Fresh food cold chain quality early warning regulation and control method based on Internet of Things

Abstract

The invention discloses a fresh cold chain quality early warning regulation and control method based on the Internet of Things, and belongs to the technical field of detection and analysis of fresh goods, and the method comprises the steps: obtaining the original quality state of goods, and obtaining the initial data of the goods; acquiring temperature, humidity, gas concentration and vibration intensity in the cold chain environment, and generating multi-source environmental parameters; based on the commodity initial data and the multi-source environment parameters, calculating to obtain a corruption activity index; generating a graded early warning signal according to the decay activity index; in response to the graded early warning signal, generating an equipment cooperation instruction; the device cooperation instruction is sent to the cold chain device cluster to execute regulation and control; and acquiring environment feedback parameters after the cold chain equipment cluster executes regulation and control, and updating the corruption activity index based on the environment feedback parameters. According to the method, the fresh food quality degradation risk can be accurately predicted, the targeting and effectiveness of regulation and control are improved, and the goods damage in the cold chain transportation process is remarkably reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of detection and analysis of fresh food, and in particular to a fresh cold chain quality early warning regulation method based on the Internet of Things. BACKGROUND

[0002] Fresh cold chain logistics is a key link to maintain the high quality of fruits, vegetables, meat and other perishable goods from the production area to the consumer. Its core is to maintain the appropriate low temperature environment of the goods through technical means in the whole process of transportation, storage, etc., to slow down its metabolism and microbial activity, thereby prolonging the shelf life. In this process, real-time investigation and analysis of the quality state of fresh goods, i.e. quality detection, is the basis for effective environmental regulation and reduction of cargo loss.

[0003] In the prior art, the quality monitoring of fresh cold chain usually adopts a relatively simple technical solution. The common practice is to arrange one or several temperature sensors in the refrigerated vehicle compartment or container to monitor the environmental temperature in real time. When the monitored temperature value exceeds the preset safety range, the control system will start or increase the power of the refrigeration equipment to cool down, or stop refrigeration when the temperature is too low. The whole process mainly focuses on threshold judgment and passive response of a single parameter of temperature, which is the mainstream environmental protection means in the industry.

[0004] However, the quality deterioration of fresh goods is a complex biochemical process. In addition to temperature, humidity, ethylene and carbon dioxide concentration, and damage caused by physical vibration and impact during transportation are all key factors affecting the spoilage rate. Monitoring temperature alone cannot fully reflect the real quality risk. Secondly, the traditional scheme is local and non-uniform in terms of environmental perception. The single sensor reading cannot represent the complex microenvironment distribution inside the whole cargo compartment, and local high-temperature hot spots caused by cargo stacking or poor air flow are easily ignored. Finally, its regulation logic is passive and single, lacks the ability to predict the quality deterioration trend, and the regulation measures lack pertinence and effect verification, which cannot cope with complex risk scenarios. SUMMARY

[0005] To solve the above problems, the present application provides a fresh cold chain quality early warning regulation method based on the Internet of Things, which adopts multi-source environmental parameter fusion and spoilage kinetics model to calculate the quality index, and based on hierarchical early warning and spatial thermal map for precise collaborative regulation and closed-loop feedback verification. The technical scheme can realize accurate prediction of fresh quality deterioration risk, improve the targeting and effectiveness of regulation, and significantly reduce cargo loss during cold chain transportation.

[0006] The above object can be achieved by the following scheme:

[0007] A fresh food cold chain quality early warning regulation method based on the Internet of Things, comprising: obtaining the original quality state of goods to obtain commodity initial data; obtaining temperature, humidity, gas concentration and vibration intensity in the cold chain environment to generate multi-source environmental parameters; based on the commodity initial data and the multi-source environmental parameters, a spoilage activity index is calculated; according to the spoilage activity index, a graded early warning signal is generated; in response to the graded early warning signal, a device coordination instruction is generated; the device coordination instruction is sent to the cold chain device cluster to execute regulation; the environmental feedback parameters after the cold chain device cluster executes regulation are obtained, and the spoilage activity index is updated based on the environmental feedback parameters.

[0008] Optionally, the multi-source environmental parameter generation includes: collecting temperature and humidity through a temperature and humidity integrated probe to obtain temperature and humidity parameters; collecting carbon dioxide and ethylene through a gas concentration sensor array to obtain gas concentration parameters; collecting physical impact on the surface of the goods packaging through a vibration sensing patch to obtain vibration intensity parameters; timestamp alignment and association of the temperature parameters, humidity parameters, gas concentration parameters and vibration intensity parameters are performed to generate the multi-source environmental parameters.

[0009] Optionally, the calculation of the spoilage activity index based on the commodity initial data and the multi-source environmental parameters includes: according to the commodity type identifier in the commodity initial data, a corresponding spoilage kinetics model is loaded from a preset model library; the temperature parameter and the humidity parameter in the multi-source environmental parameters are input into the spoilage kinetics model to calculate a basic spoilage coefficient; the gas concentration parameter and the vibration intensity parameter in the multi-source environmental parameters are used to calculate a dynamic spoilage acceleration factor; the product operation of the basic spoilage coefficient and the dynamic spoilage acceleration factor is performed to generate the spoilage activity index.

[0010] Optionally, the loading of the corresponding spoilage kinetics model from the preset model library according to the commodity type identifier in the commodity initial data includes: extracting the commodity type identifier and the initial biochemical index from the commodity initial data; according to the commodity type identifier, the corresponding spoilage kinetics model parameters are extracted from the model library; the spoilage kinetics model is loaded based on the spoilage kinetics model parameters.

