avoiding early decay or quality decline. Through precise control of the light, excessive energy waste is avoided. The system only supplements light when needed, avoiding unnecessary energy consumption, which helps with energy conservation and cost reduction.

[0111] In another embodiment, the quality prediction sub-module includes:

[0112] A trend analysis unit for parsing each data period in the environmental change trend stream in chronological order;

[0113] A metabolic feature extraction unit for extracting the gas exchange features of the current data period based on the agricultural product respiration metabolism model and integrating them into a metabolic feature sequence each time it parses;

[0114] A correlation evaluation unit for analyzing the parameter correlation degree between the currently parsed data period and the previous data period. When the change rate of ethylene concentration is positively correlated with the carbon dioxide accumulation amount within a preset time window, it is determined as the associated storage state;

[0115] A prediction model input unit for inputting the metabolomic feature sequence obtained in real time into a preset quality prediction model after each parsing to obtain a quality prediction result;

[0116] An emergency regulation determination unit for immediately triggering a temperature and humidity regulation instruction to adjust the temperature and humidity if the correlation degree exceeds a preset correlation threshold and the prediction result is a risk of quality deterioration;

[0117] A progressive regulation determination unit for outputting a progressive regulation strategy if the correlation degree is lower than the preset threshold and the prediction result continues to be normal maturation.

[0118] The working principle of the above technical solution is as follows: The trend analysis unit is responsible for parsing the change trend of the storage environment in chronological order, including key parameters such as temperature, humidity, oxygen (O2), carbon dioxide (CO2), and ethylene (C2H4) concentration. Suppose apples are stored in a cold storage, and the system collects data every 1 hour, obtaining the temperature (3°C), humidity (90%), CO2 concentration (0.5%), and ethylene concentration (0.1 ppm). These data are recorded and form an environmental change trend stream for analyzing its change over time.

[0119] During the storage process of agricultural products, respiration occurs, consuming oxygen, releasing carbon dioxide, and generating gases such as ethylene. The metabolic feature extraction unit extracts the gas exchange features of the current storage environment based on the respiration metabolism model of agricultural products and integrates them into a metabolic feature sequence. For example, the ethylene released by apples during storage can promote their own ripening, accompanied by the accumulation of carbon dioxide.

[0120] The metabolic feature extraction unit records the changes in CO2 and C2H4 concentrations in each time period, such as:

[0121] After 1 hour: CO2 = 0.6%, C2H2 = 0.12 ppm

[0122] After 2 hours: CO2 = 0.7%, C2H4 = 0.15 ppm

[0123] After 3 hours: CO2 = 0.9%, C2H4 = 0.2 ppm

[0124] These data will be integrated into the metabolic feature sequence for further analysis of the ripening state of apples.

[0125] The correlation assessment unit is used to analyze the parameter correlation between the current data period and the previous data period, and determine whether it is in the associated storage state. If the change rate of ethylene concentration is positively correlated with the carbon dioxide accumulation within a certain time window, it indicates that the apple is accelerating ripening and may even enter the deterioration stage. For example: by calculation, it is found that the ethylene concentration increases by 20% per hour, and the carbon dioxide accumulation increases synchronously by 0.2%, and the two show a positive correlation trend in the past 4 hours. The system determines that the current apple is in the associated storage state and has a strong metabolic activity.

[0126] The prediction model input unit inputs the integrated metabolic feature sequence into the quality prediction model, which predicts the future quality change trend of agricultural products based on historical data and machine learning algorithms. For example: after analysis by the prediction model, it judges the ripening state of the apple and expects that it may enter the quality deterioration stage within 48 hours and needs to be regulated. The prediction result shows that under the current environmental conditions, the ripening speed of the apple is faster than the standard storage requirement, which will lead to accelerated decay.

[0127] The emergency regulation determination unit, if the prediction result shows a risk of quality deterioration and the change rates of ethylene and carbon dioxide exceed the preset correlation threshold, the system will trigger an emergency temperature and humidity regulation instruction to quickly adjust the storage environment to slow down the metabolic rate. For example: due to the excessive respiratory metabolism of the apple, the system decides to lower the temperature (from 3°C to 1°C), increase the oxygen supply (from 18% to 21%), and reduce the ethylene accumulation (activate the ethylene adsorption device), which can effectively extend the storage time of the apple and avoid premature ripening or decay.

