Cold-chain logistics data supervision method and system based on Internet of Things

Abstract

The invention discloses a cold-chain logistics data supervision method and system based on the Internet of Things, and belongs to the technical field of logistics data processing. The system comprises a data acquisition module, a data analysis module, a risk management module and an execution supervision module. The data acquisition module is used for acquiring historical logs and parameter information of the refrigerator car and logistics details of this time; the data analysis module is used for predicting the next unloading duration, generating a temperature field evolution video by adopting a physical simulation model, and dividing an influence area for each cargo after deframing; the risk management module is used for calculating the average temperature of the influence area so as to analyze the risk index of each cargo; and the execution supervision module analyzes and marks the goods according to the risk indexes, establishes schemes for the marked goods, adjusts the sequence of the schemes and executes the schemes in sequence. According to the invention, through Internet of Things multi-source data perception, dynamic risk modeling and priority temperature control strategies, cold-chain logistics full-link refined management and control are realized, and the fresh food quality and transportation efficiency are significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics data processing, and specifically to a cold chain logistics data supervision method and system based on the Internet of Things. Background Art

[0002] With the rapid development of the global economy and the continuous improvement of people's living standards, the demand for cold chain logistics is increasing day by day. Cold chain logistics refers to a logistics method that uses temperature control technology to ensure that goods maintain their quality within a specified temperature range during the transportation and storage of goods. Especially in the food field, the importance of cold chain logistics is more prominent.

[0003] At the present stage, traditional monitoring methods often have some problems. For example, 1. Traditional technologies use fixed temperature threshold alarms, ignoring the cumulative effect of time-varying risks caused by individual differences of goods and the superposition of short-term high temperatures, which accelerates spoilage. As a result, the protection ability for high-risk goods is insufficient, and the false alarm and missed alarm rates are high. 2. Traditional technologies rarely pay attention to the destructive impact of external hot air influx on the temperature of the carriage when the vehicle door is opened during the unloading process. It is impossible to predict the temperature rise trajectory of each good during the unloading stage, resulting in uncontrollable risks for goods during the critical unloading link. 3. Traditional technologies rely on fixed priority scheduling or manual experience for parameter adjustment, and cannot dynamically allocate refrigeration resources. When multiple categories of goods are mixed, it is necessary to sacrifice the temperature control accuracy of some goods to ensure the overall situation, which pushes up the loss cost. Therefore, at the present stage, a more efficient and intelligent logistics data supervision technical solution is needed to solve the above problems. Summary of the Invention

[0004] The purpose of the present invention is to provide a cold chain logistics data supervision method and system based on the Internet of Things to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides a cold chain logistics data supervision method based on the Internet of Things, including:

[0006] S100. Collect the historical logs and parameter information of the refrigerated truck, as well as the current logistics details.

[0007] S200. Predict the next unloading duration according to the collected data, and divide the influence areas for the goods.

[0008] S300. Calculate the average temperature of the influence areas to analyze the risk index of each good.

[0009] S400. Mark the goods according to the risk index and plan the solutions, and execute them in sequence after adjusting the solution order.

[0010] In S100, the historical log includes the delivery records for each stop for unloading goods. Each delivery record includes the total weight of the unloading and the unloading duration. The parameter information includes the real-time GPS location, the driving speed, and the temperature information. The temperature information includes the real-time temperature outside the carriage and the real-time thermal field distribution map inside the carriage.

[0011] The logistics details include the transportation route map and the cargo list. The transportation route map includes the locations of each unloading point. The cargo list includes the weight of each cargo, the delivery location, the temperature comparison table, and the temperature influence set.

[0012] The temperature comparison table includes the microbial growth rate of the cargo at different temperatures. The temperature influence set includes the relationship diagram between different ambient temperatures and the initial temperature. The relationship diagram represents the relationship between the cargo temperature and the influence duration when the cargo is affected by the ambient temperature.

[0013] The ambient temperature refers to the temperature of the air around the cargo. The initial temperature refers to the initial temperature value of the cargo before being affected by the ambient temperature. Each cargo has a temperature influence set. There must be at least one different temperature value between the ambient temperature and the initial temperature among different relationship diagrams within the same temperature influence set.

[0014] In each relationship diagram, the ambient temperature and the initial temperature are fixed. The cargo temperature is between the initial temperature and the ambient temperature. The cargo temperature refers to the temperature of the cargo itself. The influence duration refers to the duration during which the cargo temperature is affected by the ambient temperature. Each relationship diagram is generated in advance by the data obtained from testing different cargos in different temperature environments by manual.

[0015] Each type of cargo has its own temperature comparison table, and different cargos have different temperature comparison tables. The cargo refers to fresh or perishable products, and they need to be stored at a low temperature inside the refrigerated carriage to slow down the growth and reproduction rate of microorganisms.

[0016] S200 includes:

[0017] S201. Mark the current GPS location of the refrigerated truck on the transportation route map, and identify the location u of the next unloading point according to the marked location. Screen out all the cargos with the delivery location of u in the cargo list, and calculate the total weight L of these cargos sum .

[0018] S202. Extract all the delivery records in the historical log. Take the unloading duration in each delivery record as the dependent variable, and the total weight of the unloading as the independent variable and package them as samples. All the samples are input into the linear regression model for training to obtain the duration relationship expression.

[0019] S203. Substitute the total weight L sum into the duration relationship expression to calculate the estimated unloading duration T n . Obtain the current thermal field distribution map Inow and the external temperature of the carriage, use a physical simulation model to simulate and analyze the duration T after the carriage door is opened during the unloading stage n of the temperature distribution change inside the inner carriage, and output a video of the temperature field evolution with a duration of T n .

[0020] S204. Decode the temperature field evolution video, and mark the positions of each cargo in each image frame respectively. Set the distance p, and plan a circular area with p as the radius centered on the position of each cargo as the influence area. And so on, divide the influence areas for each cargo in the thermal field distribution map I now in the same way.

