An agricultural product cold chain logistics internet of things intelligent monitoring method and system

Abstract

The application discloses an Internet of Things intelligent monitoring method and system for agricultural product cold-chain logistics, relates to the technical field of logistics monitoring, and comprises the following steps: constructing a cold-chain transportation twin model; acquiring the product type of agricultural products and initial micro-environment data in a warehouse, obtaining microbial electrical signal data and gas metabolism data; obtaining comprehensive quality evolution data of the agricultural products; obtaining real-time micro-environment data at a current time point, obtaining a deterioration influence parameter caused by the environment on the agricultural products; simulating in the cold-chain transportation twin model to obtain a predicted deterioration degree value; adjusting the micro-environment and physical field in the warehouse, constructing a dormant warehouse, and mapping the dormant warehouse to the cold-chain transportation twin model; and sending the cold-chain transportation twin model to monitoring personnel, so that the monitoring personnel can check the warehouse and manually intervene. The application has the effects of improving the accuracy, forward-looking nature and operation convenience of monitoring data of agricultural products in the cold-chain logistics transportation process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of logistics monitoring, in particular to a method and system for intelligent monitoring of agricultural product cold-chain logistics based on the Internet of Things. BACKGROUND

[0002] Cold-chain transportation is a very common transportation method, which can prolong the freshness of agricultural products and ensure that the agricultural products will not spoil during long-distance transportation.

[0003] In the prior art, when monitoring agricultural products during cold-chain transportation, a temperature and humidity sensor is generally arranged in the warehouse to monitor the temperature and humidity in the warehouse, and the temperature and humidity data in the warehouse are used to determine whether the goods may have problems. Alternatively, manual inspection is used to enter the warehouse to inspect the agricultural products at regular intervals. Through the above method, the agricultural products during cold-chain transportation can only be monitored from a relatively broad perspective, which is not only time-consuming and labor-intensive, but also cannot obtain accurate data. On the other hand, the buyers and sellers of agricultural products cannot obtain accurate data of the agricultural products during transportation, which not only causes psychological pressure but also cannot reduce losses. Therefore, how to more accurately and intelligently monitor the cold-chain logistics of agricultural products has become a problem to be solved. SUMMARY

[0004] The purpose of the present application is to provide a method and system for intelligent monitoring of agricultural product cold-chain logistics based on the Internet of Things to solve the problems raised in the background.

[0005] In a first aspect, the present application provides a method for intelligent monitoring of agricultural product cold-chain logistics based on the Internet of Things, which comprises:

[0006] Obtaining cold storage warehouse parameters, goods product parameters, goods loading schemes, and route information to construct a cold-chain transportation twin model;

[0007] Obtaining the product type of the agricultural products and the initial micro-environment data in the warehouse, performing biological detection on the agricultural products according to the product type to obtain microorganism electrical signal data and gas metabolism data;

[0008] According to the microorganism electrical signal data, first quality evolution data is obtained, and according to the gas metabolism data, second quality evolution data is obtained, and the first quality evolution data and the second quality evolution data are combined to obtain comprehensive quality evolution data of the agricultural products;

[0009] According to the gas metabolism data, the initial microenvironment data is modified to obtain real-time microenvironment data at the current time point, and a deterioration influence parameter of the environment on the agricultural products is obtained according to the real-time microenvironment data;

[0010] The comprehensive quality evolution data and the deterioration influence parameter are substituted into the cold chain transportation twin model for simulation to obtain a predicted deterioration degree value;

[0011] It is judged whether the predicted deterioration degree value exceeds a preset deterioration degree threshold value, and if it is judged that the deterioration degree value reaches the deterioration degree threshold value, the microenvironment and the physical field in the warehouse are adjusted to construct a dormant warehouse, and the dormant warehouse is mapped into the cold chain transportation twin model;

[0012] The cold chain transportation twin model is sent to a monitoring personnel, and the monitoring personnel views real-time and predicted situations in the warehouse and manually intervenes.

[0013] Preferably, the cold storage warehouse parameters, the cargo product parameters, the cargo loading scheme, and the route information are obtained to construct the cold chain transportation twin model, and the steps are specifically as follows:

[0014] The cold storage warehouse parameters, the cargo product parameters, and the cargo loading scheme are obtained;

[0015] According to the cold storage warehouse parameters, a model framework of the digital twin model is constructed, and according to the cargo loading scheme, the model framework is filled with goods to obtain an initial twin model;

[0016] According to the cargo product parameters, the initial twin model is filled with biological data to obtain an in-warehouse twin model;

[0017] The route information of the cold chain transportation is obtained, external meteorological data of a position corresponding to the route information is extracted, and an out-of-warehouse twin model is constructed according to the external meteorological data;

[0018] The in-warehouse twin model and the out-of-warehouse twin model are combined to generate a cold chain transportation twin model.

[0019] Preferably, the biological detection of the agricultural products according to the agricultural product types is performed to obtain microorganism electrical signal data and gas metabolism data, and the steps are specifically as follows:

[0020] According to the agricultural product types, basic product parameters of the agricultural products are obtained, common surface microorganism data and initial product cell parameters are obtained according to the basic product parameters;

[0021] According to the common surface microorganism data, initial microorganism types are identified, and a microorganism rapid detection method is obtained according to the initial microorganism types;

[0022] According to the microbial rapid detection method, the microorganisms existing in the agricultural products are identified by electric signals to obtain microbial electric signal data;

[0023] According to the initial product cell parameters, product cell types and current cell activity are obtained, and the current cell respiration intensity is obtained according to the current cell activity;

[0024] According to the product cell types and the current cell respiration intensity, cell respiration rate, respiration product concentration and cell respiration product are obtained, and gas metabolism data are obtained in combination with the cell respiration rate, the respiration product concentration and the cell respiration product.