[0128] The progressive regulation determination unit, if the correlation is lower than the threshold and the prediction result shows that the apple is still in the normal ripening state, the system will not take immediate emergency measures but output a progressive regulation strategy to maintain the optimal storage environment. For example: the prediction model shows that the apple is still in the normal ripening stage and there is no risk of quality deterioration in the short term. So the system slowly adjusts the storage environment, including: lowering the temperature by 0.5°C every day to gradually reduce the metabolic rate; controlling the humidity between 85% - 90% to prevent water loss; maintaining the CO2 concentration within 0.5% to avoid excessive accumulation affecting the quality. Through this progressive regulation, both over-intervention is avoided and the optimal storage state of the apple can be maintained.

[0129] The beneficial effects of the above technical solution are as follows: By means of trend analysis + metabolic monitoring + intelligent prediction + hierarchical regulation, efficient storage management of agricultural products is achieved. It can not only predict the quality change trend of agricultural products, but also take emergency or progressive regulation according to specific situations to ensure the stable quality of agricultural products, reduce losses, and maximize the storage time.

[0130] In another embodiment, the relevance assessment unit includes:

[0131] A gas phase identification subunit for identifying the ethylene release phase in the current data period and the carbon dioxide absorption phase in the previous period;

[0132] A metabolic balance calculation subunit for calculating the metabolic balance coefficient of the two gas phases, and determining metabolic imbalance when the coefficient is lower than the preset balance threshold;

[0133] A light influence factor acquisition subunit for acquiring the influence factor of the current light intensity on the photosynthesis of agricultural products;

[0134] A comprehensive correlation degree generation subunit for weighted fusion of the metabolic balance coefficient and the light influence factor to generate an environmental correlation degree index;

[0135] A storage state classification subunit for reclassifying the storage stage and updating the regulation strategy library when the environmental correlation degree index breaks through the dynamic adjustment boundary.

[0136] The working principle of the above technical solution is as follows: The task of the gas phase identification subunit is to identify the gas phase in the current period by detecting the changes in the concentrations of ethylene (C2H2) and carbon dioxide (CO2) in the air. Ethylene is an important hormone in the process of plant maturation and senescence and has an important impact on the post-ripening process of agricultural products. Carbon dioxide is the gas absorbed during the process of plant photosynthesis. Suppose in a vegetable storage environment, a high ethylene concentration indicates that vegetables such as tomatoes and bananas are ripening, while a high carbon dioxide concentration indicates active photosynthesis. The system compares the ethylene release phase in the current period with the carbon dioxide absorption phase in the previous period to determine whether the current environment is suitable for storing these agricultural products.

[0137] The task of the metabolic balance calculation subunit is to evaluate the metabolic status of agricultural products in the current environment by calculating the metabolic balance coefficient. When the metabolic balance coefficient is lower than the preset threshold, the system determines metabolic imbalance, resulting in a decline in the quality of agricultural products. For example, when storing tomatoes, the system calculates a metabolic balance coefficient based on the concentrations of ethylene and carbon dioxide. If this coefficient is lower than the preset balance threshold, it indicates that there is a problem with the balance between the respiration (consuming oxygen and releasing carbon dioxide) and photosynthesis (absorbing carbon dioxide and releasing oxygen) of the plant, leading to a decline in the quality of tomatoes. At this time, the system will issue an instruction to adjust the storage conditions.

[0138] The task of the light influence factor acquisition subunit is to obtain the influence factor on the photosynthesis of agricultural products according to the current light intensity. During the storage of agricultural products, the light intensity directly affects the photosynthesis efficiency, and thus affects the metabolic balance of agricultural products. For example, when storing apples, if the light intensity is too low, the photosynthesis of apples will be inhibited, resulting in metabolic imbalance. The system calculates the influence factor by detecting the current light intensity and combining the plant's light requirements to further adjust the storage environment.

[0139] The comprehensive correlation degree generation subunit performs weighted fusion on the metabolic balance coefficient and the light influence factor to generate a comprehensive environmental correlation degree index, which reflects whether the current storage environment is suitable for the optimal storage of agricultural products. Suppose when storing bananas, the metabolic balance coefficient and the light influence factor are 0.75 and 0.80 respectively. After weighted calculation, a comprehensive environmental correlation degree index is generated. Suppose the weight of the metabolic balance coefficient is 0.6 and the weight of the light influence factor is 0.4, then the final correlation degree index is 0.78. According to this index, the system can judge whether the current environment needs to be adjusted.