[0021] S300 includes:

[0022] S301. Calculate the average temperature of the influence area of cargo h in each image frame. All image frames are arranged in chronological order, and image frames with the same average temperature and adjacent to each other are combined. The time range of all image frames within the combination is used as the duration.

[0023] Each combination has one or more images. In a combination with two or more image frames, each image frame has an adjacent relationship with at least one other image frame, and the average temperature of the influence area of cargo h in all image frames within the same combination is the same.

[0024] S302. Obtain the average temperature CW of the influence area of cargo h in the thermal field distribution map I now , arrange all combinations in chronological order. Obtain the average temperature AW1 and duration T1 of the first combination, screen out the relationship graph G1 with the ambient temperature of AW1 and the initial temperature of CW f , and obtain the cargo temperature HW1 at the influence duration of T1 in the relationship graph G1. f

[0025] S303. Continue to obtain the average temperature AW2 and duration T2 of the second combination, screen out the relationship graph G2 with the ambient temperature of AW2 and the initial temperature of HW1, and obtain the cargo temperature HW2 at the influence duration of T2 in the relationship graph G2.

[0026] And so on, calculate the corresponding cargo temperatures of each combination in sequence according to the arrangement order.

[0027] S304. Obtain the temperature comparison table of cargo h, and find the corresponding microbial growth rate ZS according to the cargo temperature of each combination i . Substitute into the formula to calculate the risk index FX h :[[]]END]]

[0028]

[0029] ​Where α is a constant greater than 1, j is the number of all combinations, and ZS k and ZS k-1 are the microbial growth rates corresponding to the k-th and (k - 1)-th combinations respectively, ZS f is the temperature CW f corresponding to the microbial growth rate, T i is the duration of the i-th combination.

[0030] And so on, calculate the risk index of each cargo respectively.

[0031] Set the risk weight according to the proportion of the duration. The microbial growth rate corresponding to the cargo temperature of each combination is used as the main risk judgment factor, and the risk of the change range of the microbial growth rate is amplified in the form of a logarithmic function.

[0032] Considering the dual effects of the fluctuation range and the duration, compared with the traditional single threshold method, the corruption risk can be quantified more accurately.

[0033] High-risk cargos are quickly highlighted through the numerical amplification effect, which is convenient for priority scheduling. Convert the complex temperature dynamics into quantitative indicators, and achieve a leap from empirical judgment to data-driven decision-making.

[0034] S400 includes:

[0035] S401. Obtain the current driving speed of the refrigerated truck. Calculate the driving distance through the current GPS position of the refrigerated truck and the position of the next unloading point in the transportation route map, and divide the driving distance by the driving speed to get the driving duration T xs .

[0036] S402. Set the exponential threshold, mark all cargos with risk indexes greater than the exponential threshold, and count the sum of the risk indexes of all marked cargos, FX sum , and substitute it into the formula to calculate the reserved duration T rd for each marked cargo respectively:

[0037]

[0038] Where FX m is the risk index of the marked cargo m.

[0039] Allocate the reserved duration according to the proportion of the risk index of a single marked cargo to the total risk index of all marked cargos. The total duration is limited to the driving duration to ensure that the adjustment operation is completed within a limited time.

[0040] Through elastic resource allocation, high-risk cargos can obtain more adjustment time, maximizing the reduction of the corruption probability. At the same time, avoid over-concentrating resources resulting in the failure of temperature control for other cargos, and balance the overall risk.

[0041] The dynamic allocation mechanism based on risk weights solves the core problem of the conflict between limited resources and multi-objective temperature control requirements in the cold chain scenario.

[0042] S403. Obtain the temperature comparison table of each marked cargo, and take the temperature corresponding to the minimum microbial growth rate as the optimal temperature of the corresponding marked cargo.

[0043] Establish a plan for each marked cargo respectively, and take the reserved duration and the optimal temperature of the marked cargo as the adjustment duration and the adjustment temperature of the corresponding plan respectively.

[0044] S404. Sort all the plans in descending order according to the risk index, and execute each plan in turn according to the sorting order. The execution duration of each plan is the same as the adjustment duration.

[0045] When executing the plan, by adjusting the wind speed, direction and air temperature of the air-conditioning equipment in the refrigerated truck, and analyzing in combination with the real-time thermal field distribution map, control the cargo temperature of the marked cargo corresponding to the plan not to exceed the adjustment temperature.

[0046] During the execution of the plan, try to ensure that the impact on the cargo temperature of other goods caused by adjusting the parameters of the air-conditioning equipment is minimized. When executing the second plan after the first plan is completed, attention should be paid to whether the temperature of the marked cargo corresponding to the first plan rebounds, and control and adjustment should be carried out based on the multi-objective temperature.

[0047] During the actual operation process, try to reduce the risk index of the marked cargo below the index threshold through one adjustment, and avoid generating plans for the same marked cargo multiple times for repeated adjustment. Ensure that during the sequential execution of each plan, the cargo temperature of the marked cargo corresponding to the completed plan does not exceed the adjustment temperature.

[0048] S405. Calculate the risk index of each cargo in real time, mark the cargo and generate and execute the plan dynamically.

[0049] The cold chain logistics data supervision system based on the Internet of Things includes a data collection module, a data analysis module, a risk management module and an execution supervision module.

[0050] The data collection module is used to collect the historical logs and parameter information of the refrigerated truck, as well as the logistics details of this time.

[0051] The data analysis module is used to predict the next unloading duration, generate a temperature field evolution video using a physical simulation model, and divide the influence area for each cargo after frame-by-frame analysis.

[0052] The risk management module is used to calculate the average temperature of the influence area, so as to analyze the risk index of each cargo.

[0053] The execution supervision module analyzes and marks goods based on the risk index, establishes a plan for the marked goods, and executes them in sequence after adjusting the plan order.

[0054] The data collection module includes a historical log collection unit, a vehicle parameter collection unit, and a logistics information collection unit.

[0055] The historical log collection unit is used to collect the delivery records when the refrigerated truck stops and unloads goods each time. Each delivery record includes the total unloading weight and the unloading duration.