[0025] Preferably, according to the microbial electric signal data, first quality evolution data are obtained, and according to the gas metabolism data, second quality evolution data are obtained, and the steps are specifically as follows:

[0026] According to the microbial electric signal data, microbial types and the number of microorganisms corresponding to each microbial type are obtained;

[0027] According to the microbial types, monomer catalytic effect value of each microbial type on quality evolution of the agricultural products is obtained;

[0028] In combination with the number of microorganisms and the monomer catalytic effect value, comprehensive catalytic effect value of the overall microbial community on quality evolution of the agricultural products is obtained, and first quality evolution data are obtained according to the comprehensive catalytic effect value;

[0029] According to the cell respiration rate and the respiration product concentration in the gas metabolism data, cell metabolism rate is obtained;

[0030] According to the cell respiration product, metabolic cell type ratio is obtained, and second quality evolution data are obtained according to the cell metabolism rate and the metabolic cell type ratio.

[0031] Preferably, according to the gas metabolism data, the initial microenvironment data are modified to obtain real-time microenvironment data at a current time point, and the step of obtaining a deterioration influence parameter of the environment on the agricultural products according to the real-time microenvironment data is specifically as follows:

[0032] According to the cell metabolism rate and the cell respiration product, microenvironment modification parameters are obtained, the initial microenvironment data are modified according to the microenvironment modification parameters to obtain real-time microenvironment data at a current time point;

[0033] According to the real-time microenvironment data, extract microenvironment components in the microenvironment, and identify target microenvironment components in the microenvironment components that have an impact on the deterioration of agricultural products;

[0034] Classify the target microenvironment components to obtain inhibitory components that have an inhibitory effect on the deterioration of agricultural products and accelerating components that have an accelerating effect on the deterioration of agricultural products;

[0035] Effectively evaluate the inhibitory components and the accelerating components respectively to obtain inhibitory effect evaluation values and accelerating effect evaluation values, and combine the inhibitory effect evaluation values and the accelerating effect evaluation values to obtain a deterioration impact parameter.

[0036] Preferably, the comprehensive quality evolution data and the deterioration impact parameter are substituted into the cold chain transportation twin model for simulation to obtain a predicted deterioration degree value, specifically:

[0037] Substitute the comprehensive quality evolution data and the deterioration impact parameter into the cold chain transportation twin model, and the cold chain transportation twin model simulates transportation;

[0038] During the simulation transportation, the quality change of the agricultural products is monitored to obtain simulation quality change data, and a simulation quality change curve is generated according to the simulation quality change data;

[0039] When the value of the simulation quality change curve reaches a preset spoilage value, the simulation is stopped;

[0040] Repeat the simulation multiple times to generate multiple simulation quality change curves, set the multiple simulation quality change curves in the same coordinate system, fit the multiple simulation quality change curves to generate a target quality change curve, and record the predicted deterioration degree values at different time points on the target quality change curve.

[0041] Preferably, the microenvironment and the physical field in the warehouse are adjusted to construct a dormant warehouse, and the step of mapping to the cold chain transportation twin model is specifically:

[0042] Extract the time point at which the deterioration degree value reaches the deterioration degree threshold, and set a redundant time period according to the time point to obtain a target time point;

[0043] At the target time point, extract the real-time microenvironment data and real-time physical field data in the warehouse;

[0044] According to the real-time microenvironment data, filter the accelerating components in the microenvironment and retain the inhibitory components to obtain a dormant microenvironment;

[0045] According to the real-time physical field data, the electromagnetic wave frequency and the light parameter in the warehouse are adjusted to obtain a dormant physical field;

[0046] In combination with the dormant microenvironment and the dormant physical field, a dormant warehouse is constructed, and the dormant warehouse is mapped into the cold chain transportation twin model.

[0047] Preferably, the cold chain transportation twin model is sent to a monitoring personnel, the monitoring personnel views the real-time situation and the predicted situation in the warehouse, and a step of manual intervention is performed, specifically:

[0048] The cold chain transportation twin model is visualized to obtain a visual model, and the visual model is sent to a monitoring screen of the monitoring personnel;

[0049] In the visual model, the real-time microenvironment data, the real-time physical field data, and the target quality change curve are displayed on the monitoring screen;

[0050] A current time point is extracted, and a current deterioration degree value of the agricultural product is labeled according to the current time point and the target quality change curve;

[0051] Microenvironment adjustment buttons and physical field adjustment buttons are set on the monitoring screen, and the monitoring personnel can manually adjust the microenvironment and the physical field in real time according to the real-time situation and the predicted situation.