[0140] The storage state classification subunit reclassifies the storage stage according to the change of the comprehensive environmental correlation degree index and updates the control strategy. The storage stage includes different parameters such as temperature and humidity control, gas concentration, etc. to ensure the optimal preservation of agricultural products. Suppose when storing apples, the comprehensive environmental correlation degree index breaks through the dynamic adjustment boundary (for example, exceeds 0.85). The system will judge that the current environment is no longer suitable for continuing to store apples, so it will automatically adjust the environmental parameters and enter a new storage stage. For example, lower the temperature, increase the humidity, or adjust the gas composition to prevent the apples from ripening or rotting too quickly.

[0141] The beneficial effects of the above technical solution are as follows: By real-time monitoring of the gas phase, metabolic balance, and light influence, the system can accurately adjust the storage conditions, thereby extending the fresh-keeping period of agricultural products and reducing losses. The system can dynamically adjust the storage strategy according to the comprehensive correlation degree index, avoid excessive or insufficient intervention, and improve the storage efficiency. By automatically monitoring and adjusting the storage environment, the system reduces manual intervention, reduces errors caused by human factors, and improves the accuracy of storage management. By precisely controlling the temperature, humidity, and gas composition, it avoids excessive energy consumption (such as excessive cooling or humidification) and resource waste, improves energy utilization efficiency, and meets the requirements of sustainable development.

[0142] In another embodiment, the metabolic feature extraction unit includes:

[0143] The metabolic parameter calibration subunit is used to obtain the standard respiration metabolic curves of different agricultural products and establish a metabolic parameter calibration template;

[0144] A real-time metabolism tracking subunit, configured to identify the deviation between the actual metabolism rate and the theoretical value in the current data period according to a calibration template;

[0145] A feature vector construction subunit, configured to encode the ethylene concentration change gradient, the carbon dioxide accumulation slope, and the light response delay time into a multi-dimensional feature vector;

[0146] A metabolism map update subunit, configured to construct a dynamic metabolism map based on the feature vectors of three consecutive data periods, and perform a difference comparison with the benchmark map in the regulation strategy library, and feed back the comparison result to the relevance assessment unit in real time.

[0147] The working principle of the above technical solution is as follows: The main task of the metabolism parameter calibration subunit is to obtain the standard respiratory metabolism curves of different agricultural products and establish a metabolism parameter calibration template. During the storage of agricultural products, respiration occurs, consuming oxygen and releasing carbon dioxide. Different types of agricultural products have different respiration metabolism rates. Therefore, the standard metabolism curve of each agricultural product needs to be obtained through experiments. Suppose we choose apples as the research object. First, we use experimental equipment to monitor the respiration metabolism of apples under different storage conditions, such as measuring the hourly oxygen consumption and carbon dioxide release. Then, these experimental data are fitted through a mathematical model to obtain the standard respiratory metabolism curve of apples and form a metabolism parameter calibration template.

[0148] The real-time metabolism tracking subunit identifies the deviation between the actual metabolism rate and the theoretical value in the current data period by obtaining the metabolism data of agricultural products in real time and comparing it with the standard template. Taking apples as an example, during actual storage, we will monitor the respiration metabolism data of apples in real time, such as oxygen consumption and carbon dioxide release. Then, by comparing these real-time data with the standard template (the respiration metabolism curve of apples), we can calculate the deviation between the current actual metabolism rate and the theoretical value. If a large deviation between the metabolism rate and the theoretical value is found in a certain period, it means that there is a problem with the storage environment of the apples, such as too high temperature or too low humidity.

[0149] The task of the feature vector construction subunit is to convert multiple metabolism features (such as ethylene concentration change gradient, carbon dioxide accumulation slope, light response delay time) into a multi-dimensional feature vector to describe the comprehensive characteristics of agricultural product metabolism. Taking apples as an example, during storage, apples produce ethylene, which is a hormone that affects fruit ripening. We can measure multiple indicators such as the ethylene concentration change gradient in the apple storage environment, the carbon dioxide accumulation slope, and the response delay time of apples under different light conditions. These indicators can be converted into a multi-dimensional feature vector, for example: [ethylene concentration change gradient, carbon dioxide accumulation slope, light response delay time]. This feature vector can be used to comprehensively describe the metabolism of apples.