[0056] The vehicle parameter collection unit is used to collect the real-time GPS position, driving speed, and temperature information of the refrigerated truck. The temperature information includes the real-time temperature outside the carriage and the real-time thermal field distribution map inside the carriage.

[0057] The logistics information collection unit is used to collect the current transportation route map and the cargo list. The transportation route map includes the locations of each unloading point, and the cargo list includes the weight, delivery location, temperature comparison table, and temperature impact set of each cargo.

[0058] The temperature comparison table includes the microbial growth rate of goods at different temperatures. The temperature impact set includes the relationship diagram between different ambient temperatures and initial temperatures, and the relationship diagram represents the relationship between the cargo temperature and the influence duration when the cargo is affected by the ambient temperature.

[0059] Through multi-source Internet of Things sensors and historical databases, real-time collection of cold chain logistics parameters and artificially generated experimental data is carried out. A multi-dimensional data foundation is constructed to support subsequent risk analysis and decision-making.

[0060] The data analysis module includes a logistics prediction unit and an impact analysis unit.

[0061] The logistics prediction unit is used to output a video of the temperature field evolution.

[0062] First, mark the current GPS position of the refrigerated truck on the transportation route map and identify the location u of the next unloading point. Calculate the total weight L of all goods with the delivery location being u sum 。

[0063] Secondly, take the unloading duration in each delivery record in the historical log as the dependent variable, and the total unloading weight as the independent variable and package them as samples. All samples are input into the linear regression model for training to obtain the duration relationship expression, and substitute the total weight L sum Calculate the estimated unloading duration T n 。

[0064] Finally, obtain the current thermal field distribution map I now and the temperature outside the carriage, and use the physical simulation model to simulate and analyze the change of the temperature distribution inside the carriage after the carriage door is opened during the unloading stage for a duration of T n inside the carriage, and output the temperature distribution change inside the carriage with a duration of Tn Video of the temperature field evolution

[0065] The impact analysis unit is used to divide the impact area

[0066] First, decompose the video of the temperature field evolution, and mark the positions of each cargo in each image frame respectively

[0067] Secondly, set the distance p, and plan a circular area with each cargo position as the center and p as the radius as the impact area

[0068] Finally, in the thermal field distribution map I now Divide the impact area for each cargo in the same way

[0069] Use the linear regression model to predict the unloading duration, and simulate the dynamic change of the temperature field around the cargo through CFD simulation to divide the impact area. Improve the prediction of unloading efficiency and identify temperature-sensitive areas in advance

[0070] The risk management module includes a cargo temperature analysis unit and an index calculation unit

[0071] The cargo temperature analysis unit is used to establish combinations for the cargo and analyze the cargo temperature

[0072] First, calculate the average temperature of the impact area of cargo h in each image frame; arrange all image frames in chronological order, and establish combinations for image frames with the same average temperature and adjacent ones. The time range of all image frames within the combination is used as the duration

[0073] Secondly, obtain the average temperature CW of the impact area of cargo h in the thermal field distribution map I now f , arrange all combinations in chronological order

[0074] Then, obtain the average temperature AW1 and duration T1 of the first combination, screen out the relationship diagram G1 with the ambient temperature of AW1 and the initial temperature of CW f , and obtain the cargo temperature HW1 when the impact duration in the relationship diagram G1 is T1

[0075] Continue to obtain the average temperature AW2 and duration T2 of the second combination, screen out the relationship diagram G2 with the ambient temperature of AW2 and the initial temperature of HW1, and obtain the cargo temperature HW2 when the impact duration in the relationship diagram G2 is T2

[0076] Finally, calculate the cargo temperatures corresponding to each combination in sequence according to the arrangement order

[0077] The index calculation unit is used to calculate the risk index of the cargo

[0078] ​First, obtain the temperature comparison table of goods h, and find the corresponding microbial growth rate ZS according to the temperature of each combination of goods. i .

[0079] Secondly, according to the formula: Calculate the risk index FX h .

[0080] Among them, α is a constant greater than 1, j is the number of all combinations, ZS k and ZS k-1 are the microbial growth rates corresponding to the k-th and k-1-th combinations respectively, ZS f is the microbial growth rate corresponding to the temperature CW f , T i is the duration of the i-th combination.

[0081] Finally, calculate the risk index of each good respectively.

[0082] Based on the relationship diagram between the temperature field duration and the goods experiment, dynamically quantitatively decode the microbial growth risk index to achieve dynamic control of the goods corruption risk.

[0083] The execution supervision module includes a plan generation unit and a dynamic execution unit.

[0084] The plan generation unit is used to establish a plan.

[0085] First, analyze the GPS position and driving speed of the refrigerated truck, and calculate the driving duration T to reach the next unloading point xs .

[0086] Secondly, set an index threshold, mark all goods with a risk index greater than the index threshold, and count the sum FX of the risk indices of all marked goods sum .

[0087] Then, according to the formula: Calculate the reserved duration T of each marked good respectively rd .

[0088] Among them, FX m is the risk index of the marked good m.

[0089] Finally, take the temperature corresponding to the minimum microbial growth rate in the temperature comparison table of each marked good as the optimal temperature.

[0090] Establish a plan for each marked good, and take the reserved duration and optimal temperature of the marked good as the adjustment duration and adjustment temperature of the corresponding plan respectively.

[0091] The dynamic execution unit is used to execute the plan.

[0092] All plans are sorted in descending order according to the risk index, and are executed in the order in which the plans are arranged. The execution time of each plan is the same as the adjustment time.

[0093] When executing the plan, by adjusting the air-conditioning equipment in the refrigerated truck and combining the real-time thermal field distribution map feedback, the temperature of the goods marked in the control plan is controlled to be no greater than the adjusted temperature; the execution order of the plan is dynamically adjusted according to the changes in the risk index of each cargo.