[0052] In a second aspect, the present application provides an Internet of Things intelligent monitoring system for agricultural product cold chain logistics, the system comprising:

[0053] A model construction module is configured to obtain cold storage warehouse parameters, cargo product parameters, cargo loading schemes, and route information, and construct a cold chain transportation twin model;

[0054] A biological detection module is configured to obtain the product type of the agricultural product and initial microenvironment data in the warehouse, perform biological detection on the agricultural product according to the product type, and obtain microbial electrical signal data and gas metabolism data;

[0055] A quality evolution module is configured to obtain first quality evolution data according to the microbial electrical signal data, obtain second quality evolution data according to the gas metabolism data, and obtain comprehensive quality evolution data of the agricultural product in combination with the first quality evolution data and the second quality evolution data;

[0056] An influence parameter module is configured to correct the initial microenvironment data according to the gas metabolism data to obtain real-time microenvironment data at a current time point, and obtain a deterioration influence parameter of the agricultural product caused by the environment according to the real-time microenvironment data;

[0057] A simulation prediction module is configured to input the comprehensive quality evolution data and the deterioration influence parameter into the cold chain transportation twin model for simulation to obtain a predicted deterioration degree value.

[0058] A warehouse adjustment module is configured to determine whether the predicted deterioration degree value exceeds a preset deterioration degree threshold value, and if the deterioration degree value reaches the deterioration degree threshold value, adjust the micro environment and physical field in the warehouse, construct a dormant warehouse, and map to the cold chain transportation twin model.

[0059] A monitoring intervention module is configured to send the cold chain transportation twin model to a monitoring personnel, and the monitoring personnel can view the real-time situation and predicted situation in the warehouse and perform manual intervention.

[0060] In summary, the present application has at least one of the following beneficial technical effects:

[0061] The cold chain transportation twin model is constructed by obtaining the refrigerated warehouse parameters, product parameters, product loading scheme, and route information. Then, at the beginning of transportation, the type of agricultural products and the initial micro environment data in the warehouse are obtained, the appropriate biological detection means is selected according to the type of agricultural products, the microorganisms on the surface of the agricultural products are monitored to obtain the microorganism electrical signal data, and the cell activity of the agricultural products is monitored to obtain the gas metabolism data. Then, the comprehensive quality evolution data of the agricultural products is obtained according to the microorganism electrical signal and the gas metabolism data. Then, the initial micro environment data is corrected according to the gas metabolism data to obtain real-time micro environment data, and the data that has inhibitory effect and accelerating effect on the deterioration of agricultural products in the real-time micro environment data is identified to obtain the deterioration influence parameter. The deterioration influence parameter and the comprehensive quality evolution data are input into the cold chain transportation twin model for simulation to obtain a predicted deterioration degree value. When the predicted deterioration degree value reaches the deterioration threshold value, the micro environment and physical field in the warehouse are automatically adjusted to further threshold the deterioration of the agricultural products. At the same time, the cold chain transportation twin model is sent to the monitoring personnel, and the monitoring personnel can view the real-time situation and predicted situation in the warehouse and perform manual intervention. The accuracy, forward-looking and operation convenience of the monitoring data of agricultural products in the cold chain logistics transportation process are improved. BRIEF DESCRIPTION OF DRAWINGS

[0062] Fig. 1 is a step flow chart of an Internet of Things intelligent monitoring method for agricultural product cold chain logistics provided by an embodiment of the present application;

[0063] Fig. 2 is a module block diagram of an Internet of Things intelligent monitoring system for agricultural product cold chain logistics provided by an embodiment of the present application.

[0064] Label explanation: 1, model construction module; 2, biological detection module; 3, quality evolution module; 4, influence parameter module; 5, simulation prediction module; 6, in-store adjustment module; 7, monitoring intervention module. DETAILED DESCRIPTION

[0065] The following will be described in conjunction with the accompanying drawings Figs. 1-2 The application will be further described in detail, but the embodiments of the application are not limited thereto.

[0066] The embodiment of the application discloses an Internet of Things intelligent monitoring method and system for agricultural product cold chain logistics.

[0067] In the embodiment, an Internet of Things intelligent monitoring method for agricultural product cold chain logistics is disclosed, which comprises the following steps:

[0068] S100: Obtain cold storage warehouse parameters, cargo product parameters, cargo loading schemes, and route information, and construct a cold chain transportation twin model;

[0069] S200: Obtain the product type of the agricultural product and the initial micro-environment data in the warehouse, perform biological detection on the agricultural product according to the product type, and obtain microorganism electrical signal data and gas metabolism data;

[0070] S300: Obtain first quality evolution data according to the microorganism electrical signal data, obtain second quality evolution data according to the gas metabolism data, and obtain comprehensive quality evolution data of the agricultural product by combining the first quality evolution data and the second quality evolution data;

[0071] S400: Correct the initial micro-environment data according to the gas metabolism data to obtain real-time micro-environment data at the current time point, and obtain a deterioration influence parameter of the environment on the agricultural product according to the real-time micro-environment data;

[0072] S500: Substitute the comprehensive quality evolution data and the deterioration influence parameter into the cold chain transportation twin model for simulation to obtain a predicted deterioration degree value;

[0073] S600: Determine whether the predicted deterioration degree value exceeds a preset deterioration degree threshold value, if the predicted deterioration degree value reaches the deterioration degree threshold value, adjust the micro-environment and the physical field in the warehouse, construct a dormant warehouse, and map the dormant warehouse to the cold chain transportation twin model;

[0074] S700: Send the cold chain transportation twin model to a monitoring personnel, and the monitoring personnel views the real-time situation and the predicted situation in the warehouse and manually intervenes.

[0075] It should be pointed out that the above process is only the basic step of the embodiment, and in the specific implementation process, part of the steps can be appropriately added, reduced or modified without affecting the overall implementation effect.

[0076] The steps of obtaining the refrigerated warehouse parameters, the product parameters, the product loading scheme, and the route information to construct the cold chain transportation twin model are as follows:

[0077] Obtain the refrigerated warehouse parameters, the product parameters, and the product loading scheme.