[0150] The metabolic map update subunit constructs a dynamic metabolic map based on the eigenvectors of three consecutive data periods, compares the differences with the benchmark map in the regulation strategy library, and feeds back to the relevance assessment unit in real time. Suppose we have data for 3 time periods: the first time period (T1) is the metabolic characteristics of the apples when they are just stored in the warehouse, the second time period (T2) is the data after one week of storage, and the third time period (T3) is the data after two weeks of storage. Each time period has corresponding eigenvectors: [ethylene concentration change gradient, carbon dioxide accumulation slope, light response delay time]. Combining these three eigenvectors, a dynamic metabolic map is constructed. This map can be used to show the metabolic change trend of the apples. Then, this metabolic map will be compared with the benchmark map in the regulation strategy library. For example, the benchmark map shows how the metabolic characteristics of the apples should change under normal storage conditions, while the actual map may show abnormal fluctuations in ethylene concentration and carbon dioxide release. According to the comparison results, the system will feedback the differences and adjust the storage conditions, such as adjusting the temperature, humidity or ventilation conditions, to optimize the storage environment of the apples.

[0151] The beneficial effects of the above technical solution are: through the update of the metabolic map and the comparison with the benchmark map, the system can diagnose the possible abnormalities in the storage process in real time, ensure the best storage environment for agricultural products, improve the quality and storage period of agricultural products. It can achieve accurate tracking, evaluation and regulation of the metabolic state of agricultural products, and ensure the quality stability of agricultural products during storage.

[0152] In another embodiment, the storage regulation strategy library includes:

[0153] A gas component safety threshold matrix for different types of agricultural products, where each matrix element corresponds to the extreme values of ethylene / carbon dioxide concentration under specific temperature and humidity conditions;

[0154] A dynamic light regulation strategy tree, and the strategy tree nodes contain the matching relationship between the light intensity - wavelength - irradiation period combination parameters and the photosynthesis requirements at different maturity stages;

[0155] An environmental parameter coupling rule library, which stores the influence function of temperature fluctuation on the gas diffusion coefficient and the humidity - light synergistic action model.

[0156] The working principle of the above technical solution is as follows: The gas component safety threshold matrix stores the safety concentration thresholds of gas components (such as ethylene and carbon dioxide) of different agricultural products under different temperature and humidity conditions. These thresholds are obtained through experiments or research and are used to ensure that agricultural products are not affected by excessive ethylene or carbon dioxide during storage, thereby avoiding rotting or over-ripening. Suppose we are storing bananas. Bananas are fruits with strong respiration and are very sensitive to ethylene and carbon dioxide. During storage, temperature and humidity have a direct impact on gas concentration. For example, the temperature is set at 12°C and the humidity is set at 85%. At this time, the ethylene concentration threshold for bananas is 0.5 ppm (parts per million), and the carbon dioxide concentration threshold is 1.0%. If the ethylene concentration exceeds 0.5 ppm or the carbon dioxide concentration exceeds 1.0% under this temperature and humidity condition, the system will trigger an alarm and adjust the storage environment to prevent the bananas from over-ripening. During storage, gas sensors will continuously monitor the concentrations of ethylene and carbon dioxide and compare them with the values in the safety threshold matrix to ensure that the gas concentrations are always kept within the safe range.

[0157] The dynamic light regulation strategy tree is used to adjust parameters such as the intensity, wavelength, and irradiation period of light according to the maturity stages of different agricultural products to meet the photosynthesis requirements of agricultural products. Each strategy tree node represents a light combination parameter and matches the photosynthesis requirements of a specific maturity stage. Suppose we are storing tomatoes. As a kind of fruit, tomatoes require appropriate light during the ripening process to promote their photosynthesis and color change. If tomatoes are in the immature stage, they have a lower demand for light intensity and are suitable for a shorter light cycle. At this time, the light intensity is 3000 lux, the wavelength is concentrated in the red light range (620 - 750 nm), and the irradiation period is 6 hours per day. If tomatoes gradually enter the mature stage and the photosynthesis requirements increase, the system will adjust the light parameters through the dynamic light regulation strategy tree. For example, the light intensity will be increased to 4000 lux, the irradiation period will be extended to 12 hours, and at the same time, the wavelength will tend to blue or purple light to promote the ripening of the fruit. Each regulation strategy tree node corresponds to specific light conditions and can be dynamically adjusted according to the maturity stage of tomatoes, enabling them to grow or ripen in the best environment.