[0094] Generate adjustment plans based on risk priorities, and suppress the spoilage rate of high-risk goods in advance through closed-loop temperature control. Optimize resource allocation and reduce the interference of temperature control on low-risk goods.

[0095] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0096] Dynamic fusion of multi-source heterogeneous data: Integrate multi-dimensional data such as temperature inside and outside the car, thermal field distribution, GPS trajectory, cargo attributes, etc., break through the limitations of single parameter monitoring of existing technologies, and build panoramic perception capabilities.

[0097] Microbial-driven dynamic risk assessment: Combined with cargo-specific temperature comparison tables and relationship diagrams, a spatiotemporal continuous risk index model is established to quantify the impact of cumulative microbial growth rate fluctuations and duration, replacing the traditional static threshold method to achieve accurate risk quantification.

[0098] Adaptive priority temperature control strategy: Dynamically allocate resources based on risk index and adjust air conditioning parameters through multi-objective optimization algorithm to minimize interference with other goods while suppressing the spoilage of high-risk goods.

[0099] Intelligent full-link collaborative decision-making: Open up the data closed loop of risk prediction and temperature control execution, upgrade traditional discrete operations to global linkage decision-making, and eliminate the data island problem of existing technologies.

[0100] The present invention realizes precise temperature control coordination and risk adaptive management of the entire cold chain logistics chain through multi-dimensional Internet of Things data fusion and physical simulation prediction, combined with dynamic risk classification assessment and closed-loop temperature control optimization mechanism, and comprehensively improves transportation efficiency and cargo preservation performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0101] The accompanying 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 of the present invention. In the accompanying drawings:

[0102] Figure 1 It is a flow chart of the cold chain logistics data supervision method based on the Internet of Things of the present invention;

[0103] Figure 2It is a schematic structural diagram of the cold chain logistics data supervision system based on the Internet of Things of the present invention. Specific embodiments

[0104] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0105] Please refer to Figure 1 , the present invention provides a cold chain logistics data supervision method based on the Internet of Things, including:

[0106] S100. Collect the historical logs and parameter information of the refrigerated truck, as well as the details of this logistics.

[0107] S200. Predict the next unloading duration according to the collected data and divide the influence areas for the goods.

[0108] S300. Calculate the average temperature of the influence area to analyze the risk index of each good.

[0109] S400. Mark the goods according to the risk index and plan the solutions, and execute them in sequence after adjusting the solution order.

[0110] In S100, the historical logs include the delivery records when unloading at each stop, and each delivery record includes the total unloading weight and the unloading duration. The parameter information includes the real-time GPS position, driving speed, and temperature information. The temperature information includes the real-time temperature outside the carriage and the real-time thermal field distribution map inside the carriage.

[0111] The logistics details include the transportation route map and the goods list. The transportation route map includes the positions of each unloading point, and the goods list includes the weight, delivery location, temperature comparison table, and temperature influence set of each good.

[0112] The temperature comparison table includes the microbial growth rate of the goods at different temperatures. The temperature influence set includes the relationship diagram between different ambient temperatures and initial temperatures, and the relationship diagram represents the relationship between the temperature of the goods and the influence duration when the goods are affected by the ambient temperature.

[0113] The ambient temperature refers to the temperature of the air around the goods, and the initial temperature refers to the initial temperature value of the goods before being affected by the ambient temperature. Each good has a temperature influence set, and there must be at least one different temperature value between the ambient temperatures and initial temperatures of different relationship diagrams within the same temperature influence set.

[0114] In each relationship graph, the ambient temperature and the initial temperature are fixed, and the cargo temperature is between the initial temperature and the ambient temperature. The cargo temperature refers to the temperature of the cargo itself, and the influence duration refers to the duration during which the cargo temperature is affected by the ambient temperature. Each relationship graph is generated in advance by artificial means from the data obtained by testing different goods in different temperature environments.

[0115] Each type of cargo has its own temperature comparison table, and the temperature comparison tables for different cargos are different. Cargo refers to fresh or perishable products, which need to be stored at a low temperature inside the refrigerated compartment to slow down the growth and reproduction rate of microorganisms.

[0116] S200 includes:

[0117] S201. Mark the current GPS position of the refrigerated truck on the transportation route map, identify the position u of the next unloading point according to the marked position. Screen out all the cargos with the delivery location u in the cargo list, and calculate the total weight L of these cargos sum 。

[0118] S202. Extract all the delivery records in the historical log, take the unloading duration in each delivery record as the dependent variable, and the total unloading weight as the independent variable and package them as samples. All the samples are input into the linear regression model for training to obtain the duration relationship expression.

[0119] S203. The total weight L sum is substituted into the duration relationship expression to calculate the estimated unloading duration T n 。Obtain the current thermal field distribution map I now and the temperature outside the compartment, and use the physical simulation model to simulate and analyze the change of the temperature distribution inside the compartment during the unloading stage after the compartment door is opened for a duration T n inside, and output the temperature field evolution video with a duration of T n 。

[0120] S204. Decode the temperature field evolution video, and mark the positions of each cargo in each image frame respectively. Set the distance p, and use the position of each cargo as the center of a circle with a radius of p to plan a circular area as the influence area. And so on, divide the influence areas for each cargo in the thermal field distribution map I now in the same way.

[0121] S300 includes:

[0122] S301. Calculate the average temperature of the influence area of the cargo h in each image frame. All the image frames are arranged in chronological order, and the image frames with the same average temperature and adjacent to each other are combined. The time range of all the image frames in the combination is used as the duration.

[0123] For each combination, there is one or more images. In a combination with two or more image frames, each image frame has an adjacent relationship with at least one other image frame. The average temperature of the affected area of the goods h in all the image frames within the same combination is the same.

[0124] S302. Obtain the thermal field distribution map I now The average temperature CW of the affected area of the goods h f , arrange all the combinations in chronological order. Obtain the average temperature AW1 and the duration T1 of the first combination, and filter out the relationship graph G1 with the ambient temperature of AW1 and the initial temperature of CW f , and obtain the goods temperature HW1 when the influence duration in the relationship graph G1 is T1.