[0078] According to the refrigerated warehouse parameters, a model framework of the digital twin model is constructed, and the model framework is filled with goods according to the product loading scheme to obtain an initial twin model.

[0079] According to the product parameters, the initial twin model is filled with biological data to obtain an in-warehouse twin model.

[0080] Obtain the route information of the cold chain transportation, extract the external meteorological data of the corresponding position of the route information, and construct an out-of-warehouse twin model according to the external meteorological data.

[0081] Combine the in-warehouse twin model and the out-of-warehouse twin model to generate a cold chain transportation twin model.

[0082] In the application, taking strawberry cold chain transportation as an example, first, obtain the refrigerated warehouse parameters, including the warehouse size of 10 meters long, 5 meters wide, and 3 meters high, and the temperature setting of 0°C to 2°C. The product parameters include strawberry variety of red strawberry, weight of 500 kg, and high perishability. The product loading scheme is that strawberry boxes are stacked in the middle of the warehouse, each box size is 0.5m x 0.3m x 0.2m, and there are 100 boxes. The route information is from Hangzhou to Beijing, the total distance is 1200 kilometers, and the expected transportation time is 12 hours. Then, according to the refrigerated warehouse parameters, a model framework of the digital twin model is constructed, which includes the three-dimensional structure of the warehouse and the temperature control system. Then, according to the product loading scheme, the goods are filled in the model framework to simulate the position and stacking mode of the strawberry boxes, and an initial twin model is obtained. Then, according to the product parameters, biological data such as strawberry moisture content of 85% and sugar content of 10% are added to the initial twin model to generate an in-warehouse twin model. At the same time, obtain the external meteorological data of the corresponding position of the route information, the temperature in Hangzhou is 25°C, the humidity is 70%, the temperature in Beijing is 20°C, the humidity is 60%, and there may be light rain in Shandong. According to these meteorological data, an out-of-warehouse twin model is constructed, including temperature, humidity, and rainfall influence. Finally, combine the in-warehouse twin model and the out-of-warehouse twin model to generate a complete cold chain transportation twin model for whole-process simulation.

[0083] The step of performing biological detection on agricultural products according to the type of agricultural products to obtain microbial electrical signal data and gas metabolism data is as follows:

[0084] obtaining a basic product parameter of the agricultural product based on the agricultural product category, and obtaining common surface microorganism data and initial product cell parameters according to the basic product parameter;

[0085] identifying initial microorganism categories according to the common surface microorganism data, and obtaining a microorganism rapid detection method according to the initial microorganism categories;

[0086] performing electrical signal identification on microorganisms existing in the agricultural product according to the microorganism rapid detection method, and obtaining microorganism electrical signal data;

[0087] obtaining product cell categories and current cell activity according to the initial product cell parameters, and obtaining current cell respiration intensity according to the current cell activity;

[0088] obtaining cell respiration rate, respiration product concentration and cell respiration product according to the product cell categories and the current cell respiration intensity, and obtaining gas metabolism data by combining the cell respiration rate, the respiration product concentration and the cell respiration product.

[0089] In the foregoing method, taking strawberry cold chain transportation as an example, a basic product parameter is obtained based on the strawberry category, including that the strawberry has a thin skin and a pH value of 3.5. According to the basic product parameter, common surface microorganism data such as mold (Botrytis cinerea) and bacteria (Escherichia coli) and initial product cell parameters such as an initial cell activity value of 80% are obtained by searching a database. Then, initial microorganism categories are identified as Botrytis cinerea and Escherichia coli according to the common surface microorganism data, and a microorganism rapid detection method is selected according to the categories, and an electrochemical sensor is used. Next, electrical signal identification is performed on microorganisms existing on the surface of the strawberry according to the microorganism rapid detection method, and it is detected that the electrical signal intensity of Botrytis cinerea is 45 mV and the frequency is 1.5 Hz, and the electrical signal intensity of Escherichia coli is 30 mV and the frequency is 2 Hz, and microorganism electrical signal data is obtained. Then, product cell categories are obtained as epidermal cells and pulp cells, and the current cell activity is 75% according to the initial product cell parameters. According to the current cell activity, the current cell respiration intensity is calculated as 4 mg CO2 / kg / h. Then, the cell respiration rate is 0.4 ml / g / h, the respiration product concentration is CO2 0.25% and ethylene 0.1%, and the cell respiration product includes carbon dioxide and ethylene gas, which are obtained according to the product cell categories and the current cell respiration intensity. The gas metabolism data is generated by combining the respiration rate, the respiration product concentration and the respiration product.

[0090] The steps of obtaining first quality evolution data according to the microorganism electrical signal data and obtaining second quality evolution data according to the gas metabolism data are as follows:

[0091] microorganism types and the number of microorganisms corresponding to each microorganism type are obtained according to the microorganism electrical signal data;

[0092] According to the type of microorganism, the monomer catalytic effect value of each type of microorganism on the quality evolution of agricultural products is obtained;

[0093] In combination with the number of microorganisms and the monomer catalytic effect value, the comprehensive catalytic effect value of the overall microbial community on the quality evolution of agricultural products is obtained, and the first quality evolution data is obtained according to the comprehensive catalytic effect value;

[0094] According to the cell respiration rate and the concentration of respiratory products in the gas metabolism data, the cell metabolism rate is obtained;

[0095] According to the cell respiration product, the metabolic cell type ratio is obtained, and the second quality evolution data is obtained according to the cell metabolism rate and the metabolic cell type ratio.