[0011] Optionally, the calculating the dynamic spoilage acceleration factor using the gas concentration parameter and the vibration intensity parameter in the multi-source environment parameters comprises: establishing an association model for characterizing a physical damage indicator of the goods based on the vibration intensity parameter; comparing the vibration intensity parameter with a preset impact threshold, and when the vibration intensity parameter exceeds the impact threshold, calculating a current physical damage indicator of the goods based on the association model and the vibration intensity parameter; generating a spoilage rate correction coefficient using the current physical damage indicator, to represent an increased susceptibility of the goods to quality degradation caused by physical impact; and calculating the dynamic spoilage acceleration factor based on the spoilage rate correction coefficient and the gas concentration parameter.

[0012] Optionally, the generating a hierarchical early warning signal according to the spoilage activity index comprises: comparing the spoilage activity index with a preset first risk threshold and a preset second risk threshold; wherein the first risk threshold is lower than the second risk threshold; and determining the early warning signal as a safety signal, a first-level early warning signal, or a second-level early warning signal according to the comparison result, to obtain the hierarchical early warning signal.

[0013] Optionally, the generating a device coordination instruction in response to the hierarchical early warning signal comprises: when the hierarchical early warning signal is a first-level early warning signal, generating a local fan balancing instruction as the device coordination instruction; and when the hierarchical early warning signal is a second-level early warning signal, performing the following steps: obtaining sensor spatial position information associated with the multi-source environment parameters, and generating a spoilage activity index spatial distribution heat map; identifying a high-risk area based on the spoilage activity index spatial distribution heat map; generating a directional cooling instruction for the high-risk area and a coordinated air supply instruction for a neighboring area of the high-risk area, and combining the directional cooling instruction and the coordinated air supply instruction to obtain the device coordination instruction.

[0014] Optionally, the updating the spoilage activity index based on the environment feedback parameter comprises: after the cold chain device cluster performs regulation and control, reacquiring multi-source environment parameters to generate an environment feedback parameter; recalculating an updated spoilage activity index based on the environment feedback parameter; calculating a decline rate of the updated spoilage activity index relative to the spoilage activity index before regulation and control; and when the decline rate is lower than a preset efficiency judgment threshold, triggering a backup strategy generation.

[0015] Optionally, the triggering a backup strategy generation comprises: analyzing an air supply path of the high-risk area based on the spoilage activity index spatial distribution heat map, and identifying an air supply blind area; calculating a supply angle adjustment parameter for optimizing air flow coverage for the air supply blind area; and generating a backup coordination instruction based on the supply angle adjustment parameter and sending it to the cold chain device cluster.

[0016] Based on the same inventive concept, the application also provides a fresh food cold chain quality early warning regulation system based on Internet of Things, which comprises: a commodity data acquisition module for acquiring the original quality state of goods to obtain initial data of commodities; a multi-source perception module for acquiring temperature, humidity, gas concentration and vibration intensity in the cold chain environment to generate multi-source environmental parameters; a quality index calculation module for calculating a spoilage activity index based on the initial data of commodities and the multi-source environmental parameters; a risk early warning module for generating a graded early warning signal according to the spoilage activity index; a collaborative regulation module for generating device coordination instructions in response to the graded early warning signal; an instruction sending module for sending the device coordination instructions to a cold chain device cluster for execution of regulation; and a feedback verification module for acquiring environmental feedback parameters after the cold chain device cluster executes the regulation and updating the spoilage activity index based on the environmental feedback parameters.

[0017] Compared with the prior art, the application has the following advantages:

[0018] 1. The application fuses multi-dimensional environmental parameters such as temperature, humidity, gas concentration and vibration intensity, and loads a dedicated spoilage kinetics model in combination with the type characteristics of commodities to construct a comprehensive spoilage activity index. This multi-factor coupled evaluation method can more comprehensively and accurately reflect the real quality degradation dynamics of fresh commodities in a complex transportation environment compared with the traditional temperature-dependent monitoring, thereby greatly improving the accuracy and scientificity of quality state evaluation.

[0019] 2. The application realizes the transformation from extensive regulation to precise and targeted regulation. By generating a spatial distribution thermodynamic map of the spoilage activity index, the system can accurately locate the specific high-risk areas of quality degradation risk in the cargo hold. The directional cooling and collaborative air supply instructions generated further can focus the regulation resources on the problem core, avoiding global and high-energy consumption blind cooling, and significantly improving the efficiency and energy utilization rate of regulation.

[0020] 3. The application establishes an adaptive closed-loop regulation system including feedback verification and backup strategies. After executing the regulation instructions, the system actively evaluates the actual effect of the regulation measures, and when the effect is not good, it can further analyze the reasons, such as identifying air supply blind areas, and automatically generating backup strategies for secondary optimization. This intelligent feedback and correction mechanism ensures that the system has higher robustness and environmental adaptability when facing complex and variable field conditions, and guarantees the final effectiveness of the regulation.

[0021] Other features and advantages of the present application will be set forth in the descriptions that follow, and in part will be apparent from the description, or can be learned by practice of the application. The purposes and other advantages of the present application will be realized and attained by the structures particularly pointed out in the written description and claims hereof. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings described below are some embodiments of the present application, and the ordinary skilled in the art can obtain other drawings according to these drawings without any creative work.

[0023] Figure 1 is a flowchart of a fresh food cold chain quality early warning regulation method based on the Internet of Things according to an embodiment of the present application.