[0125] S303. Continue to obtain the average temperature AW2 and the duration T2 of the second combination, filter out the relationship graph G2 with the ambient temperature of AW2 and the initial temperature of HW1, and obtain the goods temperature HW2 when the influence duration in the relationship graph G2 is T2.

[0126] And so on, calculate the corresponding goods temperatures of each combination in sequence according to the arranged order.

[0127] S304. Obtain the temperature comparison table of the goods h, and find the corresponding microbial growth rate ZS according to the goods temperature of each combination i . Substitute into the formula to calculate the risk index FX h :

[0128]

[0129] In the formula, α is a constant greater than 1, j is the number of all combinations, ZS k and ZS k-1 are the microbial growth rates corresponding to the kth and the (k - 1)th combinations respectively, ZS f is the microbial growth rate corresponding to the temperature CW f , and T i is the duration of the ith combination.

[0130] And so on, calculate the risk index of each goods respectively.

[0131] Set the risk weight according to the proportion of the duration. The microbial growth rates corresponding to the goods temperatures of each combination are used as the main risk judgment factors, and the risk of the change range of the microbial growth rate is amplified in the form of a logarithmic function.

[0132] By comprehensively considering the dual influences of the fluctuation range and the duration, compared with the traditional single threshold method, the corruption risk can be quantified more accurately.

[0133] High-risk goods are quickly highlighted through numerical amplification effects, facilitating priority scheduling. Convert complex temperature dynamics (fluctuations + persistence) into quantitative metrics, achieving a leap from experience-based judgment to data-driven decision-making.

[0134] S400 includes:

[0135] S401. Obtain the current driving speed of the refrigerated truck. Calculate the driving distance through the current GPS position of the refrigerated truck and the position of the next unloading point in the transportation route map, and divide the driving distance by the driving speed to obtain the driving duration T xs .

[0136] S402. Set an exponential threshold, mark all goods with a risk index greater than the exponential threshold, and calculate the sum of the risk indices FX of all marked goods sum , and substitute it into the formula to calculate the reserved duration T for each marked good rd :

[0137]

[0138] In the formula, FX m is the risk index of marked good m.

[0139] Allocate the reserved duration according to the proportion of the risk index of a single marked good to the total risk index of all marked goods. The total duration is limited to the driving duration (the time for the refrigerated truck to reach the next unloading point) to ensure that the adjustment operation is completed within a limited time.

[0140] Through elastic resource allocation, high-risk goods can obtain more adjustment time, maximizing the reduction of the spoilage probability. At the same time, avoid over-concentrating resources leading to the failure of temperature control for other goods and balance the overall risk.

[0141] Based on the dynamic allocation mechanism of risk weights, solve the core problem of the conflict between limited resources and multi-objective temperature control requirements in the cold chain scenario.

[0142] S403. Obtain the temperature comparison table for each marked good, and use the temperature corresponding to the minimum microbial growth rate as the optimal temperature for the corresponding marked good.

[0143] Establish a plan for each marked good respectively, and use the reserved duration and optimal temperature of the marked good as the adjustment duration and adjustment temperature of the corresponding plan respectively.

[0144] S404. Sort all plans in descending order according to the risk index, and execute each plan in turn according to the sorting order. The execution duration of each plan is the same as the adjustment duration.

[0145] When implementing the solution, analyze by adjusting the wind speed, direction, and temperature of the air-conditioning equipment in the refrigerated truck and combining with the real-time thermal field distribution map, and control the cargo temperature of the marked cargo corresponding to the solution not to exceed the adjusted temperature.

[0146] During the implementation of the solution, try to ensure that the impact of adjusting the parameters of the air-conditioning equipment on the temperatures of other cargos is minimized. When implementing the second solution after the first solution is completed, attention should be paid to whether the temperature of the marked cargo corresponding to the first solution rebounds, and control adjustments should be made based on multi-objective temperatures.

[0147] During the actual operation process, try to reduce the risk index of the marked cargo below the index threshold through one adjustment, and avoid repeatedly adjusting the same marked cargo by generating multiple solutions. Ensure that during the sequential execution of each solution, the temperature of the marked cargo corresponding to the completed solution does not exceed the adjusted temperature.

[0148] S405. Calculate the risk index of each cargo in real time, mark the cargo, and generate and dynamically execute the solution.

[0149] Please refer to Figure 2 , the present invention provides an Internet of Things-based cold chain logistics data supervision system, including a data acquisition module, a data analysis module, a risk management module, and an execution supervision module.

[0150] The data acquisition module is used to acquire the historical logs and parameter information of the refrigerated truck, as well as the current logistics details.

[0151] The data analysis module is used to predict the next unloading duration, generate a temperature field evolution video using a physical simulation model, and divide the influence areas for each cargo after frame-by-frame analysis.

[0152] The risk management module is used to calculate the average temperature of the influence area, so as to analyze the risk index of each cargo.

[0153] The execution supervision module analyzes and marks the cargo based on the risk index, establishes a solution for the marked cargo, and sequentially executes the solutions after adjusting the solution order.

[0154] The data acquisition module includes a historical log acquisition unit, a vehicle parameter acquisition unit, and a logistics information acquisition unit.

[0155] The historical log acquisition unit is used to acquire the delivery records when the refrigerated truck stops for unloading each time, and each delivery record includes the total unloading weight and the unloading duration.

[0156] The vehicle parameter acquisition unit is used to acquire the real-time GPS position, driving speed, and temperature information of the refrigerated truck. The temperature information includes the real-time temperature outside the carriage and the real-time thermal field distribution map inside the carriage.

[0157] The logistics information collection unit is used to collect the transportation route map and the cargo list for this time. The transportation route map includes the locations of each unloading point, and the cargo list includes the weight, delivery location, temperature comparison table, and temperature influence set of each cargo.