[0158] The environmental parameter coupling rule library stores environmental parameter coupling rules related to temperature and humidity, describes the variation law of gas diffusion coefficient under different temperature conditions, and the model of the synergistic effect of humidity and light. Through these rules, environmental factors such as temperature, humidity, and light can be precisely adjusted to optimize the storage conditions of agricultural products. Suppose we are storing citrus fruits. Citrus fruits are sensitive to temperature and humidity changes. Too high or too low temperature will affect their respiration and water evaporation. The system uses the influence function in the coupling rule library to obtain the influence of temperature fluctuation on the gas diffusion coefficient. For example, when the temperature rises from 10°C to 15°C, the gas diffusion coefficient will increase accordingly, which means that gases such as carbon dioxide diffuse faster, and the concentration thresholds of ethylene and carbon dioxide need to be adjusted accordingly. In addition, there is also an interaction between humidity and light. For example, under higher humidity conditions, the change in light intensity has a greater impact on water evaporation. Therefore, the system will adjust the light intensity through the synergistic effect model to ensure the balance of humidity and light. When the system detects a temperature change, it will adjust the gas concentration threshold, humidity, and light conditions in real time according to the influence function of the coupling rule library, so as to ensure the best storage environment for citrus fruits.

[0159] The beneficial effects of the above technical solution are as follows: The storage regulation strategy library can adjust and optimize the storage environment in real time and dynamically. The gas component safety threshold matrix ensures that the gas concentration of agricultural products remains within a safe range. The dynamic light regulation strategy tree adjusts the light parameters according to the growth and maturity stages of agricultural products, while the environmental parameter coupling rule library ensures the storage of agricultural products in the best environment through precise temperature, humidity, and light synergistic regulation.

[0160] In another embodiment, as Figure 3 shown, a monitoring method for agricultural product storage includes:

[0161] S101: Through a multi-modal sensor network deployed in the storage warehouse, obtain the environmental data stream including temperature, humidity, gas components, and light intensity in real time;

[0162] S102: Based on the preset agricultural product storage threshold conditions and the physiological characteristics of the target agricultural product, determine the monitoring parameters that need to be dynamically regulated in the environmental data stream;

[0163] S103: Obtain the preset storage regulation strategy library corresponding to the monitoring parameters;

[0164] S104: According to the preset storage regulation strategy library, match the corresponding regulation strategy, and based on the regulation strategy, adjust the storage environment in real time and dynamically.

[0165] The working principle of the above technical solution is as follows: Step S104 includes:

[0166] Based on the environmental data stream, obtain the first data period when the monitoring condition is first triggered, and at the same time obtain the data type of the first monitoring parameter;

[0167] If the data type is gas composition, identify the first gas concentration feature in the first data period;

[0168] Match the first gas concentration feature with the standard gas threshold in the corresponding stored regulation strategy library to obtain the first gas matching strategy;

[0169] If the first gas matching strategy is that the concentration exceeds the standard, start the hierarchical ventilation program, preferentially enable the low-speed circulation mode, and output the first gas regulation instruction;

[0170] If the first matching strategy is within the safe range, continuously obtain the second data period after the first data period, where the first matching strategy includes the first gas matching strategy and the first light matching strategy;

[0171] Integrate the first data period and the second data period into an environmental change trend stream in time series;

[0172] Determine the first regulation strategy according to the environmental change trend stream. The first gas regulation strategy is an environmental parameter adjustment plan based on the prediction of the maturity of agricultural products.

[0173] Step S104 further includes:

[0174] If the data type is light condition, identify the first light distribution feature in the first data period;

[0175] Match the first light distribution feature with the standard light atlas in the corresponding stored regulation strategy library to obtain the first light matching strategy;

[0176] If the first light matching strategy is spectral loss, automatically adjust the LED lighting system and output the first light regulation instruction.

[0177] Determine the first regulation strategy, including:

[0178] Parse each data period in the environmental change trend stream in chronological order;

[0179] Each time of parsing, based on the agricultural product respiration metabolism model, extract the gas exchange features of the current data period and integrate them into a metabolism feature sequence;

[0180] Analyze the parameter correlation degree between the currently parsed data period and the previous data period. When the change rate of ethylene concentration and the accumulation amount of carbon dioxide are positively correlated within a preset time window, it is determined as the associated storage state;

[0181] After each parsing is completed, input the real-time obtained metabolism feature sequence into a preset quality prediction model to obtain the quality prediction result;

[0182] If the correlation degree exceeds the preset correlation threshold and the prediction result is the risk of quality deterioration, immediately trigger the temperature and humidity control instruction to adjust the temperature and humidity.