[0024] Figure 2 is a corruption activity index spatial distribution heat map according to an embodiment of the present application.

[0025] Figure 3 is a structural schematic diagram of a fresh food cold chain quality early warning regulation system based on the Internet of Things according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the purposes, technical solutions and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely explain the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by the ordinary skilled in the art without any creative work are within the protection scope of the present application.

[0027] With reference to Figure 1 An embodiment of the present application proposes a fresh food cold chain quality early warning regulation method based on the Internet of Things, which adopts multi-source environmental parameter fusion and corruption kinetics model to calculate quality index, and adopts a technical scheme of precise collaborative regulation and closed-loop feedback verification based on hierarchical early warning and spatial heat map, so as to realize precise prediction of fresh food quality deterioration risk, improve the targeting and effectiveness of regulation, and significantly reduce the damage in the cold chain transportation process.

[0028] The method of the embodiment specifically includes:

[0029] Obtain the original quality state of the goods to obtain the initial data of the goods;

[0030] Obtain the temperature, humidity, gas concentration and vibration intensity in the cold chain environment to generate multi-source environmental parameters;

[0031] Based on the commodity initial data and the multi-source environmental parameters, a corruption activity index is calculated;

[0032] According to the corruption activity index, a hierarchical early warning signal is generated;

[0033] In response to the hierarchical early warning signal, a device coordination instruction is generated;

[0034] The device coordination instruction is sent to the cold chain device cluster to perform regulation and control;

[0035] Obtain the environmental feedback parameters after the cold chain device cluster performs regulation and control, and update the corruption activity index based on the environmental feedback parameters.

[0036] Specifically, the initial inherent properties of the goods and the real-time collected multi-source environmental parameters are obtained, the static commodity benchmark data and the dynamic environmental influence factors are combined, and a corruption activity index that can comprehensively quantify the current quality degradation risk is generated through specific calculation. The index is then used as a basis for decision-making and is mapped to different levels of early warning signals. In response to these hierarchical signals, strategic device coordination instructions are generated, and the cold chain device cluster is driven for precise regulation and control. Finally, by obtaining the environmental feedback parameters after regulation and control, the corruption activity index is re-evaluated and updated, forming a complete closed-loop control process, thereby realizing continuous, dynamic and adaptive early warning and regulation of fresh food quality.

[0037] Optionally, the generation of multi-source environmental parameters includes:

[0038] Temperature and humidity are collected by a temperature and humidity integrated probe to obtain temperature parameters and humidity parameters;

[0039] Carbon dioxide and ethylene are collected by a gas concentration sensor array to obtain gas concentration parameters;

[0040] Physical impact on the surface of the goods packaging is collected by a vibration sensing patch to obtain vibration intensity parameters;

[0041] The temperature parameters, humidity parameters, gas concentration parameters and vibration intensity parameters are time-stamped aligned and associated to generate the multi-source environmental parameters.

[0042] Specifically, integrated temperature and humidity probes are deployed throughout the cold chain environment where fresh produce is stored. These probes collect temperature and humidity information in real time and synchronously, generating temperature and humidity parameters. These integrated temperature and humidity probes are composite sensors that combine temperature and humidity sensors, ensuring high correlation between temperature and humidity data acquired at the same physical location and time. Secondly, a gas concentration sensor array is deployed to monitor key biochemical gases that impact fresh produce quality. This array includes sensors specifically designed to detect carbon dioxide (CO2), a measure of the intensity of respiration, and ethylene, a key plant hormone that ripens and accelerates decay. Continuous monitoring from this array provides accurate gas concentration parameters. Furthermore, to quantify the impact of physical factors on goods during transportation, vibration sensing patches are attached directly to the surface of the goods packaging. These patches are sensors that sense and record changes in acceleration. They effectively capture physical impact and sustained vibration caused by bumpy roads or improper loading and unloading operations, generating vibration intensity parameters. Finally, the acquired temperature, humidity, gas concentration, and vibration intensity parameters are integrated and processed. The core of this step is timestamp alignment and correlation. The system attaches a precise timestamp to each sensor data acquisition. Then, through data processing algorithms, all parameters from different sources at the same time point or within a very small time window are combined into a unified data set. This correlation operation ultimately generates multi-source environmental parameters that comprehensively and dynamically reflect the comprehensive status of the cold chain environment, providing an accurate data foundation for subsequent quality status assessment.

[0043] Optionally, the calculating the corruption activity index based on the initial commodity data and the multi-source environmental parameters includes:

[0044] According to the commodity category identifier in the initial commodity data, a corresponding corruption dynamics model is loaded from a preset model library;

[0045] Inputting the temperature parameter and the humidity parameter in the multi-source environmental parameters into the corruption dynamics model to calculate the basic corruption coefficient;

[0046] Utilizing the gas concentration parameter and the vibration intensity parameter in the multi-source environmental parameters, a dynamic corruption acceleration factor is calculated;

[0047] The basic corruption coefficient and the dynamic corruption acceleration factor are multiplied to generate a corruption activity index.