[0158] The temperature comparison table includes the microbial growth rate of the cargo at different temperatures. The temperature influence set includes a relationship diagram of different ambient temperatures and the initial temperature, and the relationship diagram represents the relationship between the cargo temperature and the influence duration under the influence of the ambient temperature.

[0159] Through multi-source Internet of Things sensors (GPS, temperature and humidity probes, weight sensors) and historical databases, real-time collection of cold chain logistics parameters and experimentally generated data (temperature comparison table and relationship diagram) by humans. Build a multi-dimensional data foundation to support subsequent risk analysis and decision-making.

[0160] The data analysis module includes a logistics prediction unit and an impact analysis unit.

[0161] The logistics prediction unit is used to output a video of the temperature field evolution.

[0162] First, mark the current GPS position of the refrigerated truck on the transportation route map and identify the location u of the next unloading point. Calculate the total weight L of all the cargo with the delivery location being u sum 。

[0163] Secondly, take the unloading duration in each delivery record in the historical log as the dependent variable, and the total unloading weight as the independent variable and package them as samples. All the samples are input into the linear regression model for training to obtain the duration relationship expression, and substitute the total weight L sum Calculate the estimated unloading duration T n 。

[0164] Finally, obtain the current thermal field distribution map I now and the temperature outside the carriage, and use the physical simulation model to simulate and analyze the change of the temperature distribution inside the carriage after the carriage door is opened during the unloading stage for the duration T n inside the carriage, and output a video of the temperature field evolution with the duration T n 。

[0165] The impact analysis unit is used to divide the impact area.

[0166] First, decompose the video of the temperature field evolution, and mark the locations of each cargo in each image frame respectively.

[0167] Secondly, set the distance p, and plan a circular area with the location of each cargo as the center and p as the radius as the impact area.

[0168] Finally, divide the impact area for each cargo in the thermal field distribution map I now in the same way.

[0169] Predict the unloading duration using a linear regression model, simulate the dynamic change of the temperature field around the goods through CFD simulation, and divide the affected areas. Improve the prediction of unloading efficiency and identify temperature-sensitive areas in advance.

[0170] The risk management module includes a cargo temperature analysis unit and an index calculation unit.

[0171] The cargo temperature analysis unit is used to establish combinations for the goods and analyze the cargo temperature.

[0172] First, calculate the average temperature of the affected area of the goods h in each image frame; arrange all the image frames in chronological order, and establish combinations for the image frames with the same average temperature and adjacent ones. The time range of all the image frames within the combination is used as the duration.

[0173] Second, obtain the thermal field distribution map I now The average temperature CW f of the affected area of the goods h in it, and arrange all the combinations in chronological order.

[0174] Then, obtain the average temperature AW1 and duration T1 of the first combination, screen out the relationship graph G1 with the ambient temperature of AW1 and the initial temperature of CW f , and obtain the cargo temperature HW1 when the influence duration in the relationship graph G1 is T1.

[0175] Continue to obtain the average temperature AW2 and duration T2 of the second combination, screen out the relationship graph G2 with the ambient temperature of AW2 and the initial temperature of HW1, and obtain the cargo temperature HW2 when the influence duration in the relationship graph G2 is T2.

[0176] Finally, calculate the corresponding cargo temperatures of each combination in sequence according to the arranged order.

[0177] The index calculation unit is used to calculate the risk index of the goods.

[0178] First, obtain the temperature comparison table of the goods h, and find the corresponding microbial growth rate ZS i according to the cargo temperature of each combination.

[0179] Second, according to the formula: Calculate the risk index FX h .

[0180] Among them, α is a constant greater than 1, j is the number of all combinations, ZS k and ZS k-1 are the microbial growth rates corresponding to the kth and k - 1th combinations respectively, ZS f is the microbial growth rate corresponding to the temperature CW f , and T iis the duration of the i-th combination.

[0181] Finally, calculate the risk index of each cargo respectively.

[0182] Based on the relationship graph between the temperature field duration and the cargo experiment, dynamically quantify and decode the microbial growth risk index to achieve dynamic control of the cargo spoilage risk.

[0183] The execution supervision module includes a scheme generation unit and a dynamic execution unit.

[0184] The scheme generation unit is used to establish a scheme.

[0185] First, analyze the GPS position and driving speed of the refrigerated truck, and calculate the driving duration T to reach the next unloading point xs .

[0186] Secondly, set an index threshold, mark all the cargos with a risk index greater than the index threshold, and count the sum FX of the risk indexes of all the marked cargos sum .

[0187] Then, according to the formula: calculate the reserved duration T of each marked cargo respectively rd .

[0188] where FX m is the risk index of the marked cargo m.

[0189] Finally, take the temperature corresponding to the minimum microbial growth rate in the temperature comparison table of each marked cargo as the optimal temperature.

[0190] Establish a scheme for each marked cargo, and use the reserved duration and the optimal temperature of the marked cargo as the adjustment duration and the adjustment temperature of the corresponding scheme respectively.

[0191] The dynamic execution unit is used to execute the scheme.

[0192] Sort all the schemes in descending order according to the risk index, and execute them in sequence according to the scheme arrangement order. The execution duration of each scheme is the same as the adjustment duration.

[0193] When executing the scheme, control the cargo temperature of the marked cargo corresponding to the scheme not to be greater than the adjustment temperature by adjusting the air-conditioning equipment in the refrigerated truck and combining the feedback of the real-time heat field distribution map; dynamically adjust the scheme execution order according to the change of the risk index of each cargo.

[0194] Generate an adjustment scheme according to the risk priority, and suppress the spoilage rate of high-risk cargos in advance through closed-loop temperature control (air-conditioning parameter adjustment). Optimize resource allocation and reduce the interference of temperature control on low-risk cargos.