[0096] In the application, taking strawberry cold chain transportation as an example, according to the microbial electrical signal data, it is analyzed that the type of microorganism is gray mold and escherichia coli, the number of gray mold is 50 per square centimeter, and the number of escherichia coli is 30 per square centimeter. Then according to the type of microorganism, the monomer catalytic effect value of gray mold on the quality of strawberry is 0.8 (indicating that 0.8% of the unit accelerates corruption) and the monomer catalytic effect value of escherichia coli is 0.5. Then, in combination with the number of microorganisms and the monomer catalytic effect value, the comprehensive catalytic effect value of the microbial community is calculated: gray mold contributes 50x0.8=40, escherichia coli contributes 30x0.5=15, and the total is 55. According to the comprehensive catalytic effect value 55, the first quality evolution data is obtained, indicating that the microorganism causes 55% of the corruption acceleration. At the same time, according to the cell respiration rate 0.4 ml / g / h and the respiratory product concentration CO2 0.25% in the gas metabolism data, the cell metabolism rate is calculated as 0.1 g / g / h. Then, according to the cell respiration product including carbon dioxide and ethylene, the metabolic cell type ratio is analyzed, with epidermal cells accounting for 60% and pulp cells accounting for 40%. Then, according to the cell metabolism rate 0.1 g / g / h and the metabolic cell type ratio, the second quality evolution data is calculated: epidermal cell corruption contributes 0.06 g / g / h, pulp cell contributes 0.04 g / g / h, and the total indicates the quality loss caused by the decrease of cell activity.

[0097] According to the gas metabolism data, the initial microenvironment data is modified to obtain real-time microenvironment data at the current time point, and the step of obtaining the modification of the microenvironment data according to the real-time microenvironment data is obtained. The modification of the microenvironment data according to the real-time microenvironment data is obtained.

[0098] According to the cell metabolism rate and the cell respiration product, the microenvironment modification parameter is obtained, and the initial microenvironment data is modified according to the microenvironment modification parameter to obtain real-time microenvironment data at the current time point;

[0099] According to the real-time micro-environment data, extract micro-environment components in the micro-environment, and identify target micro-environment components in the micro-environment components that have an impact on the deterioration of agricultural products;

[0100] Classify the target micro-environment components to obtain inhibitory components that have an inhibitory effect on the deterioration of agricultural products and accelerating components that have an accelerating effect on the deterioration of agricultural products;

[0101] Effectively evaluate the inhibitory components and accelerating components respectively to obtain inhibitory effect evaluation values and accelerating effect evaluation values, and combine the inhibitory effect evaluation values and the accelerating effect evaluation values to obtain a deterioration impact parameter.

[0102] In the application, take strawberry cold chain transportation as an example, according to the cell metabolic rate 0.1 g / g / h and the cell respiration product CO2 concentration 0.25%, calculate the micro-environment correction parameter as temperature adjustment-0.5°C and humidity adjustment+5%. Then, according to the micro-environment correction parameter, correct the initial micro-environment data (warehouse temperature 1.5°C, humidity 85%): lower the temperature by 0.5°C to 1.0°C, and raise the humidity by 5% to 90%, to obtain the real-time micro-environment data at the current time point. Then, according to the real-time micro-environment data, extract micro-environment components including oxygen 21%, carbon dioxide 0.25%, and ethylene 0.1%. Identify the part of the target micro-environment components that has an impact on the deterioration of strawberries: carbon dioxide inhibits spoilage, and ethylene accelerates spoilage. Then, classify the target micro-environment components: carbon dioxide is an inhibitory component, and ethylene is an accelerating component. Then, evaluate the effects respectively: the inhibitory effect evaluation value of carbon dioxide is 0.6 (each 0.1% concentration accelerates spoilage by 1%), and the accelerating effect evaluation value of ethylene is 0.4 (each 0.1% concentration delays spoilage by 0.8%). Combine the accelerating effect evaluation value 0.4 and the inhibitory effect evaluation value 0.6 to calculate the deterioration impact parameter: the net effect is 0.6-0.4=0.2, indicating that the environment causes the spoilage to slow down by 0.2%.

[0103] The steps of substituting the comprehensive quality evolution data and the deterioration impact parameter into the cold chain transportation twin model for simulation to obtain a predicted deterioration degree value are as follows:

[0104] Substitute the comprehensive quality evolution data and the deterioration impact parameter into the cold chain transportation twin model, and the cold chain transportation twin model simulates the transportation;

[0105] During the simulation process, monitor the quality change of the agricultural products to obtain simulation quality change data, and generate a simulation quality change curve according to the simulation quality change data;

[0106] When the value of the simulation quality change curve reaches a preset spoilage value, the simulation is stopped;

[0107] The simulation is repeated for multiple times to generate multiple simulation quality change curves, and the multiple simulation quality change curves are set in the same coordinate system, and the multiple simulation quality change curves are fitted to generate a target quality change curve, and the predicted degree of deterioration values at different time points on the target quality change curve are recorded.