[0048] Specifically, first, the key commodity category identifier is extracted from the obtained commodity initial data, for example, it is determined whether the batch of goods is strawberries or leafy vegetables. Then, the commodity category identifier is used as an index to search in the preset model library. The spoilage kinetics model that completely matches the current commodity category is loaded through the index. After loading the model, the temperature parameter and the humidity parameter are separated from the multi-source environmental parameters, and the two parameters are used as input variables to substitute into the loaded spoilage kinetics model for operation. The result of the model operation is a quantitative index, that is, the basic spoilage coefficient, which represents the basic quality deterioration rate of the commodity due to its own metabolism and microbial activity under the current temperature and humidity conditions. At the same time, the other two key data in the multi-source environmental parameters, that is, the gas concentration parameter and the vibration intensity parameter, are also processed. Through comprehensive analysis of the concentration of ripening gas ethylene, metabolic product carbon dioxide and the vibration intensity of physical impact on the goods packaging, a dynamic spoilage acceleration factor is calculated, which is a correction factor for quantifying the superimposed effect and acceleration effect of ripening gas and physical damage in the external environment on the basic spoilage process. Finally, the product operation of the two key indicators calculated above is performed:

[0049] ,

[0050] wherein, represents the spoilage activity index, which is a comprehensive index for evaluating the real-time quality risk of the commodity. represents the basic spoilage coefficient, which is calculated by the selected spoilage kinetics model based on real-time temperature and humidity parameters. represents the dynamic spoilage acceleration factor, which is obtained by modeling and analyzing real-time gas concentration parameters and vibration intensity parameters. The basic spoilage coefficient and the dynamic spoilage acceleration factor are both dimensionless relative values or rate units that can be multiplied.

[0051] Optionally, the loading of the corresponding spoilage kinetics model from the preset model library according to the commodity category identifier in the commodity initial data comprises:

[0052] extracting the commodity category identifier and the initial biochemical index from the commodity initial data;

[0053] extracting the corresponding spoilage kinetics model parameters from the model library according to the commodity category identifier;

[0054] loading the spoilage kinetics model based on the spoilage kinetics model parameters.

[0055] Specifically, first, the product category identifier and the initial biochemical indicators are extracted from the previously acquired product initial data. The product category identifier is a clear label used to distinguish whether the goods are fruits, vegetables, or meat, etc. The initial biochemical indicators are a set of quantitative initial state data, such as the initial hardness, sugar-acid ratio or total number of microbial colonies of the goods, which together constitute the quality baseline of the batch of goods before the start of cold chain transportation. Then, the extracted product category identifier is used as the key index to accurately search and match in the pre-established model library. The model library stores a large number of spoilage kinetics model parameters for different fresh products. These parameters are fitted from a large amount of experimental data and can represent the spoilage law of a specific product under different environments, such as the activation energy or rate constant of a specific spoilage reaction. Once a successful match is made, a set of exclusive spoilage kinetics model parameters will be retrieved from the model library. Finally, these obtained spoilage kinetics model parameters are used to instantiate or configure a general spoilage kinetics model framework. This process can be understood as substituting specific parameter values into a universal mathematical model structure, thereby generating a personalized spoilage kinetics model that is completely tailored to the current transportation goods. After the model is constructed, it will be directly used in the subsequent step, i.e., receiving real-time collected temperature and humidity parameters, and then calculating the basic spoilage coefficient reflecting the current environmental impact, ensuring the prediction accuracy and pertinence of the entire early warning and control method.

[0056] Optionally, the calculating the dynamic spoilage acceleration factor using the gas concentration parameter and the vibration intensity parameter in the multi-source environmental parameters comprises:

[0057] Based on the vibration intensity parameter, an association model for characterizing the physical damage indicator of the goods is established;

[0058] The vibration intensity parameter is compared with a preset impact threshold value, and when the vibration intensity parameter exceeds the impact threshold value, the current physical damage indicator of the goods is calculated based on the association model and the vibration intensity parameter;

[0059] Using the current physical damage indicator of the goods, a spoilage rate correction coefficient is generated to represent the increased susceptibility of the goods to quality deterioration due to physical impact;

[0060] Based on the spoilage rate correction coefficient and the gas concentration parameter, a dynamic spoilage acceleration factor is calculated.

[0061] Specifically, first, a correlation model is established, which is based on previous experimental data and reveals the quantitative relationship between the vibration intensity parameters of different intensity and frequency and the specific physical damage of the goods. In real-time monitoring of cold chain transportation, the system continuously acquires vibration intensity parameters collected by vibration sensing patches and compares them with a pre-set impact threshold continuously. The impact threshold is the key limit to distinguish normal transportation bumps from severe impacts that may cause damage. Once the monitored vibration intensity parameters exceed the impact threshold, the system determines that a potential damage event has occurred. At this time, the aforementioned correlation model is immediately invoked, and the excessive vibration intensity parameters are taken as input to calculate a quantitative current physical damage index of the goods, which objectively reflects the degree of compression, damage or internal organization destruction of the goods due to impact. Then, using the calculated physical damage index of the goods, a spoilage rate correction coefficient is further generated, which represents the degree of increase in the susceptibility of the quality deterioration of the goods due to physical damage. The more severe the physical damage, the more the cell structure is destroyed, the more the channels for microbial infection and oxidative browning are unblocked, so the value of the spoilage rate correction coefficient is larger, which means that the internal tendency of quality deterioration is enhanced. Finally, the spoilage rate correction coefficient reflecting the influence of physical damage is combined with the real-time acquired gas concentration parameters to calculate the final dynamic spoilage acceleration factor. The gas concentration parameters mainly include the concentrations of the ripening hormone ethylene and the respiratory product carbon dioxide. This final calculation combines two completely different but interrelated acceleration effects, namely the increase in susceptibility caused by physical damage and the acceleration of biochemical reactions triggered by the environment. The calculation can be represented by the following formula:

[0062] ,

[0063] wherein, represents the dynamic spoilage acceleration factor, which is a dimensionless multiplier for amplifying the basic spoilage rate. is the spoilage rate correction coefficient, also a dimensionless value, which is calculated according to the physical damage index of the goods, and its value tends to 1 when there is no significant physical damage, and increases with the severity of damage. is a gas effect factor calculated according to the gas concentration parameters, which quantifies the catalytic effect of the current gas environment on the spoilage process, and is also a dimensionless multiplier.