[0195] Example 1:

[0196] Suppose there are three marked goods, A1, A2, and A3, in the refrigerated truck, and their risk indices are 2.5, 3, and 4.5 respectively; when the driving duration is 30 minutes, substitute into the formula to calculate the reserved duration for each marked good respectively:

[0197] Reserved duration for A1:

[0198] Reserved duration for A2:

[0199] Reserved duration for A3:

[0200] Establish solutions B1, B2, and B3 for marked goods A1, A2, and A3 respectively;

[0201] First, execute solution B3. When the execution duration meets 13.5 minutes, select solution B2 to execute again. When the execution duration meets 9 minutes, finally select solution B1 to execute, with an execution duration of 7.5 minutes.

[0202] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0203] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A cold chain logistics data supervision method based on the Internet of Things, characterized in that: The method includes: S100. Collect the historical logs and parameter information of the refrigerated truck, as well as the current logistics details; S200. Predict the next unloading duration based on the collected data and divide the affected areas for the goods; S300. Calculate the average temperature of the affected areas to analyze the risk index of each good; S400. Mark the goods according to the risk index and plan the solutions, and execute them in sequence after adjusting the solution order.

2. The cold chain logistics data supervision method based on the Internet of Things according to claim 1, wherein: In S100, the historical logs include the delivery records when unloading at each stop. Each delivery record includes the total unloading weight and the unloading duration; the parameter information includes the real-time GPS position, driving speed, and temperature information; the temperature information includes the real-time temperature outside the carriage and the real-time thermal field distribution map inside the carriage; the logistics details include the transportation route map and the goods list. The transportation route map includes the positions of each unloading point, and the goods list includes the weight, delivery location, temperature comparison table, and temperature influence set of each good; The temperature comparison table includes the microbial growth rate of the goods at different temperatures; the temperature influence set includes the relationship diagram between different ambient temperatures and the initial temperature. The relationship diagram represents the relationship between the temperature of the goods and the influence duration when the goods are affected by the ambient temperature.

3. The cold chain logistics data supervision method based on the Internet of Things according to claim 2, characterized in that: S200 includes: S201. Mark the current GPS position of the refrigerated truck on the transportation route map, and identify the position u of the next unloading point according to the marked position; Screen out all the goods with the delivery position u in the cargo list, and calculate the total weight L of these goods sum ; S202. Extract all delivery records from the historical logs. Take the unloading duration in each delivery record as the dependent variable and the total unloading weight as the independent variable and package them as samples. All samples are input into the linear regression model for training to obtain the duration relationship expression; S203. Total weight L sum Substitute it into the duration relationship expression to calculate the expected unloading duration T n ; Obtain the current thermal field distribution map I now and the temperature outside the carriage, and use the physical simulation model to simulate and analyze the change in the temperature distribution inside the carriage after the carriage door is opened during the unloading stage for a duration T n and output the temperature field evolution video with a duration of T n ; S204. Decode the temperature field evolution video, and mark the positions of each cargo in each image frame respectively; set the distance p, and plan a circular area with a radius of p centered on the position of each cargo as the influence area; and so on, divide the influence areas for each cargo in the thermal field distribution map I now in the same way.

4. The cold chain logistics data supervision method based on the Internet of Things according to claim 3, characterized in that: S300 includes: S301. Calculate the average temperature of the affected area of good h in each image frame; all image frames are arranged in chronological order. Image frames with the same average temperature and adjacent to each other are combined. The time range difference of all image frames within the combination is used as the duration; S302. Obtain the thermal field distribution map I now The average temperature CW of the affected area of the goods h f , arrange all combinations in chronological order; obtain the average temperature AW1 and the duration T1 of the first combination, and screen out the relationship diagram G1 with the ambient temperature of AW1 and the initial temperature of CW f ; obtain the temperature HW1 of the goods when the influence duration in the relationship diagram G1 is T1 S303. Continue to obtain the average temperature AW2 and duration T2 of the second combination. Screen out the relationship diagram G2 with the ambient temperature of AW2 and the initial temperature of HW1. Obtain the temperature HW2 of the goods when the influence duration in the relationship diagram G2 is T2; and so on. Calculate the corresponding goods temperatures of each combination in sequence according to the arrangement order; S304. Obtain the temperature comparison table of goods h, and find the corresponding microbial growth rate ZS according to the temperature of each combination of goods i ; Substitute into the formula to calculate the risk index FX h : where α is a constant greater than 1, j is the number of all combinations, ZS k and ZS k-1 are the microbial growth rates corresponding to the k-th and (k - 1)-th combinations respectively, ZS f is the temperature CW f corresponding microbial growth rate, T i is the duration of the i-th combination; and so on, calculate the risk index of each cargo respectively.

5. The cold chain logistics data supervision method based on the Internet of Things according to claim 4, characterized in that: S400 includes: S401. Obtain the current driving speed of the refrigerated truck, calculate the driving distance based on the current GPS position of the refrigerated truck and the position of the next unloading point in the transportation route map, and divide the driving distance by the driving speed to obtain the driving duration T xs ; S402. Set an exponential threshold, mark all goods with a risk index greater than the exponential threshold, and calculate the sum of the risk indices FX of all marked goods sum , and substitute it into the formula to calculate the reserved duration T of each marked good rd : where, FX m is the risk index for marking the goods m; S403. Obtain the temperature comparison table of each marked good. Take the temperature corresponding to the minimum microbial growth rate as the optimal temperature of the corresponding marked good; establish solutions for each marked good respectively. Take the reserved duration and the optimal temperature of the marked good as the adjustment duration and adjustment temperature of the corresponding solution respectively; S404. Sort all solutions in descending order according to the risk index, and execute each solution in sequence according to the arrangement order; the execution duration of each solution is the same as the adjustment duration. When executing the solution, analyze by adjusting the wind speed, direction, and air temperature of the air conditioning equipment in the refrigerated truck, and combine the real-time thermal field distribution map to control the temperature of the goods corresponding to the solution not to exceed the adjustment temperature; S405. Calculate the risk index of each good in real time, mark the goods, and generate the dynamic execution of the solution.