[0183] If the correlation degree is lower than the preset threshold and the prediction result continues to be normal maturity, output a progressive control strategy.

[0184] Analyze the parameter correlation degree between the current parsed data period and the previous data period, including:

[0185] Identify the ethylene release phase in the current data period and the carbon dioxide absorption phase in the previous period;

[0186] Calculate the metabolic balance coefficient of the two gas phases, and determine metabolic imbalance when the coefficient is lower than the preset balance threshold;

[0187] Obtain the influence factor of the current light intensity on the photosynthesis of agricultural products;

[0188] Perform weighted fusion on the metabolic balance coefficient and the light influence factor to generate an environmental correlation index;

[0189] When the environmental correlation index breaks through the dynamically adjusted boundary, re-divide the storage stage and update the control strategy library.

[0190] Extract the gas exchange characteristics of the current data period, including:

[0191] Obtain the standard respiratory metabolism curves of different agricultural products and establish a metabolic parameter calibration template;

[0192] Identify the deviation between the actual metabolic rate and the theoretical value in the current data period according to the calibration template;

[0193] Encode the ethylene concentration change gradient, carbon dioxide accumulation slope, and light response delay time into a multi-dimensional feature vector;

[0194] Construct a dynamic metabolic map based on the feature vectors of three consecutive data periods, and perform differential comparison with the reference map in the control strategy library. The comparison result is fed back to the correlation evaluation unit in real time.

[0195] The beneficial effects of the above technical solutions are as follows: It can ensure the precise control of environmental conditions during the storage of agricultural products, thereby optimizing the preservation quality of agricultural products and avoiding quality losses caused by environmental fluctuations. The data provided by the multi-modal sensors provide accurate basis for intelligent control, and the control strategy library ensures the scientificity and practicality of control measures, ultimately improving the storage efficiency, extending the freshness period, and reducing resource waste.

[0196] In another embodiment, the step S102 includes:

[0197] S1021: Perform time - segment division processing on the environmental data stream to obtain multiple data segments;

[0198] S1022: Based on gas chromatography analysis technology and spectral analysis algorithms, perform component analysis on multiple data segments respectively to obtain the corresponding gas components and current lighting conditions;

[0199] S1023: Use the gas components and the current lighting conditions together as monitoring parameters.

[0200] The working principle of the above - mentioned technical solution is as follows: First, the environmental data stream collected by the sensor is cut according to time into multiple segments. Each segment contains environmental data within a certain period, such as temperature, humidity, gas components, light intensity, etc. Suppose the data streams of temperature, humidity, and gas concentration (such as ethylene concentration) in a certain storage warehouse are continuously collected within 24 hours a day. The system will divide these data at a certain time interval (such as every hour, every half - hour, or every 10 minutes) to generate multiple data segments (for example: 00:00 - 01:00, 01:00 - 02:00, etc.). During the storage of apples, certain gases such as ethylene will affect the ripening process of apples during specific time periods. If the gas concentration is too high at night (such as 21:00 - 22:00), it will accelerate the ripening of apples, while during the day (such as 09:00 - 10:00), different changes will occur due to the higher temperature. At this time, dividing the data segments helps to accurately analyze the impact of environmental changes at different times on agricultural products.

[0201] Use gas chromatography (GC) analysis technology to accurately measure the gas components in each period, and at the same time combine spectral analysis algorithms to analyze the light intensity and its wavelength distribution. Gas chromatography analysis: This is a commonly used technology for analyzing gas components. Different gases are separated by a chromatographic column, and then the concentration of each gas is detected by a sensor. For example, gas chromatography analysis can be used to detect the concentrations of ethylene, carbon dioxide, oxygen, and other volatile substances in a warehouse. Spectral analysis algorithm: This algorithm is used to analyze the light intensity and its wavelength distribution, and then judge the impact of light conditions in the storage environment on agricultural products. For example, some vegetables such as leafy vegetables (such as lettuce, spinach) require less light to delay their ripening, while fruits (such as strawberries) may require more light to extend their shelf life. For example: The system will obtain the concentrations of various gas components through chromatographic analysis based on the gas data and light data in each period, and at the same time obtain the light intensity at different time periods through the spectral algorithm. For example, in the period from 00:00 to 01:00, a relatively high carbon dioxide concentration may be detected, while in the period from 09:00 to 10:00, there will be stronger light. For the storage of grapes, grapes are highly sensitive to ethylene, especially at night when the light intensity is low. An increase in ethylene concentration may cause the grapes to ripen prematurely. Therefore, through this technical analysis, the system can identify and adjust the ethylene concentration and light conditions to prevent the grapes from spoiling during storage.