[0108] In use, taking strawberry cold chain transportation as an example, the comprehensive quality evolution data (microbial spoilage acceleration 55%) and the deterioration influence parameter (environmental inhibition 0.2%) are substituted into the cold chain transportation twin model. The model starts to simulate transportation: from Hangzhou to Beijing, simulates the temperature and humidity changes in the warehouse and the external meteorological influence. During the simulation process, the quality change of strawberries is monitored, the initial quality value is 100% (fresh), data is recorded every 1 hour of simulation, and a simulation quality change curve is generated: the quality decreases to 99.5% at the first hour, and decreases to 95% at the sixth hour. When the simulation quality change curve value reaches the preset spoilage value 80% (indicating the spoilage threshold), the simulation is stopped. Then repeat the simulation 5 times to generate multiple curves: the first time reaches 80% at 10 hours, the second time at 9.5 hours, the third time at 10.2 hours, the fourth time at 9.8 hours, and the fifth time at 10.5 hours. Then set the five curves in the same coordinate system and perform fitting processing: the average arrival time is 10 hours. The target quality change curve is generated, and the predicted degree of deterioration values at different time points are recorded: the quality is 90% at the fifth hour, the quality is 85% at the eighth hour, and the quality is 80% at the tenth hour.

[0109] Adjust the microenvironment and physical field in the warehouse to build a dormant warehouse, and map it to the cold chain transportation twin model, specifically:

[0110] Extract the time point at which the degree of deterioration value reaches the degree of deterioration threshold, and set a redundant time period according to the time point to obtain a target time point;

[0111] At the target time point, extract real-time microenvironment data and real-time physical field data in the warehouse;

[0112] According to the real-time microenvironment data, filter the acceleration components in the microenvironment, and retain the inhibition components to obtain a dormant microenvironment;

[0113] According to the real-time physical field data, adjust the electromagnetic wave frequency and light parameters in the warehouse to obtain a dormant physical field;

[0114] Combine the dormant microenvironment and the dormant physical field to build a dormant warehouse, and map the dormant warehouse to the cold chain transportation twin model.

[0115] In the application, taking the cold chain transportation of strawberries as an example, the time point at which the deterioration degree threshold of 80% is extracted from the predicted deterioration degree value is 10 hours. Then, according to the time point, a redundant time period of 2 hours is set, and the target time point is the 8th hour. Then, at the target time point (transportation for 8 hours), the real-time micro-environment data in the warehouse is extracted: temperature 1.0°C, humidity 90%, and real-time physical field data: electromagnetic wave frequency 50Hz, light intensity 200 lux. According to the real-time micro-environment data, filter the acceleration (ethylene) in the micro-environment, use the adsorbent to reduce the ethylene concentration from 0.1% to 0.025%, retain the inhibitory component (carbon dioxide), maintain the CO2 concentration at 0.1%, and obtain the dormant micro-environment. Then, according to the real-time physical field data, adjust the electromagnetic wave frequency in the warehouse to 30Hz (reduce microbial activity), and the light parameter to 100 lux (reduce light effect), obtain the dormant physical field. Finally, combine the dormant micro-environment (high CO2, low ethylene) and the dormant physical field (low frequency electromagnetic wave, weak light) to construct the dormant warehouse, and map this state to the cold chain transportation twin model for subsequent monitoring.

[0116] The cold chain transportation twin model is sent to the monitoring personnel, who views the real-time and predicted conditions in the warehouse and performs manual intervention steps, which are as follows:

[0117] The cold chain transportation twin model is visualized to obtain a visual model, and the visual model is sent to the monitoring screen of the monitoring personnel;

[0118] In the visual model, the real-time micro-environment data, real-time physical field data and target quality change curve are displayed on the monitoring screen;

[0119] The current time point is extracted, and the current deterioration degree value of the agricultural products is marked according to the current time point and the target quality change curve;

[0120] Micro-environment adjustment buttons and physical field adjustment buttons are set on the monitoring screen, and the monitoring personnel can manually adjust the micro-environment and physical field according to the real-time and predicted conditions.

[0121] In use, taking the cold chain transportation of strawberries as an example, the cold chain transportation twin model is visualized to generate an image containing a 3D model of the warehouse and data, and then sent to the monitoring screen of the monitoring personnel. In the visualized model, the real-time micro-environment data (temperature 1.0°C, humidity 90%), real-time physical field data (electromagnetic wave 30Hz, light 100 lux) and target quality change curve (showing the quality decrease over time) are displayed on the screen. Then extract the current time point, such as the 6th hour of transportation, and according to the target quality change curve, mark the current degree of deterioration value as 90%. Then set the micro-environment adjustment button (for adjusting temperature and humidity) and the physical field adjustment button (for adjusting electromagnetic wave and light) on the monitoring screen. The monitoring personnel manually intervenes according to the real-time situation (such as temperature fluctuation) and the predicted situation (the curve shows that the quality will decrease to 85% at the 8th hour), and manually intervenes: press the micro-environment button to reduce the temperature from 1.0°C to 0.5°C, and press the physical field button to adjust the light intensity from 100 lux to 50 lux, in order to delay the corruption.