6. The cold chain logistics data supervision system based on the Internet of Things is characterized in that: The system includes a data collection module, a data analysis module, a risk management module, and an execution supervision module; The data collection module is used to collect the historical logs and parameter information of the refrigerated truck, as well as the current logistics details; The data analysis module is used to predict the duration of the next unloading. It adopts a physical simulation model to generate a video of the temperature field evolution. After frame extraction, influence areas are divided for each cargo. The risk management module is used to calculate the average temperature of the influence area, so as to analyze the risk index of each cargo. The execution supervision module analyzes and marks the cargoes based on the risk index, establishes a plan for the marked cargoes, and executes them in turn after adjusting the plan order.

7. The cold chain logistics data supervision system based on the Internet of Things according to claim 6, characterized in that: The data collection module includes a historical log collection unit, a vehicle parameter collection unit, and a logistics information collection unit. The historical log collection unit is used to collect the delivery records when the refrigerated truck stops for unloading each time. Each delivery record includes the total unloading weight and the unloading duration. The vehicle parameter collection unit is used to collect the real-time GPS position, driving speed, and temperature information of the refrigerated truck. The temperature information includes the real-time temperature outside the carriage and the real-time thermal field distribution map inside the carriage. The logistics information collection unit is used to collect the transportation route map and the cargo list for this time. The transportation route map includes the positions of each unloading point, and the cargo list includes the weight, delivery location, temperature comparison table, and temperature influence set of each cargo. The temperature comparison table includes the microbial growth rate of the cargo at different temperatures. The temperature influence set includes the relationship diagram between different ambient temperatures and initial temperatures, and the relationship diagram represents the relationship between the cargo temperature and the influence duration when the cargo is affected by the ambient temperature.

8. The cold chain logistics data supervision system based on the Internet of Things according to claim 7, characterized in that: The data analysis module includes a logistics prediction unit and an influence analysis unit. The logistics prediction unit is used to output the video of the temperature field evolution. First, mark the current GPS position of the refrigerated truck on the transportation route map and identify the location u of the next unloading point; calculate the total weight L of all goods with the delivery location being u sum ; Secondly, take the unloading duration in each delivery record in the historical log as the dependent variable, and the total unloading weight as the independent variable, and package them into samples; input all samples into the linear regression model for training to obtain the duration relationship expression, and substitute the total weight L sum Calculate the estimated unloading duration T n ; Finally, obtain the current hot field distribution map I now and the external temperature of the carriage, and use a physical simulation model to simulate and analyze the change in the temperature distribution inside the carriage during the unloading stage after the carriage door is opened for a duration T n of the internal temperature distribution inside the carriage, and output a temperature field evolution video with a duration of T n ; The influence analysis unit is used to divide the influence area. First, extract the frames of the temperature field evolution video, and mark the positions of each cargo in each image frame respectively. Secondly, set the distance p, and plan a circular area with each cargo's position as the center and p as the radius as the influence area. Finally, in the thermal field distribution diagram I now divide the influence areas for each cargo in the same way.

9. The cold chain logistics data supervision system based on the Internet of Things according to claim 8, characterized in that: The risk management module includes a cargo temperature analysis unit and an index calculation unit. The cargo temperature analysis unit is used to establish a combination for the cargo and analyze the cargo temperature. First, calculate the average temperature of the influence area of cargo h in each image frame. Arrange all the image frames in chronological order, and establish a combination for the image frames with the same average temperature and adjacent to each other. The time range of all the image frames in the combination is used as the duration. Secondly, obtain the thermal field distribution map I now The average temperature CW in the influence area of the goods h f , arrange all combinations in chronological order; Then, obtain the average temperature AW1 and the duration T1 of the first combination, and filter out the relationship graph G1 where the ambient temperature is AW1 and the initial temperature is CW f ; obtain the cargo temperature HW1 when the influence duration is T1 in the relationship graph G1 Continue to obtain the average temperature AW2 and duration T2 of the second combination, screen out the relationship diagram G2 with the ambient temperature of AW2 and the initial temperature of HW1, and obtain the cargo temperature HW2 when the influence duration in the relationship diagram G2 is T2. Finally, calculate the cargo temperatures corresponding to each combination in turn according to the arrangement order. The index calculation unit is used to calculate the risk index of the cargo. First, obtain the temperature comparison table of the goods h, and find the corresponding microbial growth rate ZS according to the temperature of each combination of goods i ; Secondly, according to the formula: Calculate the risk index FX h ; Among them, α is a constant greater than 1, j is the number of all combinations, ZS k and ZS k-1 are the microbial growth rates corresponding to the k-th and (k - 1)-th combinations respectively, ZS f is the temperature CW f corresponding microbial growth rate, T i is the duration of the i-th combination; Finally, calculate the risk index of each cargo respectively.

10. The cold chain logistics data supervision system based on the Internet of Things according to claim 9, characterized in that: The execution supervision module includes a plan generation unit and a dynamic execution unit. The plan generation unit is used to establish a plan. First, analyze the GPS position and driving speed of the refrigerated truck, and calculate the driving duration T to reach the next unloading point xs ; Secondly, set an exponential threshold to mark all goods with a risk index greater than the exponential threshold, and count the sum of the risk indices of all marked goods, FX sum ; Then, according to the formula: Calculate the reserved duration T of each marked cargo respectively rd ; where FX m is the risk index of the marked cargo m; Finally, take the temperature corresponding to the minimum microbial growth rate in the temperature comparison table of each marked cargo as the optimal temperature. Establish a plan for each marked cargo, and take the reserved duration and the optimal temperature of the marked cargo as the adjustment duration and adjustment temperature of the corresponding plan respectively. The dynamic execution unit is used to execute the plan. Sort all the plans in descending order according to the risk index, and execute them in turn according to the plan arrangement order. The execution duration of each plan is the same as the adjustment duration. When implementing the solution, by adjusting the air-conditioning equipment in the refrigerated truck and combining with the feedback of the real-time thermal field distribution map, the cargo temperature of the marked cargo corresponding to the solution is controlled not to exceed the adjusted temperature; the execution order of the solution is dynamically adjusted according to the change of the risk index of each cargo.

Images