[0064] Optionally, generating a graded warning signal according to the spoilage activity index comprises:

[0065] comparing the spoilage activity index with a pre-set first risk threshold and a pre-set second risk threshold; wherein the first risk threshold is lower than the second risk threshold;

[0066] According to the comparison result, the early warning signal is determined as a safety signal, a first-level early warning signal or a second-level early warning signal, to obtain a hierarchical early warning signal.

[0067] Specifically, the corruption activity index calculated in the previous stage is compared with a first risk threshold value and a second risk threshold value. The two threshold values are numerical values determined in advance according to the storage characteristics of specific fresh commodities, combined with historical transportation data and quality safety standards, through experiments or expert evaluation, and the first risk threshold value is lower than the second risk threshold value in value, so as to build a risk level ladder from low to high. If the current calculated corruption activity index is less than or equal to the first risk threshold value, the system determines that the current cold chain environment state is ideal, and the risk of quality degradation of the commodity is extremely low, and therefore generates a safety signal. If the value of the corruption activity index has exceeded the first risk threshold value, but is still less than or equal to the second risk threshold value, it indicates that the risk of quality degradation of the commodity has begun to appear and deserves attention, and a first-level early warning signal is generated at this time. If the value of the corruption activity index has broken through and is higher than the second risk threshold value, it indicates that the commodity is facing a significant risk of quality degradation, and the situation is more urgent, and the system immediately generates the highest level of second-level early warning signal. The final output of the hierarchical early warning signal, i.e. the safety signal, the first-level early warning signal or the second-level early warning signal, provides clear decision input for the subsequent cooperative regulation module.

[0068] Optionally, the generating of the device cooperative instruction in response to the hierarchical early warning signal comprises:

[0069] When the hierarchical early warning signal is a first-level early warning signal, a local fan balancing instruction is generated as the device cooperative instruction; and when the hierarchical early warning signal is a second-level early warning signal, the following steps are performed:

[0070] Obtaining sensor spatial position information associated with the multi-source environmental parameters to generate a corruption activity index spatial distribution heat map;

[0071] Identifying a high-risk area based on the corruption activity index spatial distribution heat map;

[0072] Generating a directional refrigeration instruction for the high-risk area and a cooperative air supply instruction for a neighboring area of the high-risk area, and combining the directional refrigeration instruction and the cooperative air supply instruction to obtain the device cooperative instruction.

[0073] Specifically, when the system receives a Level 1 warning signal, it indicates that the risk of cargo quality deterioration is still in its early stages and is becoming localized or mild. At this point, a local fan balancing command is generated as a device coordination command. This command aims to perform a gentle global adjustment by regulating the speed and coordinated operation of the fans in the cold chain equipment cluster to optimize airflow distribution throughout the cargo hold. This aims to eliminate potential hotspots or dead zones where temperature or gas concentrations are uneven, thereby eliminating emerging risks and restoring overall environmental balance. When the warning signal is upgraded to Level 2, indicating a significant and imminent risk of cargo quality deterioration, the system first obtains the spatial location information of the sensors associated with the multi-source environmental parameters that triggered the warning. This information is pre-entered into the system and includes the three-dimensional coordinates of each sensor, enabling the system to associate abstract risk data with specific physical locations within the cargo hold. Based on this location information and the corresponding corruption activity index at each location, a heat map of the spatial distribution of the corruption activity index is generated using algorithms such as spatial interpolation. The heat map visually displays the distribution of risks in the entire cargo hold, where areas with high corruption activity index are marked with eye-catching colors or forms. Figure 2 As shown, the heat map is then subjected to image analysis or data clustering to automatically identify the areas with the highest corruption activity index and define them as high-risk areas. For the precisely located high-risk areas, a directional refrigeration instruction will be generated. This instruction precisely controls the refrigeration unit closest to the area to increase the refrigeration power, thereby achieving strong cooling of the core of the problem. At the same time, in order to assist and enhance the effect of directional refrigeration, the system will also generate collaborative air supply instructions for the adjacent areas of the high-risk area, instructing the fans in these areas to adjust the air supply angle and air volume to form a collaborative airflow field, which serves to accelerate the heat extraction from the high-risk areas and prevent high-temperature or high-concentration harmful gases from spreading to the surrounding areas. Finally, the system combines the directional refrigeration instruction and the collaborative air supply instruction into a unified equipment coordination instruction, and sends it to the cold chain equipment cluster to ensure that various control actions can be executed synchronously and coordinated.

[0074] Optionally, updating the corruption activity index based on the environmental feedback parameter includes:

[0075] After the cold chain equipment cluster performs regulation, reacquiring multi-source environmental parameters to generate environmental feedback parameters;

[0076] Recalculating an updated corruption activity index based on the environmental feedback parameter;

[0077] Calculate the decline rate of the updated corruption activity index relative to the corruption activity index before regulation;

[0078] When the decline rate is lower than a preset performance judgment threshold, a backup strategy is triggered to generate.