[0122] The embodiment of the present application provides an intelligent monitoring system for agricultural product cold chain logistics based on Internet of Things, which uses any one of the above-mentioned intelligent monitoring methods for agricultural product cold chain logistics based on Internet of Things. The system includes the following contents:

[0123] Model construction module 1: used for acquiring cold storage warehouse parameters, cargo product parameters, cargo loading scheme and route information, and constructing a cold chain transportation twin model;

[0124] Biological detection module 2: used for acquiring the product type of agricultural products and the initial micro-environment data in the warehouse, and performing biological detection on the agricultural products according to the product type to obtain microorganism electric signal data and gas metabolism data;

[0125] Quality evolution module 3: used for obtaining first quality evolution data according to the microorganism electric signal data, obtaining second quality evolution data according to the gas metabolism data, and combining the first quality evolution data and the second quality evolution data to obtain comprehensive quality evolution data of the agricultural products;

[0126] Influence parameter module 4: used for performing environment data correction on the initial micro-environment data according to the gas metabolism data to obtain real-time micro-environment data at the current time point, and obtaining a deterioration influence parameter caused by the environment to the agricultural products according to the real-time micro-environment data;

[0127] Simulation prediction module 5: used for simulating the comprehensive quality evolution data and the deterioration influence parameter in the cold chain transportation twin model to obtain a predicted deterioration degree value;

[0128] The in-warehouse adjustment module 6 is used for judging whether the predicted deterioration degree value exceeds a preset deterioration degree threshold value, and if it is judged that the deterioration degree value reaches the deterioration degree threshold value, the micro environment and the physical field in the warehouse are adjusted, a dormant warehouse is constructed, and is mapped into the cold chain transportation twin model;

[0129] The monitoring intervention module 7 is used for sending the cold chain transportation twin model to a monitoring personnel, the monitoring personnel views the real-time situation and the predicted situation in the warehouse, and manually intervenes.

[0130] The above are preferred embodiments of the present application, and are not intended to limit the protection scope of the present application, so that: any equivalent changes made according to the structure, shape, principle of the present application should be covered within the protection scope of the present application.

Claims

1. An Internet of Things intelligent monitoring method for agricultural product cold chain logistics, characterized in that, The method comprises the following steps: acquiring cold storage parameters, product parameters, loading schemes, and route information to build a cold chain transportation twin model; acquiring product types and initial micro-environment data in the cold storage, performing biological detection on the agricultural products according to the product types to obtain microbial electrical signal data and gas metabolism data; obtaining first quality evolution data according to the microbial electrical signal data, obtaining second quality evolution data according to the gas metabolism data, and combining the first quality evolution data and the second quality evolution data to obtain comprehensive quality evolution data of the agricultural products; correcting the initial micro-environment data according to the gas metabolism data to obtain real-time micro-environment data at a current time point, and obtaining a deterioration influence parameter of the environment on the agricultural products according to the real-time micro-environment data; inputting the comprehensive quality evolution data and the deterioration influence parameter into the cold chain transportation twin model to simulate and obtain a predicted deterioration degree value; judging whether the predicted deterioration degree value exceeds a preset deterioration degree threshold value, and if the deterioration degree value reaches the deterioration degree threshold value, adjusting the micro-environment and physical field in the cold storage to build a dormant cold storage and map it to the cold chain transportation twin model; sending the cold chain transportation twin model to a monitoring personnel, and the monitoring personnel views real-time and predicted conditions in the cold storage and manually intervenes; the steps of obtaining first quality evolution data according to the microbial electrical signal data and obtaining second quality evolution data according to the gas metabolism data are specifically as follows: obtaining microbial types and the number of microorganisms corresponding to each microbial type according to the microbial electrical signal data; obtaining a single catalytic effect value of each microbial type on the quality evolution of the agricultural products according to the microbial types; combining the number of microorganisms and the single catalytic effect value to obtain a comprehensive catalytic effect value of the overall microbial community on the quality evolution of the agricultural products, and obtaining first quality evolution data according to the comprehensive catalytic effect value; obtaining a cell metabolism rate according to the cell respiration rate and the concentration of respiratory products in the gas metabolism data; obtaining a metabolic cell type ratio according to the cell respiratory products, and obtaining second quality evolution data according to the cell metabolism rate and the metabolic cell type ratio; the steps of adjusting the micro-environment and physical field in the cold storage to build a dormant cold storage and map it to the cold chain transportation twin model are specifically as follows: extracting a target time point by setting a redundant time period forward from a time point at which the deterioration degree value reaches the deterioration degree threshold value; extracting real-time micro-environment data and real-time physical field data in the cold storage at the target time point; filtering accelerating components in the micro-environment and retaining inhibiting components to obtain a dormant micro-environment according to the real-time micro-environment data; adjusting electromagnetic wave frequency and light parameters in the cold storage according to the real-time physical field data to obtain a dormant physical field; In combination with the dormant microenvironment and the dormant physical field, a dormant warehouse is constructed, and the dormant warehouse is mapped into the cold chain transportation twin model. 2.The agricultural product cold-chain logistics Internet of Things intelligent monitoring method according to claim 1, characterized in that, The steps for constructing the cold chain transportation twin model include obtaining cold storage parameters, product parameters, loading schemes, and route information, specifically as follows: Obtain cold storage parameters, product parameters, and loading schemes. According to the cold storage parameters, a model framework of the digital twin model is constructed, and the model framework is filled with goods according to the loading scheme to obtain an initial twin model. According to the product parameters, the initial twin model is filled with biological data to obtain an in-warehouse twin model. Obtain the route information of the cold chain transportation, extract the external meteorological data of the corresponding position of the route information, and construct an out-of-warehouse twin model according to the external meteorological data. Combine the in-warehouse twin model and the out-of-warehouse twin model to generate a cold chain transportation twin model. 3.The method of claim 2, wherein, The steps for biological detection of agricultural products according to the type of agricultural products to obtain microbial electrical signal data and gas metabolism data are as follows: Based on the type of agricultural products, obtain the basic product parameters of the agricultural products, and according to the basic product parameters, obtain common surface microbial data and initial product cell parameters. According to the common surface microbial data, identify the initial microbial species, and according to the initial microbial species, obtain a rapid microbial detection method. According to the rapid microbial detection method, identify the existing microorganisms in the agricultural products by electrical signal to obtain microbial electrical signal data. According to the initial product cell parameters, obtain the product cell type and the current cell activity, and according to the current cell activity, obtain the current cell respiration intensity. According to the product cell type and the current cell respiration intensity, obtain the cell respiration rate, the respiration product concentration, and the cell respiration product, and combine the cell respiration rate, the respiration product concentration, and the cell respiration product to obtain gas metabolism data. 4.The agricultural product cold-chain logistics Internet of Things intelligent monitoring method according to claim 3, characterized in that, The steps for environment data correction of the initial microenvironment data according to the gas metabolism data to obtain real-time microenvironment data at the current time point, and obtaining the deterioration influence parameter of the agricultural products caused by the environment according to the real-time microenvironment data are as follows: According to the cell metabolism rate and the cell respiration product, obtain a microenvironment correction parameter, and according to the microenvironment correction parameter, correct the initial microenvironment data to obtain real-time microenvironment data at the current time point. According to the real-time microenvironment data, extract the microenvironment components in the microenvironment, and identify the target microenvironment components that have an impact on the deterioration of agricultural products among the microenvironment components. Classify the target microenvironment components to obtain inhibitory components that have an inhibitory effect on the deterioration of agricultural products and accelerating components that have an accelerating effect on the deterioration of agricultural products. Respectively evaluate the inhibitory components and the accelerating components to obtain inhibitory effect evaluation values and accelerating effect evaluation values, and combine the inhibitory effect evaluation values and the accelerating effect evaluation values to obtain the deterioration influence parameter. 5.The agricultural product cold-chain logistics Internet of Things intelligent monitoring method according to claim 4, characterized in that, The step of inputting the comprehensive quality evolution data and the deterioration influence parameter into the cold chain transportation twin model for simulation to obtain a predicted deterioration degree value is specifically as follows: The step of inputting the comprehensive quality evolution data and the deterioration influence parameter into the cold chain transportation twin model for simulation to obtain a predicted deterioration degree value is specifically as follows: In the simulation process, the quality change of the agricultural products is monitored to obtain simulation quality change data, and a simulation quality change curve is generated according to the simulation quality change data; When the value of the simulation quality change curve reaches a preset spoilage value, the simulation is stopped; A plurality of simulation quality change curves are generated by repeating the simulation multiple times, and the plurality of simulation quality change curves are set in the same coordinate system, fitted, and a target quality change curve is generated, and the predicted deterioration degree values at different time points on the target quality change curve are recorded. 6.The agricultural product cold-chain logistics Internet of Things intelligent monitoring method according to claim 5, characterized in that, The step of sending the cold chain transportation twin model to the monitoring personnel, who views the real-time and predicted conditions in the warehouse and manually intervenes is specifically as follows: The step of sending the cold chain transportation twin model to the monitoring personnel, who views the real-time and predicted conditions in the warehouse and manually intervenes is specifically as follows: The real-time microenvironment data, the real-time physical field data, and the target quality change curve are displayed on the monitoring screen in the visualized model; The current time point is extracted, and the current deterioration degree value of the agricultural products is labeled according to the current time point and the target quality change curve; Microenvironment adjustment buttons and physical field adjustment buttons are set on the monitoring screen, and the monitoring personnel can manually adjust the microenvironment and the physical field in real time according to the real-time and predicted conditions.