[0202] Comprehensively consider the gas concentration after component analysis and the light conditions as a comprehensive monitoring parameter for subsequent dynamic regulation. Combine the concentration data of each gas (such as ethylene, carbon dioxide) obtained from gas analysis with the light intensity in the current period. For example, if the ethylene concentration is too high and the light conditions are suitable in a certain period, it will cause fruits such as apples and bananas to ripen faster. Therefore, these environmental parameters will be integrated together as the basis for future regulation. For the environment for storing bananas, if the ethylene concentration is too high and the light intensity is strong, the ripening speed of bananas will increase. The system will prompt the manager to reduce the ethylene concentration and adjust the light intensity to delay the ripening of bananas and extend their shelf life according to these data.

[0203] The beneficial effects of the above technical solution are: Through periodization processing and combined analysis of gas components and light conditions, it helps to provide a more accurate storage environment regulation plan, extend the shelf life of agricultural products, improve storage efficiency, while reducing resource waste and minimizing the negative impact of the environment on agricultural products.

[0204] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A monitoring device for agricultural product storage, characterized in that: include: The acquisition module is used to obtain real-time environmental data streams including temperature, humidity, gas composition and light intensity through a multimodal sensor network deployed in the storage warehouse; An analysis module for determining monitoring parameters that need to be dynamically regulated in the environmental data stream based on preset agricultural product storage threshold conditions and target agricultural product physiological characteristics; A control strategy module is used to obtain a preset storage control strategy library corresponding to the monitoring parameters; The intelligent control module is used to match the corresponding control strategy according to the preset storage control strategy library, and to make real-time dynamic adjustments to the storage environment based on the control strategy.

2. The monitoring device for agricultural product storage according to claim 1, characterized in that: The analysis modules include: The time segmentation submodule is used to segment the environmental data stream into time segments to obtain multiple data time segments; The detection submodule is used to analyze the components of multiple data periods based on gas chromatography analysis technology and spectrum analysis algorithm to obtain the corresponding gas components and current light conditions; The determination submodule is used to use the gas composition and the current light conditions as monitoring parameters.

3. The monitoring device for agricultural product storage according to claim 1, characterized in that: Intelligent control module includes: An initial data acquisition submodule, used to acquire a first data period of the first triggering monitoring condition based on the environmental data stream, and simultaneously acquire a data type of the first monitoring parameter; A gas matching submodule, for identifying a first gas concentration feature in a first data period if the data type is a gas composition; A first strategy matching submodule, used to match the first gas concentration feature with the standard gas threshold in the corresponding storage control strategy library to obtain a first gas matching strategy; The ventilation control submodule is used to start the graded ventilation program, give priority to the low-speed circulation mode, and output the first gas control instruction if the first gas matching strategy is that the concentration exceeds the standard; A continuous monitoring submodule, configured to continuously acquire a second data period after the first data period if the first matching strategy is within a safe range, wherein the first matching strategy includes a first gas matching strategy and a first illumination matching strategy; A data sequence construction submodule, for integrating the first data period and the second data period into an environmental change trend stream according to a time series; The quality prediction submodule is used to determine the first control strategy according to the environmental change trend flow. The first gas control strategy is an environmental parameter adjustment plan based on the prediction of agricultural product maturity.

4. The monitoring device for agricultural product storage according to claim 3, characterized in that: The intelligent control module also includes: an illumination analysis submodule, for identifying a first illumination distribution feature in a first data period if the data type is illumination condition; A second strategy matching submodule is used to match the first illumination distribution feature with a standard illumination map in a corresponding storage control strategy library to obtain a first illumination matching strategy; The fill light control submodule is used to automatically adjust the LED lighting system and output a first lighting control instruction if the first lighting matching strategy is spectrum loss.