[0079] Specifically, after the cold chain equipment cluster executes the equipment coordination instruction, a complete data collection is performed again to reacquire the temperature, humidity, gas concentration and vibration intensity in the cold chain environment. The data collected this time is referred to as environmental feedback parameters, which are essentially a new set of multi-source environmental parameters reflecting the state of the environment after regulation. Next, the new set of environmental feedback parameters is taken as input variables and substituted into the same calculation process as the foregoing steps, that is, the spoilage kinetics model is loaded based on the commodity type identifier, and an updated spoilage activity index is recalculated in combination with the gas concentration and vibration intensity. This index objectively quantifies the current quality deterioration risk level faced by the goods after the regulation measures take effect. The risk reduction rate brought by the regulation measures, that is, the decline rate of the spoilage activity index, is calculated:

[0080] ,

[0081] wherein, represents the decline rate of the spoilage activity index, which measures the efficiency of the regulation measures in reducing the risk per unit time. is the spoilage activity index before the regulation instruction is executed, that is, the value triggering the warning signal. is the updated spoilage activity index newly calculated based on the environmental feedback parameters. is the time interval elapsed from the occurrence to the re-measurement after the regulation, which is accurately obtained from the system clock. Finally, the calculated decline rate is compared with a preset performance judgment threshold, which is a benchmark value set based on historical data and expert experience, representing the minimum risk mitigation rate that an effective regulation measure should achieve under a specific warning level. When it is found that the decline rate is lower than the performance judgment threshold, it means that the current regulation strategy is ineffective or has failed, and a backup strategy generation mechanism is immediately triggered to seek a more effective solution.

[0082] Optionally, the triggering of the backup strategy generation includes:

[0083] Based on the spoilage activity index spatial distribution thermodynamic map, the air supply path of the high-risk area is analyzed, and an air supply blind area is identified;

[0084] For the air supply blind area, an air supply angle adjustment parameter for optimizing air flow coverage is calculated;

[0085] Based on the air supply angle adjustment parameter, a backup coordination instruction is generated and sent to the cold chain equipment cluster.

[0086] Specifically, first, based on the previously generated spatial distribution of the corruption activity index heat map in response to the secondary early warning, the high-risk areas still existing are analyzed in depth. The heat map is combined with the internal three-dimensional structure model of the cold chain cargo hold and the operating parameters of the fans in the current cold chain equipment cluster, and through computational fluid dynamics simulation or air flow path modeling, the air supply path around the high-risk area is analyzed and reproduced. Through this analysis, the system can accurately identify the air supply blind area, that is, those local spaces that are in a high-risk state but cannot obtain sufficient cold air flow coverage due to cargo stacking shielding or defects in the existing air flow organization mode. After accurately identifying the location and range of the air supply blind area, the system will specifically calculate the air supply angle adjustment parameters for optimizing air flow coverage. This is an optimization solving process aimed at eliminating or minimizing the air supply blind area, and through algorithm iteration, the air supply angle of the fan most related to the blind area is adjusted, including the horizontal swing angle and the vertical pitch angle. The algorithm simulates the air flow distribution under different angle combinations until an optimal angle parameter combination is found that can most effectively guide cold air to the air supply blind area. The final output of the calculation is a specific set of numerical values, that is, the air supply angle adjustment parameters. Finally, based on the set of calculated air supply angle adjustment parameters, a new backup cooperative instruction is generated, which specifically instructs the specific fan unit to adjust its air supply angle to the new optimized value. This backup cooperative instruction is then sent to the cold chain equipment cluster for immediate execution, thereby achieving a secondary precise correction of the air flow organization.

[0087] Based on the same inventive concept, as shown in Figure 3 The application also provides an Internet of Things-based fresh food cold chain quality early warning and regulation system, which comprises:

[0088] A commodity data acquisition module is configured to acquire the original quality state of the goods and obtain initial commodity data.

[0089] A multi-source perception module is configured to acquire the temperature, humidity, gas concentration and vibration intensity in the cold chain environment and generate multi-source environmental parameters.

[0090] A quality index calculation module is configured to calculate a corruption activity index based on the initial commodity data and the multi-source environmental parameters.

[0091] A risk early warning module is configured to generate a graded early warning signal based on the corruption activity index.

[0092] A cooperative regulation module is configured to generate a device cooperative instruction in response to the graded early warning signal.

[0093] An instruction sending module is configured to send the device cooperative instruction to a cold chain equipment cluster for execution of regulation.

[0094] a feedback verification module, configured to obtain an environmental feedback parameter after the cold chain device cluster performs the regulation and control, and update the spoilage activity index based on the environmental feedback parameter.

[0095] To verify the feasibility of the application in implementation, the application is applied to the cross-regional cold chain transportation business of a large fresh food supply chain enterprise. The enterprise is mainly responsible for transporting high-quality strawberries produced in Kunming, Yunnan to the high-end fresh food market in Shanghai. Strawberries are extremely sensitive to temperature, humidity, gas environment and physical vibration. The traditional fixed temperature regulation mode is difficult to cope with the complex dynamic changes in the transportation process, resulting in high loss rate.

[0096] In this embodiment, the enterprise deploys the system described in the application in a batch of standard refrigerated containers. Before transportation, the original quality state of the batch of strawberries is collected as a benchmark for subsequent evaluation. During the transportation process of about 48 hours, the system monitors and dynamically regulates the environment in the container. To verify the beneficial effects of the application, one refrigerated container deploying the system is used as the experimental group, and another container of the same batch of strawberries using traditional constant temperature control (set temperature of 2°C, no other dynamic regulation) is used as the control group.