7. An intelligent monitoring system for agricultural product cold chain logistics based on Internet of Things, wherein the system uses the method for intelligent monitoring of agricultural product cold chain logistics based on Internet of Things according to any one of claims 1-6. The system comprises: A model construction module for obtaining cold storage warehouse parameters, cargo product parameters, cargo loading schemes, and route information, and constructing a cold chain transportation twin model; A biological detection module for obtaining the product type of the agricultural products and the initial microenvironment data in the warehouse, performing biological detection on the agricultural products according to the product type to obtain microbial electrical signal data and gas metabolism data; A quality evolution module for obtaining first quality evolution data according to the microbial electrical signal data, obtaining second quality evolution data according to the gas metabolism data, and combining the first quality evolution data and the second quality evolution data to obtain comprehensive quality evolution data of the agricultural products; An influence parameter module for performing environment data correction on the initial microenvironment data according to the gas metabolism data to obtain real-time microenvironment data at a current time point, and obtaining a deterioration influence parameter caused by the environment to the agricultural products according to the real-time microenvironment data; An simulation and prediction module for inputting the comprehensive quality evolution data and the deterioration influence parameter into the cold chain transportation twin model for simulation to obtain a predicted deterioration degree value; An simulation and prediction module for inputting the comprehensive quality evolution data and the deterioration influence parameter into the cold chain transportation twin model for simulation to obtain a predicted deterioration degree value; The in-warehouse adjustment module is configured to judge whether the predicted deterioration degree value exceeds a preset deterioration degree threshold value, and if the deterioration degree value reaches the deterioration degree threshold value, the micro environment and the physical field in the warehouse are adjusted, a dormant warehouse is constructed, and the dormant warehouse is mapped into the cold-chain transportation twin model. The monitoring intervention module is configured to send the cold-chain transportation twin model to a monitoring personnel, the monitoring personnel views real-time and predicted conditions in the warehouse, and manually intervenes.

Images