5. The monitoring device for agricultural product storage according to claim 3, characterized in that: Quality prediction submodule, including: A trend analysis unit, used to analyze each data period in the environmental change trend stream in chronological order; The metabolic feature extraction unit is used to extract the gas exchange characteristics of the current data period based on the agricultural product respiratory metabolism model during each analysis and integrate them into a metabolic feature sequence; A correlation evaluation unit is used to analyze the correlation between the parameters of the current analyzed data period and the previous data period, and when the ethylene concentration change rate and the carbon dioxide accumulation amount are positively correlated within a preset time window, it is determined to be a correlated storage state; The prediction model input unit is used to input the metabolic feature sequence obtained in real time into the preset quality prediction model after each analysis is completed to obtain the quality prediction result; An emergency control judgment unit is used to immediately trigger a temperature and humidity control instruction to adjust the temperature and humidity if the correlation exceeds a preset correlation threshold and the prediction result is a risk of quality deterioration; The progressive control determination unit is used to output a progressive control strategy if the correlation degree is lower than a preset threshold and the prediction result continues to be normal maturity.

6. The monitoring device for agricultural product storage according to claim 5, characterized in that: Relevance Assessment Unit, including: A gas phase identification subunit, used to identify the ethylene release phase of the current data period and the carbon dioxide absorption phase of the previous period; A metabolic balance calculation subunit, used to calculate the metabolic balance coefficient of the two gas phases, and when the coefficient is lower than a preset balance threshold, it is determined to be a metabolic imbalance; The light impact factor acquisition subunit is used to obtain the impact factor of the current light intensity on the photosynthesis of agricultural products; The comprehensive correlation generation subunit is used to perform weighted fusion of the metabolic balance coefficient and the light influencing factor to generate an environmental correlation index; The storage status classification subunit is used to re-divide the storage stage and update the control strategy library when the environmental correlation index exceeds the dynamic adjustment boundary.

7. The monitoring device for agricultural product storage according to claim 5, characterized in that: Metabolic feature extraction unit, including: The metabolic parameter calibration subunit is used to obtain the standard respiratory metabolic curves of different agricultural products and establish a metabolic parameter calibration template; A real-time metabolic tracking subunit, which is used to identify the deviation between the actual metabolic rate and the theoretical value in the current data period according to the calibration template; A feature vector construction subunit is used to encode the ethylene concentration gradient, carbon dioxide accumulation slope and light response delay time into a multi-dimensional feature vector; The metabolic map updating subunit is used to construct a dynamic metabolic map based on the characteristic vectors of three consecutive data periods, and compare the differences with the benchmark map in the regulation strategy library. The comparison results are fed back to the correlation evaluation unit in real time.

8. The monitoring device for agricultural product storage according to claim 1, characterized in that: The storage control policy library includes: Gas composition safety threshold matrix for different types of agricultural products, where each matrix element corresponds to the extreme value of ethylene / carbon dioxide concentration under specific temperature and humidity conditions; Dynamic light regulation strategy tree, where the strategy tree nodes contain the matching relationship between the light intensity-wavelength-irradiation cycle combination parameters and the photosynthesis requirements at different maturity stages; The environmental parameter coupling rule base stores the impact function of temperature fluctuation on gas diffusion coefficient and the synergistic model of humidity and light.

9. A monitoring method for agricultural product storage, characterized in that: include: S101: A multimodal sensor network deployed in the storage warehouse is used to obtain real-time environmental data streams including temperature, humidity, gas composition, and light intensity; S102: Determine monitoring parameters that need to be dynamically regulated in the environmental data stream based on preset agricultural product storage threshold conditions and target agricultural product physiological characteristics; S103: Obtaining a preset storage control strategy library corresponding to the monitoring parameters; S104: Matching corresponding regulation strategies according to a preset storage regulation strategy library, and dynamically adjusting the storage environment in real time based on the regulation strategies.

10. The monitoring method for agricultural product storage according to claim 9, characterized in that: Step S102 includes: S1021: performing time segmentation processing on the environmental data stream to obtain multiple data time segments; S1022: Based on the gas chromatography analysis technology and spectrum analysis algorithm, component analysis is performed on multiple data time periods to obtain corresponding gas components and current light conditions; S1023: The gas composition and the current light conditions are used as monitoring parameters.

Images