[0097] On July 15, 2024, when loading, the system in the experimental group first scans the two-dimensional code on the package of the goods to obtain the initial data of the goods, the product type is identified as “Red Beauty Strawberries”, and the initial biochemical indicators are recorded, such as the average hardness is 7.6N, and the average sugar-acid ratio is 8.5. At the same time, the multi-source perception module deployed in the container starts to work. The temperature and humidity integrated probe collects temperature and humidity in real time, the gas concentration sensor array monitors the concentration of carbon dioxide (CO2) and ethylene (C2H4), and the vibration perception patch is fixed on the surface of the strawberry packaging box at several different positions to collect physical impact information. All sensor data are attached with accurate time stamps and integrated into multi-source environmental parameters.

[0098] During transportation, the system loads the corresponding decay kinetics model parameters from the model library based on the initial data of the commodity "red strawberry". At 3:20 am on July 16, while passing through a mountainous road, a corner of the vibration sensing patch detects vibrations that exceed the preset impact threshold for a long time, and the system determines that physical damage has occurred. Based on this, the system calculates the decay rate correction coefficient as 1.2. At the same time, the ethylene concentration in this area increases slightly. After comprehensive calculation, the decay activity index of this area rises and exceeds the first risk threshold. The system immediately generates a first-level warning signal and generates a local fan balancing instruction in response, adjusting the air circulation in the entire box to try to disperse the locally accumulated ethylene gas and balance the temperature. At 10:45 am on July 16, despite the first-level control, due to the over-tight stacking of the goods, the temperature in the high-risk area did not decrease but increased, causing the decay activity index to further rise and break through the second risk threshold. The system immediately generates a second-level warning signal.

[0099] In response to the second-level warning signal, the system immediately obtains the spatial position information of the sensor and generates a decay activity index spatial distribution heat map, accurately identifying the left upper corner of the rear of the box as a high-risk area. For this high-risk area, the system generates a directional cooling instruction, instructing the cooling unit closest to the area to increase the cooling power. At the same time, a cooperative air supply instruction is generated for the adjacent area to direct cold air flow to the area. After 5 minutes of control execution, the system obtains environmental feedback parameters and updates the decay activity index, finding that its decline rate is lower than the preset efficiency judgment threshold. This indicates that the control effect is not good. The system immediately triggers the standby strategy generation: by analyzing the heat map and air flow model, it identifies that there is a blind area of air supply in the high-risk area caused by improper stacking of goods. The system quickly calculates the air supply angle adjustment parameters for optimizing air flow coverage and generates a standby cooperative instruction to fine-tune the angle of the nearby fan louvers. After executing the standby instruction, feedback verification again shows that the decay activity index begins to decline rapidly, and the risk is effectively controlled.

[0100] After 48 hours of transportation to Shanghai, the strawberries in the experimental and control groups were subjected to quality detection and damage statistics. The data shows that the experimental group applying the present application has a significant effect on quality preservation and risk control.

[0101] Table 1 Comparison of key indicators of quality deterioration

[0102]

[0103] Table 2 Comparison of warning and control response efficiency

[0104]

[0105] Table 3 Comparison of final damage rate and quality evaluation

[0106]

[0107] From the data of Tables 1-3 above, it can be seen that after applying the method of the present application, the key indicators of the experimental group are significantly better than those of the control group. Table 1 shows that the experimental group effectively inhibited the increase of spoilage activity index and ethylene concentration through real-time regulation, and controlled the quality deterioration process at a lower level. Table 2 shows that the system of the present application can achieve rapid and accurate identification of risks and automatic intervention, and the response time is shortened from hours to minutes. The final results of Table 3 prove that the present application directly brings economic benefits, and the total loss rate of the experimental group is reduced by 9.3%, and the rate of excellent strawberries is increased by 23%, significantly improving the value and market competitiveness of the goods. These data fully prove the advancement, effectiveness and practical value of the present application in fresh cold chain management.

[0108] It should be noted that the electrical connection between the above-mentioned units does not necessarily represent the direct connection of the line, and the indirect connection mode can also be applied to the embodiments of the present application as long as the purpose of the present application is achieved. The above-mentioned is only an exemplary embodiment of the present application, and cannot limit the scope of the present application.

[0109] That is, any equivalent changes and modifications made according to the teachings of the present application are still within the scope of the present application. Other embodiments of the present application will be readily apparent to those skilled in the art upon considering the specification and practice of the true principles disclosed herein. The present application is intended to cover any variations, uses, or adaptive changes to the present application that follow the general principles of the present application and include common knowledge or conventional technical means in the art that are not described in the present application.

Claims

1. A method for early warning and control of fresh cold chain quality based on the Internet of Things, characterized in that: The method: Obtain the original quality status of the goods and obtain the initial data of the goods; Obtain temperature, humidity, gas concentration, and vibration intensity within the cold chain environment to generate multi-source environmental parameters; Calculating a corruption activity index based on the initial commodity data and the multi-source environmental parameters; generating a graded early warning signal based on the corruption activity index; generating a device coordination instruction in response to the graded warning signal; Sending the equipment coordination instruction to the cold chain equipment cluster to perform regulation; Obtain environmental feedback parameters after the cold chain equipment cluster performs regulation, and update the corruption activity index based on the environmental feedback parameters.

2. The method for early warning and control of fresh cold chain quality based on the Internet of Things according to claim 1, characterized in that: Generating multi-source environment parameters includes: The temperature and humidity are collected by the temperature and humidity integrated probe to obtain temperature parameters and humidity parameters; The gas concentration parameters are obtained by collecting carbon dioxide and ethylene through a gas concentration sensor array; The vibration sensing patch collects the physical impact on the surface of the cargo packaging and obtains the vibration intensity parameters; The temperature parameter, humidity parameter, gas concentration parameter and vibration intensity parameter are time stamp aligned and associated to generate the multi-source environmental parameter.

3. The method for early warning and control of fresh cold chain quality based on the Internet of Things according to claim 2, characterized in that: The calculation of the corruption activity index based on the initial commodity data and the multi-source environmental parameters includes: According to the commodity category identifier in the initial commodity data, a corresponding corruption dynamics model is loaded from a preset model library; Inputting the temperature parameter and the humidity parameter in the multi-source environmental parameters into the corruption dynamics model to calculate the basic corruption coefficient; Utilizing the gas concentration parameter and the vibration intensity parameter in the multi-source environmental parameters, a dynamic corruption acceleration factor is calculated; The basic corruption coefficient and the dynamic corruption acceleration factor are multiplied to generate a corruption activity index.

4. The method for early warning and control of fresh cold chain quality based on the Internet of Things according to claim 3 is characterized in that: The step of loading the corresponding corruption dynamics model from a preset model library according to the commodity category identifier in the initial commodity data includes: Extracting commodity category identification and initial biochemical indicators from the initial commodity data; extracting corresponding corruption dynamics model parameters from the model library according to the commodity category identifier; The corruption dynamics model is loaded based on the corruption dynamics model parameters.

5. The method for early warning and control of fresh cold chain quality based on the Internet of Things according to claim 3 is characterized in that: The method of calculating the dynamic corruption acceleration factor by using the gas concentration parameter and the vibration intensity parameter in the multi-source environmental parameters includes: Establishing a correlation model for characterizing physical damage indicators of cargo based on the vibration intensity parameters; comparing the vibration intensity parameter with a preset impact threshold, and when the vibration intensity parameter exceeds the impact threshold, calculating a current cargo physical damage index based on the correlation model and the vibration intensity parameter; Using current cargo physical damage indicators, a spoilage rate correction factor is generated to characterize the increased susceptibility of cargo to quality degradation due to physical impact; Based on the corruption rate correction coefficient and the gas concentration parameter, a dynamic corruption acceleration factor is calculated.

6. The method for early warning and control of fresh cold chain quality based on the Internet of Things according to claim 1, characterized in that: Generating a graded warning signal according to the corruption activity index includes: comparing the corruption activity index with a preset first risk threshold and a preset second risk threshold; wherein the first risk threshold is lower than the second risk threshold; Based on the comparison results, the warning signal is determined as a safety signal, a first-level warning signal or a second-level warning signal to obtain a graded warning signal.

7. The method for early warning and control of fresh cold chain quality based on the Internet of Things according to claim 6, characterized in that: The generating of a device coordination instruction in response to the graded warning signal includes: When the graded warning signal is a level one warning signal, a local fan balancing instruction is generated as the equipment coordination instruction; when the graded warning signal is a level two warning signal, the following steps are performed: Acquiring sensor spatial location information associated with the multi-source environmental parameters and generating a heat map of spatial distribution of corruption activity index; Identifying high-risk areas based on the spatial distribution heat map of the corruption activity index; A directional cooling instruction is generated for the high-risk area, and a coordinated air supply instruction is generated for an area adjacent to the high-risk area. The directional cooling instruction and the coordinated air supply instruction are combined to obtain an equipment coordinated instruction.

8. The method for early warning and control of fresh cold chain quality based on the Internet of Things according to claim 1, characterized in that: Updating the corruption activity index based on the environmental feedback parameter includes: After the cold chain equipment cluster performs regulation, reacquiring multi-source environmental parameters to generate environmental feedback parameters; Recalculating an updated corruption activity index based on the environmental feedback parameter; Calculate the decline rate of the updated corruption activity index relative to the corruption activity index before regulation; When the drop rate is lower than a preset performance judgment threshold, the generation of a backup strategy is triggered.

9. The method for early warning and control of fresh cold chain quality based on the Internet of Things according to claim 8, characterized in that: The triggering of backup strategy generation includes: Based on the spatial distribution heat map of the corruption activity index, the air supply paths in high-risk areas are analyzed to identify air supply blind spots; For the air supply blind area, calculating and obtaining air supply angle adjustment parameters for optimizing airflow coverage; Based on the air supply angle adjustment parameter, a backup coordination instruction is generated and sent to the cold chain equipment cluster.

10. A fresh cold chain quality early warning and control system based on the Internet of Things, applied to the fresh cold chain quality early warning and control method based on the Internet of Things as described in any one of claims 1 to 9, characterized in that: The system comprises: The commodity data acquisition module is used to obtain the original quality status of the goods and obtain the initial data of the goods; Multi-source sensing module, used to obtain temperature, humidity, gas concentration and vibration intensity in the cold chain environment and generate multi-source environmental parameters; a quality index calculation module, configured to calculate a corruption activity index based on the initial commodity data and the multi-source environmental parameters; a risk warning module, configured to generate a graded warning signal based on the corruption activity index; a collaborative control module, configured to generate a device collaborative instruction in response to the graded warning signal; An instruction sending module, used to send the device coordination instruction to the cold chain equipment cluster to perform regulation; The feedback verification module is used to obtain the environmental feedback parameters after the cold chain equipment cluster performs regulation and update the corruption activity index based on the environmental feedback parameters.

Images